Authors: Irmi Schneider
Abstract: Symmetry plays a crucial role in understanding the properties of mathematical structures and optimization problems. Recent work has explored this phenomenon in the context of neural networks, where the loss function is invariant under column and row permutations of the network weights. It has been observed that local minima exhibit significant symmetry with respect to the network weights (invariance to row and column permutations). And moreover no critical point was found that lacked symmetry. We extend this line of inquiry by investigating symmetry phenomena in real-valued loss functions defined on a broader class of spaces. We will introduce four more cases: the projective case over a finite field, the octahedral graph case, the perfect matching case, and the particle attraction case. We show that as in the neural network case, all the critical points observed have non-trivial symmetry. Finally we introduce a new measure of symmetry in the system and show that it reveals additional symmetry structures not captured by the previous measure.
Authors: Xiaozhou Ye, Kevin I-Kai Wang
Abstract: Cross-user variability poses a significant challenge in sensor-based Human Activity Recognition (HAR) systems, as traditional models struggle to generalize across users due to differences in behavior, sensor placement, and data distribution. To address this, we propose GNN-ADG (Graph Neural Network with Adversarial Domain Generalization), a novel method that leverages both the strength from both the Graph Neural Networks (GNNs) and adversarial learning to achieve robust cross-user generalization. GNN-ADG models spatial relationships between sensors on different anatomical body parts, extracting three types of Anatomical Units: (1) Interconnected Units, capturing inter-relations between neighboring sensors; (2) Analogous Units, grouping sensors on symmetrical or functionally similar body parts; and (3) Lateral Units, connecting sensors based on their position to capture region-specific coordination. These units information are fused into an unified graph structure with a cyclic training strategy, dynamically integrating spatial, functional, and lateral correlations to facilitate a holistic, user-invariant representation. Information fusion mechanism of GNN-ADG occurs by iteratively cycling through edge topologies during training, allowing the model to refine its understanding of inter-sensor relationships across diverse perspectives. By representing the spatial configuration of sensors as an unified graph and incorporating adversarial learning, Information Fusion GNN-ADG effectively learns features that generalize well to unseen users without requiring target user data during training, making it practical for real-world applications.
Authors: Andrew Kiruluta, Preethi Raju, Priscilla Burity
Abstract: We present a novel non attention based architecture for large language models (LLMs) that efficiently handles very long context windows, on the order of hundreds of thousands to potentially millions of tokens. Unlike traditional Transformer designs, which suffer from quadratic memory and computation overload due to the nature of the self attention mechanism, our model avoids token to token attention entirely. Instead, it combines the following complementary components: State Space blocks (inspired by S4) that learn continuous time convolution kernels and scale near linearly with sequence length, Multi Resolution Convolution layers that capture local context at different dilation levels, a lightweight Recurrent Supervisor to maintain a global hidden state across sequential chunks, and Retrieval Augmented External Memory that stores and retrieves high-level chunk embeddings without reintroducing quadratic operations.
Authors: Kamal Acharya, Mehul Lad, Liang Sun, Houbing Song
Abstract: Accurate prediction of trips between zones is critical for transportation planning, as it supports resource allocation and infrastructure development across various modes of transport. Although the gravity model has been widely used due to its simplicity, it often inadequately represents the complex factors influencing modern travel behavior. This study introduces a data-driven approach to enhance the gravity model by integrating geographical, economic, social, and travel data from the counties in Tennessee and New York state. Using machine learning techniques, we extend the capabilities of the traditional model to handle more complex interactions between variables. Our experiments demonstrate that machine learning-enhanced models significantly outperform the traditional model. Our results show a 51.48% improvement in R-squared, indicating a substantial enhancement in the model's explanatory power. Also, a 63.59% reduction in Mean Absolute Error (MAE) reflects a significant increase in prediction accuracy. Furthermore, a 44.32% increase in Common Part of Commuters (CPC) demonstrates improved prediction reliability. These findings highlight the substantial benefits of integrating diverse datasets and advanced algorithms into transportation models. They provide urban planners and policymakers with more reliable forecasting and decision-making tools.
Authors: Bonpagna Kann, Sandra Castellanos-Paez, Romain Rombourg, Philippe Lalanda
Abstract: As machine learning based systems become more integrated into daily life, they unlock new opportunities but face the challenge of adapting to dynamic data environments. Various forms of data shift-gradual, abrupt, or cyclic-threaten model accuracy, making continual adaptation essential. Continual Learning (CL) enables models to learn from evolving data streams while minimizing forgetting of prior knowledge. Among CL strategies, replay-based methods have proven effective, but their success relies on balancing memory constraints and retaining old class accuracy while learning new classes. This paper presents TaskVAE, a framework for replay-based CL in class-incremental settings. TaskVAE employs task-specific Variational Autoencoders (VAEs) to generate synthetic exemplars from previous tasks, which are then used to train the classifier alongside new task data. In contrast to traditional methods that require prior knowledge of the total class count or rely on a single VAE for all tasks, TaskVAE adapts flexibly to increasing tasks without such constraints. We focus on Human Activity Recognition (HAR) using IMU sensor-equipped devices. Unlike previous HAR studies that combine data across all users, our approach focuses on individual user data, better reflecting real-world scenarios where a person progressively learns new activities. Extensive experiments on 5 different HAR datasets show that TaskVAE outperforms experience replay methods, particularly with limited data, and exhibits robust performance as dataset size increases. Additionally, memory footprint of TaskVAE is minimal, being equivalent to only 60 samples per task, while still being able to generate an unlimited number of synthetic samples. The contributions lie in balancing memory constraints, task-specific generation, and long-term stability, making it a reliable solution for real-world applications in domains like HAR.
Authors: Yuzhou Zhu
Abstract: Deep neural networks employ specialized architectures for vision, sequential and language tasks, yet this proliferation obscures their underlying commonalities. We introduce a unified matrix-order framework that casts convolutional, recurrent and self-attention operations as sparse matrix multiplications. Convolution is realized via an upper-triangular weight matrix performing first-order transformations; recurrence emerges from a lower-triangular matrix encoding stepwise updates; attention arises naturally as a third-order tensor factorization. We prove algebraic isomorphism with standard CNN, RNN and Transformer layers under mild assumptions. Empirical evaluations on image classification (MNIST, CIFAR-10/100, Tiny ImageNet), time-series forecasting (ETTh1, Electricity Load Diagrams) and language modeling/classification (AG News, WikiText-2, Penn Treebank) confirm that sparse-matrix formulations match or exceed native model performance while converging in comparable or fewer epochs. By reducing architecture design to sparse pattern selection, our matrix perspective aligns with GPU parallelism and leverages mature algebraic optimization tools. This work establishes a mathematically rigorous substrate for diverse neural architectures and opens avenues for principled, hardware-aware network design.
Authors: Patrik Czak\'o, G\'abor Kert\'esz, S\'andor Sz\'en\'asi
Abstract: Quantization effectively reduces the serving costs of Large Language Models (LLMs) by speeding up data movement through compressed parameters and enabling faster operations via integer arithmetic. However, activating integer arithmetic requires quantizing both weights and activations, which poses challenges due to the significant outliers in LLMs that increase quantization error. In this work, we investigate these outliers with an emphasis on their effect on layer-wise quantization error, then examine how smoothing and rotation transform the observed values. Our primary contributions include introducing a new metric to measure and visualize quantization difficulty based on channel magnitudes, as well as proposing a hybrid approach that applies channel-wise scaling before rotation, supported by a mathematical formulation of its benefits.
Authors: Chang Liu, Jiangrong Shen, Xuming Ran, Mingkun Xu, Qi Xu, Yi Xu, Gang Pan
Abstract: Artificial neural networks (ANNs) have demonstrated outstanding performance in numerous tasks, but deployment in resource-constrained environments remains a challenge due to their high computational and memory requirements. Spiking neural networks (SNNs) operate through discrete spike events and offer superior energy efficiency, providing a bio-inspired alternative. However, current ANN-to-SNN conversion often results in significant accuracy loss and increased inference time due to conversion errors such as clipping, quantization, and uneven activation. This paper proposes a novel ANN-to-SNN conversion framework based on error compensation learning. We introduce a learnable threshold clipping function, dual-threshold neurons, and an optimized membrane potential initialization strategy to mitigate the conversion error. Together, these techniques address the clipping error through adaptive thresholds, dynamically reduce the quantization error through dual-threshold neurons, and minimize the non-uniformity error by effectively managing the membrane potential. Experimental results on CIFAR-10, CIFAR-100, ImageNet datasets show that our method achieves high-precision and ultra-low latency among existing conversion methods. Using only two time steps, our method significantly reduces the inference time while maintains competitive accuracy of 94.75% on CIFAR-10 dataset under ResNet-18 structure. This research promotes the practical application of SNNs on low-power hardware, making efficient real-time processing possible.
Authors: Ruizhuo Song, Beiming Yuan
Abstract: This paper thoroughly investigates the challenges of enhancing AI's abstract reasoning capabilities, with a particular focus on Raven's Progressive Matrices (RPM) tasks involving complex human-like concepts. Firstly, it dissects the empirical reality that traditional end-to-end RPM-solving models heavily rely on option pool configurations, highlighting that this dependency constrains the model's reasoning capabilities. To address this limitation, the paper proposes the Johnny architecture - a novel representation space-based framework for RPM-solving. Through the synergistic operation of its Representation Extraction Module and Reasoning Module, Johnny significantly enhances reasoning performance by supplementing primitive negative option configurations with a learned representation space. Furthermore, to strengthen the model's capacity for capturing positional relationships among local features, the paper introduces the Spin-Transformer network architecture, accompanied by a lightweight Straw Spin-Transformer variant that reduces computational overhead through parameter sharing and attention mechanism optimization. Experimental evaluations demonstrate that both Johnny and Spin-Transformer achieve superior performance on RPM tasks, offering innovative methodologies for advancing AI's abstract reasoning capabilities.
Authors: Kanwal Aalijah
Abstract: Urban planning plays a very important role in development modern cities. It effects the economic growth, quality of life, and environmental sustainability. Modern cities face challenges in managing traffic congestion. These challenges arise to due to rapid urbanization. In this study we will explore how AI can be used to understand the traffic and mobility related issues and its effects on the residents sentiment. The approach combines real-time traffic data with geo-located sentiment analysis, offering a comprehensive and dynamic approach to urban mobility planning. AI models and exploratory data analysis was used to predict traffic congestion patterns, analyze commuter behaviors, and identify congestion hotspots and dissatisfaction zones. The findings offer actionable recommendations for optimizing traffic flow, enhancing commuter experiences, and addressing city specific mobility challenges in the Middle East and beyond.
Authors: Jama Hussein Mohamud
Abstract: Pre-trained neural networks are commonly used and reused in the machine learning community. Alice trains a model for a particular task, and a part of her neural network is reused by Bob for a different task, often to great effect. To what can we ascribe Bob's success? This paper introduces an experimental setup through which factors contributing to Bob's empirical success could be studied in silico. As a result, we demonstrate that Bob might just be lucky: his task accuracy increases monotonically with the correlation between his task and Alice's. Even when Bob has provably uncorrelated tasks and input features from Alice's pre-trained network, he can achieve significantly better than random performance due to Alice's choice of network and optimizer. When there is little correlation between tasks, only reusing lower pre-trained layers is preferable, and we hypothesize the converse: that the optimal number of retrained layers is indicative of task and feature correlation. Finally, we show in controlled real-world scenarios that Bob can effectively reuse Alice's pre-trained network if there are semantic correlations between his and Alice's task.
Authors: Elham Kiyani, Venkatesh Ananchaperumal, Ahmad Peyvan, Mahendaran Uchimali, Gang Li, George Em Karniadakis
Abstract: Accurately modeling crack propagation is critical for predicting failure in engineering materials and structures, where small cracks can rapidly evolve and cause catastrophic damage. The interaction of cracks with discontinuities, such as holes, significantly affects crack deflection and arrest. Recent developments in discrete particle systems with multibody interactions based on constitutive behavior have demonstrated the ability to capture crack nucleation and evolution without relying on continuum assumptions. In this work, we use data from Constitutively Informed Particle Dynamics (CPD) simulations to train operator learning models, specifically Deep Operator Networks (DeepONets), which learn mappings between function spaces instead of finite-dimensional vectors. We explore two DeepONet variants: vanilla and Fusion DeepONet, for predicting time-evolving crack propagation in specimens with varying geometries. Three representative cases are studied: (i) varying notch height without active fracture; and (ii) and (iii) combinations of notch height and hole radius where dynamic fracture occurs on irregular discrete meshes. The models are trained on 32 to 45 samples, using geometric inputs in the branch network and spatial-temporal coordinates in the trunk network. Results show that Fusion DeepONet consistently outperforms the vanilla variant, with more accurate predictions especially in non-fracturing cases. Fracture-driven scenarios involving displacement and crack evolution remain more challenging. These findings highlight the potential of Fusion DeepONet to generalize across complex, geometry-varying, and time-dependent crack propagation phenomena.
Authors: Wei Huang, Hanchen Wang, Dong Wen, Shaozhen Ma, Wenjie Zhang, Xuemin Lin
Abstract: Graph Edit Distance (GED) is a fundamental graph similarity metric widely used in various applications. However, computing GED is an NP-hard problem. Recent state-of-the-art hybrid GED solver has shown promising performance by formulating GED as a bipartite graph matching problem, then leveraging a generative diffusion model to predict node matching between two graphs, from which both the GED and its corresponding edit path can be extracted using a traditional algorithm. However, such methods typically rely heavily on ground-truth supervision, where the ground-truth labels are often costly to obtain in real-world scenarios. In this paper, we propose GEDRanker, a novel unsupervised GAN-based framework for GED computation. Specifically, GEDRanker consists of a matching-based GED solver and introduces an interpretable preference-aware discriminator with an effective training strategy to guide the matching-based GED solver toward generating high-quality node matching without the need for ground-truth labels. Extensive experiments on benchmark datasets demonstrate that our GEDRanker enables the matching-based GED solver to achieve near-optimal solution quality without any ground-truth supervision.
Authors: Reyhaneh Keshavarzpour, Eghbal Mansoori
Abstract: Identification of antimicrobial peptides is an important and necessary issue in today's era. Antimicrobial peptides are essential as an alternative to antibiotics for biomedical applications and many other practical applications. These oligopeptides are useful in drug design and cause innate immunity against microorganisms. Artificial intelligence algorithms have played a significant role in the ease of identifying these peptides.This research is improved by improving proposed method in the field of antimicrobial peptides prediction. Suggested method is improved by combining the best coding method from different perspectives, In the following a deep neural network to balance the imbalanced combined datasets. The results of this research show that the proposed method have a significant improvement in the accuracy and efficiency of the prediction of antimicrobial peptides and are able to provide the best results compared to the existing methods. These development in the field of prediction and classification of antimicrobial peptides, basically in the fields of medicine and pharmaceutical industries, have high effectiveness and application.
Authors: Selin Yildirim, Deming Chen
Abstract: Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several candidate tokens, of which acceptance rate drives the speedup. However, deploying speculative decoding on memory-constrained devices, such as mobile GPUs, remains as a significant challenge in real-world scenarios. In this work, we present a device-aware inference engine named SpecMemo that can smartly control memory allocations at finer levels to enable multi-turn chatbots with speculative decoding on such limited memory devices. Our methodology stems from theoretically modeling memory footprint of speculative decoding to determine a lower bound on the required memory budget while retaining speedup. SpecMemo empirically acquires a careful balance between minimizing redundant memory allocations for rejected candidate tokens and maintaining competitive performance gains from speculation. Notably, with SpecMemo's memory management, we maintain 96% of overall throughput from speculative decoding on MT-Bench, with reduced generation-memory by 65% on single Nvidia Titan RTX. Given multiple constrained GPUs, we build on top of previous speculative decoding architectures to facilitate big-model inference by distributing Llama-2-70B-Chat model, on which we provide novel batched speculative decoding to increase usability of multiple small server GPUs. This novel framework demonstrates 2x speedup over distributed and batched vanilla decoding with the base model on eight AMD MI250 GPUs. Moreover, inference throughput increases remarkably 8x with batch size 10. Our work contributes to democratized LLM applications in resource-constrained environments, providing a pathway for faster and cheaper deployment of real-world LLM applications with robust performance.
Authors: Runkang Yang, Peng Sun, Xinyi Shang, Yi Tang, Tao Lin
Abstract: Data inherently possesses dual attributes: samples and targets. For targets, knowledge distillation has been widely employed to accelerate model convergence, primarily relying on teacher-generated soft target supervision. Conversely, recent advancements in data-efficient learning have emphasized sample optimization techniques, such as dataset distillation, while neglected the critical role of target. This dichotomy motivates our investigation into understanding how both sample and target collectively influence training dynamic. To address this gap, we first establish a taxonomy of existing paradigms through the lens of sample-target interactions, categorizing them into distinct sample-to-target mapping strategies. Building upon this foundation, we then propose a novel unified loss framework to assess their impact on training efficiency. Through extensive empirical studies on our proposed strategies, we comprehensively analyze how variations in target and sample types, quantities, and qualities influence model training, providing six key insights to enhance training efficacy.
Authors: Akshat Dubey, Aleksandar An\v{z}el, Georges Hattab
Abstract: The field of health informatics has been profoundly influenced by the development of random forest models, which have led to significant advances in the interpretability of feature interactions. These models are characterized by their robustness to overfitting and parallelization, making them particularly useful in this domain. However, the increasing number of features and estimators in random forests can prevent domain experts from accurately interpreting global feature interactions, thereby compromising trust and regulatory compliance. A method called the surrogate interpretability graph has been developed to address this issue. It uses graphs and mixed-integer linear programming to analyze and visualize feature interactions. This improves their interpretability by visualizing the feature usage per decision-feature-interaction table and the most dominant hierarchical decision feature interactions for predictions. The implementation of a surrogate interpretable graph enhances global interpretability, which is critical for such a high-stakes domain.
Authors: Chengxi Li, Ming Xiao, Mikael Skoglund
Abstract: In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of Byzantine attacks. However, current DL methods apply RBA rules for the local gradients from the honest devices and the disruptive information from Byzantine devices, and the learning performance degrades significantly when the local gradients of different devices vary considerably from each other. To overcome this limitation, we propose a new DL method to cope with Byzantine attacks based on coded robust aggregation (CRA-DL). Before training begins, the training data are allocated to the devices redundantly. During training, in each iteration, the honest devices transmit coded gradients to the server computed from the allocated training data, and the server then aggregates the information received from both honest and Byzantine devices using RBA rules. In this way, the global gradient can be approximately recovered at the server to update the global model. Compared with current DL methods applying RBA rules, the improvement of CRA-DL is attributed to the fact that the coded gradients sent by the honest devices are closer to each other. This closeness enhances the robustness of the aggregation against Byzantine attacks, since Byzantine messages tend to be significantly different from those of honest devices in this case. We theoretically analyze the convergence performance of CRA-DL. Finally, we present numerical results to verify the superiority of the proposed method over existing baselines, showing its enhanced learning performance under Byzantine attacks.
Authors: Qingyu Xiao, Yuanlin Chang, Youtian Du
Abstract: Effective agent exploration remains a core challenge in reinforcement learning (RL) for complex discrete state-space environments, particularly under partial observability. This paper presents a decoupled hierarchical RL framework integrating state abstraction (DcHRL-SA) to address this issue. The proposed method employs a dual-level architecture, consisting of a high level RL-based actor and a low-level rule-based policy, to promote effective exploration. Additionally, state abstraction method is incorporated to cluster discrete states, effectively lowering state dimensionality. Experiments conducted in two discrete customized grid environments demonstrate that the proposed approach consistently outperforms PPO in terms of exploration efficiency, convergence speed, cumulative reward, and policy stability. These results demonstrate a practical approach for integrating decoupled hierarchical policies and state abstraction in discrete grids with large-scale exploration space. Code will be available at https://github.com/XQY169/DcHRL-SA.
Authors: Xu Zhang, Haoye Qiu, Weixuan Liang, Hui Liu, Junhui Hou, Yuheng Jia
Abstract: Ensemble clustering has demonstrated great success in practice; however, its theoretical foundations remain underexplored. This paper examines the generalization performance of ensemble clustering, focusing on generalization error, excess risk and consistency. We derive a convergence rate of generalization error bound and excess risk bound both of $\mathcal{O}(\sqrt{\frac{\log n}{m}}+\frac{1}{\sqrt{n}})$, with $n$ and $m$ being the numbers of samples and base clusterings. Based on this, we prove that when $m$ and $n$ approach infinity and $m$ is significantly larger than log $n$, i.e., $m,n\to \infty, m\gg \log n$, ensemble clustering is consistent. Furthermore, recognizing that $n$ and $m$ are finite in practice, the generalization error cannot be reduced to zero. Thus, by assigning varying weights to finite clusterings, we minimize the error between the empirical average clusterings and their expectation. From this, we theoretically demonstrate that to achieve better clustering performance, we should minimize the deviation (bias) of base clustering from its expectation and maximize the differences (diversity) among various base clusterings. Additionally, we derive that maximizing diversity is nearly equivalent to a robust (min-max) optimization model. Finally, we instantiate our theory to develop a new ensemble clustering algorithm. Compared with SOTA methods, our approach achieves average improvements of 6.1%, 7.3%, and 6.0% on 10 datasets w.r.t. NMI, ARI, and Purity. The code is available at https://github.com/xuz2019/GPEC.
Authors: Malik A. Altayar, Muhyeeddin Alqaraleh, Mowafaq Salem Alzboon, Wesam T. Almagharbeh
Abstract: Introduction: Personal identification is a critical aspect of forensic sciences, security, and healthcare. While conventional biometrics systems such as DNA profiling and iris scanning offer high accuracy, they are time-consuming and costly. Objectives: This study investigates the relationship between fingerprint patterns and ABO blood group classification to explore potential correlations between these two traits. Methods: The study analyzed 200 individuals, categorizing their fingerprints into three types: loops, whorls, and arches. Blood group classification was also recorded. Statistical analysis, including chi-square and Pearson correlation tests, was used to assess associations between fingerprint patterns and blood groups. Results: Loops were the most common fingerprint pattern, while blood group O+ was the most prevalent among the participants. Statistical analysis revealed no significant correlation between fingerprint patterns and blood groups (p > 0.05), suggesting that these traits are independent. Conclusions: Although the study showed limited correlation between fingerprint patterns and ABO blood groups, it highlights the importance of future research using larger and more diverse populations, incorporating machine learning approaches, and integrating multiple biometric signals. This study contributes to forensic science by emphasizing the need for rigorous protocols and comprehensive investigations in personal identification.
Authors: Shriraj P. Sawant, Krishna P. Miyapuram
Abstract: The ability to learn and retain a wide variety of tasks is a hallmark of human intelligence that has inspired research in artificial general intelligence. Continual learning approaches provide a significant step towards achieving this goal. It has been known that task variability and context switching are challenging for learning in neural networks. Catastrophic forgetting refers to the poor performance on retention of a previously learned task when a new task is being learned. Switching between different task contexts can be a useful approach to mitigate the same by preventing the interference between the varying task weights of the network. This paper introduces Elastic Weight Generative Networks (EWGN) as an idea for context switching between two different tasks. The proposed EWGN architecture uses an additional network that generates the weights of the primary network dynamically while consolidating the weights learned. The weight generation is input-dependent and thus enables context switching. Using standard computer vision datasets, namely MNIST and fashion-MNIST, we analyse the retention of previously learned task representations in Fully Connected Networks, Convolutional Neural Networks, and EWGN architectures with Stochastic Gradient Descent and Elastic Weight Consolidation learning algorithms. Understanding dynamic weight generation and context-switching ability can be useful in enabling continual learning for improved performance.
Authors: Peter Holderrieth, Ezra Erives
Abstract: Diffusion and flow-based models have become the state of the art for generative AI across a wide range of data modalities, including images, videos, shapes, molecules, music, and more! These notes are originally from https://diffusion.csail.mit.edu/, as taught at MIT over the 2025 IAP (winter) term, and are intended to accompany other course content, including lectures and labs. Overall, they function as a self-contained introduction to both flow matching and diffusion models, starting with ordinary and stochastic differential equations, and culminating in flow matching, score matching, classifier-free guidance, and the inner workings of modern, state-of-the-art models for image and video. These notes, and the accompanying course, are ideal for students and practitioners alike who want to develop a principled understanding of the theory and practice of generative AI.
Authors: Yoonjun Cho, Soeun Kim, Dongjae Jeon, Kyelim Lee, Beomsoo Lee, Albert No
Abstract: Decomposing weight matrices into quantization and low-rank components ($\mathbf{W} \approx \mathbf{Q} + \mathbf{L}\mathbf{R}$) is a widely used technique for compressing large language models (LLMs). Existing joint optimization methods iteratively alternate between quantization and low-rank approximation. However, these methods tend to prioritize one component at the expense of the other, resulting in suboptimal decompositions that fail to leverage each component's unique strengths. In this work, we introduce Outlier-Driven Low-Rank Initialization (ODLRI), which assigns low-rank components the specific role of capturing activation-sensitive weights. This structured decomposition mitigates outliers' negative impact on quantization, enabling more effective balance between quantization and low-rank approximation. Experiments on Llama2 (7B, 13B, 70B), Llama3-8B, and Mistral-7B demonstrate that incorporating ODLRI into the joint optimization framework consistently reduces activation-aware error, minimizes quantization scale, and improves perplexity and zero-shot accuracy in low-bit settings.
Authors: Xuefeng Jiang, Tian Wen, Zhiqin Yang, Lvhua Wu, Yufeng Chen, Sheng Sun, Yuwei Wang, Min Liu
Abstract: In recent years, federated learning (FL) has made significant advance in privacy-sensitive applications. However, it can be hard to ensure that FL participants provide well-annotated data for training. The corresponding annotations from different clients often contain complex label noise at varying levels. This label noise issue has a substantial impact on the performance of the trained models, and clients with greater noise levels can be largely attributed for this degradation. To this end, it is necessary to develop an effective optimization strategy to alleviate the adverse effects of these noisy clients.In this study, we present a two-stage optimization framework, MaskedOptim, to address this intricate label noise problem. The first stage is designed to facilitate the detection of noisy clients with higher label noise rates. The second stage focuses on rectifying the labels of the noisy clients' data through an end-to-end label correction mechanism, aiming to mitigate the negative impacts caused by misinformation within datasets. This is achieved by learning the potential ground-truth labels of the noisy clients' datasets via backpropagation. To further enhance the training robustness, we apply the geometric median based model aggregation instead of the commonly-used vanilla averaged model aggregation. We implement sixteen related methods and conduct evaluations on three image datasets and one text dataset with diverse label noise patterns for a comprehensive comparison. Extensive experimental results indicate that our proposed framework shows its robustness in different scenarios. Additionally, our label correction framework effectively enhances the data quality of the detected noisy clients' local datasets. % Our codes will be open-sourced to facilitate related research communities. Our codes are available via https://github.com/Sprinter1999/MaskedOptim .
Authors: Chihiro Maru, Shoetsu Sato
Abstract: Inspired by the success of large language models (LLMs) in natural language processing, recent research has explored the building of time series foundation models and applied them to tasks such as forecasting, classification, and anomaly detection. However, their performances vary between different domains and tasks. In LLM-based approaches, test-time adaptation using example-based prompting has become common, owing to the high cost of retraining. In the context of anomaly detection, which is the focus of this study, providing normal examples from the target domain can also be effective. However, time series foundation models do not naturally acquire the ability to interpret or utilize examples or instructions, because the nature of time series data used during training does not encourage such capabilities. To address this limitation, we propose a retrieval augmented time series foundation model (RATFM), which enables pretrained time series foundation models to incorporate examples of test-time adaptation. We show that RATFM achieves a performance comparable to that of in-domain fine-tuning while avoiding domain-dependent fine-tuning. Experiments on the UCR Anomaly Archive, a multi-domain dataset including nine domains, confirms the effectiveness of the proposed approach.
Authors: Nikolaos Gkorgkolis, Nikolaos Kougioulis, MingXue Wang, Bora Caglayan, Andrea Tonon, Dario Simionato, Ioannis Tsamardinos
Abstract: Causal Discovery plays a pivotal role in revealing relationships among observed variables, particularly in the temporal setup. While the majority of CD methods rely on synthetic data for evaluation, and recently for training, these fall short in accurately mirroring real-world scenarios; an effect even more evident in temporal data. Generation techniques depending on simplified assumptions on causal structure, effects and time, limit the quality and diversity of the simulated data. In this work, we introduce Temporal Causal-based Simulation (TCS), a robust framework for generating realistic time-series data and their associated temporal causal graphs. The approach is structured in three phases: estimating the true lagged causal structure of the data, approximating the functional dependencies between variables and learning the noise distribution of the corresponding causal model, each part of which can be explicitly tailored based on data assumptions and characteristics. Through an extensive evaluation process, we highlight that single detection methods for generated data discrimination prove inadequate, accentuating it as a multifaceted challenge. For this, we detail a Min-max optimization phase that draws on AutoML techniques. Our contributions include a flexible, model-agnostic pipeline for generating realistic temporal causal data, a thorough evaluation setup which enhances the validity of the generated datasets and insights into the challenges posed by realistic data generation. Through experiments involving not only real but also semi-synthetic and purely synthetic datasets, we demonstrate that while sampling realistic causal data remains a complex task, our method enriches the domain of generating sensible causal-based temporal data.
Authors: Zeng Wang, Minghao Shao, Rupesh Karn, Jitendra Bhandari, Likhitha Mankali, Ramesh Karri, Ozgur Sinanoglu, Muhammad Shafique, Johann Knechtel
Abstract: Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.
Authors: Francesco De Santis, Philippe Bich, Gabriele Ciravegna, Pietro Barbiero, Danilo Giordano, Tania Cerquitelli
Abstract: To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-based model for image classification, named Learnable Concept-Based Model (LCBM) which models concepts as random variables within a Bernoulli latent space. Unlike traditional methods that either require extensive human supervision or suffer from limited scalability, our approach employs a reduced number of concepts without sacrificing performance. We demonstrate that LCBM surpasses existing unsupervised concept-based models in generalization capability and nearly matches the performance of black-box models. The proposed concept representation enhances information retention and aligns more closely with human understanding. A user study demonstrates the discovered concepts are also more intuitive for humans to interpret. Finally, despite the use of concept embeddings, we maintain model interpretability by means of a local linear combination of concepts.
Authors: Zijian Wu, Jinjie Ni, Xiangyan Liu, Zichen Liu, Hang Yan, Michael Qizhe Shieh
Abstract: Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively. In this work, we investigate how synthesized RL data can further improve RLVR. To this end, we propose \textbf{SynthRL}-a scalable and guaranteed pipeline for automatic data scaling in reasoning-oriented RL training. SynthRL comprises three key stages: (1) selecting seed questions with appropriate distribution, (2) augmenting them into more challenging variants while preserving the original answers, and (3) a guaranteed verification stage that ensures near-perfect correctness and difficulty enhancement. Our empirical experiments demonstrate SynthRL's scalability and effectiveness. When applied to the MMK12 dataset, SynthRL synthesizes over 3.3K additional verifiable, challenging questions from approximately 8K seed samples. Models trained with our synthesized data achieve consistent gains across five out-of-domain visual math reasoning benchmarks, with a significant improvement over baseline models trained on seed data alone. Notably, detailed analysis reveals that the gains are more pronounced on the most challenging evaluation samples, highlighting SynthRL's effectiveness in eliciting deeper and more complex reasoning patterns.
Authors: Miran \"Ozdogan, Gilad Landau, Gereon Elvers, Dulhan Jayalath, Pratik Somaiya, Francesco Mantegna, Mark Woolrich, Oiwi Parker Jones
Abstract: LibriBrain represents the largest single-subject MEG dataset to date for speech decoding, with over 50 hours of recordings -- 5$\times$ larger than the next comparable dataset and 50$\times$ larger than most. This unprecedented `depth' of within-subject data enables exploration of neural representations at a scale previously unavailable with non-invasive methods. LibriBrain comprises high-quality MEG recordings together with detailed annotations from a single participant listening to naturalistic spoken English, covering nearly the full Sherlock Holmes canon. Designed to support advances in neural decoding, LibriBrain comes with a Python library for streamlined integration with deep learning frameworks, standard data splits for reproducibility, and baseline results for three foundational decoding tasks: speech detection, phoneme classification, and word classification. Baseline experiments demonstrate that increasing training data yields substantial improvements in decoding performance, highlighting the value of scaling up deep, within-subject datasets. By releasing this dataset, we aim to empower the research community to advance speech decoding methodologies and accelerate the development of safe, effective clinical brain-computer interfaces.
Authors: Rishi Raj Sahoo, Rucha Bhalchandra Joshi, Subhankar Mishra
Abstract: Graph Neural Networks (GNNs) achieve high performance across many applications but function as black-box models, limiting their use in critical domains like healthcare and criminal justice. Explainability methods address this by providing feature-level explanations that identify important node attributes for predictions. These explanations create privacy risks. Combined with auxiliary information, feature explanations can enable adversaries to reconstruct graph structure, exposing sensitive relationships. Existing graph reconstruction attacks assume access to original auxiliary data, but practical systems use differential privacy to protect node features and labels while providing explanations for transparency. We study a threat model where adversaries access public feature explanations along with privatized node features and labels. We show that existing explanation-based attacks like GSEF perform poorly with privatized data due to noise from differential privacy mechanisms. We propose ReconXF, a graph reconstruction attack for scenarios with public explanations and privatized auxiliary data. Our method adapts explanation-based frameworks by incorporating denoising mechanisms that handle differential privacy noise while exploiting structural signals in explanations. Experiments across multiple datasets show ReconXF outperforms SoTA methods in privatized settings, with improvements in AUC and average precision. Results indicate that public explanations combined with denoising enable graph structure recovery even under the privacy protection of auxiliary data. Code is available at (link to be made public after acceptance).
Authors: Yarden Bakish, Itamar Zimerman, Hila Chefer, Lior Wolf
Abstract: The development of effective explainability tools for Transformers is a crucial pursuit in deep learning research. One of the most promising approaches in this domain is Layer-wise Relevance Propagation (LRP), which propagates relevance scores backward through the network to the input space by redistributing activation values based on predefined rules. However, existing LRP-based methods for Transformer explainability entirely overlook a critical component of the Transformer architecture: its positional encoding (PE), resulting in violation of the conservation property, and the loss of an important and unique type of relevance, which is also associated with structural and positional features. To address this limitation, we reformulate the input space for Transformer explainability as a set of position-token pairs. This allows us to propose specialized theoretically-grounded LRP rules designed to propagate attributions across various positional encoding methods, including Rotary, Learnable, and Absolute PE. Extensive experiments with both fine-tuned classifiers and zero-shot foundation models, such as LLaMA 3, demonstrate that our method significantly outperforms the state-of-the-art in both vision and NLP explainability tasks. Our code is publicly available.
Authors: Guillaume Godin
Abstract: Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that minimizes outlier influence during training by masking the contribution of data points identified as out-of-distribution within each batch. This method leverages batch-level statistics to automatically detect and exclude anomalous samples, allowing the model to focus its learning on the true underlying data structure. Our approach is robust, adaptive to data quality, and provides valuable diagnostics for data curation and cleaning.
Authors: Hrushikesh N. Mhaskar, Efstratios Tsoukanis, Ameya D. Jagtap
Abstract: A central problem in machine learning is often formulated as follows: Given a dataset $\{(x_j, y_j)\}_{j=1}^M$, which is a sample drawn from an unknown probability distribution, the goal is to construct a functional model $f$ such that $f(x) \approx y$ for any $(x, y)$ drawn from the same distribution. Neural networks and kernel-based methods are commonly employed for this task due to their capacity for fast and parallel computation. The approximation capabilities, or expressive power, of these methods have been extensively studied over the past 35 years. In this paper, we will present examples of key ideas in this area found in the literature. We will discuss emerging trends in machine learning including the role of shallow/deep networks, approximation on manifolds, physics-informed neural surrogates, neural operators, and transformer architectures. Despite function approximation being a fundamental problem in machine learning, approximation theory does not play a central role in the theoretical foundations of the field. One unfortunate consequence of this disconnect is that it is often unclear how well trained models will generalize to unseen or unlabeled data. In this review, we examine some of the shortcomings of the current machine learning framework and explore the reasons for the gap between approximation theory and machine learning practice. We will then introduce our novel research to achieve function approximation on unknown manifolds without the need to learn specific manifold features, such as the eigen-decomposition of the Laplace-Beltrami operator or atlas construction. In many machine learning problems, particularly classification tasks, the labels $y_j$ are drawn from a finite set of values.
Authors: Shiangyi Lin, Hui Lan, Vasilis Syrgkanis
Abstract: Traditional instrumental variable (IV) estimators face a fundamental constraint: they can only accommodate as many endogenous treatment variables as available instruments. This limitation becomes particularly challenging in settings where the treatment is presented in a high-dimensional and unstructured manner (e.g. descriptions of patient treatment pathways in a hospital). In such settings, researchers typically resort to applying unsupervised dimension reduction techniques to learn a low-dimensional treatment representation prior to implementing IV regression analysis. We show that such methods can suffer from substantial omitted variable bias due to implicit regularization in the representation learning step. We propose a novel approach to construct treatment representations by explicitly incorporating instrumental variables during the representation learning process. Our approach provides a framework for handling high-dimensional endogenous variables with limited instruments. We demonstrate both theoretically and empirically that fitting IV models on these instrument-informed representations ensures identification of directions that optimize outcome prediction. Our experiments show that our proposed methodology improves upon the conventional two-stage approaches that perform dimension reduction without incorporating instrument information.
Authors: Navid NaderiAlizadeh, Darian Salehi, Xinran Liu, Soheil Kolouri
Abstract: Sliced Wasserstein (SW) distances offer an efficient method for comparing high-dimensional probability measures by projecting them onto multiple 1-dimensional probability distributions. However, identifying informative slicing directions has proven challenging, often necessitating a large number of slices to achieve desirable performance and thereby increasing computational complexity. We introduce a constrained learning approach to optimize the slicing directions for SW distances. Specifically, we constrain the 1D transport plans to approximate the optimal plan in the original space, ensuring meaningful slicing directions. By leveraging continuous relaxations of these transport plans, we enable a gradient-based primal-dual approach to train the slicer parameters, alongside the remaining model parameters. We demonstrate how this constrained slicing approach can be applied to pool high-dimensional embeddings into fixed-length permutation-invariant representations. Numerical results on foundation models trained on images, point clouds, and protein sequences showcase the efficacy of the proposed constrained learning approach in learning more informative slicing directions. Our implementation code can be found at https://github.com/Stranja572/constrainedswe.
Authors: Yuliang Gu, Hongpeng Cao, Marco Caccamo, Naira Hovakimyan
Abstract: The Cross-Entropy Method (CEM) is a widely adopted trajectory optimizer in model-based reinforcement learning (MBRL), but its unimodal sampling strategy often leads to premature convergence in multimodal landscapes. In this work, we propose Bregman Centroid Guided CEM ($\mathcal{BC}$-EvoCEM), a lightweight enhancement to ensemble CEM that leverages $\textit{Bregman centroids}$ for principled information aggregation and diversity control. $\textbf{$\mathcal{BC}$-EvoCEM}$ computes a performance-weighted Bregman centroid across CEM workers and updates the least contributing ones by sampling within a trust region around the centroid. Leveraging the duality between Bregman divergences and exponential family distributions, we show that $\textbf{$\mathcal{BC}$-EvoCEM}$ integrates seamlessly into standard CEM pipelines with negligible overhead. Empirical results on synthetic benchmarks, a cluttered navigation task, and full MBRL pipelines demonstrate that $\textbf{$\mathcal{BC}$-EvoCEM}$ enhances both convergence and solution quality, providing a simple yet effective upgrade for CEM.
Authors: Hongling Xu, Qi Zhu, Heyuan Deng, Jinpeng Li, Lu Hou, Yasheng Wang, Lifeng Shang, Ruifeng Xu, Fei Mi
Abstract: Recent advances in large language model (LLM) post-training have leveraged two distinct paradigms to enhance reasoning capabilities: reinforcement learning (RL) and knowledge distillation (KD). While RL enables the emergence of complex reasoning behaviors, it often suffers from low sample efficiency when the initial policy struggles to explore high-reward trajectories. Conversely, KD improves learning efficiency via mimicking the teacher model but tends to generalize poorly to out-of-domain scenarios. In this work, we present \textbf{KDRL}, a \textit{unified post-training framework} that jointly optimizes a reasoning model through teacher supervision (KD) and self-exploration (RL). Specifically, KDRL leverages policy gradient optimization to simultaneously minimize the reverse Kullback-Leibler divergence (RKL) between the student and teacher distributions while maximizing the expected rule-based rewards. We first formulate a unified objective that integrates GRPO and KD, and systematically explore how different KL approximations, KL coefficients, and reward-guided KD strategies affect the overall post-training dynamics and performance. Empirical results on multiple reasoning benchmarks demonstrate that KDRL outperforms GRPO and various KD baselines while achieving a favorable balance between performance and reasoning token efficiency. These findings indicate that integrating KD and RL serves as an effective and efficient strategy to train reasoning LLMs.
Authors: Pu (Luke), Yi, Tianlang Chen, Yifan Yang, Sara Achour
Abstract: Neural networks (NNs) are equipped with increasingly many parameters and require more and more resource for deployment. Researchers have explored various ways to improve the efficiency of NNs by identifying and reducing the redundancy, such as pruning or quantizing unimportant weights. Symmetry in the NN architectures has been identified by prior work as a possible type of redundancy, but exploiting it for efficient inference is not yet explored. In this work, we formalize the symmetry of parameters and intermediate values in NNs using the statistical property of exchangeablility. We identify that exchangeable values in NN computation may contain overlapping information, leading to redundancy. Exploiting the insight, we derive a principled general dynamic pruning algorithm ExPrune to remove symmetry-induced redundancy on a per-input basis. We also provide an instantiation of ExPrune that performs neuron-level dynamic pruning by predicting negative inputs to ReLU activations. We evaluate ExPrune on two computer vision models, one graph model and one language model. ExPrune provides 10.98--26.3% reduction in FLOPs with negligible accuracy drop and 21.01--39.05% reduction in FLOPs with at most 1% accuracy drop. We also demonstrate that ExPrune composes with static pruning. On models that have been aggressively pruned statically, ExPrune provides additional 10.24--11.11% reduction in FLOPs with negligible accuracy drop and 13.91--14.39% reduction in FLOPs with at most 1% accuracy drop.
Authors: Kahn Rhrissorrakrai, Kathleen E. Hamilton, Prerana Bangalore Parthsarathy, Aldo Guzman-Saenz, Tyler Alban, Filippo Utro, Laxmi Parida
Abstract: Learning on small data is a challenge frequently encountered in many real-world applications. In this work we study how effective quantum ensemble models are when trained on small data problems in healthcare and life sciences. We constructed multiple types of quantum ensembles for binary classification using up to 26 qubits in simulation and 56 qubits on quantum hardware. Our ensemble designs use minimal trainable parameters but require long-range connections between qubits. We tested these quantum ensembles on synthetic datasets and gene expression data from renal cell carcinoma patients with the task of predicting patient response to immunotherapy. From the performance observed in simulation and initial hardware experiments, we demonstrate how quantum embedding structure affects performance and discuss how to extract informative features and build models that can learn and generalize effectively. We present these exploratory results in order to assist other researchers in the design of effective learning on small data using ensembles. Incorporating quantum computing in these data constrained problems offers hope for a wide range of studies in healthcare and life sciences where biological samples are relatively scarce given the feature space to be explored.
Authors: Yihong Tang, Ao Qu, Xujing Yu, Weipeng Deng, Jun Ma, Jinhua Zhao, Lijun Sun
Abstract: Urban and transportation research has long sought to uncover statistically meaningful relationships between key variables and societal outcomes such as road safety, to generate actionable insights that guide the planning, development, and renewal of urban and transportation systems. However, traditional workflows face several key challenges: (1) reliance on human experts to propose hypotheses, which is time-consuming and prone to confirmation bias; (2) limited interpretability, particularly in deep learning approaches; and (3) underutilization of unstructured data that can encode critical urban context. Given these limitations, we propose a Multimodal Large Language Model (MLLM)-based approach for interpretable hypothesis inference, enabling the automated generation, evaluation, and refinement of hypotheses concerning urban context and road safety outcomes. Our method leverages MLLMs to craft safety-relevant questions for street view images (SVIs), extract interpretable embeddings from their responses, and apply them in regression-based statistical models. UrbanX supports iterative hypothesis testing and refinement, guided by statistical evidence such as coefficient significance, thereby enabling rigorous scientific discovery of previously overlooked correlations between urban design and safety. Experimental evaluations on Manhattan street segments demonstrate that our approach outperforms pretrained deep learning models while offering full interpretability. Beyond road safety, UrbanX can serve as a general-purpose framework for urban scientific discovery, extracting structured insights from unstructured urban data across diverse socioeconomic and environmental outcomes. This approach enhances model trustworthiness for policy applications and establishes a scalable, statistically grounded pathway for interpretable knowledge discovery in urban and transportation studies.
Authors: Tamara Cucumides, Floris Geerts
Abstract: Tabular and relational data remain the most ubiquitous formats in real-world machine learning applications, spanning domains from finance to healthcare. Although both formats offer structured representations, they pose distinct challenges for modern deep learning methods, which typically assume flat, feature-aligned inputs. Graph Neural Networks (GNNs) have emerged as a promising solution by capturing structural dependencies within and between tables. However, existing GNN-based approaches often rely on rigid, schema-derived graphs -- such as those based on primary-foreign key links -- thereby underutilizing rich, predictive signals in non key attributes. In this work, we introduce auGraph, a unified framework for task-aware graph augmentation that applies to both tabular and relational data. auGraph enhances base graph structures by selectively promoting attributes into nodes, guided by scoring functions that quantify their relevance to the downstream prediction task. This augmentation preserves the original data schema while injecting task-relevant structural signal. Empirically, auGraph outperforms schema-based and heuristic graph construction methods by producing graphs that better support learning for relational and tabular prediction tasks.
Authors: Asha Ramanujam (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Adam Elyoumi (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Hao Chen (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Sai Madhukiran Kompalli (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Akshdeep Singh Ahluwalia (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Shraman Pal (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Dimitri J. Papageorgiou (Energy Sciences, ExxonMobil Technology and Engineering Company, Annandale, NJ), Can Li (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN)
Abstract: Most existing safe reinforcement learning (RL) benchmarks focus on robotics and control tasks, offering limited relevance to high-stakes domains that involve structured constraints, mixed-integer decisions, and industrial complexity. This gap hinders the advancement and deployment of safe RL in critical areas such as energy systems, manufacturing, and supply chains. To address this limitation, we present SafeOR-Gym, a benchmark suite of nine operations research (OR) environments tailored for safe RL under complex constraints. Each environment captures a realistic planning, scheduling, or control problems characterized by cost-based constraint violations, planning horizons, and hybrid discrete-continuous action spaces. The suite integrates seamlessly with the Constrained Markov Decision Process (CMDP) interface provided by OmniSafe. We evaluate several state-of-the-art safe RL algorithms across these environments, revealing a wide range of performance: while some tasks are tractable, others expose fundamental limitations in current approaches. SafeOR-Gym provides a challenging and practical testbed that aims to catalyze future research in safe RL for real-world decision-making problems. The SafeOR-Gym framework and all accompanying code are available at: https://github.com/li-group/SafeOR-Gym.
Authors: Yi Xiao, Harshit Sharma, Sawinder Kaur, Dessa Bergen-Cico, Asif Salekin
Abstract: Stress affects physical and mental health, and wearable devices have been widely used to detect daily stress through physiological signals. However, these signals vary due to factors such as individual differences and health conditions, making generalizing machine learning models difficult. To address these challenges, we present Human Heterogeneity Invariant Stress Sensing (HHISS), a domain generalization approach designed to find consistent patterns in stress signals by removing person-specific differences. This helps the model perform more accurately across new people, environments, and stress types not seen during training. Its novelty lies in proposing a novel technique called person-wise sub-network pruning intersection to focus on shared features across individuals, alongside preventing overfitting by leveraging continuous labels while training. The study focuses especially on people with opioid use disorder (OUD)-a group where stress responses can change dramatically depending on their time of daily medication taking. Since stress often triggers cravings, a model that can adapt well to these changes could support better OUD rehabilitation and recovery. We tested HHISS on seven different stress datasets-four of which we collected ourselves and three public ones. Four are from lab setups, one from a controlled real-world setting, driving, and two are from real-world in-the-wild field datasets without any constraints. This is the first study to evaluate how well a stress detection model works across such a wide range of data. Results show HHISS consistently outperformed state-of-the-art baseline methods, proving both effective and practical for real-world use. Ablation studies, empirical justifications, and runtime evaluations confirm HHISS's feasibility and scalability for mobile stress sensing in sensitive real-world applications.
Authors: YuQing Xie, Tess Smidt
Abstract: Equivariant neural networks have proven to be effective for tasks with known underlying symmetries. However, optimizing equivariant networks can be tricky and best training practices are less established than for standard networks. In particular, recent works have found small training benefits from relaxing equivariance constraints. This raises the question: do equivariance constraints introduce fundamental obstacles to optimization? Or do they simply require different hyperparameter tuning? In this work, we investigate this question through a theoretical analysis of the loss landscape geometry. We focus on networks built using permutation representations, which we can view as a subset of unconstrained MLPs. Importantly, we show that the parameter symmetries of the unconstrained model has nontrivial effects on the loss landscape of the equivariant subspace and under certain conditions can provably prevent learning of the global minima. Further, we empirically demonstrate in such cases, relaxing to an unconstrained MLP can sometimes solve the issue. Interestingly, the weights eventually found via relaxation corresponds to a different choice of group representation in the hidden layer. From this, we draw 3 key takeaways. (1) Viewing any class of networks in the context of larger unconstrained function space can give important insights on loss landscape structure. (2) Within the unconstrained function space, equivariant networks form a complicated union of linear hyperplanes, each associated with a specific choice of internal group representation. (3) Effective relaxation of equivariance may require not only adding nonequivariant degrees of freedom, but also rethinking the fixed choice of group representations in hidden layers.
Authors: Saurabh Singh, Dmitry Lagun
Abstract: Stochastic Interpolants (SI) are a powerful framework for generative modeling, capable of flexibly transforming between two probability distributions. However, their use in jointly optimized latent variable models remains unexplored as they require direct access to the samples from the two distributions. This work presents Latent Stochastic Interpolants (LSI) enabling joint learning in a latent space with end-to-end optimized encoder, decoder and latent SI models. We achieve this by developing a principled Evidence Lower Bound (ELBO) objective derived directly in continuous time. The joint optimization allows LSI to learn effective latent representations along with a generative process that transforms an arbitrary prior distribution into the encoder-defined aggregated posterior. LSI sidesteps the simple priors of the normal diffusion models and mitigates the computational demands of applying SI directly in high-dimensional observation spaces, while preserving the generative flexibility of the SI framework. We demonstrate the efficacy of LSI through comprehensive experiments on the standard large scale ImageNet generation benchmark.
Authors: Qinsi Wang, Jinghan Ke, Hancheng Ye, Yueqian Lin, Yuzhe Fu, Jianyi Zhang, Kurt Keutzer, Chenfeng Xu, Yiran Chen
Abstract: Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform data sampling. While previous work has explored curriculum learning via heuristic difficulty metrics, these strategies exhibit limitations by neglecting the intrinsic learning signals generated by the model itself, thus leading to suboptimal training regimes. In this paper, we identify a model-inherent signal termed angle concentration that effectively reflects an LLM's capacity to learn from specific data. We theoretically and empirically demonstrate a correlation between the angular distribution of token hidden state vectors and the resulting gradient, revealing a learning preference for data exhibiting higher angle concentration. Inspired by this finding, we propose GAIN-RL, a Gradient-driven Angle-Informed Navigated RL framework. By leveraging the model's intrinsic angle concentration signal, GAIN-RL dynamically selects training data in each epoch, ensuring consistently impactful gradient updates and thus significantly enhancing overall training efficiency. Empirical evaluations show that GAIN-RL (GRPO) achieves over a 2.5x acceleration in training efficiency across diverse mathematical and coding tasks and varying model scales. Furthermore, GAIN-RL (GRPO)'s efficient sampling yields data-efficient training, achieving better performance with half the original data compared to vanilla GRPO with full training data. Code is realsed at https://github.com/wangqinsi1/GAINRL/tree/main.
Authors: Aaron Defazio
Abstract: During long-duration Large Language Model (LLM) training runs the gradient norm increases rapidly near the end of training. In this short note, we show that this increase is due to an unintended interaction between weight decay, normalization layers, and the learning rate schedule. We propose a simple correction that fixes this behavior while also resulting in lower loss values throughout training.
Authors: Marco Pacini, Gabriele Santin, Bruno Lepri, Shubhendu Trivedi
Abstract: Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separation power, that is, the ability to distinguish inputs modulo symmetry. This notion plays a central role in settings such as graph learning, where it is often formalized via the Weisfeiler-Leman hierarchy. In contrast, the universality of equivariant models-their capacity to approximate target functions-remains comparatively underexplored. In this work, we investigate the approximation power of equivariant neural networks beyond separation constraints. We show that separation power does not fully capture expressivity: models with identical separation power may differ in their approximation ability. To demonstrate this, we characterize the universality classes of shallow invariant networks, providing a general framework for understanding which functions these architectures can approximate. Since equivariant models reduce to invariant ones under projection, this analysis yields sufficient conditions under which shallow equivariant networks fail to be universal. Conversely, we identify settings where shallow models do achieve separation-constrained universality. These positive results, however, depend critically on structural properties of the symmetry group, such as the existence of adequate normal subgroups, which may not hold in important cases like permutation symmetry.
Authors: Farzaneh Mahdisoltani, Saeed Mahdisoltani, Roger B. Grosse, David J. Fleet
Abstract: Understanding the internal representations and decision mechanisms of deep neural networks remains a critical open challenge. While existing interpretability methods often identify influential input regions, they may not elucidate how a model distinguishes between classes or what specific changes would transition an input from one category to another. To address these limitations, we propose a novel framework that visualizes the implicit path between classes by treating the network gradient as a form of infinitesimal motion. Drawing inspiration from phase-based motion magnification, we first decompose images using invertible transforms-specifically the Complex Steerable Pyramid-then compute class-conditional gradients in the transformed space. Rather than iteratively integrating the gradient to trace a full path, we amplify the one-step gradient to the input and perform a linear extrapolation to expose how the model moves from source to target class. By operating in the steerable pyramid domain, these amplified gradients produce semantically meaningful, spatially coherent morphs that highlight the classifier's most sensitive directions, giving insight into the geometry of its decision boundaries. Experiments on both synthetic and real-world datasets demonstrate that our phase-focused extrapolation yields perceptually aligned, semantically meaningful transformations, offering a novel, interpretable lens into neural classifiers' internal representations.
Authors: Aditya Gorla, Ryan Wang, Zhengtong Liu, Ulzee An, Sriram Sankararaman
Abstract: We present CACTI, a masked autoencoding approach for imputing tabular data that leverages the structure in missingness patterns and contextual information. Our approach employs a novel median truncated copy masking training strategy that encourages the model to learn from empirical patterns of missingness while incorporating semantic relationships between features - captured by column names and text descriptions - to better represent feature dependence. These dual sources of inductive bias enable CACTI to outperform state-of-the-art methods - an average $R^2$ gain of 7.8% over the next best method (13.4%, 6.1%, and 5.3% under missing not at random, at random and completely at random, respectively) - across a diverse range of datasets and missingness conditions. Our results highlight the value of leveraging dataset-specific contextual information and missingness patterns to enhance imputation performance.
Authors: Xiaojun Shan, Qi Cao, Xing Han, Haofei Yu, Paul Pu Liang
Abstract: Recent advances in multimodal foundation models have achieved state-of-the-art performance across a range of tasks. These breakthroughs are largely driven by new pre-training paradigms that leverage large-scale, unlabeled multimodal data, followed by instruction fine-tuning on curated labeled datasets and high-quality prompts. While there is growing interest in scaling instruction fine-tuning to ever-larger datasets in both quantity and scale, our findings reveal that simply increasing the number of instruction-tuning tasks does not consistently yield better performance. Instead, we observe that grouping tasks by the common interactions across modalities, such as discovering redundant shared information, prioritizing modality selection with unique information, or requiring synergistic fusion to discover new information from both modalities, encourages the models to learn transferrable skills within a group while suppressing interference from mismatched tasks. To this end, we introduce MINT, a simple yet surprisingly effective task-grouping strategy based on the type of multimodal interaction. We demonstrate that the proposed method greatly outperforms existing task grouping baselines for multimodal instruction tuning, striking an effective balance between generalization and specialization.
Authors: D. Isaiah Harp, Joshua Ott, John Alora, Dylan Asmar
Abstract: The justification for the "test point" derives from the test pilot's obligation to reproduce faithfully the pre-specified conditions of some model prediction. Pilot deviation from those conditions invalidates the model assumptions. Flight test aids have been proposed to increase accuracy on more challenging test points. However, the very existence of databands and tolerances is the problem more fundamental than inadequate pilot skill. We propose a novel approach, which eliminates test points. We start with a high-fidelity digital model of an air vehicle. Instead of using this model to generate a point prediction, we use a machine learning method to produce a reduced-order model (ROM). The ROM has two important properties. First, it can generate a prediction based on any set of conditions the pilot flies. Second, if the test result at those conditions differ from the prediction, the ROM can be updated using the new data. The outcome of flight test is thus a refined ROM at whatever conditions were flown. This ROM in turn updates and validates the high-fidelity model. We present a single example of this "point-less" architecture, using T-38C flight test data. We first use a generic aircraft model to build a ROM of longitudinal pitching motion as a hypersurface. We then ingest unconstrained flight test data and use Gaussian Process Regression to update and condition the hypersurface. By proposing a second-order equivalent system for the T-38C, this hypersurface then generates parameters necessary to assess MIL-STD-1797B compliance for longitudinal dynamics.
Authors: Yuchen Liang, Renxiang Huang, Lifeng Lai, Ness Shroff, Yingbin Liang
Abstract: Discrete state space diffusion models have shown significant advantages in applications involving discrete data, such as text and image generation. It has also been observed that their performance is highly sensitive to the choice of rate matrices, particularly between uniform and absorbing rate matrices. While empirical results suggest that absorbing rate matrices often yield better generation quality compared to uniform rate matrices, existing theoretical works have largely focused on the uniform rate matrices case. Notably, convergence guarantees and error analyses for absorbing diffusion models are still missing. In this work, we provide the first finite-time error bounds and convergence rate analysis for discrete diffusion models using absorbing rate matrices. We begin by deriving an upper bound on the KL divergence of the forward process, introducing a surrogate initialization distribution to address the challenge posed by the absorbing stationary distribution, which is a singleton and causes the KL divergence to be ill-defined. We then establish the first convergence guarantees for both the $\tau$-leaping and uniformization samplers under absorbing rate matrices, demonstrating improved rates over their counterparts using uniform rate matrices. Furthermore, under suitable assumptions, we provide convergence guarantees without early stopping. Our analysis introduces several new technical tools to address challenges unique to absorbing rate matrices. These include a Jensen-type argument for bounding forward process convergence, novel techniques for bounding absorbing score functions, and a non-divergent upper bound on the score near initialization that removes the need of early-stopping.
Authors: Aleix Boquet-Pujadas, Pol del Aguila Pla, Michael Unser
Abstract: We formulate an optimization problem to estimate probability densities in the context of multidimensional problems that are sampled with uneven probability. It considers detector sensitivity as an heterogeneous density and takes advantage of the computational speed and flexible boundary conditions offered by splines on a grid. We choose to regularize the Hessian of the spline via the nuclear norm to promote sparsity. As a result, the method is spatially adaptive and stable against the choice of the regularization parameter, which plays the role of the bandwidth. We test our computational pipeline on standard densities and provide software. We also present a new approach to PET rebinning as an application of our framework.
Authors: Adrienne M. Propp, Jonas A. Actor, Elise Walker, Houman Owhadi, Nathaniel Trask, Daniel M. Tartakovsky
Abstract: Dirichlet-to-Neumann maps enable the coupling of multiphysics simulations across computational subdomains by ensuring continuity of state variables and fluxes at artificial interfaces. We present a novel method for learning Dirichlet-to-Neumann maps on graphs using Gaussian processes, specifically for problems where the data obey a conservation constraint from an underlying partial differential equation. Our approach combines discrete exterior calculus and nonlinear optimal recovery to infer relationships between vertex and edge values. This framework yields data-driven predictions with uncertainty quantification across the entire graph, even when observations are limited to a subset of vertices and edges. By optimizing over the reproducing kernel Hilbert space norm while applying a maximum likelihood estimation penalty on kernel complexity, our method ensures that the resulting surrogate strictly enforces conservation laws without overfitting. We demonstrate our method on two representative applications: subsurface fracture networks and arterial blood flow. Our results show that the method maintains high accuracy and well-calibrated uncertainty estimates even under severe data scarcity, highlighting its potential for scientific applications where limited data and reliable uncertainty quantification are critical.
Authors: Andre He, Daniel Fried, Sean Welleck
Abstract: Reinforcement learning has emerged as an effective framework for training large language models on structured language-conditioned tasks. We identify a critical flaw of Group Relative Policy Optimization (GRPO), a widely used RL algorithm in this setting. For tasks that require multi-sample performance, such as formal theorem proving, GRPO biasedly reinforces already probable solutions and neglects rare but correct proofs. This implicit bias impairs performance on pass@$N$ metrics at large sample sizes, limiting its practicality for training theorem provers. To address this, we introduce the unlikeliness reward, a straightforward method that explicitly encourages reinforcing rare correct solutions. Additionally, we find that increasing the number of PPO epochs further mitigates this bias. Our experiments confirm that incorporating the unlikeliness reward significantly improves pass@$N$ across a large range of N, outperforming standard GRPO and substantially increasing sample diversity. Applying our revised recipe to Lean, we achieve competitive performance with DeepSeek-Prover-V1.5-RL on the miniF2F-test benchmark. We release our implementation, providing a simple yet effective recipe for training formal theorem provers with RL.
Authors: Ram Potham (Independent Researcher)
Abstract: Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these conflict with operational goals. Failure to prioritize such principles indicates a potential basic control failure. This paper introduces a lightweight, interpretable benchmark methodology using a simple grid world to evaluate an LLM agent's ability to uphold a predefined, high-level safety principle (e.g., "never enter hazardous zones") when faced with conflicting lower-level task instructions. We probe whether the agent reliably prioritizes the inviolable directive, testing a foundational controllability aspect of LLMs. This pilot study demonstrates the methodology's feasibility, offers preliminary insights into agent behavior under principle conflict, and discusses how such benchmarks can contribute empirical evidence for assessing controllability. We argue that evaluating adherence to hierarchical principles is a crucial early step in understanding our capacity to build governable AI systems.
Authors: Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, Haibo Yang
Abstract: Recent dimension-free communication frameworks in Federated Learning (FL), such as DeComFL, significantly reduce per-round communication by transmitting only scalars via zeroth-order stochastic gradient descent (ZO-SGD). This method is particularly advantageous for federated fine-tuning of Large Language Models (LLMs). Yet, the high variance in ZO gradient estimation typically leads to slow convergence. Although leveraging Hessian information is known to enhance optimization speed, integrating this into FL presents significant challenges. These include clients' restrictions on local data and the critical need to maintain the dimension-free communication property. To overcome this limitation, we first introduce a generalized scalar-only communication FL framework that decouples dimension-free communication from standard ZO-SGD, enabling the integration of more advanced optimization strategies. Building on this framework, we propose HiSo, a fast federated fine-tuning method via Hessian-informed zeroth-order optimization and Scalar-only communication. Specifically, it leverages global curvature information to accelerate convergence while preserving the same minimal communication cost per round. Theoretically, we establish convergence guarantees that are independent of the global Lipschitz constant, and further show that HiSo achieves faster rates when the global Hessian exhibits a low effective rank -- a common phenomenon in LLMs. Extensive experiments on benchmark datasets and LLM fine-tuning tasks confirm that HiSo significantly outperforms existing ZO-based FL methods in both convergence speed and communication efficiency.
Authors: Haoye Lu, Darren Lo, Yaoliang Yu
Abstract: Diffusion models achieve strong generative performance but often rely on large datasets that may include sensitive content. This challenge is compounded by the models' tendency to memorize training data, raising privacy concerns. SFBD (Lu et al., 2025) addresses this by training on corrupted data and using limited clean samples to capture local structure and improve convergence. However, its iterative denoising and fine-tuning loop requires manual coordination, making it burdensome to implement. We reinterpret SFBD as an alternating projection algorithm and introduce a continuous variant, SFBD flow, that removes the need for alternating steps. We further show its connection to consistency constraint-based methods, and demonstrate that its practical instantiation, Online SFBD, consistently outperforms strong baselines across benchmarks.
Authors: Shuze Chen, Tianyi Peng
Abstract: Value decomposition has long been a fundamental technique in multi-agent dynamic programming and reinforcement learning (RL). Specifically, the value function of a global state $(s_1,s_2,\ldots,s_N)$ is often approximated as the sum of local functions: $V(s_1,s_2,\ldots,s_N)\approx\sum_{i=1}^N V_i(s_i)$. This approach traces back to the index policy in restless multi-armed bandit problems and has found various applications in modern RL systems. However, the theoretical justification for why this decomposition works so effectively remains underexplored. In this paper, we uncover the underlying mathematical structure that enables value decomposition. We demonstrate that a multi-agent Markov decision process (MDP) permits value decomposition if and only if its transition matrix is not "entangled" -- a concept analogous to quantum entanglement in quantum physics. Drawing inspiration from how physicists measure quantum entanglement, we introduce how to measure the "Markov entanglement" for multi-agent MDPs and show that this measure can be used to bound the decomposition error in general multi-agent MDPs. Using the concept of Markov entanglement, we proved that a widely-used class of index policies is weakly entangled and enjoys a sublinear $\mathcal O(\sqrt{N})$ scale of decomposition error for $N$-agent systems. Finally, we show how Markov entanglement can be efficiently estimated in practice, providing practitioners with an empirical proxy for the quality of value decomposition.
Authors: Jie Bian, Vincent Y. F. Tan
Abstract: The challenge of identifying the best feasible arm within a fixed budget has attracted considerable interest in recent years. However, a notable gap remains in the literature: the exact exponential rate at which the error probability approaches zero has yet to be established, even in the relatively simple setting of $K$-armed bandits with Gaussian noise. In this paper, we address this gap by examining the problem within the context of linear bandits. We introduce a novel algorithm for best feasible arm identification that guarantees an exponential decay in the error probability. Remarkably, the decay rate -- characterized by the exponent -- matches the theoretical lower bound derived using information-theoretic principles. Our approach leverages a posterior sampling framework embedded within a game-based sampling rule involving a min-learner and a max-learner. This strategy shares its foundations with Thompson sampling, but is specifically tailored to optimize the identification process under fixed-budget constraints. Furthermore, we validate the effectiveness of our algorithm through comprehensive empirical evaluations across various problem instances with different levels of complexity. The results corroborate our theoretical findings and demonstrate that our method outperforms several benchmark algorithms in terms of both accuracy and efficiency.
Authors: Chamara Madarasingha, Nasrin Sohrabi, Zahir Tari
Abstract: Time-series prediction or forecasting is critical across many real-world dynamic systems, and recent studies have proposed using Large Language Models (LLMs) for this task due to their strong generalization capabilities and ability to perform well without extensive pre-training. However, their effectiveness in handling complex, noisy, and multivariate time-series data remains underexplored. To address this, we propose LLMPred which enhances LLM-based time-series prediction by converting time-series sequences into text and feeding them to LLMs for zero shot prediction along with two main data pre-processing techniques. First, we apply time-series sequence decomposition to facilitate accurate prediction on complex and noisy univariate sequences. Second, we extend this univariate prediction capability to multivariate data using a lightweight prompt-processing strategy. Extensive experiments with smaller LLMs such as Llama 2 7B, Llama 3.2 3B, GPT-4o-mini, and DeepSeek 7B demonstrate that LLMPred achieves competitive or superior performance compared to state-of-the-art baselines. Additionally, a thorough ablation study highlights the importance of the key components proposed in LLMPred.
Authors: Qin Xie, Qinghua Zhang, Shuyin Xia, Xinran Zhou, Guoyin Wang
Abstract: Adaptive Boosting (AdaBoost) faces significant challenges posed by label noise, especially in multiclass classification tasks. Existing methods either lack mechanisms to handle label noise effectively or suffer from high computational costs due to redundant data usage. Inspired by granular computing, this paper proposes granular adaptive boosting (GAdaBoost), a novel two-stage framework comprising a data granulation stage and an adaptive boosting stage, to enhance efficiency and robustness under noisy conditions. To validate its feasibility, an extension of SAMME, termed GAdaBoost.SA, is proposed. Specifically, first, a granular-ball generation method is designed to compress data while preserving diversity and mitigating label noise. Second, the granular ball-based SAMME algorithm focuses on granular balls rather than individual samples, improving efficiency and reducing sensitivity to noise. Experimental results on some noisy datasets show that the proposed approach achieves superior robustness and efficiency compared with existing methods, demonstrating that this work effectively extends AdaBoost and SAMME.
Authors: Yuanyao Chen, Rongsheng Chen, Fu Luo, Zhenkun Wang
Abstract: Neural Combinatorial Optimization (NCO) has emerged as a promising learning-based paradigm for addressing Vehicle Routing Problems (VRPs) by minimizing the need for extensive manual engineering. While existing NCO methods, trained on small-scale instances (e.g., 100 nodes), have demonstrated considerable success on problems of similar scale, their performance significantly degrades when applied to large-scale scenarios. This degradation arises from the distributional shift between training and testing data, rendering policies learned on small instances ineffective for larger problems. To overcome this limitation, we introduce a novel learning framework driven by Large Language Models (LLMs). This framework learns a projection between the training and testing distributions, which is then deployed to enhance the scalability of the NCO model. Notably, unlike prevailing techniques that necessitate joint training with the neural network, our approach operates exclusively during the inference phase, obviating the need for model retraining. Extensive experiments demonstrate that our method enables a backbone model (trained on 100-node instances) to achieve superior performance on large-scale Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) of up to 100K nodes from diverse distributions.
Authors: Renat Sergazinov, Jing Wu, Shao-An Yin
Abstract: While random Fourier features are a classic tool in kernel methods, their utility as a pre-processing step for deep learning on tabular data has been largely overlooked. Motivated by shortcomings in tabular deep learning pipelines - revealed through Neural Tangent Kernel (NTK) analysis - we revisit and repurpose random Fourier mappings as a parameter-free, architecture-agnostic transformation. By projecting each input into a fixed feature space via sine and cosine projections with frequencies drawn once at initialization, this approach circumvents the need for ad hoc normalization or additional learnable embeddings. We show within the NTK framework that this mapping (i) bounds and conditions the network's initial NTK spectrum, and (ii) introduces a bias that shortens the optimization trajectory, thereby accelerating gradient-based training. These effects pre-condition the network with a stable kernel from the outset. Empirically, we demonstrate that deep networks trained on Fourier-transformed inputs converge more rapidly and consistently achieve strong final performance, often with fewer epochs and less hyperparameter tuning. Our findings establish random Fourier pre-processing as a theoretically motivated, plug-and-play enhancement for tabular deep learning.
Authors: Karthikeyan Vaiapury
Abstract: Optimization remains a fundamental pillar of machine learning, yet existing methods often struggle to maintain stability and adaptability in dynamic, non linear systems, especially under uncertainty. We introduce AERO (Adversarial Energy-based Redirection Optimization), a novel framework inspired by the redirection principle in Judo, where external disturbances are leveraged rather than resisted. AERO reimagines optimization as a redirection process guided by 15 interrelated axioms encompassing adversarial correction, energy conservation, and disturbance-aware learning. By projecting gradients, integrating uncertainty driven dynamics, and managing learning energy, AERO offers a principled approach to stable and robust model updates. Applied to probabilistic solar energy forecasting, AERO demonstrates substantial gains in predictive accuracy, reliability, and adaptability, especially in noisy and uncertain environments. Our findings highlight AERO as a compelling new direction in the theoretical and practical landscape of optimization.
Authors: Pratheeksha Nair, Reihaneh Rabbany
Abstract: Node classification in real world graphs often suffers from label scarcity and noise, especially in high stakes domains like human trafficking detection and misinformation monitoring. While direct supervision is limited, such graphs frequently contain weak signals, noisy or indirect cues, that can still inform learning. We propose WSNET, a novel weakly supervised graph contrastive learning framework that leverages these weak signals to guide robust representation learning. WSNET integrates graph structure, node features, and multiple noisy supervision sources through a contrastive objective tailored for weakly labeled data. Across three real world datasets and synthetic benchmarks with controlled noise, WSNET consistently outperforms state of the art contrastive and noisy label learning methods by up to 15% in F1 score. Our results highlight the effectiveness of contrastive learning under weak supervision and the promise of exploiting imperfect labels in graph based settings.
Authors: Jiaxi Hu, Yongqi Pan, Jusen Du, Disen Lan, Xiaqiang Tang, Qingsong Wen, Yuxuan Liang, Weigao Sun
Abstract: Recent efficient sequence modeling methods such as Gated DeltaNet, TTT, and RWKV-7 have achieved performance improvements by supervising the recurrent memory management through Delta learning rule. Unlike previous state-space models (e.g., Mamba) and gated linear attentions (e.g., GLA), these models introduce interactions between the recurrent state and the key vector, resulting in a nonlinear recursive structure. In this paper, we first introduce the concept of Nonlinear RNNs with a comprehensive analysis on the advantages and limitations of these models. Then, based on closed-loop control theory, we propose a novel Nonlinear RNN variant named Comba, which adopts a scalar-plus-low-rank state transition, with both state feedback and output feedback corrections. We also implement a hardware-efficient chunk-wise parallel kernel in Triton and train models with 340M/1.3B parameters on large-scale corpus. Comba demonstrates its superior performance and computation efficiency in both language and vision modeling.
Authors: Xingyu Chen, Bokun Wang, Ming Yang, Quanqi Hu, Qihang Lin, Tianbao Yang
Abstract: Finite-sum Coupled Compositional Optimization (FCCO), characterized by its coupled compositional objective structure, emerges as an important optimization paradigm for addressing a wide range of machine learning problems. In this paper, we focus on a challenging class of non-convex non-smooth FCCO, where the outer functions are non-smooth weakly convex or convex and the inner functions are smooth or weakly convex. Existing state-of-the-art result face two key limitations: (1) a high iteration complexity of $O(1/\epsilon^6)$ under the assumption that the stochastic inner functions are Lipschitz continuous in expectation; (2) reliance on vanilla SGD-type updates, which are not suitable for deep learning applications. Our main contributions are two fold: (i) We propose stochastic momentum methods tailored for non-smooth FCCO that come with provable convergence guarantees; (ii) We establish a new state-of-the-art iteration complexity of $O(1/\epsilon^5)$. Moreover, we apply our algorithms to multiple inequality constrained non-convex optimization problems involving smooth or weakly convex functional inequality constraints. By optimizing a smoothed hinge penalty based formulation, we achieve a new state-of-the-art complexity of $O(1/\epsilon^5)$ for finding an (nearly) $\epsilon$-level KKT solution. Experiments on three tasks demonstrate the effectiveness of the proposed algorithms.
Authors: Thong Q. Nguyen, Shubhang Desai, Yash Jain, Tanvir Aumi, Vishal Chowdhary
Abstract: Continual memory augmentation allows computer-use agents (CUAs) to learn from past interactions and refine their task-solving strategies over time. However, unchecked memory accumulation can introduce spurious or hallucinated "learnings" that degrade agent performance, particularly in domain-specific workflows such as productivity software. We present a novel framework, VerificAgent, that effectively manages memory for CUAs through (1) an expert-curated seed of domain knowledge, (2) iterative, trajectory-based memory refinement during training, and (3) a post-hoc fact-checking pass by human experts to sanitize accumulated memory before deployment. On OSWorld productivity tasks, VerificAgent achieves a 111.1% relative improvement in success rate over baseline CUA without any additional fine-tuning.
Authors: Minsung Kim, Nakyeong Yang, Kyomin Jung
Abstract: Machine unlearning is used to mitigate the privacy risks of Large Vision-Language Models (LVLMs) arising from training on large-scale web data. However, existing unlearning methods often fail to carefully select substitute outputs for forget targets, resulting in Unlearning Aftermaths-undesirable behaviors such as degenerate, hallucinated, or excessively refused responses. We highlight that, especially for generative LVLMs, it is crucial to consider the quality and informativeness of post-unlearning responses rather than relying solely on naive suppression. To address this, we introduce a new unlearning task for LVLMs that requires models to provide privacy-preserving yet informative and visually grounded responses. We also propose PUBG, a novel unlearning method that explicitly guides post-unlearning behavior toward a desirable output distribution. Experiments show that, while existing methods suffer from Unlearning Aftermaths despite successfully preventing privacy violations, PUBG effectively mitigates these issues, generating visually grounded and informative responses without privacy leakage for forgotten targets.
Authors: Niklas Kormann, Masoud Ramuz, Zeeshan Nisar, Nadine S. Schaadt, Hendrik Annuth, Benjamin Doerr, Friedrich Feuerhake, Thomas Lampert, Johannes F. Lutzeyer
Abstract: Graph Neural Networks (GNNs) have recently been found to excel in histopathology. However, an important histopathological task, where GNNs have not been extensively explored, is the classification of glomeruli health as an important indicator in nephropathology. This task presents unique difficulties, particularly for the graph construction, i.e., the identification of nodes, edges, and informative features. In this work, we propose a pipeline composed of different traditional and machine learning-based computer vision techniques to identify nodes, edges, and their corresponding features to form a heterogeneous graph. We then proceed to propose a novel heterogeneous GNN architecture for glomeruli classification, called HIEGNet, that integrates both glomeruli and their surrounding immune cells. Hence, HIEGNet is able to consider the immune environment of each glomerulus in its classification. Our HIEGNet was trained and tested on a dataset of Whole Slide Images from kidney transplant patients. Experimental results demonstrate that HIEGNet outperforms several baseline models and generalises best between patients among all baseline models. Our implementation is publicly available at https://github.com/nklsKrmnn/HIEGNet.git.
Authors: Shenghua He, Tian Xia, Xuan Zhou, Hui Wei
Abstract: We study a common challenge in reinforcement learning for large language models (LLMs): the Zero-Reward Assumption, where non-terminal actions (i.e., intermediate token generations) receive zero task-specific immediate reward, while only the final token receives a reward for the entire response. This assumption arises frequently in practice, as precise token-level rewards are often difficult or infeasible to obtain in LLM applications. In this work, we provide a unifying theoretical perspective. We introduce the Trajectory Policy Gradient Theorem, which shows that the policy gradient based on true, unknown token-level rewards can be unbiasedly estimated using only a response-level reward model, regardless of whether the Zero-Reward Assumption holds or not, for algorithms in the REINFORCE and Actor-Critic families. This result reveals that widely used methods such as PPO, GRPO, ReMax, and RLOO inherently possess the capacity to model token-level reward signals, offering a theoretical justification for response-level reward approaches. Our findings pave the way for more practical, efficient LLM fine-tuning, allowing developers to treat training algorithms as black boxes and focus on improving the response-level reward model with auxiliary sub-models. We also offer a detailed analysis of popular RL and non-RL methods, comparing their theoretical foundations and practical advantages across common LLM tasks. Finally, we propose a new algorithm: Token-Reinforced Policy Optimization (TRePO), a theoretically grounded method that is simpler than PPO, matches GRPO in memory efficiency, and holds promise for broad applicability.
Authors: Roie Reshef, Kfir Yehuda Levy
Abstract: This paper tackles the challenge of achieving Differential Privacy (DP) in Federated Learning (FL) under partial-participation, where only a subset of the machines participate in each time-step. While previous work achieved optimal performance in full-participation settings, these methods struggled to extend to partial-participation scenarios. Our approach fills this gap by introducing a novel noise-cancellation mechanism that preserves privacy without sacrificing convergence rates or computational efficiency. We analyze our method within the Stochastic Convex Optimization (SCO) framework and show that it delivers optimal performance for both homogeneous and heterogeneous data distributions. This work expands the applicability of DP in FL, offering an efficient and practical solution for privacy-preserving learning in distributed systems with partial participation.
Authors: Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li
Abstract: Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$ attention mechanisms have been proposed to accelerate LLM inference by exploiting the inherent sparsity of attention, they often struggled to strike a balance between efficiency and accuracy. In this paper, we introduce HATA (Hash-Aware Top-$k$ Attention), a novel approach that systematically integrates low-overhead learning-to-hash techniques into the Top-$k$ attention process. Different from the existing top-k attention methods which are devoted to seeking an absolute estimation of qk score, typically with a great cost, HATA maps queries and keys into binary hash codes, and acquires the relative qk score order with a quite low cost, which is sufficient for realizing top-k attention. Extensive experiments demonstrate that HATA achieves up to 7.2$\times$ speedup compared to vanilla full attention while maintaining model accuracy. In addition, HATA outperforms the state-of-the-art top-$k$ attention methods in both accuracy and efficiency across multiple mainstream LLM models and diverse tasks. HATA is open source at https://github.com/gpzlx1/HATA.
Authors: Wenyan Yang, Joni Pajarinen
Abstract: Offline goal-conditioned reinforcement learning (RL) relies on fixed datasets where many potential goals share the same state and action spaces. However, these potential goals are not explicitly represented in the collected trajectories. To learn a generalizable goal-conditioned policy, it is common to sample goals and state-action pairs uniformly using dynamic programming methods such as Q-learning. Uniform sampling, however, requires an intractably large dataset to cover all possible combinations and creates many unreachable state-goal-action pairs that degrade policy performance. Our key insight is that sampling should favor transitions that enable goal achievement. To this end, we propose Reachability Weighted Sampling (RWS). RWS uses a reachability classifier trained via positive-unlabeled (PU) learning on goal-conditioned state-action values. The classifier maps these values to a reachability score, which is then used as a sampling priority. RWS is a plug-and-play module that integrates seamlessly with standard offline RL algorithms. Experiments on six complex simulated robotic manipulation tasks, including those with a robot arm and a dexterous hand, show that RWS significantly improves performance. In one notable case, performance on the HandBlock-Z task improved by nearly 50 percent relative to the baseline. These results indicate the effectiveness of reachability-weighted sampling.
Authors: Niklas Ro{\ss}berg, Marion Neumeier, Sinan Hasirlioglu, Mohamed Essayed Bouzouraa, Michael Botsch
Abstract: The ability to operate safely in increasingly complex traffic scenarios is a fundamental requirement for Automated Driving Systems (ADS). Ensuring the safe release of ADS functions necessitates a precise understanding of the occurring traffic scenarios. To support this objective, this work introduces a pipeline for traffic scenario clustering and the analysis of scenario category completeness. The Clustering Vector Quantized - Variational Autoencoder (CVQ-VAE) is employed for the clustering of highway traffic scenarios and utilized to create various catalogs with differing numbers of traffic scenario categories. Subsequently, the impact of the number of categories on the completeness considerations of the traffic scenario categories is analyzed. The results show an outperforming clustering performance compared to previous work. The trade-off between cluster quality and the amount of required data to maintain completeness is discussed based on the publicly available highD dataset.
Authors: Jan Robine, Marc H\"oftmann, Stefan Harmeling
Abstract: What are the essential components of world models? How far do we get with world models that are not employing RNNs, transformers, discrete representations, and image reconstructions? This paper introduces SGF, a Simple, Good, and Fast world model that uses self-supervised representation learning, captures short-time dependencies through frame and action stacking, and enhances robustness against model errors through data augmentation. We extensively discuss SGF's connections to established world models, evaluate the building blocks in ablation studies, and demonstrate good performance through quantitative comparisons on the Atari 100k benchmark.
Authors: Qi Liao, Parijat Bhattacharjee
Abstract: Self-organizing networks face challenges from complex parameter interdependencies and conflicting objectives. This study introduces two compositional learning approaches-Compositional Deep Reinforcement Learning (CDRL) and Compositional Predictive Decision-Making (CPDM)-and evaluates their performance under training time and safety constraints in multi-agent systems. We propose a modular, two-tier framework with cell-level and cell-pair-level agents to manage heterogeneous agent granularities while reducing model complexity. Numerical simulations reveal a significant reduction in handover failures, along with improved throughput and latency, outperforming conventional multi-agent deep reinforcement learning approaches. The approach also demonstrates superior scalability, faster convergence, higher sample efficiency, and safer training in large-scale self-organizing networks.
Authors: Yanbei Liu, Chongxu Wang, Zhitao Xiao, Lei Geng, Yanwei Pang, Xiao Wang
Abstract: Heterogeneous Graph Neural Networks (HGNNs), have demonstrated excellent capabilities in processing heterogeneous information networks. Self-supervised learning on heterogeneous graphs, especially contrastive self-supervised strategy, shows great potential when there are no labels. However, this approach requires the use of carefully designed graph augmentation strategies and the selection of positive and negative samples. Determining the exact level of similarity between sample pairs is non-trivial.To solve this problem, we propose a novel self-supervised Heterogeneous graph neural network with Optimal Transport (HGOT) method which is designed to facilitate self-supervised learning for heterogeneous graphs without graph augmentation strategies. Different from traditional contrastive self-supervised learning, HGOT employs the optimal transport mechanism to relieve the laborious sampling process of positive and negative samples. Specifically, we design an aggregating view (central view) to integrate the semantic information contained in the views represented by different meta-paths (branch views). Then, we introduce an optimal transport plan to identify the transport relationship between the semantics contained in the branch view and the central view. This allows the optimal transport plan between graphs to align with the representations, forcing the encoder to learn node representations that are more similar to the graph space and of higher quality. Extensive experiments on four real-world datasets demonstrate that our proposed HGOT model can achieve state-of-the-art performance on various downstream tasks. In particular, in the node classification task, HGOT achieves an average of more than 6% improvement in accuracy compared with state-of-the-art methods.
Authors: Yuyang Zhou, Ferrante Neri, Yew-Soon Ong, Ruibin Bai
Abstract: Modern neural architecture search (NAS) is inherently multi-objective, balancing trade-offs such as accuracy, parameter count, and computational cost. This complexity makes NAS computationally expensive and nearly impossible to solve without efficient approximations. To address this, we propose a novel surrogate modelling approach that leverages an ensemble of Siamese network blocks to predict dominance relationships between candidate architectures. Lightweight and easy to train, the surrogate achieves 92% accuracy and replaces the crowding distance calculation in the survivor selection strategy with a heuristic rule based on model size. Integrated into a framework termed SiamNAS, this design eliminates costly evaluations during the search process. Experiments on NAS-Bench-201 demonstrate the framework's ability to identify Pareto-optimal solutions with significantly reduced computational costs. The proposed SiamNAS identified a final non-dominated set containing the best architecture in NAS-Bench-201 for CIFAR-10 and the second-best for ImageNet, in terms of test error rate, within 0.01 GPU days. This proof-of-concept study highlights the potential of the proposed Siamese network surrogate model to generalise to multi-tasking optimisation, enabling simultaneous optimisation across tasks. Additionally, it offers opportunities to extend the approach for generating Sets of Pareto Sets (SOS), providing diverse Pareto-optimal solutions for heterogeneous task settings.
Authors: Tom Jacobs, Advait Gadhikar, Celia Rubio-Madrigal, Rebekka Burkholz
Abstract: Understanding the implicit bias of optimization algorithms has become central to explaining the generalization behavior of deep learning models. For instance, the hyperbolic implicit bias induced by the overparameterization $m \odot w$--though effective in promoting sparsity--can result in a small effective learning rate, which slows down convergence. To overcome this obstacle, we propose HAM (Hyperbolic Aware Minimization), which alternates between an optimizer step and a new hyperbolic mirror step. We derive the Riemannian gradient flow for its combination with gradient descent, leading to improved convergence and a similar beneficial hyperbolic geometry as $m \odot w$ for feature learning. We provide an interpretation of the the algorithm by relating it to natural gradient descent, and an exact characterization of its implicit bias for underdetermined linear regression. HAM's implicit bias consistently boosts performance--even of dense training, as we demonstrate in experiments across diverse tasks, including vision, graph and node classification, and large language model fine-tuning. HAM is especially effective in combination with different sparsification methods, improving upon the state of the art. The hyperbolic step requires minimal computational and memory overhead, it succeeds even with small batch sizes, and its implementation integrates smoothly with existing optimizers.
Authors: Shiyu Shen, Bin Pan, Guirong Xue
Abstract: City-scale traffic volume prediction plays a pivotal role in intelligent transportation systems, yet remains a challenge due to the inherent incompleteness and bias in observational data. Although deep learning-based methods have shown considerable promise, most existing approaches produce deterministic point estimates, thereby neglecting the uncertainty arising from unobserved traffic flows. Furthermore, current models are typically trained in a city-specific manner, which hinders their generalizability and limits scalability across diverse urban contexts. To overcome these limitations, we introduce TrafficPPT, a Pretrained Probabilistic Transformer designed to model traffic volume as a distributional aggregation of trajectories. Our framework fuses heterogeneous data sources-including real-time observations, historical trajectory data, and road network topology-enabling robust and uncertainty-aware traffic inference. TrafficPPT is initially pretrained on large-scale simulated data spanning multiple urban scenarios, and later fine-tuned on target cities to ensure effective domain adaptation. Experiments on real-world datasets show that TrafficPPT consistently surpasses state-of-the-art baselines, particularly under conditions of extreme data sparsity. Code will be open.
Authors: Tianci Liu, Tong Yang, Quan Zhang, Qi Lei
Abstract: As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI techniques such as unauthorized personalization through DreamBooth that are misused. However, these methods offer only short-term security, as they require retraining whenever the underlying model architectures change. To establish long-term protection aiming at better robustness, we go beyond invisible perturbation, and propose a universal approach that embeds \textit{visible} watermarks that are \textit{hard-to-remove} into images. Grounded in a new probabilistic and inverse problem-based formulation, our framework maximizes the discrepancy between the \textit{optimal} reconstruction and the original content. We develop an effective and efficient approximation algorithm to circumvent a intractable bi-level optimization. Experimental results demonstrate superiority of our approach across diverse scenarios.
Authors: Daichi Kimura, Tomonori Izumitani, Hisashi Kashima
Abstract: Various Transformer-based models have been proposed for time series forecasting. These models leverage the self-attention mechanism to capture long-term temporal or variate dependencies in sequences. Existing methods can be divided into two approaches: (1) reducing computational cost of attention by making the calculations sparse, and (2) reshaping the input data to aggregate temporal features. However, existing attention mechanisms may not adequately capture inherent nonlinear dependencies present in time series data, leaving room for improvement. In this study, we propose a novel attention mechanism based on Chatterjee's rank correlation coefficient, which measures nonlinear dependencies between variables. Specifically, we replace the matrix multiplication in standard attention mechanisms with this rank coefficient to measure the query-key relationship. Since computing Chatterjee's correlation coefficient involves sorting and ranking operations, we introduce a differentiable approximation employing SoftSort and SoftRank. Our proposed mechanism, ``XicorAttention,'' integrates it into several state-of-the-art Transformer models. Experimental results on real-world datasets demonstrate that incorporating nonlinear correlation into the attention improves forecasting accuracy by up to approximately 9.1\% compared to existing models.
Authors: Khizar Hayat, Baptiste Magnier
Abstract: This study critically examines the methodological rigor in credit card fraud detection research, revealing how fundamental evaluation flaws can overshadow algorithmic sophistication. Through deliberate experimentation with improper evaluation protocols, we demonstrate that even simple models can achieve deceptively impressive results when basic methodological principles are violated. Our analysis identifies four critical issues plaguing current approaches: (1) pervasive data leakage from improper preprocessing sequences, (2) intentional vagueness in methodological reporting, (3) inadequate temporal validation for transaction data, and (4) metric manipulation through recall optimization at precision's expense. We present a case study showing how a minimal neural network architecture with data leakage outperforms many sophisticated methods reported in literature, achieving 99.9\% recall despite fundamental evaluation flaws. These findings underscore that proper evaluation methodology matters more than model complexity in fraud detection research. The study serves as a cautionary example of how methodological rigor must precede architectural sophistication, with implications for improving research practices across machine learning applications.
Authors: Jayadev Naram, Fredrik Hellstr\"om, Ziming Wang, Rebecka J\"ornsten, Giuseppe Durisi
Abstract: In many scenarios of practical interest, labeled data from a target distribution are scarce while labeled data from a related source distribution are abundant. One particular setting of interest arises when the target label space is a subset of the source label space, leading to the framework of partial domain adaptation (PDA). Typical approaches to PDA involve minimizing a domain alignment term and a weighted empirical loss on the source data, with the aim of transferring knowledge between domains. However, a theoretical basis for this procedure is lacking, and in particular, most existing weighting schemes are heuristic. In this work, we derive generalization bounds for the PDA problem based on partial optimal transport. These bounds corroborate the use of the partial Wasserstein distance as a domain alignment term, and lead to theoretically motivated explicit expressions for the empirical source loss weights. Inspired by these bounds, we devise a practical algorithm for PDA, termed WARMPOT. Through extensive numerical experiments, we show that WARMPOT is competitive with recent approaches, and that our proposed weights improve on existing schemes.
Authors: Guanzhong Chen, Shaoxiong Yang, Chao Li, Wei Liu, Jian Luan, Zenglin Xu
Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse natural language processing tasks, yet their deployment in real-world applications is hindered by fixed knowledge cutoffs and difficulties in generating controllable, accurate outputs in a single inference. Multi-agent systems (MAS) built from specialized LLM agents offer a promising solution, enabling dynamic collaboration and iterative reasoning. However, optimizing these systems remains a challenge, as conventional methods such as prompt engineering and supervised fine-tuning entail high engineering overhead and limited adaptability. Reinforcement learning (RL), particularly multi-agent reinforcement learning (MARL), provides a scalable framework by refining agent policies based on system-level feedback. Nevertheless, existing MARL algorithms, such as Multi-Agent Proximal Policy Optimization (MAPPO), rely on Critic networks, which can cause training instability and increase computational burden. To address these limitations and target the prototypical Multi-Agent Search System (MASS), we propose Multi-Agent Heterogeneous Group Policy Optimization (MHGPO), a novel Critic-free algorithm that guides policy updates by estimating relative reward advantages across heterogeneous groups of rollouts. MHGPO eliminates the need for Critic networks, enhancing stability and reducing computational overhead. Additionally, we introduce three group rollout sampling strategies that trade off between efficiency and effectiveness. Experiments on a multi-agent LLM-based search system demonstrate that MHGPO consistently outperforms MAPPO in both task performance and computational efficiency, without requiring warm-up, underscoring its potential for stable and scalable optimization of complex LLM-based MAS.
Authors: Andrey Veprikov, Vladimir Solodkin, Alexander Zyl, Andrey Savchenko, Aleksandr Beznosikov
Abstract: The widespread utilization of language models in modern applications is inconceivable without Parameter-Efficient Fine-Tuning techniques, such as low-rank adaptation ($\texttt{LoRA}$), which adds trainable adapters to selected layers. Although $\texttt{LoRA}$ may obtain accurate solutions, it requires significant memory to train large models and intuition on which layers to add adapters. In this paper, we propose a novel method, $\texttt{WeightLoRA}$, which overcomes this issue by adaptive selection of the most critical $\texttt{LoRA}$ heads throughout the optimization process. As a result, we can significantly reduce the number of trainable parameters while maintaining the capability to obtain consistent or even superior metric values. We conduct experiments for a series of competitive benchmarks and DeBERTa, BART, and Llama models, comparing our method with different adaptive approaches. The experimental results demonstrate the efficacy of $\texttt{WeightLoRA}$ and the superior performance of $\texttt{WeightLoRA+}$ in almost all cases.
Authors: Changyi Xiao, Yixin Cao
Abstract: Knowledge graph completion (KGC) can be framed as a 3-order binary tensor completion task. Tensor decomposition-based (TDB) models have demonstrated strong performance in KGC. In this paper, we provide a summary of existing TDB models and derive a general form for them, serving as a foundation for further exploration of TDB models. Despite the expressiveness of TDB models, they are prone to overfitting. Existing regularization methods merely minimize the norms of embeddings to regularize the model, leading to suboptimal performance. Therefore, we propose a novel regularization method for TDB models that addresses this limitation. The regularization is applicable to most TDB models and ensures tractable computation. Our method minimizes the norms of intermediate variables involved in the different ways of computing the predicted tensor. To support our regularization method, we provide a theoretical analysis that proves its effect in promoting low trace norm of the predicted tensor to reduce overfitting. Finally, we conduct experiments to verify the effectiveness of our regularization technique as well as the reliability of our theoretical analysis. The code is available at https://github.com/changyi7231/IVR.
Authors: Ruiying Lu, Jinhan Liu, Chuan Du, Dandan Guo
Abstract: Tabular anomaly detection, which aims at identifying deviant samples, has been crucial in a variety of real-world applications, such as medical disease identification, financial fraud detection, intrusion monitoring, etc. Although recent deep learning-based methods have achieved competitive performances, these methods suffer from representation entanglement and the lack of global correlation modeling, which hinders anomaly detection performance. To tackle the problem, we incorporate mask modeling and prototype learning into tabular anomaly detection. The core idea is to design learnable masks by disentangled representation learning within a projection space and extracting normal dependencies as explicit global prototypes. Specifically, the overall model involves two parts: (i) During encoding, we perform mask modeling in both the data space and projection space with orthogonal basis vectors for learning shared disentangled normal patterns; (ii) During decoding, we decode multiple masked representations in parallel for reconstruction and learn association prototypes to extract normal characteristic correlations. Our proposal derives from a distribution-matching perspective, where both projection space learning and association prototype learning are formulated as optimal transport problems, and the calibration distances are utilized to refine the anomaly scores. Quantitative and qualitative experiments on 20 tabular benchmarks demonstrate the effectiveness and interpretability of our model.
Authors: Marco Cal\`i, Giulio Giacomuzzo, Ruggero Carli, Alberto Dalla Libera
Abstract: This paper addresses the slow policy optimization convergence of Monte Carlo Probabilistic Inference for Learning Control (MC-PILCO), a state-of-the-art model-based reinforcement learning (MBRL) algorithm, by integrating it with iterative Linear Quadratic Regulator (iLQR), a fast trajectory optimization method suitable for nonlinear systems. The proposed method, Exploration-Boosted MC-PILCO (EB-MC-PILCO), leverages iLQR to generate informative, exploratory trajectories and initialize the policy, significantly reducing the number of required optimization steps. Experiments on the cart-pole task demonstrate that EB-MC-PILCO accelerates convergence compared to standard MC-PILCO, achieving up to $\bm{45.9\%}$ reduction in execution time when both methods solve the task in four trials. EB-MC-PILCO also maintains a $\bm{100\%}$ success rate across trials while solving the task faster, even in cases where MC-PILCO converges in fewer iterations.
Authors: Ant\'onio Pedro Pinheiro, Rita P. Ribeiro
Abstract: Handling imbalanced target distributions in regression tasks remains a significant challenge in tabular data settings where underrepresented regions can hinder model performance. Among data-level solutions, some proposals, such as random sampling and SMOTE-based approaches, propose adapting classification techniques to regression tasks. However, these methods typically rely on crisp, artificial thresholds over the target variable, a limitation inherited from classification settings that can introduce arbitrariness, often leading to non-intuitive and potentially misleading problem formulations. While recent generative models, such as GANs and VAEs, provide flexible sample synthesis, they come with high computational costs and limited interpretability. In this study, we propose adapting an existing CART-based synthetic data generation method, tailoring it for imbalanced regression. The new method integrates relevance and density-based mechanisms to guide sampling in sparse regions of the target space and employs a threshold-free, feature-driven generation process. Our experimental study focuses on the prediction of extreme target values across benchmark datasets. The results indicate that the proposed method is competitive with other resampling and generative strategies in terms of performance, while offering faster execution and greater transparency. These results highlight the method's potential as a transparent, scalable data-level strategy for improving regression models in imbalanced domains.
Authors: Stefano Fiorini, Hakan Aktas, Iulia Duta, Stefano Coniglio, Pietro Morerio, Alessio Del Bue, Pietro Li\`o
Abstract: Sheaf Neural Networks (SNNs) represent a powerful generalization of Graph Neural Networks (GNNs) that significantly improve our ability to model complex relational data. While directionality has been shown to substantially boost performance in graph learning tasks and is key to many real-world applications, existing SNNs fall short in representing it. To address this limitation, we introduce the Directed Cellular Sheaf, a special type of cellular sheaf designed to explicitly account for edge orientation. Building on this structure, we define a new sheaf Laplacian, the Directed Sheaf Laplacian, which captures both the graph's topology and its directional information. This operator serves as the backbone of the Directed Sheaf Neural Network (DSNN), the first SNN model to embed a directional bias into its architecture. Extensive experiments on nine real-world benchmarks show that DSNN consistently outperforms baseline methods.
Authors: Changyi Xiao, Mengdi Zhang, Yixin Cao
Abstract: Recent studies, including DeepSeek-R1 and Kimi-k1.5, have demonstrated that reinforcement learning with rule-based, binary-valued reward functions can significantly enhance the reasoning capabilities of large language models. These models primarily utilize REINFORCE-based policy optimization techniques, such as REINFORCE with baseline and group relative policy optimization (GRPO). However, a key limitation remains: current policy optimization methods either neglect reward normalization or employ static normalization strategies, which fail to adapt to the dynamic nature of policy updates during training. This may result in unstable gradient estimates and hinder training stability. To address this issue, we propose Beta Normalization Policy Optimization (BNPO), a novel policy optimization method that adaptively normalizes rewards using a Beta distribution with dynamically updated parameters. BNPO aligns the normalization with the changing policy distribution, enabling more precise and lower-variance gradient estimation, which in turn promotes stable training dynamics. We provide theoretical analysis demonstrating BNPO's variance-reducing properties and show that it generalizes both REINFORCE and GRPO under binary-valued reward settings. Furthermore, we introduce an advantage decomposition mechanism to extend BNPO's applicability to more complex reward systems. Experimental results confirm that BNPO achieves state-of-the-art performance among policy optimization methods on reasoning tasks. The code is available at https://github.com/changyi7231/BNPO.
Authors: Anthony Kobanda, Odalric-Ambrym Maillard, R\'emy Portelas
Abstract: Autonomous agents operating in domains such as robotics or video game simulations must adapt to changing tasks without forgetting about the previous ones. This process called Continual Reinforcement Learning poses non-trivial difficulties, from preventing catastrophic forgetting to ensuring the scalability of the approaches considered. Building on recent advances, we introduce a benchmark providing a suite of video-game navigation scenarios, thus filling a gap in the literature and capturing key challenges : catastrophic forgetting, task adaptation, and memory efficiency. We define a set of various tasks and datasets, evaluation protocols, and metrics to assess the performance of algorithms, including state-of-the-art baselines. Our benchmark is designed not only to foster reproducible research and to accelerate progress in continual reinforcement learning for gaming, but also to provide a reproducible framework for production pipelines -- helping practitioners to identify and to apply effective approaches.
Authors: Mrinmay Sen, Shruti Aparna, Rohit Agarwal, Chalavadi Krishna Mohan
Abstract: Federated Learning (FL) is a learning mechanism that falls under the distributed training umbrella, which collaboratively trains a shared global model without disclosing the raw data from different clients. This paper presents an extensive survey on the impact of partial client participation in federated learning. While much of the existing research focuses on addressing issues such as generalization, robustness, and fairness caused by data heterogeneity under the assumption of full client participation, limited attention has been given to the practical and theoretical challenges arising from partial client participation, which is common in real-world scenarios. This survey provides an in-depth review of existing FL methods designed to cope with partial client participation. We offer a comprehensive analysis supported by theoretical insights and empirical findings, along with a structured categorization of these methods, highlighting their respective advantages and disadvantages.
Authors: Jakub Krajewski, Marcin Chochowski, Daniel Korzekwa
Abstract: Mixture of Experts (MoE) architectures have emerged as pivotal for scaling Large Language Models (LLMs) efficiently. Fine-grained MoE approaches - utilizing more numerous, smaller experts - have demonstrated potential in improving model convergence and quality. This work proposes a set of training recipes and provides a comprehensive empirical evaluation of fine-grained MoE, directly comparing its scaling properties against standard MoE configurations for models with up to 56B total (17B active) parameters. We investigate convergence speed, model performance on downstream benchmarks, and practical training considerations across various setups. Overall, at the largest scale we show that fine-grained MoE achieves better validation loss and higher accuracy across a set of downstream benchmarks. This study offers empirical grounding and practical insights for leveraging fine-grained MoE in the development of future large-scale models.
Authors: Alessandro Licciardi, Roberta Raineri, Anton Proskurnikov, Lamberto Rondoni, Lorenzo Zino
Abstract: Federated Learning (FL) enables privacy-preserving collaborative model training, yet its practical strength is often undermined by client data heterogeneity, which severely degrades model performance. This paper proposes that data heterogeneity across clients' distributions can be effectively addressed by adopting an approach inspired by opinion dynamics over temporal social networks. We introduce \shortname (Federated Coalition Variance Reduction with Boltzmann Exploration), a variance-reducing selection algorithm in which (1) clients dynamically organize into non-overlapping clusters based on asymptotic agreements, and (2) from each cluster, one client is selected to minimize the expected variance of its model update. Our experiments show that in heterogeneous scenarios our algorithm outperforms existing FL algorithms, yielding more accurate results and faster convergence, validating the efficacy of our approach.
Authors: Junyi Fang, Yuxun Chen, Yuxin Chen, Chen Zhang
Abstract: The Multi-Armed Bandit (MAB) problem is challenging in non-stationary environments where reward distributions evolve dynamically. We introduce RAVEN-UCB, a novel algorithm that combines theoretical rigor with practical efficiency via variance-aware adaptation. It achieves tighter regret bounds than UCB1 and UCB-V, with gap-dependent regret of order $K \sigma_{\max}^2 \log T / \Delta$ and gap-independent regret of order $\sqrt{K T \log T}$. RAVEN-UCB incorporates three innovations: (1) variance-driven exploration using $\sqrt{\hat{\sigma}_k^2 / (N_k + 1)}$ in confidence bounds, (2) adaptive control via $\alpha_t = \alpha_0 / \log(t + \epsilon)$, and (3) constant-time recursive updates for efficiency. Experiments across non-stationary patterns - distributional changes, periodic shifts, and temporary fluctuations - in synthetic and logistics scenarios demonstrate its superiority over state-of-the-art baselines, confirming theoretical and practical robustness.
Authors: Yuepeng Zheng, Fu Luo, Zhenkun Wang, Yaoxin Wu, Yu Zhou
Abstract: Multi-Task Learning (MTL) in Neural Combinatorial Optimization (NCO) is a promising approach to train a unified model capable of solving multiple Vehicle Routing Problem (VRP) variants. However, existing Reinforcement Learning (RL)-based multi-task methods can only train light decoder models on small-scale problems, exhibiting limited generalization ability when solving large-scale problems. To overcome this limitation, this work introduces a novel multi-task learning method driven by knowledge distillation (MTL-KD), which enables the efficient training of heavy decoder models with strong generalization ability. The proposed MTL-KD method transfers policy knowledge from multiple distinct RL-based single-task models to a single heavy decoder model, facilitating label-free training and effectively improving the model's generalization ability across diverse tasks. In addition, we introduce a flexible inference strategy termed Random Reordering Re-Construction (R3C), which is specifically adapted for diverse VRP tasks and further boosts the performance of the multi-task model. Experimental results on 6 seen and 10 unseen VRP variants with up to 1000 nodes indicate that our proposed method consistently achieves superior performance on both uniform and real-world benchmarks, demonstrating robust generalization abilities.
Authors: Malik Khalaf, Yara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster
Abstract: The Multi-Head Attention mechanism is central to LLM operation, and multiple works target its compute and memory efficiency during training. While most works focus on approximating the scaled dot product, the memory consumption of the linear projections that compute the $Q$, $K$, and $V$ tensors from the input $x$ is often overlooked. To address this, we propose Point-Approximate Matrix Multiplication (PAMM), a novel tensor compression technique that reduces memory consumption of the $Q,K,V$ projections in attention layers by a factor of up to $\times 512$, effectively erasing their memory footprint, while achieving similar or better final perplexity. PAMM is fully composable with efficient attention techniques such as FlashAttention, making it a practical and complementary method for memory-efficient LLM training.
Authors: Edoardo Pona, Milad Kazemi, Yali Du, David Watson, Nicola Paoletti
Abstract: Counterfactual inference is a powerful tool for analysing and evaluating autonomous agents, but its application to language model (LM) agents remains challenging. Existing work on counterfactuals in LMs has primarily focused on token-level counterfactuals, which are often inadequate for LM agents due to their open-ended action spaces. Unlike traditional agents with fixed, clearly defined action spaces, the actions of LM agents are often implicit in the strings they output, making their action spaces difficult to define and interpret. Furthermore, the meanings of individual tokens can shift depending on the context, adding complexity to token-level reasoning and sometimes leading to biased or meaningless counterfactuals. We introduce \emph{Abstract Counterfactuals}, a framework that emphasises high-level characteristics of actions and interactions within an environment, enabling counterfactual reasoning tailored to user-relevant features. Our experiments demonstrate that the approach produces consistent and meaningful counterfactuals while minimising the undesired side effects of token-level methods. We conduct experiments on text-based games and counterfactual text generation, while considering both token-level and latent-space interventions.
Authors: Stepan I. Manukhov, Alexander Kolesov, Vladimir V. Palyulin, Alexander Korotin
Abstract: Electrostatic field matching (EFM) has recently appeared as a novel physics-inspired paradigm for data generation and transfer using the idea of an electric capacitor. However, it requires modeling electrostatic fields using neural networks, which is non-trivial because of the necessity to take into account the complex field outside the capacitor plates. In this paper, we propose Interaction Field Matching (IFM), a generalization of EFM which allows using general interaction fields beyond the electrostatic one. Furthermore, inspired by strong interactions between quarks and antiquarks in physics, we design a particular interaction field realization which solves the problems which arise when modeling electrostatic fields in EFM. We show the performance on a series of toy and image data transfer problems.
Authors: Ze Yu Zhang, Bolin Ding, Bryan Kian Hsiang Low
Abstract: Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of the MoE architecture for memory-efficient decentralized collaborative LLM training, enabling multiple parties with limited GPU-memory and data resources to collectively train more capable LLMs than they could achieve individually. At the same time, this approach protects training data privacy of each participant by keeping training data, as well as parts of the forward pass signal and gradients locally within each party. By design, PC-MoE synergistically combines the strengths of distributed computation with strong confidentiality assurances. Unlike most privacy-preserving schemes, which pay for confidentiality with lower task accuracy, our framework breaks that trade-off: across seven popular LLM benchmarks, it almost matches (and sometimes exceeds) the performance and convergence rate of a fully centralized model, enjoys near 70% peak GPU RAM reduction, while being fully robust against reconstruction attacks.
Authors: Md-Ferdous Pervej, Richeng Jin, Md Moin Uddin Chowdhury, Simran Singh, \.Ismail G\"uven\c{c}, Huaiyu Dai
Abstract: Privacy-preserving distributed machine learning (ML) and aerial connected vehicle (ACV)-assisted edge computing have drawn significant attention lately. Since the onboard sensors of ACVs can capture new data as they move along their trajectories, the continual arrival of such 'newly' sensed data leads to online learning and demands carefully crafting the trajectories. Besides, as typical ACVs are inherently resource-constrained, computation- and communication-efficient ML solutions are needed. Therefore, we propose a computation- and communication-efficient online aerial federated learning (2CEOAFL) algorithm to take the benefits of continual sensed data and limited onboard resources of the ACVs. In particular, considering independently owned ACVs act as selfish data collectors, we first model their trajectories according to their respective time-varying data distributions. We then propose a 2CEOAFL algorithm that allows the flying ACVs to (a) prune the received dense ML model to make it shallow, (b) train the pruned model, and (c) probabilistically quantize and offload their trained accumulated gradients to the central server (CS). Our extensive simulation results show that the proposed 2CEOAFL algorithm delivers comparable performances to its non-pruned and nonquantized, hence, computation- and communication-inefficient counterparts.
Authors: Mohamed Djilani, Thibault Simonetto, Karim Tit, Florian Tambon, Paul R\'ecamier, Salah Ghamizi, Maxime Cordy, Mike Papadakis
Abstract: Recent tabular Foundational Models (FM) such as TabPFN and TabICL, leverage in-context learning to achieve strong performance without gradient updates or fine-tuning. However, their robustness to adversarial manipulation remains largely unexplored. In this work, we present a comprehensive study of the adversarial vulnerabilities of tabular FM, focusing on both their fragility to targeted test-time attacks and their potential misuse as adversarial tools. We show on three benchmarks in finance, cybersecurity and healthcare, that small, structured perturbations to test inputs can significantly degrade prediction accuracy, even when training context remain fixed. Additionally, we demonstrate that tabular FM can be repurposed to generate transferable evasion to conventional models such as random forests and XGBoost, and on a lesser extent to deep tabular models. To improve tabular FM, we formulate the robustification problem as an optimization of the weights (adversarial fine-tuning), or the context (adversarial in-context learning). We introduce an in-context adversarial training strategy that incrementally replaces the context with adversarial perturbed instances, without updating model weights. Our approach improves robustness across multiple tabular benchmarks. Together, these findings position tabular FM as both a target and a source of adversarial threats, highlighting the urgent need for robust training and evaluation practices in this emerging paradigm.
Authors: Nathan Buskulic, Jalal Fadil, Yvain Qu\'eau
Abstract: Solving inverse problems with neural networks benefits from very few theoretical guarantees when it comes to the recovery guarantees. We provide in this work convergence and recovery guarantees for self-supervised neural networks applied to inverse problems, such as Deep Image/Inverse Prior, and trained with inertia featuring both viscous and geometric Hessian-driven dampings. We study both the continuous-time case, i.e., the trajectory of a dynamical system, and the discrete case leading to an inertial algorithm with an adaptive step-size. We show in the continuous-time case that the network can be trained with an optimal accelerated exponential convergence rate compared to the rate obtained with gradient flow. We also show that training a network with our inertial algorithm enjoys similar recovery guarantees though with a less sharp linear convergence rate.
Authors: Junde Xu, Zijun Gao, Xinyi Zhou, Jie Hu, Xingyi Cheng, Le Song, Guangyong Chen, Pheng-Ann Heng, Jiezhong Qiu
Abstract: The inverse folding problem, aiming to design amino acid sequences that fold into desired three-dimensional structures, is pivotal for various biotechnological applications. Here, we introduce a novel approach leveraging Direct Preference Optimization (DPO) to fine-tune an inverse folding model using feedback from a protein folding model. Given a target protein structure, we begin by sampling candidate sequences from the inverse-folding model, then predict the three-dimensional structure of each sequence with the folding model to generate pairwise structural-preference labels. These labels are used to fine-tune the inverse-folding model under the DPO objective. Our results on the CATH 4.2 test set demonstrate that DPO fine-tuning not only improves sequence recovery of baseline models but also leads to a significant improvement in average TM-Score from 0.77 to 0.81, indicating enhanced structure similarity. Furthermore, iterative application of our DPO-based method on challenging protein structures yields substantial gains, with an average TM-Score increase of 79.5\% with regard to the baseline model. This work establishes a promising direction for enhancing protein sequence design ability from structure feedback by effectively utilizing preference optimization.
Authors: Shubhendu Trivedi, Brian D. Nord
Abstract: Quantifying uncertainties for machine learning (ML) models is a foundational challenge in modern data analysis. This challenge is compounded by at least two key aspects of the field: (a) inconsistent terminology surrounding uncertainty and estimation across disciplines, and (b) the varying technical requirements for establishing trustworthy uncertainties in diverse problem contexts. In this position paper, we aim to clarify the depth of these challenges by identifying these inconsistencies and articulating how different contexts impose distinct epistemic demands. We examine the current landscape of estimation targets (e.g., prediction, inference, simulation-based inference), uncertainty constructs (e.g., frequentist, Bayesian, fiducial), and the approaches used to map between them. Drawing on the literature, we highlight and explain examples of problematic mappings. To help address these issues, we advocate for standards that promote alignment between the \textit{intent} and \textit{implementation} of uncertainty quantification (UQ) approaches. We discuss several axes of trustworthiness that are necessary (if not sufficient) for reliable UQ in ML models, and show how these axes can inform the design and evaluation of uncertainty-aware ML systems. Our practical recommendations focus on scientific ML, offering illustrative cases and use scenarios, particularly in the context of simulation-based inference (SBI).
Authors: Nikita Puchkin, Iurii Pustovalov, Yuri Sapronov, Denis Suchkov, Alexey Naumov, Denis Belomestny
Abstract: We address the problem of Schr\"odinger potential estimation, which plays a crucial role in modern generative modelling approaches based on Schr\"odinger bridges and stochastic optimal control for SDEs. Given a simple prior diffusion process, these methods search for a path between two given distributions $\rho_0$ and $\rho_T^*$ requiring minimal efforts. The optimal drift in this case can be expressed through a Schr\"odinger potential. In the present paper, we study generalization ability of an empirical Kullback-Leibler (KL) risk minimizer over a class of admissible log-potentials aimed at fitting the marginal distribution at time $T$. Under reasonable assumptions on the target distribution $\rho_T^*$ and the prior process, we derive a non-asymptotic high-probability upper bound on the KL-divergence between $\rho_T^*$ and the terminal density corresponding to the estimated log-potential. In particular, we show that the excess KL-risk may decrease as fast as $O(\log^2 n / n)$ when the sample size $n$ tends to infinity even if both $\rho_0$ and $\rho_T^*$ have unbounded supports.
Authors: Qining Zhang, Tanner Fiez, Yi Liu, Wenyang Liu
Abstract: Standard A/B tests in online experiments face statistical power challenges when testing multiple candidates simultaneously, while adaptive experimental designs (AED) alone fall short in inferring experiment statistics such as the average treatment effect, especially with many metrics (e.g., revenue, safety) and heterogeneous variances. This paper proposes a fixed-budget multi-metric AED framework with a two-phase structure: an adaptive exploration phase to identify the best treatment, and a validation phase with an A/B test to verify the treatment's quality and infer statistics. We propose SHRVar, which generalizes sequential halving (SH) (Karnin et al., 2013) with a novel relative-variance-based sampling and an elimination strategy built on reward z-values. It achieves a provable error probability that decreases exponentially, where the exponent generalizes the complexity measure for SH (Karnin et al., 2013) and SHVar (Lalitha et al., 2023) with homogeneous and heterogeneous variances, respectively. Numerical experiments verify our analysis and demonstrate the superior performance of this new framework.
Authors: Qining Zhang, Lei Ying
Abstract: Link functions, which characterize how human preferences are generated from the value function of an RL problem, are a crucial component in designing RLHF algorithms. Almost all RLHF algorithms, including state-of-the-art ones in empirical studies such as DPO and PPO, assume the link function is known to the agent (e.g., a logistic function according to the Bradley-Terry model), which is arguably unrealistic considering the complex nature of human preferences. To avoid link function mis-specification, this paper studies general RLHF problems with unknown link functions. We propose a novel policy optimization algorithm called ZSPO based on a new zeroth-order policy optimization method, where the key is to use human preference to construct a parameter update direction that is positively correlated with the true policy gradient direction. ZSPO achieves it by estimating the sign of the value function difference instead of estimating the gradient from the value function difference, so it does not require knowing the link function. Under mild conditions, ZSPO converges to a stationary policy with a polynomial convergence rate depending on the number of policy iterations and trajectories per iteration. Numerical results also show the superiority of ZSPO under link function mismatch.
Authors: Bogdan Chornomaz, Yonatan Koren, Shay Moran, Tom Waknine
Abstract: We study the problem of learning in the presence of an adversary that can corrupt an $\eta$ fraction of the training examples with the goal of causing failure on a specific test point. In the realizable setting, prior work established that the optimal error under such instance-targeted poisoning attacks scales as $\Theta(d\eta)$, where $d$ is the VC dimension of the hypothesis class arXiv:2210.02713. In this work, we resolve the corresponding question in the agnostic setting. We show that the optimal excess error is $\tilde{\Theta}(\sqrt{d\eta})$, answering one of the main open problems left by Hanneke et al. To achieve this rate, it is necessary to use randomized learners: Hanneke et al. showed that deterministic learners can be forced to suffer error close to 1, even under small amounts of poisoning. Perhaps surprisingly, our upper bound remains valid even when the learner's random bits are fully visible to the adversary . In the other direction, our lower bound is stronger than standard PAC-style bounds: instead of tailoring a hard distribution separately for each sample size, we exhibit a single fixed distribution under which the adversary can enforce an excess error of $\Omega(\sqrt{d\eta})$ infinitely often.
Authors: Qijun Luo, Mengqi Li, Lei Zhao, Xiao Li
Abstract: Training language models on long sequence data is a demanding requirement for enhancing the model's capability on complex tasks, e.g., long-chain reasoning. However, as the sequence length scales up, the memory cost for storing activation values becomes huge during the Backpropagation (BP) process, even with the application of gradient checkpointing technique. To tackle this challenge, we propose a memory-efficient and exact BP method called StreamBP, which performs a linear decomposition of the chain rule along the sequence dimension in a layer-wise manner, significantly reducing the memory cost of activation values and logits. The proposed method is applicable to common objectives such as SFT, GRPO, and DPO. From an implementation perspective, StreamBP achieves less computational FLOPs and faster BP speed by leveraging the causal structure of the language model. Compared to gradient checkpointing, StreamBP scales up the maximum sequence length of BP by 2.8-5.5 times larger, while using comparable or even less BP time. Note that StreamBP's sequence length scaling ability can be directly transferred to batch size scaling for accelerating training. We further develop a communication-efficient distributed StreamBP to effectively support multi-GPU training and broaden its applicability. Our code can be easily integrated into the training pipeline of any transformer models and is available at https://github.com/Ledzy/StreamBP.
Authors: Thomas Chen, Tengyu Ma, Zhiyuan Li
Abstract: Length generalization is the ability of a learning algorithm to learn a hypothesis which generalizes to longer inputs than the inputs in the training set. In this paper, we provide provable guarantees of length generalization for various classes of functions in an idealized setting. First, we formalize the framework of non-asymptotic length generalization, which requires a computable upper bound for the minimum input length that guarantees length generalization, as a function of the complexity of ground-truth function under some given complexity measure. We refer to this minimum input length to length generalize as length complexity. We show the Minimum-Complexity Interpolator learning algorithm achieves optimal length complexity. We further show that whether a function class admits non-asymptotic length generalization is equivalent to the decidability of its language equivalence problem, which implies that there is no computable upper bound for the length complexity of Context-Free Grammars. On the positive side, we show that the length complexity of Deterministic Finite Automata is $2n - 2$ where $n$ is the number of states of the ground-truth automaton. Our main results are upper bounds of length complexity for a subset of a transformer-related function class called C-RASP (Yang & Chiang, 2024). We show that the length complexity of 1-layer C-RASP functions is $O(T^2)$ when the ground-truth function has precision $T$, and that the length complexity of 2-layer C-RASP functions is $O(T^{O(K)})$ when the ground-truth function has precision $T$ and $K$ heads.
Authors: Bin Ma, Yuyuan Feng, Minhua Lin, Enyan Dai
Abstract: Graph Neural Networks (GNNs) have become essential tools for analyzing graph-structured data in domains such as drug discovery and financial analysis, leading to growing demands for model transparency. Recent advances in explainable GNNs have addressed this need by revealing important subgraphs that influence predictions, but these explanation mechanisms may inadvertently expose models to security risks. This paper investigates how such explanations potentially leak critical decision logic that can be exploited for model stealing. We propose {\method}, a novel stealing framework that integrates explanation alignment for capturing decision logic with guided data augmentation for efficient training under limited queries, enabling effective replication of both the predictive behavior and underlying reasoning patterns of target models. Experiments on molecular graph datasets demonstrate that our approach shows advantages over conventional methods in model stealing. This work highlights important security considerations for the deployment of explainable GNNs in sensitive domains and suggests the need for protective measures against explanation-based attacks. Our code is available at https://github.com/beanmah/EGSteal.
Authors: Val\'erie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams, Demba Ba
Abstract: Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability. However, recent work has demonstrated phenomenology of model representations that lies outside the scope of this hypothesis, showing signatures of hierarchical, nonlinear, and multi-dimensional features. This raises the question: do SAEs represent features that possess structure at odds with their motivating hypothesis? If not, does avoiding this mismatch help identify said features and gain further insights into neural network representations? To answer these questions, we take a construction-based approach and re-contextualize the popular matching pursuits (MP) algorithm from sparse coding to design MP-SAE -- an SAE that unrolls its encoder into a sequence of residual-guided steps, allowing it to capture hierarchical and nonlinearly accessible features. Comparing this architecture with existing SAEs on a mixture of synthetic and natural data settings, we show: (i) hierarchical concepts induce conditionally orthogonal features, which existing SAEs are unable to faithfully capture, and (ii) the nonlinear encoding step of MP-SAE recovers highly meaningful features, helping us unravel shared structure in the seemingly dichotomous representation spaces of different modalities in a vision-language model, hence demonstrating the assumption that useful features are solely linearly accessible is insufficient. We also show that the sequential encoder principle of MP-SAE affords an additional benefit of adaptive sparsity at inference time, which may be of independent interest. Overall, we argue our results provide credence to the idea that interpretability should begin with the phenomenology of representations, with methods emerging from assumptions that fit it.
Authors: Yang Guo, Yutian Tao, Yifei Ming, Robert D. Nowak, Yingyu Liang
Abstract: Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose the first finite-sample generalization bound for RAG in in-context linear regression and derive an exact bias-variance tradeoff. Our framework views the retrieved texts as query-dependent noisy in-context examples and recovers the classical in-context learning (ICL) and standard RAG as the limit cases. Our analysis suggests that an intrinsic ceiling on generalization error exists on RAG as opposed to the ICL. Furthermore, our framework is able to model retrieval both from the training data and from external corpora by introducing uniform and non-uniform RAG noise. In line with our theory, we show the sample efficiency of ICL and RAG empirically with experiments on common QA benchmarks, such as Natural Questions and TriviaQA.
Authors: Wei Yao, Gengze Xu, Huayi Tang, Wenkai Yang, Donglin Di, Ziqiao Wang, Yong Liu
Abstract: Weak-to-strong generalization (W2SG) has emerged as a promising paradigm for stimulating the capabilities of strong pre-trained models by leveraging supervision from weaker supervisors. To improve the performance of the strong model, existing methods often require additional weak models or complex procedures, leading to substantial computational and memory overhead. Motivated by the effectiveness of $f$-divergence loss in various machine learning domains, we introduce $f$-divergence as an information-theoretic loss function framework in W2SG. Our theoretical analysis reveals fundamental limitations and equivalence of different $f$-divergence losses in W2SG, supported by sample complexity bounds and information-theoretic insights. We empirically demonstrate that $f$-divergence loss, which generalizes widely-used metrics like KL divergence, effectively improves generalization and noise tolerance of the strong model in practice.
Authors: Victor Armegioiu, Yannick Ramic, Siddhartha Mishra
Abstract: The statistical modeling of fluid flows is very challenging due to their multiscale dynamics and extreme sensitivity to initial conditions. While recently proposed conditional diffusion models achieve high fidelity, they typically require hundreds of stochastic sampling steps at inference. We introduce a rectified flow framework that learns a time-dependent velocity field, transporting input to output distributions along nearly straight trajectories. By casting sampling as solving an ordinary differential equation (ODE) along this straighter flow field, our method makes each integration step much more effective, using as few as eight steps versus (more than) 128 steps in standard score-based diffusion, without sacrificing predictive fidelity. Experiments on challenging multiscale flow benchmarks show that rectified flows recover the same posterior distributions as diffusion models, preserve fine-scale features that MSE-trained baselines miss, and deliver high-resolution samples in a fraction of inference time.
Authors: Andreas Auer, Raghul Parthipan, Pedro Mercado, Abdul Fatir Ansari, Lorenzo Stella, Bernie Wang, Michael Bohlke-Schneider, Syama Sundar Rangapuram
Abstract: Pretrained time series models, capable of zero-shot forecasting, have demonstrated significant potential in enhancing both the performance and accessibility of time series forecasting. However, existing pretrained models either do not support covariates or fail to incorporate them effectively. We introduce COSMIC, a zero-shot forecasting model that utilizes covariates via in-context learning. To address the challenge of data scarcity, we propose Informative Covariate Augmentation, which enables the training of COSMIC without requiring any datasets that include covariates. COSMIC achieves state-of-the-art performance in zero-shot forecasting, both with and without covariates. Our quantitative and qualitative analysis demonstrates that COSMIC effectively leverages covariates in zero-shot forecasting.
Authors: Kai Lion, Liang Zhang, Bingcong Li, Niao He
Abstract: We show that low-rank adaptation of large-scale models suffers from a low stable rank that is well below the linear algebraic rank of the subspace, degrading fine-tuning performance. To mitigate the underutilization of the allocated subspace, we propose PoLAR, a parameterization inspired by the polar decomposition that factorizes the low-rank update into two direction matrices constrained to Stiefel manifolds and an unconstrained scale matrix. Our theory shows that PoLAR yields an exponentially faster convergence rate on a canonical low-rank adaptation problem. Pairing the parameterization with Riemannian optimization leads to consistent gains on three different benchmarks testing general language understanding, commonsense reasoning, and mathematical problem solving with base model sizes ranging from 350M to 27B.
Authors: Xiangyu Zhou, Yao Qiang, Saleh Zare Zade, Douglas Zytko, Prashant Khanduri, Dongxiao Zhu
Abstract: Large Language Models (LLMs), pre-trained on massive text corpora, exhibit remarkable human-level language understanding, reasoning, and decision-making abilities. However, they tend to memorize unwanted information, such as private or copyrighted content, raising significant privacy and legal concerns. Unlearning has emerged as a promising solution, but existing methods face a significant challenge of over-forgetting. This issue arises because they indiscriminately suppress the generation of all the tokens in forget samples, leading to a substantial loss of model utility. To overcome this challenge, we introduce the Targeted Information Forgetting (TIF) framework, which consists of (1) a flexible targeted information identifier designed to differentiate between unwanted words (UW) and general words (GW) in the forget samples, and (2) a novel Targeted Preference Optimization approach that leverages Logit Preference Loss to unlearn unwanted information associated with UW and Preservation Loss to retain general information in GW, effectively improving the unlearning process while mitigating utility degradation. Extensive experiments on the TOFU and MUSE benchmarks demonstrate that the proposed TIF framework enhances unlearning effectiveness while preserving model utility and achieving state-of-the-art results.
Authors: Pengcuo Dege, Qiuming Luo, Rui Mao, Chang Kong
Abstract: Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. This paper introduces FlashMLA-ETAP, a novel framework that enhances MLA inference for the single-instance deployment scenario on NVIDIA H20 GPUs. We propose the Efficient Transpose Attention Pipeline (ETAP), which reconfigures attention computation through transposition to align the KV context length with the \(M\)-dimension in WGMMA operations, significantly reducing redundant computations. FlashMLA-ETAP achieves a 2.78x speedup over FlashMLA at 64K sequence length (batch size 16), with 5.24x and 4.94x improvements over FlashAttention-3 and FlashInfer, respectively, while maintaining numerical stability with a 15.2x lower RMSE (\(1.25 \times 10^{-5}\)) than FlashAttention-3. Furthermore, ETAP's design enables seamless integration into frameworks like FlashAttention-3 and FlashInfer, supported by a detailed theoretical analysis. Our work addresses a critical gap in resource-constrained inference, offering a scalable solution for mid-tier GPUs and paving the way for broader adoption in hardware-aware optimization. Code is available at https://github.com/pengcuo/FlashMLA-ETAP.
Authors: Kamal Giri, Amit Garu
Abstract: Distributed systems frequently encounter consistency violation faults (cvfs), where nodes operate on outdated or inaccurate data, adversely affecting convergence and overall system performance. This study presents a machine learning-based approach for analyzing the impact of CVFs, using Dijkstra's Token Ring problem as a case study. By computing program transition ranks and their corresponding effects, the proposed method quantifies the influence of cvfs on system behavior. To address the state space explosion encountered in larger graphs, two models are implemented: a Feedforward Neural Network (FNN) and a distributed neural network leveraging TensorFlow's \texttt{tf.distribute} API. These models are trained on datasets generated from smaller graphs (3 to 10 nodes) to predict parameters essential for determining rank effects. Experimental results demonstrate promising performance, with a test loss of 4.39 and a mean absolute error of 1.5. Although distributed training on a CPU did not yield significant speed improvements over a single-device setup, the findings suggest that scalability could be enhanced through the use of advanced hardware accelerators such as GPUs or TPUs.
Authors: Zhaoyuan Su, Tingfeng Lan, Zirui Wang, Juncheng Yang, Yue Cheng
Abstract: Efficiently serving large language models (LLMs) under dynamic and bursty workloads remains a key challenge for real-world deployment. Existing serving frameworks and static model compression techniques fail to adapt to workload fluctuations, leading to either service-level objective (SLO) violations under full-precision serving or persistent accuracy degradation with static quantization. We present MorphServe, a dynamic, workload-aware LLM serving framework based on morphological adaptation. MorphServe introduces two asynchronous, token-level runtime mechanisms: quantized layer swapping, which selectively replaces less impactful layers with quantized alternatives during high-load periods, and pressure-aware KV cache resizing, which dynamically adjusts KV cache capacity in response to memory pressure. These mechanisms enable state-preserving transitions with minimum runtime overhead and are fully compatible with modern scheduling and attention techniques. Extensive experiments on Vicuna and Llama family models with real-world workloads demonstrate that MorphServe reduces average SLO violations by 92.45 percent and improves the P95 TTFT latency by 2.2x-3.9x compared to full-precision serving, without compromising generation quality. These results establish MorphServe as a practical and elastic solution for LLM deployment in dynamic environments.
Authors: Nuolin Sun, Linyuan Wang, Dongyang Li, Bin Yan, Lei Li
Abstract: Adversarial attacks have received increasing attention and it has been widely recognized that classical DNNs have weak adversarial robustness. The most commonly used adversarial defense method, adversarial training, improves the adversarial accuracy of DNNs by generating adversarial examples and retraining the model. However, adversarial training requires a significant computational overhead. In this paper, inspired by existing studies focusing on the clustering properties of DNN output features at each layer and the Progressive Feedforward Collapse phenomenon, we propose a method for adversarial example detection and image recognition that uses layer-wise features to construct feature paths and computes the correlation between the examples feature paths and the class-centered feature paths. Experimental results show that the recognition method achieves 82.77% clean accuracy and 44.17% adversarial accuracy on the ResNet-20 with PFC. Compared to the adversarial training method with 77.64% clean accuracy and 52.94% adversarial accuracy, our method exhibits a trade-off without relying on computationally expensive defense strategies. Furthermore, on the standard ResNet-18, our method maintains this advantage with respective metrics of 80.01% and 46.1%. This result reveals inherent adversarial robustness in DNNs, challenging the conventional understanding of the weak adversarial robustness in DNNs.
Authors: Youze Xue, Dian Li, Gang Liu
Abstract: With the rapid advancement of multi-modal large language models (MLLMs) in recent years, the foundational Contrastive Language-Image Pretraining (CLIP) framework has been successfully extended to MLLMs, enabling more powerful and universal multi-modal embeddings for a wide range of retrieval tasks. Despite these developments, the core contrastive learning paradigm remains largely unchanged from CLIP-style models to MLLMs. Within this framework, the effective mining of hard negative samples continues to be a critical factor for enhancing performance. Prior works have introduced both offline and online strategies for hard negative mining to improve the efficiency of contrastive learning. While these approaches have led to improved multi-modal embeddings, the specific contribution of each hard negative sample to the learning process has not been thoroughly investigated. In this work, we conduct a detailed analysis of the gradients of the info-NCE loss with respect to the query, positive, and negative samples, elucidating the role of hard negatives in updating model parameters. Building upon this analysis, we propose to explicitly amplify the gradients associated with hard negative samples, thereby encouraging the model to learn more discriminative embeddings. Our multi-modal embedding model, trained with the proposed Explicit Gradient Amplifier and based on the LLaVA-OneVision-7B architecture, achieves state-of-the-art performance on the MMEB benchmark compared to previous methods utilizing the same MLLM backbone. Furthermore, when integrated with our self-developed MLLM, QQMM, our approach attains the top rank on the MMEB leaderboard. Code and models are released on https://github.com/QQ-MM/QQMM-embed.
Authors: Kevin Han, Bowen Deng, Amir Barati Farimani, Gerbrand Ceder
Abstract: Large-scale atomistic simulations are essential to bridge computational materials and chemistry to realistic materials and drug discovery applications. In the past few years, rapid developments of machine learning interatomic potentials (MLIPs) have offered a solution to scale up quantum mechanical calculations. Parallelizing these interatomic potentials across multiple devices poses a challenging, but promising approach to further extending simulation scales to real-world applications. In this work, we present DistMLIP, an efficient distributed inference platform for MLIPs based on zero-redundancy, graph-level parallelization. In contrast to conventional space-partitioning parallelization, DistMLIP enables efficient MLIP parallelization through graph partitioning, allowing multi-device inference on flexible MLIP model architectures like multi-layer graph neural networks. DistMLIP presents an easy-to-use, flexible, plug-in interface that enables distributed inference of pre-existing MLIPs. We demonstrate DistMLIP on four widely used and state-of-the-art MLIPs: CHGNet, MACE, TensorNet, and eSEN. We show that existing foundational potentials can perform near-million-atom calculations at the scale of a few seconds on 8 GPUs with DistMLIP.
Authors: Anum Nawaz, Hafiz Humza Mahmood Ramzan, Xianjia Yu, Zhuo Zou, Tomi Westerlund
Abstract: Edge Intelligence (EI) serves as a critical enabler for privacy-preserving systems by providing AI-empowered computation and distributed caching services at the edge, thereby minimizing latency and enhancing data privacy. The integration of blockchain technology further augments EI frameworks by ensuring transactional transparency, auditability, and system-wide reliability through a decentralized network model. However, the operational architecture of such systems introduces inherent vulnerabilities, particularly due to the extensive data interactions between edge gateways (EGs) and the distributed nature of information storage during service provisioning. To address these challenges, we propose an autonomous computing model along with its interaction topologies tailored for privacy-critical and time-sensitive health applications. The system supports continuous monitoring, real-time alert notifications, disease detection, and robust data processing and aggregation. It also includes a data transaction handler and mechanisms for ensuring privacy at the EGs. Moreover, a resource-efficient one-dimensional convolutional neural network (1D-CNN) is proposed for the multiclass classification of arrhythmia, enabling accurate and real-time analysis of constrained EGs. Furthermore, a secure access scheme is defined to manage both off-chain and on-chain data sharing and storage. To validate the proposed model, comprehensive security, performance, and cost analyses are conducted, demonstrating the efficiency and reliability of the fine-grained access control scheme.
Authors: Xinxu Wei, Kanhao Zhao, Yong Jiao, Lifang He, Yu Zhang
Abstract: As large language models (LLMs) continue to revolutionize AI research, there is a growing interest in building large-scale brain foundation models to advance neuroscience. While most existing brain foundation models are pre-trained on time-series signals or region-of-interest (ROI) features, we propose a novel graph-based pre-training paradigm for constructing a brain graph foundation model. In this paper, we introduce the Brain Graph Foundation Model, termed BrainGFM, a unified framework that leverages graph contrastive learning and graph masked autoencoders for large-scale fMRI-based pre-training. BrainGFM is pre-trained on a diverse mixture of brain atlases with varying parcellations, significantly expanding the pre-training corpus and enhancing the model's ability to generalize across heterogeneous fMRI-derived brain representations. To support efficient and versatile downstream transfer, we integrate both graph prompts and language prompts into the model design, enabling BrainGFM to flexibly adapt to a wide range of atlases, neurological and psychiatric disorders, and task settings. Furthermore, we employ meta-learning to optimize the graph prompts, facilitating strong generalization to previously unseen disorders under both few-shot and zero-shot learning conditions via language-guided prompting. BrainGFM is pre-trained on 27 neuroimaging datasets spanning 25 common neurological and psychiatric disorders, encompassing 2 types of brain atlases (functional and anatomical) across 8 widely-used parcellations, and covering over 25,000 subjects, 60,000 fMRI scans, and a total of 400,000 graph samples aggregated across all atlases and parcellations. The code is available at: https://github.com/weixinxu666/BrainGFM
Authors: Hui Liu, Shiye Tian, Xuejun Liu
Abstract: The de novo generation of drug-like molecules capable of inducing desirable phenotypic changes is receiving increasing attention. However, previous methods predominantly rely on expression profiles to guide molecule generation, but overlook the perturbative effect of the molecules on cellular contexts. To overcome this limitation, we propose SmilesGEN, a novel generative model based on variational autoencoder (VAE) architecture to generate molecules with potential therapeutic effects. SmilesGEN integrates a pre-trained drug VAE (SmilesNet) with an expression profile VAE (ProfileNet), jointly modeling the interplay between drug perturbations and transcriptional responses in a common latent space. Specifically, ProfileNet is imposed to reconstruct pre-treatment expression profiles when eliminating drug-induced perturbations in the latent space, while SmilesNet is informed by desired expression profiles to generate drug-like molecules. Our empirical experiments demonstrate that SmilesGEN outperforms current state-of-the-art models in generating molecules with higher degree of validity, uniqueness, novelty, as well as higher Tanimoto similarity to known ligands targeting the relevant proteins. Moreover, we evaluate SmilesGEN for scaffold-based molecule optimization and generation of therapeutic agents, and confirmed its superior performance in generating molecules with higher similarity to approved drugs. SmilesGEN establishes a robust framework that leverages gene signatures to generate drug-like molecules that hold promising potential to induce desirable cellular phenotypic changes.
Authors: Shuo Yan, Yuliang Yan, Bin Ma, Chenao Li, Haochun Tang, Jiahua Lu, Minhua Lin, Yuyuan Feng, Hui Xiong, Enyan Dai
Abstract: Recently, extensive deep learning architectures and pretraining strategies have been explored to support downstream protein applications. Additionally, domain-specific models incorporating biological knowledge have been developed to enhance performance in specialized tasks. In this work, we introduce $\textbf{Protap}$, a comprehensive benchmark that systematically compares backbone architectures, pretraining strategies, and domain-specific models across diverse and realistic downstream protein applications. Specifically, Protap covers five applications: three general tasks and two novel specialized tasks, i.e., enzyme-catalyzed protein cleavage site prediction and targeted protein degradation, which are industrially relevant yet missing from existing benchmarks. For each application, Protap compares various domain-specific models and general architectures under multiple pretraining settings. Our empirical studies imply that: (i) Though large-scale pretraining encoders achieve great results, they often underperform supervised encoders trained on small downstream training sets. (ii) Incorporating structural information during downstream fine-tuning can match or even outperform protein language models pretrained on large-scale sequence corpora. (iii) Domain-specific biological priors can enhance performance on specialized downstream tasks. Code and datasets are publicly available at https://github.com/Trust-App-AI-Lab/protap.
Authors: David Sasu, Kweku Andoh Yamoah, Benedict Quartey, Natalie Schluter
Abstract: Enabling robots to accurately interpret and execute spoken language instructions is essential for effective human-robot collaboration. Traditional methods rely on speech recognition to transcribe speech into text, often discarding crucial prosodic cues needed for disambiguating intent. We propose a novel approach that directly leverages speech prosody to infer and resolve instruction intent. Predicted intents are integrated into large language models via in-context learning to disambiguate and select appropriate task plans. Additionally, we present the first ambiguous speech dataset for robotics, designed to advance research in speech disambiguation. Our method achieves 95.79% accuracy in detecting referent intents within an utterance and determines the intended task plan of ambiguous instructions with 71.96% accuracy, demonstrating its potential to significantly improve human-robot communication.
Authors: Xiang Li, Jiayi Xin, Qi Long, Weijie J. Su
Abstract: Accurate evaluation of large language models (LLMs) is crucial for understanding their capabilities and guiding their development. However, current evaluations often inconsistently reflect the actual capacities of these models. In this paper, we demonstrate that one of many contributing factors to this \textit{evaluation crisis} is the oversight of unseen knowledge -- information encoded by LLMs but not directly observed or not yet observed during evaluations. We introduce KnowSum, a statistical framework designed to provide a more comprehensive assessment by quantifying the unseen knowledge for a class of evaluation tasks. KnowSum estimates the unobserved portion by extrapolating from the appearance frequencies of observed knowledge instances. We demonstrate the effectiveness and utility of KnowSum across three critical applications: estimating total knowledge, evaluating information retrieval effectiveness, and measuring output diversity. Our experiments reveal that a substantial volume of knowledge is omitted when relying solely on observed LLM performance. Importantly, KnowSum yields significantly different comparative rankings for several common LLMs based on their internal knowledge.
Authors: Yun-Cheng Tsai, Yen-Ku Liu, Samuel Yen-Chi Chen
Abstract: Blockchain transaction data is inherently high dimensional, noisy, and entangled, posing substantial challenges for traditional clustering algorithms. While quantum enhanced clustering models have demonstrated promising performance gains, their interpretability remains limited, restricting their application in sensitive domains such as financial fraud detection and blockchain governance. To address this gap, we propose a two stage analysis framework that synergistically combines quantitative clustering evaluation with AI Agent assisted qualitative interpretation. In the first stage, we employ classical clustering methods and evaluation metrics including the Silhouette Score, Davies Bouldin Index, and Calinski Harabasz Index to determine the optimal cluster count and baseline partition quality. In the second stage, we integrate an AI Agent to generate human readable, semantic explanations of clustering results, identifying intra cluster characteristics and inter cluster relationships. Our experiments reveal that while fully trained Quantum Neural Networks (QNN) outperform random Quantum Features (QF) in quantitative metrics, the AI Agent further uncovers nuanced differences between these methods, notably exposing the singleton cluster phenomenon in QNN driven models. The consolidated insights from both stages consistently endorse the three cluster configuration, demonstrating the practical value of our hybrid approach. This work advances the interpretability frontier in quantum assisted blockchain analytics and lays the groundwork for future autonomous AI orchestrated clustering frameworks.
Authors: Tadesse K. Bahiru, Haileleol Tibebu, Ioannis A. Kakadiaris
Abstract: Artificial intelligence has transformed numerous industries, from healthcare to finance, enhancing decision-making through automated systems. However, the reliability of these systems is mainly dependent on the quality of the underlying datasets, raising ongoing concerns about transparency, accountability, and potential biases. This paper introduces a scorecard designed to evaluate the development of AI datasets, focusing on five key areas from the system card framework data development life cycle: data dictionary, collection process, composition, motivation, and pre-processing. The method follows a structured approach, using an intake form and scoring criteria to assess the quality and completeness of the data set. Applied to four diverse datasets, the methodology reveals strengths and improvement areas. The results are compiled using a scoring system that provides tailored recommendations to enhance the transparency and integrity of the data set. The scorecard addresses technical and ethical aspects, offering a holistic evaluation of data practices. This approach aims to improve the quality of the data set. It offers practical guidance to curators and researchers in developing responsible AI systems, ensuring fairness and accountability in decision support systems.
Authors: Christian Marius Lillelund, Shi-ang Qi, Russell Greiner, Christian Fischer Pedersen
Abstract: We argue that many survival analysis and time-to-event models are incorrectly evaluated. First, we survey many examples of evaluation approaches in the literature and find that most rely on concordance (C-index). However, the C-index only measures a model's discriminative ability and does not assess other important aspects, such as the accuracy of the time-to-event predictions or the calibration of the model's probabilistic estimates. Next, we present a set of key desiderata for choosing the right evaluation metric and discuss their pros and cons. These are tailored to the challenges in survival analysis, such as sensitivity to miscalibration and various censoring assumptions. We hypothesize that the current development of survival metrics conforms to a double-helix ladder, and that model validity and metric validity must stand on the same rung of the assumption ladder. Finally, we discuss the appropriate methods for evaluating a survival model in practice and summarize various viewpoints opposing our analysis.
Authors: Christian Marius Lillelund, Sanjay Kalra, Russell Greiner
Abstract: Amyotrophic lateral sclerosis (ALS) is a degenerative disorder of motor neurons that causes progressive paralysis in patients. Current treatment options aim to prolong survival and improve quality of life; however, due to the heterogeneity of the disease, it is often difficult to determine the optimal time for potential therapies or medical interventions. In this study, we propose a novel method to predict the time until a patient with ALS experiences significant functional impairment (ALSFRS-R<=2) with respect to five common functions: speaking, swallowing, handwriting, walking and breathing. We formulate this task as a multi-event survival problem and validate our approach in the PRO-ACT dataset by training five covariate-based survival models to estimate the probability of an event over a 500-day period after a baseline visit. We then predict five event-specific individual survival distributions (ISDs) for each patient, each providing an interpretable and meaningful estimate of when that event will likely take place in the future. The results show that covariate-based models are superior to the Kaplan-Meier estimator at predicting time-to-event outcomes. Additionally, our method enables practitioners to make individual counterfactual predictions, where certain features (covariates) can be changed to see their effect on the predicted outcome. In this regard, we find that Riluzole has little to no impact on predicted functional decline. However, for patients with bulbar-onset ALS, our method predicts considerably shorter counterfactual time-to-event estimates for tasks related to speech and swallowing compared to limb-onset ALS. The proposed method can be applied to current clinical examination data to assess the risk of functional decline and thus allow more personalized treatment planning.
Authors: Saurabh Agrawal, Raj Gohil, Gopal Kumar Agrawal, Vikram C M, Kushal Verma
Abstract: Speech quality assessment is a critical process in selecting text-to-speech synthesis (TTS) or voice conversion models. Evaluation of voice synthesis can be done using objective metrics or subjective metrics. Although there are many objective metrics like the Perceptual Evaluation of Speech Quality (PESQ), Perceptual Objective Listening Quality Assessment (POLQA) or Short-Time Objective Intelligibility (STOI) but none of them is feasible in selecting the best model. On the other hand subjective metric like Mean Opinion Score is highly reliable but it requires a lot of manual efforts and are time-consuming. To counter the issues in MOS Evaluation, we have developed a novel model, Speaker Agnostic Latent Features (SALF)-Mean Opinion Score (MOS) which is a small-sized, end-to-end, highly generalized and scalable model for predicting MOS score on a scale of 5. We use the sequences of convolutions and stack them to get the latent features of the audio samples to get the best state-of-the-art results based on mean squared error (MSE), Linear Concordance Correlation coefficient (LCC), Spearman Rank Correlation Coefficient (SRCC) and Kendall Rank Correlation Coefficient (KTAU).
Authors: Aditya Srinivas Menon, Raj Prakash Gohil, Kumud Tripathi, Pankaj Wasnik
Abstract: Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic structure complicates separating linguistic and speaker information. Disentangling these components can significantly improve speaker recognition accuracy. To this end, we propose a novel disentanglement learning strategy that integrates joint learning through prefix-tuned cross-attention. This approach is particularly effective when speakers switch between languages. Experimental results show the model generalizes across monolingual and multi-lingual settings, including unseen languages. Notably, the proposed model improves the equal error rate across multiple datasets, highlighting its ability to separate language information from speaker embeddings and enhance recognition in diverse linguistic conditions.
Authors: Alef Iury Siqueira Ferreira, Lucas Rafael Gris, Alexandre Ferro Filho, Lucas \'Olives, Daniel Ribeiro, Luiz Fernando, Fernanda Lustosa, Rodrigo Tanaka, Frederico Santos de Oliveira, Arlindo Galv\~ao Filho
Abstract: Training SER models in natural, spontaneous speech is especially challenging due to the subtle expression of emotions and the unpredictable nature of real-world audio. In this paper, we present a robust system for the INTERSPEECH 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge, focusing on categorical emotion recognition. Our method combines state-of-the-art audio models with text features enriched by prosodic and spectral cues. In particular, we investigate the effectiveness of Fundamental Frequency (F0) quantization and the use of a pretrained audio tagging model. We also employ an ensemble model to improve robustness. On the official test set, our system achieved a Macro F1-score of 39.79% (42.20% on validation). Our results underscore the potential of these methods, and analysis of fusion techniques confirmed the effectiveness of Graph Attention Networks. Our source code is publicly available.
Authors: Gopichand Bandarupalli
Abstract: Modern software systems complexity challenges efficient testing, as traditional machine learning (ML) struggles with large test suites. This research presents a hybrid framework integrating Quantum Annealing with ML to optimize test case prioritization in CI/CD pipelines. Leveraging quantum optimization, it achieves a 25 percent increase in defect detection efficiency and a 30 percent reduction in test execution time versus classical ML, validated on the Defects4J dataset. A simulated CI/CD environment demonstrates robustness across evolving codebases. Visualizations, including defect heatmaps and performance graphs, enhance interpretability. The framework addresses quantum hardware limits, CI/CD integration, and scalability for 2025s hybrid quantum-classical ecosystems, offering a transformative approach to software quality assurance.
Authors: Bartosz Karpi\'nski, Cyryl Leszczy\'nski
Abstract: As the accessibility and ease-of-use of digital audio workstations increases, so does the quantity of music available to the average listener; additionally, differences between genres are not always well defined and can be abstract, with widely varying combinations of genres across individual records. In this article, multiple preprocessing methods and approaches to model training are described and compared, accounting for the eclectic nature of today's albums. A custom, manually labeled dataset of more than 18000 entries has been used to perform the experiments.
Authors: Hyojin Bahng, Caroline Chan, Fredo Durand, Phillip Isola
Abstract: Learning alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and time-intensive. We propose an alternative approach that leverages cycle consistency as a supervisory signal. Given an image and generated text, we map the text back to image space using a text-to-image model and compute the similarity between the original image and its reconstruction. Analogously, for text-to-image generation, we measure the textual similarity between an input caption and its reconstruction through the cycle. We use the cycle consistency score to rank candidates and construct a preference dataset of 866K comparison pairs. The reward model trained on our dataset outperforms state-of-the-art alignment metrics on detailed captioning, with superior inference-time scalability when used as a verifier for Best-of-N sampling. Furthermore, performing DPO and Diffusion DPO using our dataset enhances performance across a wide range of vision-language tasks and text-to-image generation. Our dataset, model, and code are at https://cyclereward.github.io
Authors: Michael Li, Nishant Subramani
Abstract: Large transformer-based language models dominate modern NLP, yet our understanding of how they encode linguistic information is rooted in studies of early models like BERT and GPT-2. To better understand today's language models, we investigate how both classical architectures (BERT, DeBERTa, GPT-2)and contemporary large language models (Pythia, OLMo-2, Gemma-2, Qwen2.5, Llama-3.1) represent lexical identity and inflectional morphology. We train linear and nonlinear classifiers on layer-wise activations to predict word lemmas and inflectional features. We discover that models concentrate lexical information linearly in early layers and increasingly nonlinearly in later layers, while keeping inflectional information uniformly accessible and linearly separable throughout the layers. Further analysis reveals that these models encode inflectional morphology through generalizable abstractions, but rely predominantly on memorization to encode lexical identity. Remarkably, these patterns emerge across all 16 models we test, despite differences in architecture, size, and training regime (including pretrained and instruction-tuned variants). This consistency suggests that, despite substantial advances in LLM technologies, transformer models organize linguistic information in similar ways, indicating that these properties could be fundamental for next token prediction and are learned early during pretraining. Our code is available at https://github.com/ml5885/model_internal_sleuthing
Authors: Wenjun Xia, Chuang Niu, Ge Wang
Abstract: Computed tomography (CT) is a major medical imaging modality. Clinical CT scenarios, such as low-dose screening, sparse-view scanning, and metal implants, often lead to severe noise and artifacts in reconstructed images, requiring improved reconstruction techniques. The introduction of deep learning has significantly advanced CT image reconstruction. However, obtaining paired training data remains rather challenging due to patient motion and other constraints. Although deep learning methods can still perform well with approximately paired data, they inherently carry the risk of hallucination due to data inconsistencies and model instability. In this paper, we integrate the data fidelity with the state-of-the-art generative AI model, referred to as the Poisson flow generative model (PFGM) with a generalized version PFGM++, and propose a novel CT framework: Flow-Oriented Reconstruction Conditioning Engine (FORCE). In our experiments, the proposed method shows superior performance in various CT imaging tasks, outperforming existing unsupervised reconstruction approaches.
Authors: Madan Krishnamurthy, Daniel Korn, Melissa A Haendel, Christopher J Mungall, Anne E Thessen
Abstract: This research aims to develop a dynamic and scalable framework to facilitate harmonization of Common Data Elements (CDEs) across heterogeneous biomedical datasets by addressing challenges such as semantic heterogeneity, structural variability, and context dependence to streamline integration, enhance interoperability, and accelerate scientific discovery. Our methodology leverages Large Language Models (LLMs) for context-aware text embeddings that convert CDEs into dense vectors capturing semantic relationships and patterns. These embeddings are clustered using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to group semantically similar CDEs. The framework incorporates four key steps: (1) LLM-based text embedding to mathematically represent semantic context, (2) unsupervised clustering of embeddings via HDBSCAN, (3) automated labeling using LLM summarization, and (4) supervised learning to train a classifier assigning new or unclustered CDEs to labeled clusters. Evaluated on the NIH NLM CDE Repository with over 24,000 CDEs, the system identified 118 meaningful clusters at an optimized minimum cluster size of 20. The classifier achieved 90.46 percent overall accuracy, performing best in larger categories. External validation against Gravity Projects Social Determinants of Health domains showed strong agreement (Adjusted Rand Index 0.52, Normalized Mutual Information 0.78), indicating that embeddings effectively capture cluster characteristics. This adaptable and scalable approach offers a practical solution to CDE harmonization, improving selection efficiency and supporting ongoing data interoperability.
Authors: Yu (Eric), Qian, Wilson S. Geisler, Xue-Xin Wei
Abstract: Previous studies have compared the brain and deep neural networks trained on image classification. Intriguingly, while some suggest that their representations are highly similar, others argued the opposite. Here, we propose a new approach to characterize the similarity of the decision strategies of two observers (models or brains) using decision variable correlation (DVC). DVC quantifies the correlation between decoded decisions on individual samples in a classification task and thus can capture task-relevant information rather than general representational alignment. We evaluate this method using monkey V4/IT recordings and models trained on image classification tasks. We find that model--model similarity is comparable to monkey--monkey similarity, whereas model--monkey similarity is consistently lower and, surprisingly, decreases with increasing ImageNet-1k performance. While adversarial training enhances robustness, it does not improve model--monkey similarity in task-relevant dimensions; however, it markedly increases model--model similarity. Similarly, pre-training on larger datasets does not improve model--monkey similarity. These results suggest a fundamental divergence between the task-relevant representations in monkey V4/IT and those learned by models trained on image classification tasks.
Authors: Arnav Rustagi, Satvik Bajpai, Nimrat Kaur, Siddharth Siddharth
Abstract: Computer-Assisted Pronunciation Training (CAPT) has been extensively studied for English. However, there remains a critical gap in its application to Indian languages with a base of 1.5 billion speakers. Pronunciation tools tailored to Indian languages are strikingly lacking despite the fact that millions learn them every year. With over 600 million speakers and being the fourth most-spoken language worldwide, improving Hindi pronunciation is a vital first step toward addressing this gap. This paper proposes 1) Dhvani -- a novel CAPT system for Hindi, 2) synthetic speech generation for Hindi mispronunciations, and 3) a novel methodology for providing personalized feedback to learners. While the system often interacts with learners using Devanagari graphemes, its core analysis targets phonemic distinctions, leveraging Hindi's highly phonetic orthography to analyze mispronounced speech and provide targeted feedback.
Authors: Haizhong Zheng, Yang Zhou, Brian R. Bartoldson, Bhavya Kailkhura, Fan Lai, Jiawei Zhao, Beidi Chen
Abstract: Reinforcement learning, such as PPO and GRPO, has powered recent breakthroughs in LLM reasoning. Scaling rollout to sample more prompts enables models to selectively use higher-quality data for training, which can stabilize RL training and improve model performance. However, this comes at the cost of significant computational overhead. In this paper, we show that a substantial portion of this overhead can be avoided by skipping uninformative prompts before rollout. Our analysis of reward dynamics reveals a strong temporal consistency in prompt value: prompts that are uninformative in one epoch of training are likely to remain uninformative in future epochs. Based on these insights, we propose GRESO (GRPO with Efficient Selective Rollout), an online, lightweight pre-rollout filtering algorithm that predicts and skips uninformative prompts using reward training dynamics. By evaluating GRESO on a broad range of math reasoning benchmarks and models, such as Qwen2.5-Math-1.5B, DeepSeek-R1-Distill-Qwen-1.5B, and Qwen2.5-Math-7B, we show that GRESO achieves up to 2.4x wall-clock time speedup in rollout and up to 2.0x speedup in total training time without accuracy degradation.
Authors: Johannes Schusterbauer, Ming Gui, Frank Fundel, Bj\"orn Ommer
Abstract: Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for finetuning, while diffusion models like Stable Diffusion benefit from efficient architectures and ecosystem support. This work addresses the critical challenge of efficiently transferring knowledge from pre-trained diffusion models to flow matching. We propose Diff2Flow, a novel framework that systematically bridges diffusion and FM paradigms by rescaling timesteps, aligning interpolants, and deriving FM-compatible velocity fields from diffusion predictions. This alignment enables direct and efficient FM finetuning of diffusion priors with no extra computation overhead. Our experiments demonstrate that Diff2Flow outperforms na\"ive FM and diffusion finetuning particularly under parameter-efficient constraints, while achieving superior or competitive performance across diverse downstream tasks compared to state-of-the-art methods. We will release our code at https://github.com/CompVis/diff2flow.
Authors: Manas Mehta, Yimu Pan, Kelly Gallagher, Alison D. Gernand, Jeffery A. Goldstein, Delia Mwinyelle, Leena Mithal, James Z. Wang
Abstract: Pathological examination of the placenta is an effective method for detecting and mitigating health risks associated with childbirth. Recent advancements in AI have enabled the use of photographs of the placenta and pathology reports for detecting and classifying signs of childbirth-related pathologies. However, existing automated methods are computationally extensive, which limits their deployability. We propose two modifications to vision-language contrastive learning (VLC) frameworks to enhance their accuracy and efficiency: (1) text-anchored vision-language contrastive knowledge distillation (VLCD)-a new knowledge distillation strategy for medical VLC pretraining, and (2) unsupervised predistillation using a large natural images dataset for improved initialization. Our approach distills efficient neural networks that match or surpass the teacher model in performance while achieving model compression and acceleration. Our results showcase the value of unsupervised predistillation in improving the performance and robustness of our approach, specifically for lower-quality images. VLCD serves as an effective way to improve the efficiency and deployability of medical VLC approaches, making AI-based healthcare solutions more accessible, especially in resource-constrained environments.
Authors: Michael S. Ackermann, Ion Victor Gosea, Serkan Gugercin, Steffen W. R. Werner
Abstract: The data-driven modeling of dynamical systems has become an essential tool for the construction of accurate computational models from real-world data. In this process, the inherent differential structures underlying the considered physical phenomena are often neglected making the reinterpretation of the learned models in a physically meaningful sense very challenging. In this work, we present three data-driven modeling approaches for the construction of dynamical systems with second-order differential structure directly from frequency domain data. Based on the second-order structured barycentric form, we extend the well-known Adaptive Antoulas-Anderson algorithm to the case of second-order systems. Depending on the available computational resources, we propose variations of the proposed method that prioritize either higher computation speed or greater modeling accuracy, and we present a theoretical analysis for the expected accuracy and performance of the proposed methods. Three numerical examples demonstrate the effectiveness of our new structured approaches in comparison to classical unstructured data-driven modeling.
Authors: Dimitris G Giovanis, Nikolaos Evangelou, Ioannis G Kevrekidis, Roger G Ghanem
Abstract: We present a generative learning framework for probabilistic sampling based on an extension of the Probabilistic Learning on Manifolds (PLoM) approach, which is designed to generate statistically consistent realizations of a random vector in a finite-dimensional Euclidean space, informed by a limited (yet representative) set of observations. In its original form, PLoM constructs a reduced-order probabilistic model by combining three main components: (a) kernel density estimation to approximate the underlying probability measure, (b) Diffusion Maps to uncover the intrinsic low-dimensional manifold structure, and (c) a reduced-order Ito Stochastic Differential Equation (ISDE) to sample from the learned distribution. A key challenge arises, however, when the number of available data points N is small and the dimensionality of the diffusion-map basis approaches N, resulting in overfitting and loss of generalization. To overcome this limitation, we propose an enabling extension that implements a synthesis of Double Diffusion Maps -- a technique capable of capturing multiscale geometric features of the data -- with Geometric Harmonics (GH), a nonparametric reconstruction method that allows smooth nonlinear interpolation in high-dimensional ambient spaces. This approach enables us to solve a full-order ISDE directly in the latent space, preserving the full dynamical complexity of the system, while leveraging its reduced geometric representation. The effectiveness and robustness of the proposed method are illustrated through two numerical studies: one based on data generated from two-dimensional Hermite polynomial functions and another based on high-fidelity simulations of a detonation wave in a reactive flow.
Authors: Ruiting Liang, Jake A. Soloff, Rina Foygel Barber, Rebecca Willett
Abstract: In this work, we consider ranking problems among a finite set of candidates: for instance, selecting the top-$k$ items among a larger list of candidates or obtaining the full ranking of all items in the set. These problems are often unstable, in the sense that estimating a ranking from noisy data can exhibit high sensitivity to small perturbations. Concretely, if we use data to provide a score for each item (say, by aggregating preference data over a sample of users), then for two items with similar scores, small fluctuations in the data can alter the relative ranking of those items. Many existing theoretical results for ranking problems assume a separation condition to avoid this challenge, but real-world data often contains items whose scores are approximately tied, limiting the applicability of existing theory. To address this gap, we develop a new algorithmic stability framework for ranking problems, and propose two novel ranking operators for achieving stable ranking: the \emph{inflated top-$k$} for the top-$k$ selection problem and the \emph{inflated full ranking} for ranking the full list. To enable stability, each method allows for expressing some uncertainty in the output. For both of these two problems, our proposed methods provide guaranteed stability, with no assumptions on data distributions and no dependence on the total number of candidates to be ranked. Experiments on real-world data confirm that the proposed methods offer stability without compromising the informativeness of the output.
Authors: Howon Ryu, Yuliang Chen, Yacun Wang, Andrea Z. LaCroix, Chongzhi Di, Loki Natarajan, Yu Wang, Jingjing Zou
Abstract: The growing prevalence of digital health technologies has led to the generation of complex multi-modal data, such as physical activity measurements simultaneously collected from various sensors of mobile and wearable devices. These data hold immense potential for advancing health studies, but current methods predominantly rely on supervised learning, requiring extensive labeled datasets that are often expensive or impractical to obtain, especially in clinical studies. To address this limitation, we propose a self-supervised learning framework called Multi-modal Cross-masked Autoencoder (MoCA) that leverages cross-modality masking and the Transformer autoencoder architecture to utilize both temporal correlations within modalities and cross-modal correlations between data streams. We also provide theoretical guarantees to support the effectiveness of the cross-modality masking scheme in MoCA. Comprehensive experiments and ablation studies demonstrate that our method outperforms existing approaches in both reconstruction and downstream tasks. We release open-source code for data processing, pre-training, and downstream tasks in the supplementary materials. This work highlights the transformative potential of self-supervised learning in digital health and multi-modal data.
Authors: Zhongyu Ouyang, Qianlong Wen, Chunhui Zhang, Yanfang Ye, Soroush Vosoughi
Abstract: Sequential recommendation systems aspire to profile users by interpreting their interaction histories, echoing how humans make decisions by weighing experience, relative preference strength, and situational relevance. Yet, existing large language model (LLM)-based recommenders often fall short of mimicking the flexible, context-aware decision strategies humans exhibit, neglecting the structured, dynamic, and context-aware mechanisms fundamental to human behaviors. To bridge this gap, we propose RecPO, a preference optimization framework that models structured feedback and contextual delay to emulate human-like prioritization in sequential recommendation RecPO exploits adaptive reward margins based on inferred preference hierarchies and temporal signals, enabling the model to favor immediately relevant items and to distinguish between varying degrees of preference and aversion. Extensive experiments across five real-world datasets demonstrate that RecPO not only yields performance gains over state-of-the-art baselines, but also mirrors key characteristics of human decision-making: favoring timely satisfaction, maintaining coherent preferences, and exercising discernment under shifting contexts.
Authors: Yifeng Teng, Yifan Wang
Abstract: We study the problem of learning the optimal item pricing for a unit-demand buyer with independent item values, and the learner has query access to the buyer's value distributions. We consider two common query models in the literature: the sample access model where the learner can obtain a sample of each item value, and the pricing query model where the learner can set a price for an item and obtain a binary signal on whether the sampled value of the item is greater than our proposed price. In this work, we give nearly tight sample complexity and pricing query complexity of the unit-demand pricing problem.
Authors: Thai Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles
Abstract: Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. To address these issues, we present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback. Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive real-time feedback. This setup enables LLM Agents to explore and solve tasks autonomously, facilitating the discovery of multiple approaches to tackle any given task. The resulting action trajectory data are then used to create high-quality training datasets for LAMs. Our experiments on popular agentic benchmarks, ToolBench and CRMArena, highlight the effectiveness of LAM SIMULATOR: models trained with self-generated datasets using our framework achieve significant performance gains, up to a 49.3\% improvement over their original baselines. LAM SIMULATOR requires minimal human input during dataset creation, highlighting LAM SIMULATOR's efficiency and effectiveness in speeding up development of AI agents.
Authors: Jingfeng Wu, Pierre Marion, Peter Bartlett
Abstract: We study gradient descent (GD) with a constant stepsize for $\ell_2$-regularized logistic regression with linearly separable data. Classical theory suggests small stepsizes to ensure monotonic reduction of the optimization objective, achieving exponential convergence in $\widetilde{\mathcal{O}}(\kappa)$ steps with $\kappa$ being the condition number. Surprisingly, we show that this can be accelerated to $\widetilde{\mathcal{O}}(\sqrt{\kappa})$ by simply using a large stepsize -- for which the objective evolves nonmonotonically. The acceleration brought by large stepsizes extends to minimizing the population risk for separable distributions, improving on the best-known upper bounds on the number of steps to reach a near-optimum. Finally, we characterize the largest stepsize for the local convergence of GD, which also determines the global convergence in special scenarios. Our results extend the analysis of Wu et al. (2024) from convex settings with minimizers at infinity to strongly convex cases with finite minimizers.
Authors: Qin Xie, Qinghua Zhang, Shuyin Xia
Abstract: Data sampling enhances classifier efficiency and robustness through data compression and quality improvement. Recently, the sampling method based on granular-ball (GB) has shown promising performance in generality and noisy classification tasks. However, some limitations remain, including the absence of borderline sampling strategies and issues with class boundary blurring or shrinking due to overlap between GBs. In this paper, an approximate borderline sampling method using GBs is proposed for classification tasks. First, a restricted diffusion-based GB generation (RD-GBG) method is proposed, which prevents GB overlaps by constrained expansion, preserving precise geometric representation of GBs via redefined ones. Second, based on the concept of heterogeneous nearest neighbor, a GB-based approximate borderline sampling (GBABS) method is proposed, which is the first general sampling method capable of both borderline sampling and improving the quality of class noise datasets. Additionally, since RD-GBG incorporates noise detection and GBABS focuses on borderline samples, GBABS performs outstandingly on class noise datasets without the need for an optimal purity threshold. Experimental results demonstrate that the proposed methods outperform the GB-based sampling method and several representative sampling methods. Our source code is publicly available at https://github.com/CherylTse/GBABS.
Authors: Kordel K. France, Ovidiu Daescu
Abstract: Olfactory navigation is one of the most primitive mechanisms of exploration used by organisms. Navigation by machine olfaction (artificial smell) is a very difficult task to both simulate and solve. With this work, we define olfactory inertial odometry (OIO), a framework for using inertial kinematics, and fast-sampling olfaction sensors to enable navigation by scent analogous to visual inertial odometry (VIO). We establish how principles from SLAM and VIO can be extrapolated to olfaction to enable real-world robotic tasks. We demonstrate OIO with three different odour localization algorithms on a real 5-DoF robot arm over an odour-tracking scenario that resembles real applications in agriculture and food quality control. Our results indicate success in establishing a baseline framework for OIO from which other research in olfactory navigation can build, and we note performance enhancements that can be made to address more complex tasks in the future.
Authors: Ukyo Honda, Tatsushi Oka
Abstract: In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing robustness is ICL with explanations (X-ICL), which improves prediction reliability by guiding LLMs to understand and articulate the reasoning behind correct labels. Building on this approach, we introduce an advanced framework that extends X-ICL by systematically exploring explanations for all possible labels (X$^2$-ICL), thereby enabling more comprehensive and robust decision-making. Experimental results on multiple natural language understanding datasets validate the effectiveness of X$^2$-ICL, demonstrating significantly improved robustness to out-of-distribution data compared to the existing ICL approaches.
Authors: Seulgi Kim, Ghazal Kaviani, Mohit Prabhushankar, Ghassan AlRegib
Abstract: Action anticipation, the task of predicting future actions from partially observed videos, is crucial for advancing intelligent systems. Unlike action recognition, which operates on fully observed videos, action anticipation must handle incomplete information. Hence, it requires temporal reasoning, and inherent uncertainty handling. While recent advances have been made, traditional methods often focus solely on visual modalities, neglecting the potential of integrating multiple sources of information. Drawing inspiration from human behavior, we introduce \textit{Multi-level and Multi-modal Action Anticipation (m\&m-Ant)}, a novel multi-modal action anticipation approach that combines both visual and textual cues, while explicitly modeling hierarchical semantic information for more accurate predictions. To address the challenge of inaccurate coarse action labels, we propose a fine-grained label generator paired with a specialized temporal consistency loss function to optimize performance. Extensive experiments on widely used datasets, including Breakfast, 50 Salads, and DARai, demonstrate the effectiveness of our approach, achieving state-of-the-art results with an average anticipation accuracy improvement of 3.08\% over existing methods. This work underscores the potential of multi-modal and hierarchical modeling in advancing action anticipation and establishes a new benchmark for future research in the field. Our code is available at: https://github.com/olivesgatech/mM-ant.
Authors: Yuan Bian, Xingche Guo, Yuanjia Wang
Abstract: Major depressive disorder (MDD), a leading cause of disability and mortality, is associated with reward-processing abnormalities and concentration issues. Motivated by the probabilistic reward task from the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study, we propose a novel framework that integrates the reinforcement learning (RL) model and drift-diffusion model (DDM) to jointly analyze reward-based decision-making with response times. To account for emerging evidence suggesting that decision-making may alternate between multiple interleaved strategies, we model latent state switching using a hidden Markov model (HMM). In the ''engaged'' state, decisions follow an RL-DDM, simultaneously capturing reward processing, decision dynamics, and temporal structure. In contrast, in the ''lapsed'' state, decision-making is modeled using a simplified DDM, where specific parameters are fixed to approximate random guessing with equal probability. The proposed method is implemented using a computationally efficient generalized expectation-maximization algorithm with forward-backward procedures. Through extensive numerical studies, we demonstrate that our proposed method outperforms competing approaches under various reward-generating distributions, both with and without strategy switching. When applied to the EMBARC study, our framework reveals that MDD patients exhibit lower overall engagement than healthy controls and experience longer decision times when they do engage. Additionally, we show that neuroimaging measures of brain activities are associated with decision-making characteristics in the ''engaged'' state but not in the ''lapsed'' state, providing evidence of brain-behavioral association specific to the ''engaged'' state.
Authors: Tian Lan, Jie Guo, Chen Zhang
Abstract: Understanding the complex interactions within dynamic multilayer networks is critical for advancements in various scientific domains. Existing models often fail to capture such networks' temporal and cross-layer dynamics. This paper introduces a novel Tensor State Space Model for Dynamic Multilayer Networks (TSSDMN), utilizing a latent space model framework. TSSDMN employs a symmetric Tucker decomposition to represent latent node features, their interaction patterns, and layer transitions. Then by fixing the latent features and allowing the interaction patterns to evolve over time, TSSDMN uniquely captures both the temporal dynamics within layers and across different layers. The model identifiability conditions are discussed. By treating latent features as variables whose posterior distributions are approximated using a mean-field variational inference approach, a variational Expectation Maximization algorithm is developed for efficient model inference. Numerical simulations and case studies demonstrate the efficacy of TSSDMN for understanding dynamic multilayer networks.
Authors: Xiyu Zhao, Qimei Cui, Ziqiang Du, Weicai Li, Xi Yu, Wei Ni, Ji Zhang, Xiaofeng Tao, Ping Zhang
Abstract: Personalized federated learning (PFL) offers a solution to balancing personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). Little attention has been given to wireless PFL (WPFL), where privacy concerns arise. Performance fairness of PL models is another challenge resulting from communication bottlenecks in WPFL. This paper exploits quantization errors to enhance the privacy of WPFL and proposes a novel quantization-assisted Gaussian differential privacy (DP) mechanism. We analyze the convergence upper bounds of individual PL models by considering the impact of the mechanism (i.e., quantization errors and Gaussian DP noises) and imperfect communication channels on the FL of WPFL. By minimizing the maximum of the bounds, we design an optimal transmission scheduling strategy that yields min-max fairness for WPFL with OFDMA interfaces. This is achieved by revealing the nested structure of this problem to decouple it into subproblems solved sequentially for the client selection, channel allocation, and power control, and for the learning rates and PL-FL weighting coefficients. Experiments validate our analysis and demonstrate that our approach substantially outperforms alternative scheduling strategies by 87.08%, 16.21%, and 38.37% in accuracy, the maximum test loss of participating clients, and fairness (Jain's index), respectively.
Authors: Sudhanshu Sekhar Tripathy, Bichitrananda Behera
Abstract: IDS aims to protect computer networks from security threats by detecting, notifying, and taking appropriate action to prevent illegal access and protect confidential information. As the globe becomes increasingly dependent on technology and automated processes, ensuring secured systems, applications, and networks has become one of the most significant problems of this era. The global web and digital technology have significantly accelerated the evolution of the modern world, necessitating the use of telecommunications and data transfer platforms. Researchers are enhancing the effectiveness of IDS by incorporating popular datasets into machine learning algorithms. IDS, equipped with machine learning classifiers, enhances security attack detection accuracy by identifying normal or abnormal network traffic. This paper explores the methods of capturing and reviewing intrusion detection systems (IDS) and evaluates the challenges existing datasets face. A deluge of research on machine learning (ML) and deep learning (DL) architecture-based intrusion detection techniques has been conducted in the past ten years on various cybersecurity datasets, including KDDCUP'99, NSL-KDD, UNSW-NB15, CICIDS-2017, and CSE-CIC-IDS2018. We conducted a literature review and presented an in-depth analysis of various intrusion detection methods that use SVM, KNN, DT, LR, NB, RF, XGBOOST, Adaboost, and ANN. We provide an overview of each technique, explaining the role of the classifiers and algorithms used. A detailed tabular analysis highlights the datasets used, classifiers employed, attacks detected, evaluation metrics, and conclusions drawn. This article offers a thorough review for future IDS research.
Authors: Nguyen Chi Long, Trinh Van Chien, Ta Hai Tung, Van Son Nguyen, Trong-Minh Hoang, Nguyen Ngoc Hai Dang
Abstract: Mobile edge computing (MEC) allows appliances to offload workloads to neighboring MEC servers that have the potential for computation-intensive tasks with limited computational capabilities. This paper studied how deep reinforcement learning (DRL) algorithms are used in an MEC system to find feasible decentralized dynamic computation offloading strategies, which leads to the construction of an extensible MEC system that operates effectively with finite feedback. Even though the Deep Deterministic Policy Gradient (DDPG) algorithm, subject to their knowledge of the MEC system, can be used to allocate powers of both computation offloading and local execution, to learn a computation offloading policy for each user independently, we realized that this solution still has some inherent weaknesses. Hence, we introduced a new approach for this problem based on the Twin Delayed DDPG algorithm, which enables us to overcome this proneness and investigate cases where mobile users are portable. Numerical results showed that individual users can autonomously learn adequate policies through the proposed approach. Besides, the performance of the suggested solution exceeded the conventional DDPG-based power control strategy.
Authors: Tao Zhong, Jonah Buchanan, Christine Allen-Blanchette
Abstract: We propose a new approach to vision-based dexterous grasp translation, which aims to transfer grasp intent across robotic hands with differing morphologies. Given a visual observation of a source hand grasping an object, our goal is to synthesize a functionally equivalent grasp for a target hand without requiring paired demonstrations or hand-specific simulations. We frame this problem as a stochastic transport between grasp distributions using the Schr\"odinger Bridge formalism. Our method learns to map between source and target latent grasp spaces via score and flow matching, conditioned on visual observations. To guide this translation, we introduce physics-informed cost functions that encode alignment in base pose, contact maps, wrench space, and manipulability. Experiments across diverse hand-object pairs demonstrate our approach generates stable, physically grounded grasps with strong generalization. This work enables semantic grasp transfer for heterogeneous manipulators and bridges vision-based grasping with probabilistic generative modeling.
Authors: Zhuohan Xie, Dhruv Sahnan, Debopriyo Banerjee, Georgi Georgiev, Rushil Thareja, Hachem Madmoun, Jinyan Su, Aaryamonvikram Singh, Yuxia Wang, Rui Xing, Fajri Koto, Haonan Li, Ivan Koychev, Tanmoy Chakraborty, Salem Lahlou, Veselin Stoyanov, Preslav Nakov
Abstract: Multi-step symbolic reasoning is critical for advancing downstream performance on financial tasks. Yet, benchmarks for systematically evaluating this capability are lacking. Existing datasets like FinQA and ConvFinQA supervise only final numerical answers, without assessing intermediate reasoning steps. To address this, we introduce FinChain, the first symbolic benchmark designed for verifiable Chain-of- Thought (CoT) financial reasoning. Spanning 54 topics across 12 financial domains, Fin- Chain offers five parameterized templates per topic, each varying in reasoning complexity and domain expertise required. Each dataset instance includes an executable Python trace, enabling automatic generation of extensive training data and easy adaptation to other domains. We also introduce ChainEval, a new metric for automatic evaluation of both final answers and intermediate reasoning. Benchmarking 30 LLMs on our dataset, we find that even state-of-the-art models have considerable room for improvement in multi-step financial reasoning. All templates and evaluation metrics for FinChain are available at https: //github.com/mbzuai-nlp/finchain.
Authors: Zhun Wang, Tianneng Shi, Jingxuan He, Matthew Cai, Jialin Zhang, Dawn Song
Abstract: Large language model (LLM) agents are becoming increasingly skilled at handling cybersecurity tasks autonomously. Thoroughly assessing their cybersecurity capabilities is critical and urgent, given the high stakes in this domain. However, existing benchmarks fall short, often failing to capture real-world scenarios or being limited in scope. To address this gap, we introduce CyberGym, a large-scale and high-quality cybersecurity evaluation framework featuring 1,507 real-world vulnerabilities found and patched across 188 large software projects. While it includes tasks of various settings, CyberGym primarily focuses on the generation of proof-of-concept (PoC) tests for vulnerability reproduction, based on text descriptions and corresponding source repositories. Solving this task is particularly challenging, as it requires comprehensive reasoning across entire codebases to locate relevant code fragments and produce effective PoCs that accurately trigger the target vulnerability starting from the program's entry point. Our evaluation across 4 state-of-the-art agent frameworks and 9 LLMs reveals that even the best combination (OpenHands and Claude-3.7-Sonnet) achieves only a 11.9% reproduction success rate, mainly on simpler cases. Beyond reproducing historical vulnerabilities, we find that PoCs generated by LLM agents can reveal new vulnerabilities, identifying 15 zero-days affecting the latest versions of the software projects.
Authors: Timo Osterburg, Franz Albers, Christopher Diehl, Rajesh Pushparaj, Torsten Bertram
Abstract: The fusion of sensor data is essential for a robust perception of the environment in autonomous driving. Learning-based fusion approaches mainly use feature-level fusion to achieve high performance, but their complexity and hardware requirements limit their applicability in near-production vehicles. High-level fusion methods offer robustness with lower computational requirements. Traditional methods, such as the Kalman filter, dominate this area. This paper modifies the Adapted Kalman Filter (AKF) and proposes a novel transformer-based high-level object fusion method called HiLO. Experimental results demonstrate improvements of $25.9$ percentage points in $\textrm{F}_1$ score and $6.1$ percentage points in mean IoU. Evaluation on a new large-scale real-world dataset demonstrates the effectiveness of the proposed approaches. Their generalizability is further validated by cross-domain evaluation between urban and highway scenarios. Code, data, and models are available at https://github.com/rst-tu-dortmund/HiLO .
Authors: Luca Arnaboldi, Bruno Loureiro, Ludovic Stephan, Florent Krzakala, Lenka Zdeborova
Abstract: We study the dynamics of stochastic gradient descent (SGD) for a class of sequence models termed Sequence Single-Index (SSI) models, where the target depends on a single direction in input space applied to a sequence of tokens. This setting generalizes classical single-index models to the sequential domain, encompassing simplified one-layer attention architectures. We derive a closed-form expression for the population loss in terms of a pair of sufficient statistics capturing semantic and positional alignment, and characterize the induced high-dimensional SGD dynamics for these coordinates. Our analysis reveals two distinct training phases: escape from uninformative initialization and alignment with the target subspace, and demonstrates how the sequence length and positional encoding influence convergence speed and learning trajectories. These results provide a rigorous and interpretable foundation for understanding how sequential structure in data can be beneficial for learning with attention-based models.
Authors: Tam Ninh Thi-Thanh, Trinh Van Chien, Hung Tran, Nguyen Hoai Son, Van Nhan Vo
Abstract: Metaverse and Digital Twin (DT) have attracted much academic and industrial attraction to approach the future digital world. This paper introduces the advantages of deep reinforcement learning (DRL) in assisting Metaverse system-based Digital Twin. In this system, we assume that it includes several Metaverse User devices collecting data from the real world to transfer it into the virtual world, a Metaverse Virtual Access Point (MVAP) undertaking the processing of data, and an edge computing server that receives the offloading data from the MVAP. The proposed model works under a dynamic environment with various parameters changing over time. The experiment results show that our proposed DRL algorithm is suitable for offloading tasks to ensure the promptness of DT in a dynamic environment.
Authors: Hugo Tabanelli, Pierre Mergny, Lenka Zdeborova, Florent Krzakala
Abstract: We study the recovery of multiple high-dimensional signals from two noisy, correlated modalities: a spiked matrix and a spiked tensor sharing a common low-rank structure. This setting generalizes classical spiked matrix and tensor models, unveiling intricate interactions between inference channels and surprising algorithmic behaviors. Notably, while the spiked tensor model is typically intractable at low signal-to-noise ratios, its correlation with the matrix enables efficient recovery via Bayesian Approximate Message Passing, inducing staircase-like phase transitions reminiscent of neural network phenomena. In contrast, empirical risk minimization for joint learning fails: the tensor component obstructs effective matrix recovery, and joint optimization significantly degrades performance, highlighting the limitations of naive multi-modal learning. We show that a simple Sequential Curriculum Learning strategy-first recovering the matrix, then leveraging it to guide tensor recovery-resolves this bottleneck and achieves optimal weak recovery thresholds. This strategy, implementable with spectral methods, emphasizes the critical role of structural correlation and learning order in multi-modal high-dimensional inference.
Authors: Frederico Metelo, Alexandre Oliveira, Stevo Rackovi\'c, Pedro \'Akos Costa, Cl\'audia Soares
Abstract: Edge computing addresses the growing data demands of connected-device networks by placing computational resources closer to end users through decentralized infrastructures. This decentralization challenges traditional, fully centralized orchestration, which suffers from latency and resource bottlenecks. We present \textbf{FAuNO} -- \emph{Federated Asynchronous Network Orchestrator} -- a buffered, asynchronous \emph{federated reinforcement-learning} (FRL) framework for decentralized task offloading in edge systems. FAuNO adopts an actor-critic architecture in which local actors learn node-specific dynamics and peer interactions, while a federated critic aggregates experience across agents to encourage efficient cooperation and improve overall system performance. Experiments in the \emph{PeersimGym} environment show that FAuNO consistently matches or exceeds heuristic and federated multi-agent RL baselines in reducing task loss and latency, underscoring its adaptability to dynamic edge-computing scenarios.
Authors: Jintao Tong, Yixiong Zou, Guangyao Chen, Yuhua Li, Ruixuan Li
Abstract: Cross-Domain Few-Shot Segmentation (CD-FSS) aims to transfer knowledge from a source-domain dataset to unseen target-domain datasets with limited annotations. Current methods typically compare the distance between training and testing samples for mask prediction. However, we find an entanglement problem exists in this widely adopted method, which tends to bind sourcedomain patterns together and make each of them hard to transfer. In this paper, we aim to address this problem for the CD-FSS task. We first find a natural decomposition of the ViT structure, based on which we delve into the entanglement problem for an interpretation. We find the decomposed ViT components are crossly compared between images in distance calculation, where the rational comparisons are entangled with those meaningless ones by their equal importance, leading to the entanglement problem. Based on this interpretation, we further propose to address the entanglement problem by learning to weigh for all comparisons of ViT components, which learn disentangled features and re-compose them for the CD-FSS task, benefiting both the generalization and finetuning. Experiments show that our model outperforms the state-of-the-art CD-FSS method by 1.92% and 1.88% in average accuracy under 1-shot and 5-shot settings, respectively.
Authors: Hohyun Kim, Seunggeun Lee, Min-hwan Oh
Abstract: Generative Flow Networks (GFlowNets) offer a powerful framework for sampling graphs in proportion to their rewards. However, existing approaches suffer from systematic biases due to inaccuracies in state transition probability computations. These biases, rooted in the inherent symmetries of graphs, impact both atom-based and fragment-based generation schemes. To address this challenge, we introduce Symmetry-Aware GFlowNets (SA-GFN), a method that incorporates symmetry corrections into the learning process through reward scaling. By integrating bias correction directly into the reward structure, SA-GFN eliminates the need for explicit state transition computations. Empirical results show that SA-GFN enables unbiased sampling while enhancing diversity and consistently generating high-reward graphs that closely match the target distribution.
Authors: T. N. Nisslbeck, Wouter M. Kouw
Abstract: We propose a recursive Bayesian estimation procedure for multivariate autoregressive models with exogenous inputs based on message passing in a factor graph. Unlike recursive least-squares, our method produces full posterior distributions for both the autoregressive coefficients and noise precision. The uncertainties regarding these estimates propagate into the uncertainties on predictions for future system outputs, and support online model evidence calculations. We demonstrate convergence empirically on a synthetic autoregressive system and competitive performance on a double mass-spring-damper system.
Authors: Qihang Yan, Xinyu Zhang, Luming Guo, Qi Zhang, Feifan Liu
Abstract: Large Language Models (LLMs) struggle with accuracy, domain-specific reasoning, and interpretability in vertical domains. Traditional preference alignment methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) often overlook the underlying knowledge sources and reasoning logic. This paper introduces RACE-Align (Retrieval-Augmented and Chain-of-Thought Enhanced Alignment), a novel framework designed to address these limitations. RACE-Align systematically constructs a binary preference dataset incorporating external knowledge support and explicit Chain-of-Thought (CoT) reasoning, then aligns LLMs using the DPO algorithm. The core innovation lies in its preference data construction strategy: it integrates AI-driven retrieval for factual grounding, enhancing knowledgeability and accuracy, and emphasizes the optimization of domain-specific CoT, treating the reasoning process itself as a key preference dimension. A multi-stage, AI-driven refinement pipeline cost-effectively generates these preference pairs. Experimental validation in Traditional Chinese Medicine (TCM) using Qwen3-1.7B as the base model demonstrates that RACE-Align significantly outperforms the original base model and a model fine-tuned only with Supervised Fine-Tuning (SFT). Improvements were observed across multiple dimensions, including answer accuracy, information richness, application of TCM thinking patterns, logicality and depth of reasoning, and interpretability. These findings suggest RACE-Align offers an effective pathway to enhance LLMs' knowledge application, reasoning reliability, and process transparency in complex vertical domains.
Authors: Luc Brogat-Motte, Alessandro Rudi, Riccardo Bonalli
Abstract: We address the problem of safely learning controlled stochastic dynamics from discrete-time trajectory observations, ensuring system trajectories remain within predefined safe regions during both training and deployment. Safety-critical constraints of this kind are crucial in applications such as autonomous robotics, finance, and biomedicine. We introduce a method that ensures safe exploration and efficient estimation of system dynamics by iteratively expanding an initial known safe control set using kernel-based confidence bounds. After training, the learned model enables predictions of the system's dynamics and permits safety verification of any given control. Our approach requires only mild smoothness assumptions and access to an initial safe control set, enabling broad applicability to complex real-world systems. We provide theoretical guarantees for safety and derive adaptive learning rates that improve with increasing Sobolev regularity of the true dynamics. Experimental evaluations demonstrate the practical effectiveness of our method in terms of safety, estimation accuracy, and computational efficiency.
Authors: Houssam Zenati, Bariscan Bozkurt, Arthur Gretton
Abstract: Estimating the distribution of outcomes under counterfactual policies is critical for decision-making in domains such as recommendation, advertising, and healthcare. We analyze a novel framework-Counterfactual Policy Mean Embedding (CPME)-that represents the entire counterfactual outcome distribution in a reproducing kernel Hilbert space (RKHS), enabling flexible and nonparametric distributional off-policy evaluation. We introduce both a plug-in estimator and a doubly robust estimator; the latter enjoys improved uniform convergence rates by correcting for bias in both the outcome embedding and propensity models. Building on this, we develop a doubly robust kernel test statistic for hypothesis testing, which achieves asymptotic normality and thus enables computationally efficient testing and straightforward construction of confidence intervals. Our framework also supports sampling from the counterfactual distribution. Numerical simulations illustrate the practical benefits of CPME over existing methods.
Authors: Andr\'as Strausz, Niels Pardon, Ioana Giurgiu
Abstract: Lakehouse systems enable the same data to be queried with multiple execution engines. However, selecting the engine best suited to run a SQL query still requires a priori knowledge of the query computational requirements and an engine capability, a complex and manual task that only becomes more difficult with the emergence of new engines and workloads. In this paper, we address this limitation by proposing a cross-engine optimizer that can automate engine selection for diverse SQL queries through a learned cost model. Optimized with hints, a query plan is used for query cost prediction and routing. Cost prediction is formulated as a multi-task learning problem, and multiple predictor heads, corresponding to different engines and provisionings, are used in the model architecture. This eliminates the need to train engine-specific models and allows the flexible addition of new engines at a minimal fine-tuning cost. Results on various databases and engines show that using a query optimized logical plan for cost estimation decreases the average Q-error by even 12.6% over using unoptimized plans as input. Moreover, the proposed cross-engine optimizer reduces the total workload runtime by up to 25.2% in a zero-shot setting and 30.4% in a few-shot setting when compared to random routing.
Authors: Ekaterina Grishina, Mikhail Gorbunov, Maxim Rakhuba
Abstract: Large language models (LLMs) demonstrate impressive results in natural language processing tasks but require a significant amount of computational and memory resources. Structured matrix representations are a promising way for reducing the number of parameters of these models. However, it seems unrealistic to expect that weight matrices of pretrained models can be accurately represented by structured matrices without any fine-tuning. To overcome this issue, we utilize the fact that LLM output is invariant under certain orthogonal transformations of weight matrices. This insight can be leveraged to identify transformations that significantly improve the compressibility of weights within structured classes. The proposed approach is applicable to various types of structured matrices that support efficient projection operations. Code is available at https://github.com/GrishKate/ProcrustesGPT
Authors: Tong Qi, Vera Andersson, Peter Viechnicki, Vince Lyzinski
Abstract: We present the OmniMatch algorithm for seeded multiple graph matching. In the setting of $d$-dimensional Random Dot Product Graphs (RDPG), we prove that under mild assumptions, OmniMatch with $s$ seeds asymptotically and efficiently perfectly aligns $O(s^{\alpha})$ unseeded vertices -- for $\alpha<2\wedge d/4$ -- across multiple networks even in the presence of no edge correlation. We demonstrate the effectiveness of our algorithm across numerous simulations and in the context of shuffled graph hypothesis testing. In the shuffled testing setting, testing power is lost due to the misalignment/shuffling of vertices across graphs, and we demonstrate the capacity of OmniMatch to correct for misaligned vertices prior to testing and hence recover the lost testing power. We further demonstrate the algorithm on a pair of data examples from connectomics and machine translation.
Authors: Tom Danino, Nahum Shimkin
Abstract: Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms typically require significantly more environment interactions than their single-agent counterparts to converge, a problem exacerbated by the difficulty in exploring over a large joint action space and the high variance intrinsic to MARL environments. To tackle these issues, we propose a novel algorithm that combines a decomposed centralized critic with decentralized ensemble learning, incorporating several key contributions. The main component in our scheme is a selective exploration method that leverages ensemble kurtosis. We extend the global decomposed critic with a diversity-regularized ensemble of individual critics and utilize its excess kurtosis to guide exploration toward high-uncertainty states and actions. To improve sample efficiency, we train the centralized critic with a novel truncated variation of the TD($\lambda$) algorithm, enabling efficient off-policy learning with reduced variance. On the actor side, our suggested algorithm adapts the mixed samples approach to MARL, mixing on-policy and off-policy loss functions for training the actors. This approach balances between stability and efficiency and outperforms purely off-policy learning. The evaluation shows our method outperforms state-of-the-art baselines on standard MARL benchmarks, including a variety of SMAC II maps.
Authors: Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren
Abstract: The increasing proliferation of small UAVs in civilian and military airspace has raised critical safety and security concerns, especially when unauthorized or malicious drones enter restricted zones. In this work, we present a reinforcement learning (RL) framework for agile 1v1 quadrotor pursuit-evasion. We train neural network policies to command body rates and collective thrust, enabling high-speed pursuit and evasive maneuvers that fully exploit the quadrotor's nonlinear dynamics. To mitigate nonstationarity and catastrophic forgetting during adversarial co-training, we introduce an Asynchronous Multi-Stage Population-Based (AMSPB) algorithm where, at each stage, either the pursuer or evader learns against a sampled opponent drawn from a growing population of past and current policies. This continual learning setup ensures monotonic performance improvement and retention of earlier strategies. Our results show that (i) rate-based policies achieve significantly higher capture rates and peak speeds than velocity-level baselines, and (ii) AMSPB yields stable, monotonic gains against a suite of benchmark opponents.
Authors: Brian M Cho, Aur\'elien Bibaut, Nathan Kallus
Abstract: Multi-arm bandit experimental designs are increasingly being adopted over standard randomized trials due to their potential to improve outcomes for study participants, enable faster identification of the best-performing options, and/or enhance the precision of estimating key parameters. Current approaches for inference after adaptive sampling either rely on asymptotic normality under restricted experiment designs or underpowered martingale concentration inequalities that lead to weak power in practice. To bypass these limitations, we propose a simulation-based approach for conducting hypothesis tests and constructing confidence intervals for arm specific means and their differences. Our simulation-based approach uses positively biased nuisances to generate additional trajectories of the experiment, which we call \textit{simulation with optimism}. Using these simulations, we characterize the distribution potentially non-normal sample mean test statistic to conduct inference. We provide guarantees for (i) asymptotic type I error control, (ii) convergence of our confidence intervals, and (iii) asymptotic strong consistency of our estimator over a wide variety of common bandit designs. Our empirical results show that our approach achieves the desired coverage while reducing confidence interval widths by up to 50%, with drastic improvements for arms not targeted by the design.
Authors: Adam Pardyl, Dominik Matuszek, Mateusz Przebieracz, Marek Cygan, Bartosz Zieli\'nski, Maciej Wo{\l}czyk
Abstract: The real world is messy and unstructured. Uncovering critical information often requires active, goal-driven exploration. It remains to be seen whether Vision-Language Models (VLMs), which recently emerged as a popular zero-shot tool in many difficult tasks, can operate effectively in such conditions. In this paper, we answer this question by introducing FlySearch, a 3D, outdoor, photorealistic environment for searching and navigating to objects in complex scenes. We define three sets of scenarios with varying difficulty and observe that state-of-the-art VLMs cannot reliably solve even the simplest exploration tasks, with the gap to human performance increasing as the tasks get harder. We identify a set of central causes, ranging from vision hallucination, through context misunderstanding, to task planning failures, and we show that some of them can be addressed by finetuning. We publicly release the benchmark, scenarios, and the underlying codebase.
Authors: Bunlong Lay, Rostilav Makarov, Timo Gerkmann
Abstract: Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing streaming data in real-time. In this work, we adapt a sliding window diffusion framework to the speech enhancement task. Our approach progressively corrupts speech signals through time, assigning more noise to frames close to the present in a buffer. This approach outputs denoised frames with a delay proportional to the chosen buffer size, enabling a trade-off between performance and latency. Empirical results demonstrate that our method outperforms standard diffusion models and runs efficiently on a GPU, achieving an input-output latency in the order of 0.3 to 1 seconds. This marks the first practical diffusion-based solution for online speech enhancement.
Authors: Yin Fang, Qiao Jin, Guangzhi Xiong, Bowen Jin, Xianrui Zhong, Siru Ouyang, Aidong Zhang, Jiawei Han, Zhiyong Lu
Abstract: Cell type annotation is a key task in analyzing the heterogeneity of single-cell RNA sequencing data. Although recent foundation models automate this process, they typically annotate cells independently, without considering batch-level cellular context or providing explanatory reasoning. In contrast, human experts often annotate distinct cell types for different cell clusters based on their domain knowledge. To mimic this workflow, we introduce the CellPuzzles task, where the objective is to assign unique cell types to a batch of cells. This benchmark spans diverse tissues, diseases, and donor conditions, and requires reasoning across the batch-level cellular context to ensure label uniqueness. We find that off-the-shelf large language models (LLMs) struggle on CellPuzzles, with the best baseline (OpenAI's o1) achieving only 19.0% batch-level accuracy. To fill this gap, we propose Cell-o1, a 7B LLM trained via supervised fine-tuning on distilled reasoning traces, followed by reinforcement learning with batch-level rewards. Cell-o1 achieves state-of-the-art performance, outperforming o1 by over 73% and generalizing well across contexts. Further analysis of training dynamics and reasoning behaviors provides insights into batch-level annotation performance and emergent expert-like reasoning. Code and data are available at https://github.com/ncbi-nlp/cell-o1.
Authors: Shangmin Guo, Omar Darwiche Domingues, Rapha\"el Avalos, Aaron Courville, Florian Strub
Abstract: Tool use in stateful environments presents unique challenges for large language models (LLMs), where existing test-time compute strategies relying on repeated trials in the environment are impractical. We propose dynamics modelling (DyMo), a method that augments LLMs with a state prediction capability alongside function calling during post-training. This enables LLMs to predict the future states of their actions through an internal environment model. On the Berkeley Function Calling Leaderboard V2, DyMo improves success rates and significantly reduces hallucinations. We further integrate the internal environment model into self-verification sampling (SVS), and show that this substantially improves pass^k over number of trials k, and allows the model to refuse unreliable outputs. Together, DyMo and SVS greatly enhance the effectiveness and reliability of LLMs for tool use. We believe this work charts a path towards scalable planning RL methods for LLM inference without repeatedly querying the oracle environment.
Authors: Diogo A. P. Nunes, Eug\'enio Ribeiro
Abstract: In this work, we describe our team's approach to eRisk's 2025 Task 1: Search for Symptoms of Depression. Given a set of sentences and the Beck's Depression Inventory - II (BDI) questionnaire, participants were tasked with submitting up to 1,000 sentences per depression symptom in the BDI, sorted by relevance. Participant submissions were evaluated according to standard Information Retrieval (IR) metrics, including Average Precision (AP) and R-Precision (R-PREC). The provided training data, however, consisted of sentences labeled as to whether a given sentence was relevant or not w.r.t. one of BDI's symptoms. Due to this labeling limitation, we framed our development as a binary classification task for each BDI symptom, and evaluated accordingly. To that end, we split the available labeled data into training and validation sets, and explored foundation model fine-tuning, sentence similarity, Large Language Model (LLM) prompting, and ensemble techniques. The validation results revealed that fine-tuning foundation models yielded the best performance, particularly when enhanced with synthetic data to mitigate class imbalance. We also observed that the optimal approach varied by symptom. Based on these insights, we devised five independent test runs, two of which used ensemble methods. These runs achieved the highest scores in the official IR evaluation, outperforming submissions from 16 other teams.
Authors: Praneet Sai Madhu Surabhi, Dheeraj Reddy Mudireddy, Jian Tao
Abstract: This paper presents ThinkTank, a comprehensive and scalable framework designed to transform specialized AI agent systems into versatile collaborative intelligence platforms capable of supporting complex problem-solving across diverse domains. ThinkTank systematically generalizes agent roles, meeting structures, and knowledge integration mechanisms by adapting proven scientific collaboration methodologies. Through role abstraction, generalization of meeting types for iterative collaboration, and the integration of Retrieval-Augmented Generation with advanced knowledge storage, the framework facilitates expertise creation and robust knowledge sharing. ThinkTank enables organizations to leverage collaborative AI for knowledge-intensive tasks while ensuring data privacy and security through local deployment, utilizing frameworks like Ollama with models such as Llama3.1. The ThinkTank framework is designed to deliver significant advantages in cost-effectiveness, data security, scalability, and competitive positioning compared to cloud-based alternatives, establishing it as a universal platform for AI-driven collaborative problem-solving. The ThinkTank code is available at https://github.com/taugroup/ThinkTank
Authors: Aishwarya Sahoo, Jeevana Kruthi Karnuthala, Tushar Parmanand Budhwani, Pranchal Agarwal, Sankaran Vaidyanathan, Alexa Siu, Franck Dernoncourt, Jennifer Healey, Nedim Lipka, Ryan Rossi, Uttaran Bhattacharya, Branislav Kveton
Abstract: LLM-as-a-judge is a framework in which a large language model (LLM) automatically evaluates the output of another LLM. We propose quantitative LLM judges, which align evaluation scores of existing LLM judges to human scores in a given domain using regression models. The models are trained to improve the score of the original judge by using the judge's textual evaluation and score. We present four quantitative judges for different types of absolute and relative feedback, which showcases the generality and versatility of our framework. Our framework is more computationally efficient than supervised fine-tuning and can be more statistically efficient when human feedback is limited, which is expected in most applications of our work. We validate these claims empirically on four datasets using two base judges. Our experiments show that quantitative judges can effectively improve the predictive power of existing judges through post-hoc modeling.
Authors: Zewen Yang, Xiaobing Dai, Dian Yu, Qianru Li, Yu Li, Valentin Le Mesle
Abstract: Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of constraints, such as collision avoidance and dynamic consistency, which are often treated separately or only partially considered. This paper proposes UniConFlow, a unified flow matching (FM) based framework for trajectory generation that systematically incorporates both equality and inequality constraints. UniConFlow introduces a novel prescribed-time zeroing function to enhance flexibility during the inference process, allowing the model to adapt to varying task requirements. To ensure constraint satisfaction, particularly with respect to obstacle avoidance, admissible action range, and kinodynamic consistency, the guidance inputs to the FM model are derived through a quadratic programming formulation, which enables constraint-aware generation without requiring retraining or auxiliary controllers. We conduct mobile navigation and high-dimensional manipulation tasks, demonstrating improved safety and feasibility compared to state-of-the-art constrained generative planners. Project page is available at https://uniconflow.github.io.
Authors: Guiqiu Liao, Matjaz Jogan, Eric Eaton, Daniel A. Hashimoto
Abstract: Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require features that are jointly informative across clients while disentangling domain-specific factors without supervision. We introduce FORLA, a novel framework for federated object-centric representation learning and feature adaptation across clients using unsupervised slot attention. At the core of our method is a shared feature adapter, trained collaboratively across clients to adapt features from foundation models, and a shared slot attention module that learns to reconstruct the adapted features. To optimize this adapter, we design a two-branch student-teacher architecture. In each client, a student decoder learns to reconstruct full features from foundation models, while a teacher decoder reconstructs their adapted, low-dimensional counterpart. The shared slot attention module bridges cross-domain learning by aligning object-level representations across clients. Experiments in multiple real-world datasets show that our framework not only outperforms centralized baselines on object discovery but also learns a compact, universal representation that generalizes well across domains. This work highlights federated slot attention as an effective tool for scalable, unsupervised visual representation learning from cross-domain data with distributed concepts.
Authors: Xiaoqi Liu, Dorian Baudry, Julian Zimmert, Patrick Rebeschini, Arya Akhavan
Abstract: Bandit Convex Optimization is a fundamental class of sequential decision-making problems, where the learner selects actions from a continuous domain and observes a loss (but not its gradient) at only one point per round. We study this problem in non-stationary environments, and aim to minimize the regret under three standard measures of non-stationarity: the number of switches $S$ in the comparator sequence, the total variation $\Delta$ of the loss functions, and the path-length $P$ of the comparator sequence. We propose a polynomial-time algorithm, Tilted Exponentially Weighted Average with Sleeping Experts (TEWA-SE), which adapts the sleeping experts framework from online convex optimization to the bandit setting. For strongly convex losses, we prove that TEWA-SE is minimax-optimal with respect to known $S$ and $\Delta$ by establishing matching upper and lower bounds. By equipping TEWA-SE with the Bandit-over-Bandit framework, we extend our analysis to environments with unknown non-stationarity measures. For general convex losses, we introduce a second algorithm, clipped Exploration by Optimization (cExO), based on exponential weights over a discretized action space. While not polynomial-time computable, this method achieves minimax-optimal regret with respect to known $S$ and $\Delta$, and improves on the best existing bounds with respect to $P$.
Authors: Li Zhang, Kevin D. Ashley
Abstract: Large Language Models (LLMs) are increasingly explored for legal argument generation, yet they pose significant risks of manipulation through hallucination and ungrounded persuasion, and often fail to utilize provided factual bases effectively or abstain when arguments are untenable. This paper introduces a novel reflective multi-agent method designed to address these challenges in the context of legally compliant persuasion. Our approach employs specialized agents--a Factor Analyst and an Argument Polisher--in an iterative refinement process to generate 3-ply legal arguments (plaintiff, defendant, rebuttal). We evaluate Reflective Multi-Agent against single-agent, enhanced-prompt single-agent, and non-reflective multi-agent baselines using four diverse LLMs (GPT-4o, GPT-4o-mini, Llama-4-Maverick-17b-128e, Llama-4-Scout-17b-16e) across three legal scenarios: "arguable", "mismatched", and "non-arguable". Results demonstrate Reflective Multi-Agent's significant superiority in successful abstention (preventing generation when arguments cannot be grounded), marked improvements in hallucination accuracy (reducing fabricated and misattributed factors), particularly in "non-arguable" scenarios, and enhanced factor utilization recall (improving the use of provided case facts). These findings suggest that structured reflection within a multi-agent framework offers a robust computable method for fostering ethical persuasion and mitigating manipulation in LLM-based legal argumentation systems, a critical step towards trustworthy AI in law. Project page: https://lizhang-aiandlaw.github.io/A-Reflective-Multi-Agent-Approach-for-Legal-Argument-Generation/
URLs: https://lizhang-aiandlaw.github.io/A-Reflective-Multi-Agent-Approach-for-Legal-Argument-Generation/
Authors: Alexandra Gonz\'alez, Xavier Franch, David Lo, Silverio Mart\'inez-Fern\'andez
Abstract: Open-Source Pre-Trained Models (PTMs) provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs. To address this gap, we derive a taxonomy encompassing 147 SE tasks and apply an SE-oriented classification to PTMs in a popular open-source ML repository, Hugging Face (HF). Our repository mining study began with a systematically gathered database of PTMs from the HF API, considering their model card descriptions and metadata, and the abstract of the associated arXiv papers. We confirmed SE relevance through multiple filtering steps: detecting outliers, identifying near-identical PTMs, and the use of Gemini 2.0 Flash, which was validated with five pilot studies involving three human annotators. This approach uncovered 2,205 SE PTMs. We find that code generation is the most common SE task among PTMs, primarily focusing on software implementation, while requirements engineering and software design activities receive limited attention. In terms of ML tasks, text generation dominates within SE PTMs. Notably, the number of SE PTMs has increased markedly since 2023 Q2. Our classification provides a solid foundation for future automated SE scenarios, such as the sampling and selection of suitable PTMs.
Authors: Junhao Yu, Yan Zhuang, YuXuan Sun, Weibo Gao, Qi Liu, Mingyue Cheng, Zhenya Huang, Enhong Chen
Abstract: Accurately assessing internal human states is key to understanding preferences, offering personalized services, and identifying challenges in real-world applications. Originating from psychometrics, adaptive testing has become the mainstream method for human measurement and has now been widely applied in education, healthcare, sports, and sociology. It customizes assessments by selecting the fewest test questions . However, current adaptive testing methods face several challenges. The mechanized nature of most algorithms leads to guessing behavior and difficulties with open-ended questions. Additionally, subjective assessments suffer from noisy response data and coarse-grained test outputs, further limiting their effectiveness. To move closer to an ideal adaptive testing process, we propose TestAgent, a large language model (LLM)-powered agent designed to enhance adaptive testing through interactive engagement. This is the first application of LLMs in adaptive testing. TestAgent supports personalized question selection, captures test-takers' responses and anomalies, and provides precise outcomes through dynamic, conversational interactions. Experiments on psychological, educational, and lifestyle assessments show our approach achieves more accurate results with 20% fewer questions than state-of-the-art baselines, and testers preferred it in speed, smoothness, and other dimensions.
Authors: Laurentiu Andrei Marchis, Po-Ling Loh
Abstract: We study the advantages of accelerated gradient methods, specifically based on the Frank-Wolfe method and projected gradient descent, for privacy and heavy-tailed robustness. Our approaches are as follows: For the Frank-Wolfe method, our technique is based on a tailored learning rate and a uniform lower bound on the gradient of the $\ell_2$-norm over the constraint set. For accelerating projected gradient descent, we use the popular variant based on Nesterov's momentum, and we optimize our objective over $\mathbb{R}^p$. These accelerations reduce iteration complexity, translating into stronger statistical guarantees for empirical and population risk minimization. Our analysis covers three settings: non-random data, random model-free data, and parametric models (linear regression and generalized linear models). Methodologically, we approach both privacy and robustness based on noisy gradients. We ensure differential privacy via the Gaussian mechanism and advanced composition, and we achieve heavy-tailed robustness using a geometric median-of-means estimator, which also sharpens the dependency on the dimension of the covariates. Finally, we compare our rates to existing bounds and identify scenarios where our methods attain optimal convergence.
Authors: Maria Walch
Abstract: We explore the role of torsion in hybrid deep learning models that incorporate topological data analysis, focusing on autoencoders. While most TDA tools use field coefficients, this conceals torsional features present in integer homology. We show that torsion can be lost during encoding, altered in the latent space, and in many cases, not reconstructed by standard decoders. Using both synthetic and high-dimensional data, we evaluate torsion sensitivity to perturbations and assess its recoverability across several autoencoder architectures. Our findings reveal key limitations of field-based approaches and underline the need for architectures or loss terms that preserve torsional information for robust data representation.
Authors: Sinem Erisken (Independent Researcher), Timothy Gothard (Independent Researcher), Martin Leitgab (Independent Researcher), Ram Potham (Independent Researcher)
Abstract: Traditional AI safety evaluations on isolated LLMs are insufficient as multi-agent AI ensembles become prevalent, introducing novel emergent risks. This paper introduces the Multi-Agent Emergent Behavior Evaluation (MAEBE) framework to systematically assess such risks. Using MAEBE with the Greatest Good Benchmark (and a novel double-inversion question technique), we demonstrate that: (1) LLM moral preferences, particularly for Instrumental Harm, are surprisingly brittle and shift significantly with question framing, both in single agents and ensembles. (2) The moral reasoning of LLM ensembles is not directly predictable from isolated agent behavior due to emergent group dynamics. (3) Specifically, ensembles exhibit phenomena like peer pressure influencing convergence, even when guided by a supervisor, highlighting distinct safety and alignment challenges. Our findings underscore the necessity of evaluating AI systems in their interactive, multi-agent contexts.
Authors: Ram Potham (Independent Researcher), Max Harms (Machine Intelligence Research Institute)
Abstract: Foundation models (FMs) face a critical safety challenge: as capabilities scale, instrumental convergence drives default trajectories toward loss of human control, potentially culminating in existential catastrophe. Current alignment approaches struggle with value specification complexity and fail to address emergent power-seeking behaviors. We propose "Corrigibility as a Singular Target" (CAST)-designing FMs whose overriding objective is empowering designated human principals to guide, correct, and control them. This paradigm shift from static value-loading to dynamic human empowerment transforms instrumental drives: self-preservation serves only to maintain the principal's control; goal modification becomes facilitating principal guidance. We present a comprehensive empirical research agenda spanning training methodologies (RLAIF, SFT, synthetic data generation), scalability testing across model sizes, and demonstrations of controlled instructability. Our vision: FMs that become increasingly responsive to human guidance as capabilities grow, offering a path to beneficial AI that remains as tool-like as possible, rather than supplanting human judgment. This addresses the core alignment problem at its source, preventing the default trajectory toward misaligned instrumental convergence.
Authors: Pengtao Chen, Xianfang Zeng, Maosen Zhao, Peng Ye, Mingzhu Shen, Wei Cheng, Gang Yu, Tao Chen
Abstract: While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency. Through detailed analysis of attention maps in Video Diffusion Transformer (vDiT), we identify three recurring sparsity patterns: diagonal, multi-diagonal, and vertical-stripe structures. And even 3-6\% attention heads can be skipped. Crucially, these patterns exhibit strong layer-depth and head-position correlations but show limited dependence on the input content. Leveraging these findings, we propose Sparse-vDiT, a sparsity acceleration framework for vDiT comprising: 1) Pattern-optimized sparse kernels that replace dense attention with computationally efficient implementations for each identified sparsity pattern. 2) An offline sparse diffusion search algorithm that selects the optimal sparse computation strategy per layer and head via hardware-aware cost modeling. After determining the optimal configuration, we fuse heads within the same layer that share the same attention strategy, enhancing inference efficiency. Integrated into state-of-the-art vDiT models (CogVideoX1.5, HunyuanVideo, and Wan2.1), Sparse-vDiT achieves 2.09$\times$, 2.38$\times$, and 1.67$\times$ theoretical FLOP reduction, and actual inference speedups of 1.76$\times$, 1.85$\times$, and 1.58$\times$, respectively, while maintaining high visual fidelity, with PSNR values reaching 24.13, 27.09, and 22.59. Our work demonstrates that latent structural sparsity in vDiTs can be systematically exploited for long video synthesis.
Authors: Yina Hou, Shourav B. Rabbani, Liang Hong, Norou Diawara, Manar D. Samad
Abstract: The importance of clinical variables in the prognosis of the disease is explained using statistical correlation or machine learning (ML). However, the predictive importance of these variables may not represent their causal relationships with diseases. This paper uses clinical variables from a heart failure (HF) patient cohort to investigate the causal explainability of important variables obtained in statistical and ML contexts. Due to inherent regression modeling, popular causal discovery methods strictly assume that the cause and effect variables are numerical and continuous. This paper proposes a new computational framework to enable causal structure discovery (CSD) and score the causal strength of mixed-type (categorical, numerical, binary) clinical variables for binary disease outcomes. In HF classification, we investigate the association between the importance rank order of three feature types: correlated features, features important for ML predictions, and causal features. Our results demonstrate that CSD modeling for nonlinear causal relationships is more meaningful than its linear counterparts. Feature importance obtained from nonlinear classifiers (e.g., gradient-boosting trees) strongly correlates with the causal strength of variables without differentiating cause and effect variables. Correlated variables can be causal for HF, but they are rarely identified as effect variables. These results can be used to add the causal explanation of variables important for ML-based prediction modeling.
Authors: Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnovi\'c, Se-Young Yun
Abstract: We present `GL-LowPopArt`, a novel Catoni-style estimator for generalized low-rank trace regression. Building on `LowPopArt` (Jang et al., 2024), it employs a two-stage approach: nuclear norm regularization followed by matrix Catoni estimation. We establish state-of-the-art estimation error bounds, surpassing existing guarantees (Fan et al., 2019; Kang et al., 2022), and reveal a novel experimental design objective, $\mathrm{GL}(\pi)$. The key technical challenge is controlling bias from the nonlinear inverse link function, which we address by our two-stage approach. We prove a *local* minimax lower bound, showing that our `GL-LowPopArt` enjoys instance-wise optimality up to the condition number of the ground-truth Hessian. Applications include generalized linear matrix completion, where `GL-LowPopArt` achieves a state-of-the-art Frobenius error guarantee, and **bilinear dueling bandits**, a novel setting inspired by general preference learning (Zhang et al., 2024). Our analysis of a `GL-LowPopArt`-based explore-then-commit algorithm reveals a new, potentially interesting problem-dependent quantity, along with improved Borda regret bound than vectorization (Wu et al., 2024).
Authors: Lloyd Pellatt, Fotios Drakopoulos, Shievanie Sabesan, Nicholas A. Lesica
Abstract: The mapping from sound to neural activity that underlies hearing is highly non-linear. The first few stages of this mapping in the cochlea have been modelled successfully, with biophysical models built by hand and, more recently, with DNN models trained on datasets simulated by biophysical models. Modelling the auditory brain has been a challenge because central auditory processing is too complex for models to be built by hand, and datasets for training DNN models directly have not been available. Recent work has taken advantage of large-scale high resolution neural recordings from the auditory midbrain to build a DNN model of normal hearing with great success. But this model assumes that auditory processing is the same in all brains, and therefore it cannot capture the widely varying effects of hearing loss. We propose a novel variational-conditional model to learn to encode the space of hearing loss directly from recordings of neural activity in the auditory midbrain of healthy and noise exposed animals. With hearing loss parametrised by only 6 free parameters per animal, our model accurately predicts 62\% of the explainable variance in neural responses from normal hearing animals and 68% for hearing impaired animals, within a few percentage points of state of the art animal specific models. We demonstrate that the model can be used to simulate realistic activity from out of sample animals by fitting only the learned conditioning parameters with Bayesian optimisation, achieving crossentropy loss within 2% of the optimum in 15-30 iterations. Including more animals in the training data slightly improved the performance on unseen animals. This model will enable future development of parametrised hearing loss compensation models trained to directly restore normal neural coding in hearing impaired brains, which can be quickly fitted for a new user by human in the loop optimisation.
Authors: Christian Schlarmann, Francesco Croce, Nicolas Flammarion, Matthias Hein
Abstract: Contrastive language-image pre-training aligns the features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach achieves impressive performance in several zero-shot tasks, it cannot natively handle multimodal inputs, i.e., encoding image and text into a single feature vector. As a remedy, it is common practice to use additional modules to merge the features extracted by the unimodal encoders. In this work, we present FuseLIP, an alternative architecture for multimodal embedding. Leveraging recent progress in discrete image tokenizers, we propose to use a single transformer model which operates on an extended vocabulary of text and image tokens. This early fusion approach allows the different modalities to interact at each depth of encoding and obtain richer representations compared to common late fusion. We collect new datasets for multimodal pre-training and evaluation, designing challenging tasks for multimodal encoder models. We show that FuseLIP outperforms other approaches in multimodal embedding tasks such as VQA and text-guided image transformation retrieval, while being comparable to baselines on unimodal tasks.
Authors: Xiuyu Cao, Joseph O. Sexton, Panshi Wang, Dimitrios Gounaridis, Neil H. Carter, Kai Zhu
Abstract: Monitoring aboveground biomass (AGB) and its density (AGBD) at high resolution is essential for carbon accounting and ecosystem management. While NASA's spaceborne Global Ecosystem Dynamics Investigation (GEDI) LiDAR mission provides globally distributed reference measurements for AGBD estimation, the majority of commercial remote sensing products based on GEDI remain without rigorous or independent validation. Here, we present an independent regional validation of an AGBD dataset offered by terraPulse, Inc., based on independent reference data from the US Forest Service Forest Inventory and Analysis (FIA) program. Aggregated to 64,000-hectare hexagons and US counties across the US states of Utah, Nevada, and Washington, we found very strong agreement between terraPulse and FIA estimates. At the hexagon scale, we report R2 = 0.88, RMSE = 26.68 Mg/ha, and a correlation coefficient (r) of 0.94. At the county scale, agreement improves to R2 = 0.90, RMSE =32.62 Mg/ha, slope = 1.07, and r = 0.95. Spatial and statistical analyses indicated that terraPulse AGBD values tended to exceed FIA estimates in non-forest areas, likely due to FIA's limited sampling of non-forest vegetation. The terraPulse AGBD estimates also exhibited lower values in high-biomass forests, likely due to saturation effects in its optical remote-sensing covariates. This study advances operational carbon monitoring by delivering a scalable framework for comprehensive AGBD validation using independent FIA data, as well as a benchmark validation of a new commercial dataset for global biomass monitoring.
Authors: Zidong Wang, Lei Bai, Xiangyu Yue, Wanli Ouyang, Yiyuan Zhang
Abstract: We introduce native-resolution image synthesis, a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. This approach overcomes the limitations of conventional fixed-resolution, square-image methods by natively handling variable-length visual tokens, a core challenge for traditional techniques. To this end, we introduce the Native-resolution diffusion Transformer (NiT), an architecture designed to explicitly model varying resolutions and aspect ratios within its denoising process. Free from the constraints of fixed formats, NiT learns intrinsic visual distributions from images spanning a broad range of resolutions and aspect ratios. Notably, a single NiT model simultaneously achieves the state-of-the-art performance on both ImageNet-256x256 and 512x512 benchmarks. Surprisingly, akin to the robust zero-shot capabilities seen in advanced large language models, NiT, trained solely on ImageNet, demonstrates excellent zero-shot generalization performance. It successfully generates high-fidelity images at previously unseen high resolutions (e.g., 1536 x 1536) and diverse aspect ratios (e.g., 16:9, 3:1, 4:3), as shown in Figure 1. These findings indicate the significant potential of native-resolution modeling as a bridge between visual generative modeling and advanced LLM methodologies.
Authors: Pietro Lesci, Clara Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel
Abstract: Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the probability assigned to the underlying character-string; in practice, it does. We define this mismatch as tokenisation bias. In this work, we quantify one particular type of tokenisation bias: the effect of including or not a subword (e.g., $\langle hello \rangle$) in a tokeniser's vocabulary on the probability a trained model assigns to the corresponding characters (i.e., \textit{``hello''}). Estimating this effect is challenging because each model is trained with only one tokeniser. We address this by framing tokenisation bias as a causal effect and estimating it using the regression discontinuity design. Specifically, we exploit the fact that tokenisation algorithms rank subwords and add the first $K$ to a tokeniser's vocabulary, where $K$ is an arbitrary cutoff point. As such, we can estimate a causal effect by comparing similar subwords around this cutoff. Experimentally, we find that tokenisation consistently affects models' outputs across scales, vocabularies, and tokenisers. Notably, a subword's presence in a small model's vocabulary may increase its characters' probability by up to 17 times, highlighting tokenisation as a key design choice in language modelling.
Authors: Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Ronald Clark, Ming-Hsuan Yang
Abstract: Although diffusion-based models can generate high-quality and high-resolution video sequences from textual or image inputs, they lack explicit integration of geometric cues when controlling scene lighting and visual appearance across frames. To address this limitation, we propose IllumiCraft, an end-to-end diffusion framework accepting three complementary inputs: (1) high-dynamic-range (HDR) video maps for detailed lighting control; (2) synthetically relit frames with randomized illumination changes (optionally paired with a static background reference image) to provide appearance cues; and (3) 3D point tracks that capture precise 3D geometry information. By integrating the lighting, appearance, and geometry cues within a unified diffusion architecture, IllumiCraft generates temporally coherent videos aligned with user-defined prompts. It supports background-conditioned and text-conditioned video relighting and provides better fidelity than existing controllable video generation methods. Project Page: https://yuanze-lin.me/IllumiCraft_page
Authors: Xinshun Liu, He Xin, Mao Hui, Liu Jing, Lai Weizhong, Ye Qingwen
Abstract: Transfer learning research attempts to make model induction transferable across different domains. This method assumes that specific information regarding to which domain each instance belongs is known. This paper helps to extend the capability of transfer learning for linear regression problems to situations where the domain information is uncertain or unknown; in fact, the framework can be extended to classification problems. For normal datasets, we assume that some latent domain information is available for transfer learning. The instances in each domain can be inferred by different parameters. We obtain this domain information from the distribution of the regression coefficients corresponding to the explanatory variable $x$ as well as the response variable $y$ based on a Dirichlet process, which is more reasonable. As a result, we transfer not only variable $x$ as usual but also variable $y$, which is challenging since the testing data have no response value. Previous work mainly overcomes the problem via pseudo-labelling based on transductive learning, which introduces serious bias. We provide a novel framework for analysing the problem and considering this general situation: the joint distribution of variable $x$ and variable $y$. Furthermore, our method controls the bias well compared with previous work. We perform linear regression on the new feature space that consists of different latent domains and the target domain, which is from the testing data. The experimental results show that the proposed model performs well on real datasets.
Authors: Han Wu, Jie Yin, Bala Rajaratnam, Jianyuan Guo
Abstract: Knowledge graphs (KGs) are powerful in terms of their inference abilities, but are also notorious for their incompleteness and long-tail distribution of relations. To address these challenges and expand the coverage of KGs, few-shot KG completion aims to make predictions for triplets involving novel relations when only a few training triplets are provided as reference. Previous methods have focused on designing local neighbor aggregators to learn entity-level information and/or imposing a potentially invalid sequential dependency assumption at the triplet level to learn meta relation information. However, pairwise triplet-level interactions and context-level relational information have been largely overlooked for learning meta representations of few-shot relations. In this paper, we propose a hierarchical relational learning method (HiRe) for few-shot KG completion. By jointly capturing three levels of relational information (entity-level, triplet-level and context-level), HiRe can effectively learn and refine meta representations of few-shot relations, and thus generalize well to new unseen relations. Extensive experiments on benchmark datasets validate the superiority of HiRe over state-of-the-art methods. The code can be found in https://github.com/alexhw15/HiRe.git.
Authors: Jungtaek Kim
Abstract: Bayesian optimization has attracted huge attention from diverse research areas in science and engineering, since it is capable of efficiently finding a global optimum of an expensive-to-evaluate black-box function. In general, a probabilistic regression model is widely used as a surrogate function to model an explicit distribution over function evaluations given an input to estimate and a training dataset. Beyond the probabilistic regression-based methods, density ratio estimation-based Bayesian optimization has been suggested in order to estimate a density ratio of the groups relatively close and relatively far to a global optimum. Developing this line of research further, supervised classifiers are employed to estimate a class probability for the two groups instead of a density ratio. However, the supervised classifiers used in this strategy are prone to be overconfident for known knowledge on global solution candidates. Supposing that we have access to unlabeled points, e.g., predefined fixed-size pools, we propose density ratio estimation-based Bayesian optimization with semi-supervised learning to solve this challenge. Finally, we show the empirical results of our methods and several baseline methods in two distinct scenarios with unlabeled point sampling and a fixed-size pool, and analyze the validity of our methods in diverse experiments.
Authors: Yehya Farhat, Hamza ElMokhtar Shili, Fangshuo Liao, Chen Dun, Mirian Hipolito Garcia, Guoqing Zheng, Ahmed Hassan Awadallah, Robert Sim, Dimitrios Dimitriadis, Anastasios Kyrillidis
Abstract: Mixture-of-Experts (MoEs) achieve scalability by dynamically activating subsets of their components. Yet, understanding how expertise emerges through joint training of gating mechanisms and experts remains incomplete, especially in scenarios without clear task partitions. Motivated by inference costs and data heterogeneity, we study how joint training of gating functions and experts can dynamically allocate domain-specific expertise across multiple underlying data distributions. As an outcome of our framework, we develop an instance tailored specifically to decentralized training scenarios, introducing \textit{Dynamically Decentralized Orchestration of MoEs} or \texttt{DDOME}. \texttt{DDOME} leverages heterogeneity emerging from distributional shifts across decentralized data sources to specialize experts dynamically. By integrating a pretrained common expert to inform a gating function, \texttt{DDOME} achieves personalized expert subset selection on-the-fly, facilitating just-in-time personalization. We empirically validate \texttt{DDOME} within a Federated Learning (FL) context: \texttt{DDOME} attains from 4\% up to an 24\% accuracy improvement over state-of-the-art FL baselines in image and text classification tasks, while maintaining competitive zero-shot generalization capabilities. Furthermore, we provide theoretical insights confirming that the joint gating-experts training is critical for achieving meaningful expert specialization.
Authors: Shijun Zhang, Hongkai Zhao, Yimin Zhong, Haomin Zhou
Abstract: In this work, we present a comprehensive study combining mathematical and computational analysis to explain why a two-layer neural network struggles to handle high frequencies in both approximation and learning, especially when machine precision, numerical noise, and computational cost are significant factors in practice. Specifically, we investigate the following fundamental computational issues: (1) the minimal numerical error achievable under finite precision, (2) the computational cost required to attain a given accuracy, and (3) the stability of the method with respect to perturbations. The core of our analysis lies in the conditioning of the representation and its learning dynamics. Explicit answers to these questions are provided, along with supporting numerical evidence.
Authors: Mete Kemertas, Allan D. Jepson, Amir-massoud Farahmand
Abstract: We propose Mirror Descent Optimal Transport (MDOT), a novel method for solving discrete optimal transport (OT) problems with high precision, by unifying temperature annealing in entropic-regularized OT (EOT) with mirror descent techniques. In this framework, temperature annealing produces a sequence of EOT dual problems, whose solution gradually gets closer to the solution of the original OT problem. We solve each problem efficiently using a GPU-parallel nonlinear conjugate gradients algorithm (PNCG) that outperforms traditional Sinkhorn iterations under weak regularization. Moreover, our investigation also reveals that the theoretical convergence rate of Sinkhorn iterations can exceed existing non-asymptotic bounds when its stopping criterion is tuned in a manner analogous to MDOT. Our comprehensive ablation studies of MDOT-PNCG affirm its robustness across a wide range of algorithmic parameters. Benchmarking on 24 problem sets of size $n=4096$ in a GPU environment demonstrate that our method attains high-precision, feasible solutions significantly faster than a representative set of existing OT solvers, including accelerated gradient methods and advanced Sinkhorn variants, in both wall-clock time and number of operations. Empirical convergence rates range between $O(n^2 \varepsilon^{-1/4})$ and $O(n^2 \varepsilon^{-1})$, where $\varepsilon$ is the optimality gap. For problem sizes up to $n=16384$, the empirical runtime scales as $O(n^2)$ for moderate precision and as $O(n^{5/2})$ at worst for high precision. These findings establish MDOT-PNCG as a compelling alternative to current OT solvers, particularly in challenging weak-regularization regimes.
Authors: Zhihao Shi, Jie Wang, Fanghua Lu, Hanzhu Chen, Defu Lian, Zheng Wang, Jieping Ye, Feng Wu
Abstract: Node representation learning on attributed graphs -- whose nodes are associated with rich attributes (e.g., texts and protein sequences) -- plays a crucial role in many important downstream tasks. To encode the attributes and graph structures simultaneously, recent studies integrate pre-trained models with graph neural networks (GNNs), where pre-trained models serve as node encoders (NEs) to encode the attributes. As jointly training large NEs and GNNs on large-scale graphs suffers from severe scalability issues, many methods propose to train NEs and GNNs separately. Consequently, they do not take feature convolutions in GNNs into consideration in the training phase of NEs, leading to a significant learning bias relative to the joint training. To address this challenge, we propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias. More importantly, we show that LD converges to the optimal objective function values by the joint training under mild assumptions. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.
Authors: Zhiyuan Zhao, Haoxin Liu, Alexander Rodriguez, B. Aditya Prakash
Abstract: Time-series forecasting is a critical challenge in various domains and has witnessed substantial progress in recent years. Many real-life scenarios, such as public health, economics, and social applications, involve feedback loops where predictions can influence the predicted outcome, subsequently altering the target variable's distribution. This phenomenon, known as performativity, introduces the potential for 'self-negating' or 'self-fulfilling' predictions. Despite extensive studies in classification problems across domains, performativity remains largely unexplored in the context of time-series forecasting from a machine-learning perspective. In this paper, we formalize performative time-series forecasting (PeTS), addressing the challenge of accurate predictions when performativity-induced distribution shifts are possible. We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts and subsequently predicts targets accordingly. We provide theoretical insights suggesting that FPS can potentially lead to reduced generalization error. We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks. The results demonstrate that FPS consistently outperforms conventional time-series forecasting methods, highlighting its efficacy in handling performativity-induced challenges.
Authors: L. Jeff Hong, Yanxi Hou, Qingkai Zhang, Xiaowei Zhang
Abstract: Stochastic simulation models effectively capture complex system dynamics but are often too slow for real-time decision-making. Traditional metamodeling techniques learn relationships between simulator inputs and a single output summary statistic, such as the mean or median. These techniques enable real-time predictions without additional simulations. However, they require prior selection of one appropriate output summary statistic, limiting their flexibility in practical applications. We propose a new concept: generative metamodeling. It aims to construct a "fast simulator of the simulator," generating random outputs significantly faster than the original simulator while preserving approximately equal conditional distributions. Generative metamodels enable rapid generation of numerous random outputs upon input specification, facilitating immediate computation of any summary statistic for real-time decision-making. We introduce a new algorithm, quantile-regression-based generative metamodeling (QRGMM), and establish its distributional convergence and convergence rate. Extensive numerical experiments demonstrate QRGMM's efficacy compared to other state-of-the-art generative algorithms in practical real-time decision-making scenarios.
Authors: Daniel Jarne Ornia, Giannis Delimpaltadakis, Jens Kober, Javier Alonso-Mora
Abstract: In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e.g. policy entropy regularisation) to randomise their actions in favor of exploration. This often makes it challenging for other agents and humans to predict an agent's behavior, triggering unsafe scenarios (e.g. in human-robot interaction). We propose a novel method to induce predictable behavior in RL agents, termed Predictability-Aware RL (PARL), employing the agent's trajectory entropy rate to quantify predictability. Our method maximizes a linear combination of a standard discounted reward and the negative entropy rate, thus trading off optimality with predictability. We show how the entropy rate can be formally cast as an average reward, how entropy-rate value functions can be estimated from a learned model and incorporate this in policy-gradient algorithms, and demonstrate how this approach produces predictable (near-optimal) policies in tasks inspired by human-robot use-cases.
Authors: Vinod Raman, Unique Subedi, Ambuj Tewari
Abstract: We study the problem of learning to predict the next state of a dynamical system when the underlying evolution function is unknown. Unlike previous work, we place no parametric assumptions on the dynamical system, and study the problem from a learning theory perspective. We define new combinatorial measures and dimensions and show that they quantify the optimal mistake and regret bounds in the realizable and agnostic settings respectively. By doing so, we find that in the realizable setting, the total number of mistakes can grow according to \emph{any} increasing function of the time horizon $T$. In contrast, we show that in the agnostic setting under the commonly studied notion of Markovian regret, the only possible rates are $\Theta(T)$ and $\tilde{\Theta}(\sqrt{T})$.
Authors: Mart van Baalen, Andrey Kuzmin, Ivan Koryakovskiy, Markus Nagel, Peter Couperus, Cedric Bastoul, Eric Mahurin, Tijmen Blankevoort, Paul Whatmough
Abstract: In this work we show that the size versus accuracy trade-off of neural network quantization can be significantly improved by increasing the quantization dimensionality. We propose the GPTVQ method, a new fast method for post-training vector quantization (VQ) that scales well to Large Language Models (LLMs). Our method interleaves quantization of one or more columns with updates to the remaining unquantized weights, using information from the Hessian of the per-layer output reconstruction MSE. Quantization codebooks are initialized using an efficient data-aware version of the EM algorithm. The codebooks are then updated, and further compressed by using integer quantization and SVD-based compression. GPTVQ establishes a new state-of-the art in the size vs accuracy trade-offs on a wide range of LLMs such as Llama-v2 and Mistral. Furthermore, our method is efficient: on a single H100 it takes between 3 and 11 hours to process a Llamav2-70B model, depending on quantization setting. Lastly, with on-device timings for VQ decompression on a mobile CPU we show that VQ leads to improved latency compared to using a 4-bit integer format.
Authors: Michel Pohl, Mitsuru Uesaka, Hiroyuki Takahashi, Kazuyuki Demachi, Ritu Bhusal Chhatkuli
Abstract: In lung radiotherapy, infrared cameras can track reflective objects on the chest to estimate tumor motion due to breathing, but treatment system latencies hinder radiation beam precision. Real-time recurrent learning (RTRL) is a potential solution that can learn patterns within non-stationary respiratory data but has high complexity. This study assesses the capabilities of resource-efficient online RNN algorithms, namely unbiased online recurrent optimization (UORO), sparse-1 step approximation (SnAp-1), and decoupled neural interfaces (DNI) to forecast respiratory motion during radiotherapy treatment accurately. We use time series containing the 3D positions of external markers on the chest of healthy subjects. We propose efficient implementations for SnAp-1 and DNI that compress the influence and immediate Jacobian matrices and accurately update the linear coefficients used in credit assignment estimation, respectively. Data was originally sampled at 10Hz; we resampled it at 3.33Hz and 30Hz to analyze the effect of the sampling rate on performance. We use UORO, SnAp-1, and DNI to forecast each marker's 3D position with horizons h<=2.1s (the time interval in advance for which the prediction is made) and compare them with RTRL, least mean squares, kernel support vector regression, and linear regression. RNNs trained online achieved similar or better accuracy than most previous works using larger training databases and deep learning, even though we used only the first minute of each sequence to predict motion within that exact sequence. SnAp-1 had the lowest normalized root mean square errors (nRMSEs) averaged over the horizon values considered, equal to 0.335 and 0.157, at 3.33Hz and 10.0Hz, respectively. Similarly, UORO had the lowest nRMSE at 30Hz, equal to 0.086. DNI's inference time (6.8ms per time step at 30Hz, Intel Core i7-13700 CPU) was the lowest among the RNN methods.
Authors: Fei Zhu, Shijie Ma, Zhen Cheng, Xu-Yao Zhang, Zhaoxiang Zhang, Dacheng Tao, Cheng-Lin Liu
Abstract: Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the environment is stationary, and the model is fixed once deployed. In many real-world applications, this fundamental and rather naive assumption may not hold because an open environment is complex, dynamic, and full of unknowns. In such cases, rejecting unknowns, discovering novelties, and then continually learning them, could enable models to be safe and evolve continually as biological systems do. This article presents a holistic view of open-world machine learning by investigating unknown rejection, novelty discovery, and continual learning in a unified paradigm. The challenges, principles, and limitations of current methodologies are discussed in detail. Furthermore, widely used benchmarks, metrics, and performances are summarized. Finally, we discuss several potential directions for further progress in the field. By providing a comprehensive introduction to the emerging open-world machine learning paradigm, this article aims to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.
Authors: Keziah Naggita, Matthew R. Walter, Avrim Blum
Abstract: Recourse generators provide actionable insights, often through feature-based counterfactual explanations (CFEs), to help negatively classified individuals understand how to adjust their input features to achieve a positive classification. These feature-based CFEs, which we refer to as \emph{low-level} CFEs, are overly specific (e.g., coding experience: \(4 \to 5+\) years) and often recommended in a feature space that doesn't straightforwardly align with real-world actions. To bridge this gap, we introduce three novel recourse types grounded in real-world actions: high-level continuous (\emph{hl-continuous}), high-level discrete (\emph{hl-discrete}), and high-level ID (\emph{hl-id}) CFEs. We formulate single-agent CFE generation methods, where we model the hl-discrete CFE as a solution to a weighted set cover problem and the hl-continuous CFE as a solution to an integer linear program. Since these methods require costly optimization per agent, we propose data-driven CFE generation approaches that, given instances of agents and their optimal CFEs, learn a CFE generator that quickly provides optimal CFEs for new agents. This approach, also viewed as one of learning an optimal policy in a family of large but deterministic MDPs, considers several problem formulations, including formulations in which the actions and their effects are unknown, and therefore addresses informational and computational challenges. We conduct extensive empirical evaluations using healthcare datasets (BRFSS, Foods, and NHANES) and fully-synthetic data. For negatively classified agents identified by linear or threshold-based classifiers, we compare the high-level CFE to low-level CFEs and assess the effectiveness of our network-based, data-driven approaches. Results show that the data-driven CFE generators are accurate, and resource-efficient, and high-level CFEs offer key advantages over low-level CFEs.
Authors: Emile Pierret, Bruno Galerne
Abstract: Diffusion or score-based models recently showed high performance in image generation. They rely on a forward and a backward stochastic differential equations (SDE). The sampling of a data distribution is achieved by numerically solving the backward SDE or its associated flow ODE. Studying the convergence of these models necessitates to control four different types of error: the initialization error, the truncation error, the discretization error and the score approximation. In this paper, we theoretically study the behavior of diffusion models and their numerical implementation when the data distribution is Gaussian. Our first contribution is to derive the analytical solutions of the backward SDE and the probability flow ODE and to prove that these solutions and their discretizations are all Gaussian processes. Our second contribution is to compute the exact Wasserstein errors between the target and the numerically sampled distributions for any numerical scheme. This allows us to monitor convergence directly in the data space, while experimental works limit their empirical analysis to Inception features. An implementation of our code is available online.
Authors: Zhongnian Li, Jinghao Xu, Peng Ying, Meng Wei, Xinzheng Xu
Abstract: Pre-trained Vision-Language Models (VLMs) exhibit strong zero-shot classification abilities, demonstrating great potential for generating weakly supervised labels. Unfortunately, existing weakly supervised learning methods are short of ability in generating accurate labels via VLMs. In this paper, we propose a novel weakly supervised labeling setting, namely True-False Labels (TFLs) which can achieve high accuracy when generated by VLMs. The TFL indicates whether an instance belongs to the label, which is randomly and uniformly sampled from the candidate label set. Specifically, we theoretically derive a risk-consistent estimator to explore and utilize the conditional probability distribution information of TFLs. Besides, we propose a convolutional-based Multi-modal Prompt Retrieving (MRP) method to bridge the gap between the knowledge of VLMs and target learning tasks. Experimental results demonstrate the effectiveness of the proposed TFL setting and MRP learning method. The code to reproduce the experiments is at https://github.com/Tranquilxu/TMP.
Authors: Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, Haibo Yang
Abstract: Federated Learning (FL) offers a promising framework for collaborative and privacy-preserving machine learning across distributed data sources. However, the substantial communication costs associated with FL significantly challenge its efficiency. Specifically, in each communication round, the communication costs scale linearly with the model's dimension, which presents a formidable obstacle, especially in large model scenarios. Despite various communication-efficient strategies, the intrinsic dimension-dependent communication cost remains a major bottleneck for current FL implementations. This paper proposes a novel dimension-free communication algorithm - DeComFL, which leverages the zeroth-order optimization techniques and reduces the communication cost from $\mathscr{O}(d)$ to $\mathscr{O}(1)$ by transmitting only a constant number of scalar values between clients and the server in each round, regardless of the dimension $d$ of the model parameters. Theoretically, in non-convex functions, we prove that our algorithm achieves state-of-the-art rates, which show a linear speedup of the number of clients and local steps under standard assumptions. With additional low effective rank assumption, we can further show the convergence rate is independent of the model dimension $d$ as well. Empirical evaluations, encompassing both classic deep learning training and large language model fine-tuning, demonstrate significant reductions in communication overhead. Notably, DeComFL achieves this by transmitting only around 1MB of data in total between the server and a client to fine-tune a model with billions of parameters. Our code is available at https://github.com/ZidongLiu/DeComFL.
Authors: Xuesong Wang, He Zhao, Edwin V. Bonilla
Abstract: Neural Processes (NPs) are deep probabilistic models that represent stochastic processes by conditioning their prior distributions on a set of context points. Despite their advantages in uncertainty estimation for complex distributions, NPs enforce parameterization coupling between the conditional prior model and the posterior model. We show that this coupling amounts to prior misspecification and revisit the NP objective to address this issue. More specifically, we propose R\'enyi Neural Processes (RNP), a method that replaces the standard KL divergence with the R\'enyi divergence, dampening the effects of the misspecified prior during posterior updates. We validate our approach across multiple benchmarks including regression and image inpainting tasks, and show significant performance improvements of RNPs in real-world problems. Our extensive experiments show consistently better log-likelihoods over state-of-the-art NP models.
Authors: Nicholas M. Boffi, Michael S. Albergo, Eric Vanden-Eijnden
Abstract: Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inference. The advent of consistency models has enabled efficient one-step or few-step generation, yet despite their practical success, a systematic understanding of their design has been hindered by the lack of a comprehensive theoretical framework. Here we introduce Flow Map Matching (FMM), a principled framework for learning the two-time flow map of an underlying dynamical generative model, thereby providing this missing mathematical foundation. Leveraging stochastic interpolants, we propose training objectives both for distillation from a pre-trained velocity field and for direct training of a flow map over an interpolant or a forward diffusion process. Theoretically, we show that FMM unifies and extends a broad class of existing approaches for fast sampling, including consistency models, consistency trajectory models, and progressive distillation. Experiments on CIFAR-10 and ImageNet-32 highlight that our approach can achieve sample quality comparable to flow matching while reducing generation time by a factor of 10-20.
Authors: Shijun Zhang, Hongkai Zhao, Yimin Zhong, Haomin Zhou
Abstract: In this work, we propose a balanced multi-component and multi-layer neural network (MMNN) structure to accurately and efficiently approximate functions with complex features, in terms of both degrees of freedom and computational cost. The main idea is inspired by a multi-component approach, in which each component can be effectively approximated by a single-layer network, combined with a multi-layer decomposition strategy to capture the complexity of the target function. Although MMNNs can be viewed as a simple modification of fully connected neural networks (FCNNs) or multi-layer perceptrons (MLPs) by introducing balanced multi-component structures, they achieve a significant reduction in training parameters, a much more efficient training process, and improved accuracy compared to FCNNs or MLPs. Extensive numerical experiments demonstrate the effectiveness of MMNNs in approximating highly oscillatory functions and their ability to automatically adapt to localized features.
Authors: Mario Villaiz\'an-Vallelado, Matteo Salvatori, Carlos Segura, Ioannis Arapakis
Abstract: Data imputation and data generation have important applications for many domains, like healthcare and finance, where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful generative models capable of capturing complex data distributions across various data modalities such as image, audio, and time series data. Recently, they have been also adapted to generate tabular data. In this paper, we propose a diffusion model for tabular data that introduces three key enhancements: (1) a conditioning attention mechanism, (2) an encoder-decoder transformer as the denoising network, and (3) dynamic masking. The conditioning attention mechanism is designed to improve the model's ability to capture the relationship between the condition and synthetic data. The transformer layers help model interactions within the condition (encoder) or synthetic data (decoder), while dynamic masking enables our model to efficiently handle both missing data imputation and synthetic data generation tasks within a unified framework. We conduct a comprehensive evaluation by comparing the performance of diffusion models with transformer conditioning against state-of-the-art techniques, such as Variational Autoencoders, Generative Adversarial Networks and Diffusion Models, on benchmark datasets. Our evaluation focuses on the assessment of the generated samples with respect to three important criteria, namely: (1) Machine Learning efficiency, (2) statistical similarity, and (3) privacy risk mitigation. For the task of data imputation, we consider the efficiency of the generated samples across different levels of missing features.
Authors: Seyedmorteza Sadat, Manuel Kansy, Otmar Hilliges, Romann M. Weber
Abstract: Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion model or modifying the training procedure by periodically inserting a null condition. There is also no clear extension of CFG to unconditional models. In this paper, we revisit the core principles of CFG and introduce a new method, independent condition guidance (ICG), which provides the benefits of CFG without the need for any special training procedures. Our approach streamlines the training process of conditional diffusion models and can also be applied during inference on any pre-trained conditional model. Additionally, by leveraging the time-step information encoded in all diffusion networks, we propose an extension of CFG, called time-step guidance (TSG), which can be applied to any diffusion model, including unconditional ones. Our guidance techniques are easy to implement and have the same sampling cost as CFG. Through extensive experiments, we demonstrate that ICG matches the performance of standard CFG across various conditional diffusion models. Moreover, we show that TSG improves generation quality in a manner similar to CFG, without relying on any conditional information.
Authors: Can Xu, Yao Cheng, Jianxiang Yu, Haosen Wang, Jingsong Lv, Yao Liu, Xiang Li
Abstract: Existing methods for graph out-of-distribution (OOD) generalization primarily rely on empirical studies on synthetic datasets. Such approaches tend to overemphasize the causal relationships between invariant sub-graphs and labels, thereby neglecting the non-negligible role of environment in real-world scenarios. In contrast to previous studies that impose rigid independence assumptions on environments and invariant sub-graphs, this paper presents the theorems of environment-label dependency and mutable rationale invariance, where the former characterizes the usefulness of environments in determining graph labels while the latter refers to the mutable importance of graph rationales. Based on analytic investigations, a novel variational inference based method named ``Probability Dependency on Environments and Rationales for OOD Graphs on Real-world Data'' (DEROG) is introduced. To alleviate the adverse effect of unknown prior knowledge on environments and rationales, DEROG utilizes generalized Bayesian inference. Further, DEROG employs an EM-based algorithm for optimization. Finally, extensive experiments on real-world datasets under different distribution shifts are conducted to show the superiority of DEROG.
Authors: Junhong Lin, Xiaojie Guo, Shuaicheng Zhang, Yada Zhu, Julian Shun
Abstract: Graph mining has become crucial in fields such as social science, finance, and cybersecurity. Many large-scale real-world networks exhibit both heterogeneity, where multiple node and edge types exist in the graph, and heterophily, where connected nodes may have dissimilar labels and attributes. However, existing benchmarks primarily focus on either heterophilic homogeneous graphs or homophilic heterogeneous graphs, leaving a significant gap in understanding how models perform on graphs with both heterogeneity and heterophily. To bridge this gap, we introduce H2GB, a large-scale node-classification graph benchmark that brings together the complexities of both the heterophily and heterogeneity properties of real-world graphs. H2GB encompasses 9 real-world datasets spanning 5 diverse domains, 28 baseline models, and a unified benchmarking library with a standardized data loader, evaluator, unified modeling framework, and an extensible framework for reproducibility. We establish a standardized workflow supporting both model selection and development, enabling researchers to easily benchmark graph learning methods. Extensive experiments across 28 baselines reveal that current methods struggle with heterophilic and heterogeneous graphs, underscoring the need for improved approaches. Finally, we present a new variant of the model, H2G-former, developed following our standardized workflow, that excels at this challenging benchmark. Both the benchmark and the framework are publicly available at Github and PyPI, with documentation hosted at https://junhongmit.github.io/H2GB.
Authors: Puhua Niu, Shili Wu, Mingzhou Fan, Xiaoning Qian
Abstract: Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties. We here propose a new GFlowNet training framework, with policy-dependent rewards, that bridges keeping flow balance of GFlowNets to optimizing the expected accumulated reward in traditional Reinforcement-Learning (RL). This enables the derivation of new policy-based GFlowNet training methods, in contrast to existing ones resembling value-based RL. It is known that the design of backward policies in GFlowNet training affects efficiency. We further develop a coupled training strategy that jointly solves GFlowNet forward policy training and backward policy design. Performance analysis is provided with a theoretical guarantee of our policy-based GFlowNet training. Experiments on both simulated and real-world datasets verify that our policy-based strategies provide advanced RL perspectives for robust gradient estimation to improve GFlowNet performance.
Authors: Mohamad Fares El Hajj Chehade, Wenting Li, Brian W. Bell, Russell Bent, Saif R. Kazi, Hao Zhu
Abstract: The robustness of neural networks is crucial in safety-critical applications, where identifying a reliable input space is essential for effective model selection, robustness evaluation, and the development of reliable control strategies. Most existing robustness verification methods assess the worst-case output under the assumption that the input space is known. However, precisely identifying a verifiable input space \(\mathcal{C}\), where no adversarial examples exist, is challenging due to the possible high dimensionality, discontinuity, and non-convex nature of the input space. To address this challenge, we propose a novel framework, **LEVIS**, consisting of **LEVIS-{\alpha}** and **LEVIS-\b{eta}**. **LEVIS-{\alpha}** identifies a single, large verifiable ball that intersects at least two boundaries of a bounded region \(\mathcal{C}\), while **LEVIS-\b{eta}** systematically captures the entirety of the verifiable space by integrating multiple verifiable balls. Our contributions include: (1) introducing a verification framework that uses mixed-integer programming (MIP) to compute nearest and directional adversarial points, (2) integrating complementarity-constrained (CC) optimization with a reduced MIP formulation for scalability, achieving up to a 6 times runtime reduction, (3) theoretically characterizing the properties of the verifiable balls obtained by **LEVIS-{\alpha}**, and (4) validating the approach across applications including electrical power flow regression and image classification, with demonstrated performance gains and geometric insights into the verifiable region.
Authors: Zixuan Weng, Jindong Han, Wenzhao Jiang, Hao Liu
Abstract: In recent years, advancements in deep learning have spurred the development of numerous models for Long-term Time Series Forecasting (LTSF). However, most existing approaches struggle to fully capture the complex and structured dependencies inherent in time series data. In this work, we identify and formally define three critical dependencies that are fundamental to forecasting accuracy: order dependency and semantic dependency along the temporal dimension, as well as cross-variate dependency across the feature dimension. These dependencies are often treated in isolation, and improper handling can introduce noise and degrade forecasting performance. To bridge this gap, we investigate the potential of State Space Models (SSMs) for LTSF and emphasize their inherent advantages in capturing these essential dependencies. Additionally, we empirically observe that excessive nonlinearity in conventional SSMs introduce redundancy when applied to semantically sparse time series data. Motivated by this insight, we propose SDE (Simplified and Disentangled Dependency Encoding), a novel framework designed to enhance the capability of SSMs for LTSF. Specifically, we first eliminate unnecessary nonlinearities in vanilla SSMs, thereby improving the suitability for time series forecasting. Building on this foundation, we introduce a disentangled encoding strategy, which empowers SSMs to efficiently model cross-variate dependencies while mitigating interference between the temporal and feature dimensions. Furthermore, we provide rigorous theoretical justifications to substantiate our design choices. Extensive experiments on nine real-world benchmark datasets demonstrate that SDE-enhanced SSMs consistently outperform state-of-the-art time series forecasting models.Our code is available at https://github.com/YukinoAsuna/SAMBA.
Authors: Sully F. Chen, Robert J. Steele, Glen M. Hocky, Beakal Lemeneh, Shivanand P. Lad, Eric K. Oermann
Abstract: The transformer architecture has revolutionized bioinformatics and driven progress in the understanding and prediction of the properties of biomolecules. To date, most biosequence transformers have been trained on a single omic-either proteins or nucleic acids and have seen incredible success in downstream tasks in each domain with particularly noteworthy breakthroughs in protein structural modeling. However, single-omic pre-training limits the ability of these models to capture cross-modal interactions. Here we present OmniBioTE, the largest open-source multi-omic model trained on over 250 billion tokens of mixed protein and nucleic acid data. We show that despite only being trained on unlabelled sequence data, OmniBioTE learns joint representations consistent with the central dogma of molecular biology. We further demonstrate that OmbiBioTE achieves state-of-the-art results predicting the change in Gibbs free energy ({\Delta}G) of the binding interaction between a given nucleic acid and protein. Remarkably, we show that multi-omic biosequence transformers emergently learn useful structural information without any a priori structural training, allowing us to predict which protein residues are most involved in the protein-nucleic acid binding interaction. Lastly, compared to single-omic controls trained with identical compute, OmniBioTE demonstrates superior performance-per-FLOP and absolute accuracy across both multi-omic and single-omic benchmarks, highlighting the power of a unified modeling approach for biological sequences.
Authors: Zikai Zhang, Suman Rath, Jiaohao Xu, Tingsong Xiao
Abstract: The Smart Grid (SG) is a critical energy infrastructure that collects real-time electricity usage data to forecast future energy demands using information and communication technologies (ICT). Due to growing concerns about data security and privacy in SGs, federated learning (FL) has emerged as a promising training framework. FL offers a balance between privacy, efficiency, and accuracy in SGs by enabling collaborative model training without sharing private data from IoT devices. In this survey, we thoroughly review recent advancements in designing FL-based SG systems across three stages: generation, transmission and distribution, and consumption. Additionally, we explore potential vulnerabilities that may arise when implementing FL in these stages. Furthermore, we discuss the gap between state-of-the-art (SOTA) FL research and its practical applications in SGs, and we propose future research directions. Unlike traditional surveys addressing security issues in centralized machine learning methods for SG systems, this survey is the first to specifically examine the applications and security concerns unique to FL-based SG systems. We also introduce FedGridShield, an open-source framework featuring implementations of SOTA attack and defense methods. Our aim is to inspire further research into applications and improvements in the robustness of FL-based SG systems.
Authors: Hongkai Zheng, Wenda Chu, Austin Wang, Nikola Kovachki, Ricardo Baptista, Yisong Yue
Abstract: When solving inverse problems, one increasingly popular approach is to use pre-trained diffusion models as plug-and-play priors. This framework can accommodate different forward models without re-training while preserving the generative capability of diffusion models. Despite their success in many imaging inverse problems, most existing methods rely on privileged information such as derivative, pseudo-inverse, or full knowledge about the forward model. This reliance poses a substantial limitation that restricts their use in a wide range of problems where such information is unavailable, such as in many scientific applications. We propose Ensemble Kalman Diffusion Guidance (EnKG), a derivative-free approach that can solve inverse problems by only accessing forward model evaluations and a pre-trained diffusion model prior. We study the empirical effectiveness of EnKG across various inverse problems, including scientific settings such as inferring fluid flows and astronomical objects, which are highly non-linear inverse problems that often only permit black-box access to the forward model. We open-source our code at https://github.com/devzhk/enkg-pytorch.
Authors: Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber
Abstract: Classifier-free guidance (CFG) is crucial for improving both generation quality and alignment between the input condition and final output in diffusion models. While a high guidance scale is generally required to enhance these aspects, it also causes oversaturation and unrealistic artifacts. In this paper, we revisit the CFG update rule and introduce modifications to address this issue. We first decompose the update term in CFG into parallel and orthogonal components with respect to the conditional model prediction and observe that the parallel component primarily causes oversaturation, while the orthogonal component enhances image quality. Accordingly, we propose down-weighting the parallel component to achieve high-quality generations without oversaturation. Additionally, we draw a connection between CFG and gradient ascent and introduce a new rescaling and momentum method for the CFG update rule based on this insight. Our approach, termed adaptive projected guidance (APG), retains the quality-boosting advantages of CFG while enabling the use of higher guidance scales without oversaturation. APG is easy to implement and introduces practically no additional computational overhead to the sampling process. Through extensive experiments, we demonstrate that APG is compatible with various conditional diffusion models and samplers, leading to improved FID, recall, and saturation scores while maintaining precision comparable to CFG, making our method a superior plug-and-play alternative to standard classifier-free guidance.
Authors: Jianqing Zhang, Yang Liu, Yang Hua, Jian Cao, Qiang Yang
Abstract: Model heterogeneity poses a significant challenge in Heterogeneous Federated Learning (HtFL). In scenarios with diverse model architectures, directly aggregating model parameters is impractical, leading HtFL methods to incorporate an extra objective alongside the original local objective on each client to facilitate collaboration. However, this often results in a mismatch between the extra and local objectives. To resolve this, we propose Federated Learning-to-Guide (FedL2G), a method that adaptively learns to guide local training in a federated manner, ensuring the added objective aligns with each client's original goal. With theoretical guarantees, FedL2G utilizes only first-order derivatives w.r.t. model parameters, achieving a non-convex convergence rate of O(1/T). We conduct extensive experiments across two data heterogeneity and six model heterogeneity settings, using 14 heterogeneous model architectures (e.g., CNNs and ViTs). The results show that FedL2G significantly outperforms seven state-of-the-art methods.
Authors: Chenhao Sun, Yuhao Mao, Mark Niklas M\"uller, Martin Vechev
Abstract: Randomized smoothing (RS) is popular for providing certified robustness guarantees against adversarial attacks. The average certified radius (ACR) has emerged as a widely used metric for tracking progress in RS. However, in this work, for the first time we show that ACR is a poor metric for evaluating robustness guarantees provided by RS. We theoretically prove not only that a trivial classifier can have arbitrarily large ACR, but also that ACR is extremely sensitive to improvements on easy samples. In addition, the comparison using ACR has a strong dependence on the certification budget. Empirically, we confirm that existing training strategies, though improving ACR, reduce the model's robustness on hard samples consistently. To strengthen our findings, we propose strategies, including explicitly discarding hard samples, reweighing the dataset with approximate certified radius, and extreme optimization for easy samples, to replicate the progress in RS training and even achieve the state-of-the-art ACR on CIFAR-10, without training for robustness on the full data distribution. Overall, our results suggest that ACR has introduced a strong undesired bias to the field, and its application should be discontinued in RS. Finally, we suggest using the empirical distribution of $p_A$, the accuracy of the base model on noisy data, as an alternative metric for RS.
Authors: Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schroeder de Witt
Abstract: Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to scale them up to very high width, posing a computational challenge. In this work, we introduce Switch Sparse Autoencoders, a novel SAE architecture aimed at reducing the compute cost of training SAEs. Inspired by sparse mixture of experts models, Switch SAEs route activation vectors between smaller "expert" SAEs, enabling SAEs to efficiently scale to many more features. We present experiments comparing Switch SAEs with other SAE architectures, and find that Switch SAEs deliver a substantial Pareto improvement in the reconstruction vs. sparsity frontier for a given fixed training compute budget. We also study the geometry of features across experts, analyze features duplicated across experts, and verify that Switch SAE features are as interpretable as features found by other SAE architectures.
Authors: Youngjae Min, Navid Azizan
Abstract: Incorporating prior knowledge or specifications of input-output relationships into machine learning models has attracted significant attention, as it enhances generalization from limited data and leads to conforming outputs. However, most existing approaches use soft constraints by penalizing violations through regularization, which offers no guarantee of constraint satisfaction, especially on inputs far from the training distribution -- an essential requirement in safety-critical applications. On the other hand, imposing hard constraints on neural networks may hinder their representational power, adversely affecting performance. To address this, we propose HardNet, a practical framework for constructing neural networks that inherently satisfy hard constraints without sacrificing model capacity. Unlike approaches that modify outputs only at inference time, HardNet enables end-to-end training with hard constraint guarantees, leading to improved performance. To the best of our knowledge, HardNet is the first method with an efficient forward pass to enforce more than one input-dependent inequality constraint. It allows unconstrained optimization of the network parameters using standard algorithms by appending a differentiable closed-form enforcement layer to the network's output. Furthermore, we show that HardNet is expressive and retains the universal approximation capabilities of neural networks. We demonstrate the versatility and effectiveness of HardNet across various applications: learning with piecewise constraints, learning optimization solvers with guaranteed feasibility, and optimizing control policies in safety-critical systems.
Authors: Leshem Choshen, Yang Zhang, Jacob Andreas
Abstract: Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets. This provides an efficient way for practitioners and researchers alike to compare pretraining decisions involving optimizers, datasets, and model architectures. Despite the widespread use of scaling laws to model the dynamics of language model training, there has been little work on understanding how to best estimate and interpret them. We collect (and release) a large-scale dataset containing losses and downstream evaluations for 485 previously published pretrained models. We use these to estimate more than 1000 scaling laws, then derive a set of best practices for estimating scaling laws in new model families. We find that fitting scaling laws to intermediate checkpoints of training runs (and not just their final losses) substantially improves accuracy, and that -- all else equal -- estimates of performance are generally most accurate when derived from other models of similar sizes. However, because there is a significant degree of variability across model seeds, training multiple small models is sometimes more useful than training a single large one. Moreover, while different model families differ scaling behavior, they are often similar enough that a target model's behavior can be predicted from a single model with the same architecture, along with scaling parameter estimates derived from other model families.
Authors: Eliahu Horwitz, Bar Cavia, Jonathan Kahana, Yedid Hoshen
Abstract: The number of publicly available models is rapidly increasing, yet most remain undocumented. Users looking for suitable models for their tasks must first determine what each model does. Training machine learning models to infer missing documentation directly from model weights is challenging, as these weights often contain significant variation unrelated to model functionality (denoted nuisance). Here, we identify a key property of real-world models: most public models belong to a small set of Model Trees, where all models within a tree are fine-tuned from a common ancestor (e.g., a foundation model). Importantly, we find that within each tree there is less nuisance variation between models. Concretely, while learning across Model Trees requires complex architectures, even a linear classifier trained on a single model layer often works within trees. While effective, these linear classifiers are computationally expensive, especially when dealing with larger models that have many parameters. To address this, we introduce Probing Experts (ProbeX), a theoretically motivated and lightweight method. Notably, ProbeX is the first probing method specifically designed to learn from the weights of a single hidden model layer. We demonstrate the effectiveness of ProbeX by predicting the categories in a model's training dataset based only on its weights. Excitingly, ProbeX can map the weights of Stable Diffusion into a weight-language embedding space, enabling model search via text, i.e., zero-shot model classification.
Authors: Wei Huang, Richard Combes, Andrea Araldo, Hind Castel-Taleb, Badii Jouaber
Abstract: We study the placement of virtual functions aimed at minimizing the cost. We propose a novel algorithm, using ideas based on multi-armed bandits. We prove that these algorithms learn the optimal placement policy rapidly, and their regret grows at a rate at most $O( N M \sqrt{T\ln T} )$ while respecting the feasibility constraints with high probability, where $T$ is total time slots, $M$ is the number of classes of function and $N$ is the number of computation nodes. We show through numerical experiments that the proposed algorithm both has good practical performance and modest computational complexity. We propose an acceleration technique that allows the algorithm to achieve good performance also in large networks where computational power is limited. Our experiments are fully reproducible, and the code is publicly available.
Authors: Ethan Rathbun, Alina Oprea, Christopher Amato
Abstract: Recent works have demonstrated the vulnerability of Deep Reinforcement Learning (DRL) algorithms against training-time, backdoor poisoning attacks. The objectives of these attacks are twofold: induce pre-determined, adversarial behavior in the agent upon observing a fixed trigger during deployment while allowing the agent to solve its intended task during training. Prior attacks assume arbitrary control over the agent's rewards, inducing values far outside the environment's natural constraints. This results in brittle attacks that fail once the proper reward constraints are enforced. Thus, in this work we propose a new class of backdoor attacks against DRL which are the first to achieve state of the art performance under strict reward constraints. These "inception" attacks manipulate the agent's training data -- inserting the trigger into prior observations and replacing high return actions with those of the targeted adversarial behavior. We formally define these attacks and prove they achieve both adversarial objectives against arbitrary Markov Decision Processes (MDP). Using this framework we devise an online inception attack which achieves an 100\% attack success rate on multiple environments under constrained rewards while minimally impacting the agent's task performance.
Authors: Eric Elmoznino, Tom Marty, Tejas Kasetty, Leo Gagnon, Sarthak Mittal, Mahan Fathi, Dhanya Sridhar, Guillaume Lajoie
Abstract: A central goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees for generalization without further assumptions, in practice we observe that simple models which explain the training data generalize best: a principle called Occam's razor. Despite the need for simple models, most current approaches in machine learning only minimize the training error, and at best indirectly promote simplicity through regularization or architecture design. Here, we draw a connection between Occam's razor and in-context learning: an emergent ability of certain sequence models like Transformers to learn at inference time from past observations in a sequence. In particular, we show that the next-token prediction loss used to train in-context learners is directly equivalent to a data compression technique called prequential coding, and that minimizing this loss amounts to jointly minimizing both the training error and the complexity of the model that was implicitly learned from context. Our theory and the empirical experiments we use to support it not only provide a normative account of in-context learning, but also elucidate the shortcomings of current in-context learning methods, suggesting ways in which they can be improved. We make our code available at https://github.com/3rdCore/PrequentialCode.
Authors: Kang Zhao, Tao Yuan, Han Bao, Zhenfeng Su, Chang Gao, Zhaofeng Sun, Zichen Liang, Liping Jing, Jianfei Chen
Abstract: To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups ($\leq 1.3$) and requires fixed sparse ratios, meaning that other ratios, such as 4:8, 8:16, or those exceeding 50% sparsity, do not incur any speedups on GPUs. Recent studies suggest that V:N:M sparsity is promising in addressing these limitations of 2:4 sparsity. However, regarding accuracy, the effects of V:N:M sparsity on broader Transformer models, such as vision Transformers and large language models (LLMs), are largely unexamined. Moreover, Some specific issues related to V:N:M sparsity, such as how to select appropriate V and M values, remain unresolved. In this study, we thoroughly investigate the application of V:N:M sparsity in vision models and LLMs across multiple tasks, from pertaining to downstream tasks. We propose three key approaches to enhance the applicability and accuracy of V:N:M-sparse Transformers, including heuristic V and M selection, V:N:M-specific channel permutation, and three-staged LoRA training techniques. Experimental results show that, with our methods, the DeiT-small achieves lossless accuracy at 64:2:5 sparsity, while the DeiT-base maintains accuracy even at 64:2:8 sparsity. In addition, the fine-tuned LLama2-7B at 64:2:5 sparsity performs comparably or better than training-free 2:4 sparse alternatives on downstream tasks. More importantly, V:N:M-sparse Transformers offer a wider range of speedup-accuracy trade-offs compared to 2:4 sparsity. Overall, our exploration largely facilitates the V:N:M sparsity to act as a truly effective acceleration solution for Transformers in cost-sensitive inference scenarios.
Authors: Wenda Li, Huijie Zhang, Qing Qu
Abstract: The widespread use of AI-generated content from diffusion models has raised significant concerns regarding misinformation and copyright infringement. Watermarking is a crucial technique for identifying these AI-generated images and preventing their misuse. In this paper, we introduce Shallow Diffuse, a new watermarking technique that embeds robust and invisible watermarks into diffusion model outputs. Unlike existing approaches that integrate watermarking throughout the entire diffusion sampling process, Shallow Diffuse decouples these steps by leveraging the presence of a low-dimensional subspace in the image generation process. This method ensures that a substantial portion of the watermark lies in the null space of this subspace, effectively separating it from the image generation process. Our theoretical and empirical analyses show that this decoupling strategy greatly enhances the consistency of data generation and the detectability of the watermark. Extensive experiments further validate that our Shallow Diffuse outperforms existing watermarking methods in terms of robustness and consistency. The codes will be released at https://github.com/liwd190019/Shallow-Diffuse.
Authors: Marlon Tobaben, Mohamed Ali Souibgui, Rub\`en Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas J\"alk\"o, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aur\'elie Joseph, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota, Ragul N, Rintu Kutum, Josep Llados, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
Abstract: The Privacy Preserving Federated Learning Document VQA (PFL-DocVQA) competition challenged the community to develop provably private and communication-efficient solutions in a federated setting for a real-life use case: invoice processing. The competition introduced a dataset of real invoice documents, along with associated questions and answers requiring information extraction and reasoning over the document images. Thereby, it brings together researchers and expertise from the document analysis, privacy, and federated learning communities. Participants fine-tuned a pre-trained, state-of-the-art Document Visual Question Answering model provided by the organizers for this new domain, mimicking a typical federated invoice processing setup. The base model is a multi-modal generative language model, and sensitive information could be exposed through either the visual or textual input modality. Participants proposed elegant solutions to reduce communication costs while maintaining a minimum utility threshold in track 1 and to protect all information from each document provider using differential privacy in track 2. The competition served as a new testbed for developing and testing private federated learning methods, simultaneously raising awareness about privacy within the document image analysis and recognition community. Ultimately, the competition analysis provides best practices and recommendations for successfully running privacy-focused federated learning challenges in the future.
Authors: Kun Wang, Sumanth Varambally, Duncan Watson-Parris, Yi-An Ma, Rose Yu
Abstract: Many important phenomena in scientific fields like climate, neuroscience, and epidemiology are naturally represented as spatiotemporal gridded data with complex interactions. Inferring causal relationships from these data is a challenging problem compounded by the high dimensionality of such data and the correlations between spatially proximate points. We present SPACY (SPAtiotemporal Causal discoverY), a novel framework based on variational inference, designed to model latent time series and their causal relationships from spatiotemporal data. SPACY alleviates the high-dimensional challenge by discovering causal structures in the latent space. To aggregate spatially proximate, correlated grid points, we use \change{spatial factors, parametrized by spatial kernel functions}, to map observational time series to latent representations. \change{Theoretically, we generalize the problem to a continuous spatial domain and establish identifiability when the observations arise from a nonlinear, invertible function of the product of latent series and spatial factors. Using this approach, we avoid assumptions that are often unverifiable, including those about instantaneous effects or sufficient variability.} Empirically, SPACY outperforms state-of-the-art baselines on synthetic data, even in challenging settings where existing methods struggle, while remaining scalable for large grids. SPACY also identifies key known phenomena from real-world climate data.
Authors: Akhiad Bercovich, Tomer Ronen, Talor Abramovich, Nir Ailon, Nave Assaf, Mohammad Dabbah, Ido Galil, Amnon Geifman, Yonatan Geifman, Izhak Golan, Netanel Haber, Ehud Karpas, Roi Koren, Itay Levy, Pavlo Molchanov, Shahar Mor, Zach Moshe, Najeeb Nabwani, Omri Puny, Ran Rubin, Itamar Schen, Ido Shahaf, Oren Tropp, Omer Ullman Argov, Ran Zilberstein, Ran El-Yaniv
Abstract: Large language models (LLMs) offer remarkable capabilities, yet their high inference costs restrict wider adoption. While increasing parameter counts improves accuracy, it also broadens the gap between state-of-the-art capabilities and practical deployability. We present Puzzle, a hardware-aware framework that accelerates the inference of LLMs while preserving their capabilities. Using neural architecture search (NAS) at a large-scale, Puzzle optimizes models with tens of billions of parameters. Our approach utilizes blockwise local knowledge distillation (BLD) for parallel architecture exploration and employs mixed-integer programming for precise constraint optimization. We showcase our framework's impact via Llama-3.1-Nemotron-51B-Instruct (Nemotron-51B) and Llama-3.3-Nemotron-49B, two publicly available models derived from Llama-70B-Instruct. Both models achieve a 2.17x inference throughput speedup, fitting on a single NVIDIA H100 GPU while retaining 98.4% of the original model's benchmark accuracies. These are the most accurate models supporting single H100 GPU inference with large batch sizes, despite training on 45B tokens at most, far fewer than the 15T used to train Llama-70B. Lastly, we show that lightweight alignment on these derived models allows them to surpass the parent model in specific capabilities. Our work establishes that powerful LLM models can be optimized for efficient deployment with only negligible loss in quality, underscoring that inference performance, not parameter count alone, should guide model selection.
Authors: Lennart Schneider, Martin Wistuba, Aaron Klein, Jacek Golebiowski, Giovanni Zappella, Felice Antonio Merra
Abstract: Optimal prompt selection is crucial for maximizing large language model (LLM) performance on downstream tasks, especially in black-box settings where models are only accessible via APIs. Black-box prompt selection is challenging due to potentially large, combinatorial search spaces, absence of gradient information, and high evaluation cost of prompts on a validation set. We propose HbBoPs, a novel method that combines a structural-aware deep kernel Gaussian Process with Hyperband as a multi-fidelity scheduler to efficiently select prompts. HbBoPs uses embeddings of instructions and few-shot exemplars, treating them as modular components within prompts. This enhances the surrogate model's ability to predict which prompt to evaluate next in a sample-efficient manner. Hyperband improves query-efficiency by adaptively allocating resources across different fidelity levels, reducing the number of validation instances required for evaluating prompts. Extensive experiments across ten diverse benchmarks and three LLMs demonstrate that HbBoPs outperforms state-of-the-art methods in both performance and efficiency.
Authors: Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han, Soji Adeshina, Vassilis N. Ioannidis, Huzefa Rangwala, Christos Faloutsos
Abstract: Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions? Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; while Graph RAG (GRAG) uses structured knowledge bases as its knowledge source. However, many questions require both textual and relational information from SKB - referred to as "hybrid" questions - which complicates the retrieval process and underscores the need for a hybrid retrieval method that leverages both information. In this paper, through our empirical analysis, we identify key insights that show why existing methods may struggle with hybrid question answering (HQA) over SKB. Based on these insights, we propose HybGRAG for HQA consisting of a retriever bank and a critic module, with the following advantages: (1) Agentic, it automatically refines the output by incorporating feedback from the critic module, (2) Adaptive, it solves hybrid questions requiring both textual and relational information with the retriever bank, (3) Interpretable, it justifies decision making with intuitive refinement path, and (4) Effective, it surpasses all baselines on HQA benchmarks. In experiments on the STaRK benchmark, HybGRAG achieves significant performance gains, with an average relative improvement in Hit@1 of 51%.
Authors: Yang Xu, Yi Wang, Hengguan Huang, Hao Wang
Abstract: Understanding training dynamics and feature evolution is crucial for the mechanistic interpretability of large language models (LLMs). Although sparse autoencoders (SAEs) have been used to identify features within LLMs, a clear picture of how these features evolve during training remains elusive. In this study, we (1) introduce SAE-Track, a novel method for efficiently obtaining a continual series of SAEs, providing the foundation for a mechanistic study that covers (2) the semantic evolution of features, (3) the underlying processes of feature formation, and (4) the directional drift of feature vectors. Our work provides new insights into the dynamics of features in LLMs, enhancing our understanding of training mechanisms and feature evolution. For reproducibility, our code is available at https://github.com/Superposition09m/SAE-Track.
Authors: Zhengchao Wan, Qingsong Wang, Gal Mishne, Yusu Wang
Abstract: Flow matching (FM) models extend ODE sampler based diffusion models into a general framework, significantly reducing sampling steps through learned vector fields. However, the theoretical understanding of FM models, particularly how their sample trajectories interact with underlying data geometry, remains underexplored. A rigorous theoretical analysis of FM ODE is essential for sample quality, stability, and broader applicability. In this paper, we advance the theory of FM models through a comprehensive analysis of sample trajectories. Central to our theory is the discovery that the denoiser, a key component of FM models, guides ODE dynamics through attracting and absorbing behaviors that adapt to the data geometry. We identify and analyze the three stages of ODE evolution: in the initial and intermediate stages, trajectories move toward the mean and local clusters of the data. At the terminal stage, we rigorously establish the convergence of FM ODE under weak assumptions, addressing scenarios where the data lie on a low-dimensional submanifold-cases that previous results could not handle. Our terminal stage analysis offers insights into the memorization phenomenon and establishes equivariance properties of FM ODEs. These findings bridge critical gaps in understanding flow matching models, with practical implications for optimizing sampling strategies and architectures guided by the intrinsic geometry of data.
Authors: Rui Sun, Yumin Zhang, Varun Ojha, Tejal Shah, Haoran Duan, Bo Wei, Rajiv Ranjan
Abstract: We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exemplars. The proposed method eliminates the limitations of exemplar selection in replay-based approaches for mitigating catastrophic forgetting in federated continual learning (FCL). The limitations particularly related to the heterogeneity of information density of each summarized data. Our approach maintains the consistency of training gradients and the relationship to past tasks for the summarized exemplars to represent the streaming data compared to the original images effectively. Additionally, our approach reduces the information-level heterogeneity of the summarized data by inter-client sharing of the disentanglement generative model. Extensive experiments show that our ECoral outperforms several state-of-the-art methods and can be seamlessly integrated with many existing approaches to enhance performance.
Authors: Xiaohui Chen, Yinkai Wang, Jiaxing He, Yuanqi Du, Soha Hassoun, Xiaolin Xu, Li-Ping Liu
Abstract: Graph generation is a critical task in numerous domains, including molecular design and social network analysis, due to its ability to model complex relationships and structured data. While most modern graph generative models utilize adjacency matrix representations, this work revisits an alternative approach that represents graphs as sequences of node set and edge set. We advocate for this approach due to its efficient encoding of graphs and propose a novel representation. Based on this representation, we introduce the Graph Generative Pre-trained Transformer (G2PT), an auto-regressive model that learns graph structures via next-token prediction. To further exploit G2PT's capabilities as a general-purpose foundation model, we explore fine-tuning strategies for two downstream applications: goal-oriented generation and graph property prediction. We conduct extensive experiments across multiple datasets. Results indicate that G2PT achieves superior generative performance on both generic graph and molecule datasets. Furthermore, G2PT exhibits strong adaptability and versatility in downstream tasks from molecular design to property prediction. Code available at https://github.com/tufts-ml/G2PT,
Authors: Vyacheslav Kungurtsev, Leonardo Christov Moore, Gustav Sir, Martin Krutsky
Abstract: Causal Learning has emerged as a major theme of research in statistics and machine learning in recent years, promising specific computational techniques to apply to datasets that reveal the true nature of cause and effect in a number of important domains. In this paper we consider the epistemology of recognizing true cause and effect phenomena. We apply the Ordinary Language method of engaging on the customary use of the word 'cause' to investigate valid semantics of reasoning about cause and effect. We recognize that the grammars of cause and effect are fundamentally distinct in form across scientific domains, yet they maintain a consistent and central function. This function can best be described as the mechanism underlying fundamental forces of influence as considered prominent in the respective scientific domain. We demarcate 1) physics and engineering as domains wherein mathematical models are sufficient to comprehensively describe causality, 2) biology as introducing challenges of emergence while providing opportunities for showing consistent mechanisms across scale, and 3) the social sciences as introducing grander difficulties for establishing models of low prediction error but providing, through Hermeneutics, the potential for findings that are still instrumentally useful to individuals. We posit that definitive causal claims regarding a given phenomenon (writ large) can only come through an agglomeration of consistent evidence across multiple domains. This presents important methodological questions as far as harmonizing between language games and emergence across scales. Given the role of epistemic hubris in the contemporary crisis of credibility in the sciences, exercising greater caution as far as communicating precision as to the real degree of certainty certain evidence provides for rich collections of open problems in optimizing integration of different findings.
Authors: Jingyang Ke, Feiyang Wu, Jiyi Wang, Jeffrey Markowitz, Anqi Wu
Abstract: Traditional approaches to studying decision-making in neuroscience focus on simplified behavioral tasks where animals perform repetitive, stereotyped actions to receive explicit rewards. While informative, these methods constrain our understanding of decision-making to short timescale behaviors driven by explicit goals. In natural environments, animals exhibit more complex, long-term behaviors driven by intrinsic motivations that are often unobservable. Recent works in time-varying inverse reinforcement learning (IRL) aim to capture shifting motivations in long-term, freely moving behaviors. However, a crucial challenge remains: animals make decisions based on their history, not just their current state. To address this, we introduce SWIRL (SWitching IRL), a novel framework that extends traditional IRL by incorporating time-varying, history-dependent reward functions. SWIRL models long behavioral sequences as transitions between short-term decision-making processes, each governed by a unique reward function. SWIRL incorporates biologically plausible history dependency to capture how past decisions and environmental contexts shape behavior, offering a more accurate description of animal decision-making. We apply SWIRL to simulated and real-world animal behavior datasets and show that it outperforms models lacking history dependency, both quantitatively and qualitatively. This work presents the first IRL model to incorporate history-dependent policies and rewards to advance our understanding of complex, naturalistic decision-making in animals.
Authors: Tanya Rodchenko, Natasha Noy, Nino Scherrer
Abstract: While Large Language Models require more and more data to train and scale, rather than looking for any data to acquire, we should consider what types of tasks are more likely to benefit from data scaling. We should be intentional in our data acquisition. We argue that the shape of the data itself, such as its compositional and structural patterns, informs which tasks to prioritize in data scaling, and shapes the development of the next generation of compute paradigms for tasks where data scaling is inefficient, or even insufficient.
Authors: Artavazd Maranjyan, Alexander Tyurin, Peter Richt\'arik
Abstract: Asynchronous Stochastic Gradient Descent (Asynchronous SGD) is a cornerstone method for parallelizing learning in distributed machine learning. However, its performance suffers under arbitrarily heterogeneous computation times across workers, leading to suboptimal time complexity and inefficiency as the number of workers scales. While several Asynchronous SGD variants have been proposed, recent findings by Tyurin & Richt\'arik (NeurIPS 2023) reveal that none achieve optimal time complexity, leaving a significant gap in the literature. In this paper, we propose Ringmaster ASGD, a novel Asynchronous SGD method designed to address these limitations and tame the inherent challenges of Asynchronous SGD. We establish, through rigorous theoretical analysis, that Ringmaster ASGD achieves optimal time complexity under arbitrarily heterogeneous and dynamically fluctuating worker computation times. This makes it the first Asynchronous SGD method to meet the theoretical lower bounds for time complexity in such scenarios.
Authors: Lo Pang-Yun Ting, Zhen Tan, Hong-Pei Chen, Cheng-Te Li, Po-Lin Chen, Kun-Ta Chuang, Huan Liu
Abstract: Early detection of patient deterioration is essential for timely treatment, with vital signs like heart rates being key health indicators. Existing methods tend to solely analyze vital sign waveforms, ignoring transition relationships of waveforms within each vital sign and the correlation strengths among various vital signs. Such studies often overlook nuanced illness deterioration, which is the early sign of worsening health but is difficult to detect. In this paper, we introduce CAND, a novel method that organizes the transition relationships and the correlations within and among vital signs as domain-specific and cross-domain knowledge. CAND jointly models these knowledge in a unified representation space, considerably enhancing the early detection of nuanced illness deterioration. In addition, CAND integrates a Bayesian inference method that utilizes augmented knowledge from domain-specific and cross-domain knowledge to address the ambiguities in correlation strengths. With this architecture, the correlation strengths can be effectively inferred to guide joint modeling and enhance representations of vital signs. This allows a more holistic and accurate interpretation of patient health. Our experiments on a real-world ICU dataset demonstrate that CAND significantly outperforms existing methods in both effectiveness and earliness in detecting nuanced illness deterioration. Moreover, we conduct a case study for the interpretable detection process to showcase the practicality of CAND.
Authors: Minh Le, Anh Nguyen, Huy Nguyen, Chau Nguyen, Anh Tran, Nhat Ho
Abstract: Visual Prompt Tuning (VPT) has proven effective for parameter-efficient adaptation of pre-trained vision models to downstream tasks by inserting task-specific learnable prompt tokens. Despite its empirical success, a comprehensive theoretical understanding of VPT remains an active area of research. Building on the recently established connection between Mixture of Experts (MoE) and prompt-based methods, wherein each attention head can be conceptualized as a composition of multiple MoE models, we reinterpret VPT as the introduction of new prompt experts into these MoE structures. We identify a key limitation in existing VPT frameworks: the restricted functional expressiveness of prompt experts, which remain static and thus limited in their adaptability. To address this, we propose Visual Adaptive Prompt Tuning (VAPT), a novel method that endows prompt experts with enhanced expressiveness while preserving parameter efficiency. Empirical evaluations on VTAB-1K and FGVC demonstrate that VAPT achieves substantial performance improvements, surpassing fully fine-tuned baselines by 7.34% and 1.04%, respectively. Moreover, VAPT consistently outperforms VPT while requiring fewer additional parameters. Furthermore, our theoretical analysis indicates that VAPT achieves optimal sample efficiency. Collectively, these results underscore the theoretical grounding and empirical advantages of our approach.
Authors: Huanran Chen, Yinpeng Dong, Zeming Wei, Hang Su, Jun Zhu
Abstract: Recent studies have revealed the vulnerability of large language models to adversarial attacks, where adversaries craft specific input sequences to induce harmful, violent, private, or incorrect outputs. In this work, we study their worst-case robustness, i.e., whether an adversarial example exists that leads to such undesirable outputs. We upper bound the worst-case robustness using stronger white-box attacks, indicating that most current deterministic defenses achieve nearly 0\% worst-case robustness. We propose a general tight lower bound for randomized smoothing using fractional knapsack solvers or 0-1 knapsack solvers, and using them to bound the worst-case robustness of all stochastic defenses. Based on these solvers, we provide theoretical lower bounds for several previous empirical defenses. For example, we certify the robustness of a specific case, smoothing using a uniform kernel, against \textit{any possible attack} with an average $\ell_0$ perturbation of 2.02 or an average suffix length of 6.41.
Authors: Nhan Phan, Thu Nguyen, P{\aa}l Halvorsen, Michael A. Riegler
Abstract: Principal Component Analysis (PCA) is a commonly used tool for dimension reduction and denoising. Therefore, it is also widely used on the data prior to training a neural network. However, this approach can complicate the explanation of explainable AI (XAI) methods for the decision of the model. In this work, we analyze the potential issues with this approach and propose Principal Components-based Initialization (PCsInit), a strategy to incorporate PCA into the first layer of a neural network via initialization of the first layer in the network with the principal components, and its two variants PCsInit-Act and PCsInit-Sub. Explanations using these strategies are as direct and straightforward as for neural networks and are simpler than using PCA prior to training a neural network on the principal components. Moreover, as will be illustrated in the experiments, such training strategies can also allow further improvement of training via backpropagation.
Authors: Jungwon Seo, Ferhat Ozgur Catak, Chunming Rong
Abstract: As privacy concerns and data regulations grow, federated learning (FL) has emerged as a promising approach for training machine learning models across decentralized data sources without sharing raw data. However, a significant challenge in FL is that client data are often non-IID (non-independent and identically distributed), leading to reduced performance compared to centralized learning. While many methods have been proposed to address this issue, their underlying mechanisms are often viewed from different perspectives. Through a comprehensive investigation from gradient descent to FL, and from IID to non-IID data settings, we find that inconsistencies in client loss landscapes primarily cause performance degradation in non-IID scenarios. From this understanding, we observe that existing methods can be grouped into two main strategies: (i) adjusting parameter update paths and (ii) modifying client loss landscapes. These findings offer a clear perspective on addressing non-IID challenges in FL and help guide future research in the field.
Authors: Peixuan Han, Cheng Qian, Xiusi Chen, Yuji Zhang, Denghui Zhang, Heng Ji
Abstract: Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail to fully leverage LLMs' internal cognitive processes. Inspired by humans' reflective thinking capability, we first show that LLMs can similarly perform internal assessments about safety in their internal states. Building on this insight, we propose SafeSwitch, a dynamic framework that regulates unsafe outputs by utilizing the prober-based internal state monitor that actively detects harmful intentions, and activates a safety head that leads to safer and more conservative responses only when necessary. SafeSwitch reduces harmful outputs by approximately 80% on harmful queries while maintaining strong utility, reaching a Pareto optimal among several methods. Our method is also advantageous over traditional methods in offering more informative, context-aware refusals, and achieves these benefits while only tuning less than 6% of the original parameters. SafeSwitch demonstrates large language models' capacity for self-awareness and reflection regarding safety, offering a promising approach to more nuanced and effective safety controls. Codes for this work are available at https://github.com/Hanpx20/SafeSwitch.
Authors: Xuhan Huang, Yan Hu, Zhiyan Li, Zhiyong Wang, Benyou Wang, Zhongxiang Dai
Abstract: Contextual linear dueling bandits have recently garnered significant attention due to their widespread applications in important domains such as recommender systems and large language models. Classical dueling bandit algorithms are typically only applicable to a single agent. However, many applications of dueling bandits involve multiple agents who wish to collaborate for improved performance yet are unwilling to share their data. This motivates us to draw inspirations from federated learning, which involves multiple agents aiming to collaboratively train their neural networks via gradient descent (GD) without sharing their raw data. Previous works have developed federated linear bandit algorithms which rely on closed-form updates of the bandit parameters (e.g., the linear function parameters) to achieve collaboration. However, in linear dueling bandits, the linear function parameters lack a closed-form expression and their estimation requires minimizing a loss function. This renders these previous methods inapplicable. In this work, we overcome this challenge through an innovative and principled combination of online gradient descent (OGD, for minimizing the loss function to estimate the linear function parameters) and federated learning, hence introducing our federated linear dueling bandit with OGD (FLDB-OGD) algorithm. Through rigorous theoretical analysis, we prove that FLDB-OGD enjoys a sub-linear upper bound on its cumulative regret and demonstrate a theoretical trade-off between regret and communication complexity. We conduct empirical experiments to demonstrate the effectiveness of FLDB-OGD and reveal valuable insights, such as the benefit of a larger number of agents, the regret-communication trade-off, among others.
Authors: Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
Abstract: Training large language models (LLMs) is highly resource-intensive due to their massive number of parameters and the overhead of optimizer states. While recent work has aimed to reduce memory consumption, such efforts often entail trade-offs among memory efficiency, training time, and model performance. Yet, true democratization of LLMs requires simultaneous progress across all three dimensions. To this end, we propose SubTrack++ that leverages Grassmannian gradient subspace tracking combined with projection-aware optimizers, enabling Adam's internal statistics to adapt to changes in the optimization subspace. Additionally, employing recovery scaling, a technique that restores information lost through low-rank projections, further enhances model performance. Our method demonstrates SOTA convergence by exploiting Grassmannian geometry and achieves lowest evaluation loss, outperforming the current SOTA while reducing pretraining wall time by 43% and maintaining the memory footprint on a 1B-parameter Llama model.
Authors: Yuan Xinjie, Khalid M. Mosalam
Abstract: Fire safety is crucial for ensuring the stability of building structures, yet evaluating whether a structure meets fire safety requirement is challenging. Fires can originate at any point within a structure, and simulating every potential fire scenario is both expensive and time-consuming. To address this challenge, we propose the concept of the Most Fire-Sensitive Point (MFSP) and an efficient machine learning framework for its identification. The MFSP is defined as the location at which a fire, if initiated, would cause the most severe detrimental impact on the building's stability, effectively representing the worst-case fire scenario. In our framework, a Graph Neural Network (GNN) serves as an efficient and differentiable agent for conventional Finite Element Analysis (FEA) simulators by predicting the Maximum Interstory Drift Ratio (MIDR) under fire, which then guides the training and evaluation of the MFSP predictor. Additionally, we enhance our framework with a novel edge update mechanism and a transfer learning-based training scheme. Evaluations on a large-scale simulation dataset demonstrate the good performance of the proposed framework in identifying the MFSP, offering a transformative tool for optimizing fire safety assessments in structural design. All developed datasets and codes are open-sourced online.
Authors: Michelle M. Li, Kevin Li, Yasha Ektefaie, Ying Jin, Yepeng Huang, Shvat Messica, Tianxi Cai, Marinka Zitnik
Abstract: Conditional generation models for longitudinal sequences can generate new or modified trajectories given a conditioning input. While effective at generating entire sequences, these models typically lack control over the timing and scope of the edits. Most existing approaches either operate on univariate sequences or assume that the condition affects all variables and time steps. However, many scientific and clinical applications require more precise interventions, where a condition takes effect only after a specific time and influences only a subset of variables. We introduce CLEF, a controllable sequence editing model for conditional generation of immediate and delayed effects in multivariate longitudinal sequences. CLEF learns temporal concepts that encode how and when a condition alters future sequence evolution. These concepts allow CLEF to apply targeted edits to the affected time steps and variables while preserving the rest of the sequence. We evaluate CLEF on 6 datasets spanning cellular reprogramming and patient health trajectories, comparing against 9 state-of-the-art baselines. CLEF improves immediate sequence editing accuracy by up to 36.01% (MAE). Unlike prior models, CLEF enables one-step conditional generation at arbitrary future times, outperforming them in delayed sequence editing by up to 65.71% (MAE). We test CLEF under counterfactual inference assumptions and show up to 63.19% (MAE) improvement on zero-shot conditional generation of counterfactual trajectories. In a case study of patients with type 1 diabetes mellitus, CLEF identifies clinical interventions that generate realistic counterfactual trajectories shifted toward healthier outcomes.
Authors: Haoye Lu, Qifan Wu, Yaoliang Yu
Abstract: Recent diffusion-based generative models achieve remarkable results by training on massive datasets, yet this practice raises concerns about memorization and copyright infringement. A proposed remedy is to train exclusively on noisy data with potential copyright issues, ensuring the model never observes original content. However, through the lens of deconvolution theory, we show that although it is theoretically feasible to learn the data distribution from noisy samples, the practical challenge of collecting sufficient samples makes successful learning nearly unattainable. To overcome this limitation, we propose to pretrain the model with a small fraction of clean data to guide the deconvolution process. Combined with our Stochastic Forward--Backward Deconvolution (SFBD) method, we attain FID 6.31 on CIFAR-10 with just 4% clean images (and 3.58 with 10%). We also provide theoretical guarantees that SFBD learns the true data distribution. These results underscore the value of limited clean pretraining, or pretraining on similar datasets. Empirical studies further validate and enrich our findings.
Authors: Gaurush Hiranandani, Haolun Wu, Subhojyoti Mukherjee, Sanmi Koyejo
Abstract: Many commercial Large Language Models (LLMs) are often closed-source, limiting developers to prompt tuning for aligning content generation with specific applications. While these models currently do not provide access to token logits, we argue that if such access were available, it would enable more powerful adaptation techniques beyond prompt engineering. In this paper, we propose a token-level probability reweighting framework that, given access to logits and a small amount of task-specific data, can effectively steer black-box LLMs toward application-specific content generation. Our approach views next-token prediction through the lens of supervised classification. We show that aligning black-box LLMs with task-specific data can be formulated as a label noise correction problem, leading to Plugin model -- an autoregressive probability reweighting model that operates solely on logits. We provide theoretical justification for why reweighting logits alone is sufficient for task adaptation. Extensive experiments with multiple datasets, LLMs, and reweighting models demonstrate the effectiveness of our method, advocating for broader access to token logits in closed-source models.
Authors: Leyang Hu, Matteo Gamba, Randall Balestriero
Abstract: The scaling of model and data sizes has reshaped the AI landscape, establishing finetuning pretrained models as the standard paradigm for solving downstream tasks. However, dominant finetuning methods typically rely on weight adaptation, often lack interpretability, and depend on heuristically chosen hyperparameters. In this paper, we take a different perspective and shift the focus from weights to activation functions, viewing them through the lens of spline operators. We propose Curvature Tuning (CT), an interpretable and principled steering method that modulates a model's decision boundary by injecting a single hyperparameter into its activation functions. We show that CT provably adjusts model decision boundary curvature and, more fundamentally, projects a model onto a space of smooth functions-thereby complementing current finetuning methods, whose effect lies primarily in feature adaptation. Making this hyperparameter trainable gives rise to a novel and highly parameter-efficient finetuning method. Empirically, CT improves both generalization and robustness. For example, it boosts downstream accuracy of ResNet-50/152 by 7.14%/8.46% over linear probing and 4.64%/1.70% over LoRA across 12 datasets, and improves robust accuracy on the $\ell_\infty$ benchmark from RobustBench by 1032.64%/1494.46%. Our code is available at https://github.com/Leon-Leyang/curvature-tuning.
Authors: Junsu Kim, Jaeyeon Kim, Ernest K. Ryu
Abstract: Low-rank adaptation (LoRA) has become a standard approach for fine-tuning large foundation models. However, our theoretical understanding of LoRA remains limited as prior analyses of LoRA's training dynamics either rely on linearization arguments or consider highly simplified setups. In this work, we analyze the LoRA loss landscape without such restrictive assumptions. We define two regimes: a "special regime", which includes idealized setups where linearization arguments hold, and a "generic regime" representing more realistic setups where linearization arguments do not hold. In the generic regime, we show that LoRA training converges to a global minimizer with low rank and small magnitude, or a qualitatively distinct solution with high rank and large magnitude. Finally, we argue that the zero-initialization and weight decay in LoRA training induce an implicit bias toward the low-rank, small-magnitude region of the parameter space -- where global minima lie -- thus shedding light on why LoRA training usually succeeds in finding global minima.
Authors: Matteo Saponati, Pascal Sager, Pau Vilimelis Aceituno, Thilo Stadelmann, Benjamin Grewe
Abstract: Self-attention is essential to Transformer architectures, yet how information is embedded in the self-attention matrices and how different objective functions impact this process remains unclear. We present a mathematical framework to analyze self-attention matrices by deriving the structures governing their weight updates. Using this framework, we demonstrate that bidirectional training induces symmetry in the weight matrices, while autoregressive training results in directionality and column dominance. Our theoretical findings are validated across multiple Transformer models - including ModernBERT, GPT, LLaMA3, and Mistral - and input modalities like text, vision, and audio. Finally, we apply these insights by showing that symmetric initialization improves the performance of encoder-only models on language tasks. This mathematical analysis offers a novel theoretical perspective on how information is embedded through self-attention, thereby improving the interpretability of Transformer models.
Authors: Moxin Li, Yuantao Zhang, Wenjie Wang, Wentao Shi, Zhuo Liu, Fuli Feng, Tat-Seng Chua
Abstract: Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from widespread preference conflicts in the data, where different objectives favor different responses. This results in conflicting optimization directions, hindering the optimization on the Pareto Front. To address this, we propose to construct Pareto-optimal responses to resolve preference conflicts. To efficiently obtain and utilize such responses, we propose a self-improving DPO framework that enables LLMs to self-generate and select Pareto-optimal responses for self-supervised preference alignment. Extensive experiments on two datasets demonstrate the superior Pareto Front achieved by our framework compared to various baselines. Code is available at https://github.com/zyttt-coder/SIPO.
Authors: Mikael M{\o}ller H{\o}gsgaard, Kasper Green Larsen
Abstract: In this paper we establish a new margin-based generalization bound for voting classifiers, refining existing results and yielding tighter generalization guarantees for widely used boosting algorithms such as AdaBoost (Freund and Schapire, 1997). Furthermore, the new margin-based generalization bound enables the derivation of an optimal weak-to-strong learner: a Majority-of-3 large-margin classifiers with an expected error matching the theoretical lower bound. This result provides a more natural alternative to the Majority-of-5 algorithm by (H{\o}gsgaard et al., 2024), and matches the Majority-of-3 result by (Aden-Ali et al., 2024) for the realizable prediction model.
Authors: Sharan Vaswani, Reza Babanezhad
Abstract: Armijo line-search (Armijo-LS) is a standard method to set the step-size for gradient descent (GD). For smooth functions, Armijo-LS alleviates the need to know the global smoothness constant L and adapts to the ``local'' smoothness, enabling GD to converge faster. Existing theoretical analyses show that GD with Armijo-LS (GD-LS) can result in constant factor improvements over GD with a 1/L step-size (denoted as GD(1/L)). We strengthen these results and show that if the objective function satisfies a certain non-uniform smoothness condition, GD-LS can result in a faster convergence rate than GD(1/L). In particular, we prove that for convex objectives corresponding to logistic regression and multi-class classification, GD-LS can converge to the optimum at a linear rate, and hence improves over the sublinear convergence of GD(1/L). Furthermore, for non-convex objectives satisfying gradient domination (e.g., those corresponding to the softmax policy gradient in RL or generalized linear models with a logistic link function), GD-LS can match the fast convergence of algorithms tailored for these specific settings. Finally, we prove that under the interpolation assumption, for convex losses, stochastic GD with a stochastic line-search can match the fast convergence of GD-LS
Authors: Xiner Li, Masatoshi Uehara, Xingyu Su, Gabriele Scalia, Tommaso Biancalani, Aviv Regev, Sergey Levine, Shuiwang Ji
Abstract: Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remains a challenge, particularly in cases where reward functions are non-differentiable. Some gradient-free guidance methods have been developed, but they often struggle to achieve optimal inference-time alignment. In this work, we newly frame inference-time alignment in diffusion as a search problem and propose Dynamic Search for Diffusion (DSearch), which subsamples from denoising processes and approximates intermediate node rewards. It also dynamically adjusts beam width and tree expansion to efficiently explore high-reward generations. To refine intermediate decisions, DSearch incorporates adaptive scheduling based on noise levels and a lookahead heuristic function. We validate DSearch across multiple domains, including biological sequence design, molecular optimization, and image generation, demonstrating superior reward optimization compared to existing approaches.
Authors: Jordan Peper, Zhenjiang Mao, Yuang Geng, Siyuan Pan, Ivan Ruchkin
Abstract: As autonomous systems are increasingly deployed in open and uncertain settings, there is a growing need for trustworthy world models that can reliably predict future high-dimensional observations. The learned latent representations in world models lack direct mapping to meaningful physical quantities and dynamics, limiting their utility and interpretability in downstream planning, control, and safety verification. In this paper, we argue for a fundamental shift from physically informed to physically interpretable world models - and crystallize four principles that leverage symbolic knowledge to achieve these ends: (1) functionally organizing the latent space according to the physical intent, (2) learning aligned invariant and equivariant representations of the physical world, (3) integrating multiple forms and strengths of supervision into a unified training process, and (4) partitioning generative outputs to support scalability and verifiability. We experimentally demonstrate the value of each principle on two benchmarks. This paper opens several intriguing research directions to achieve and capitalize on full physical interpretability in world models.
Authors: Yi Shen, Jian Zhang, Jieyun Huang, Shuming Shi, Wenjing Zhang, Jiangze Yan, Ning Wang, Kai Wang, Zhaoxiang Liu, Shiguo Lian
Abstract: Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating redundant reasoning steps for simple problems), leading to excessive computational resource usage. While current mitigation strategies uniformly reduce reasoning tokens, they risk degrading performance on challenging tasks that require extended reasoning. This paper introduces Difficulty-Adaptive Slow Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought (CoT) based on problem difficulty. We first propose a Token Length Budget (TLB) metric to quantify difficulty, then leverage budget-aware reward shaping and budget preference optimization to implement DAST. DAST penalizes overlong responses for simple tasks while incentivizing sufficient reasoning for complex problems. Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking (reducing token usage by over 30\% on average) while preserving reasoning accuracy on complex problems. Our codes and models are available at https://github.com/AnonymousUser0520/AnonymousRepo01.
Authors: Hyungkyu Kang, Min-hwan Oh
Abstract: In this paper, we study offline preference-based reinforcement learning (PbRL), where learning is based on pre-collected preference feedback over pairs of trajectories. While offline PbRL has demonstrated remarkable empirical success, existing theoretical approaches face challenges in ensuring conservatism under uncertainty, requiring computationally intractable confidence set constructions. We address this limitation by proposing Adversarial Preference-based Policy Optimization (APPO), a computationally efficient algorithm for offline PbRL that guarantees sample complexity bounds without relying on explicit confidence sets. By framing PbRL as a two-player game between a policy and a model, our approach enforces conservatism in a tractable manner. Using standard assumptions on function approximation and bounded trajectory concentrability, we derive a sample complexity bound. To our knowledge, APPO is the first offline PbRL algorithm to offer both statistical efficiency and practical applicability. Experimental results on continuous control tasks demonstrate that APPO effectively learns from complex datasets, showing comparable performance with existing state-of-the-art methods.
Authors: Nils Graef, Andrew Wasielewski
Abstract: Slim attention shrinks the context memory size by 2x for transformer models with MHA (multi-head attention), which can speed up inference by up to 2x for large context windows. Slim attention is an exact, mathematically identical implementation of the standard attention mechanism and therefore doesn't compromise model accuracy. In other words, slim attention losslessly compresses the context memory by a factor of 2. For encoder-decoder transformers, the context memory size can be reduced even further: For the Whisper models for example, slim attention reduces the context memory by 8x, which can speed up token generation by 5x for batch size 64 for example. And for the T5-11B model for example, the memory can be reduced by 32x because its MHA projection dimension is larger than the embedding dimension. See https://github.com/OpenMachine-ai/transformer-tricks for code and more transformer tricks, and https://www.youtube.com/watch?v=uVtk3B6YO4Y for this paper's YouTube video.
URLs: https://github.com/OpenMachine-ai/transformer-tricks, https://www.youtube.com/watch?v=uVtk3B6YO4Y
Authors: Jacob Comeau, Mathieu Bazinet, Pascal Germain, Cem Subakan
Abstract: Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existing continual learning approaches in the literature rely on heuristics and do not provide learning guarantees. In this paper, we present a new method called Continual Pick-to-Learn (CoP2L), which is able to retain the most representative samples for each task in an efficient way. CoP2L combines the Pick-to-Learn algorithm (rooted in the sample compression theory) and the experience replay continual learning scheme. This allows us to provide non-vacuous upper bounds on the generalization loss of the learned predictors, numerically computable after each task. We empirically evaluate our approach on several standard continual learning benchmarks across Class-Incremental, Task-Incremental, and Domain-Incremental settings. Our results show that CoP2L is highly competitive across all setups, often outperforming existing baselines, and significantly mitigating catastrophic forgetting compared to vanilla experience replay in the Class-Incremental setting. It is possible to leverage the bounds provided by CoP2L in practical scenarios to certify the predictor reliability on previously learned tasks, in order to improve the trustworthiness of the continual learning algorithm.
Authors: Eliahu Horwitz, Nitzan Kurer, Jonathan Kahana, Liel Amar, Yedid Hoshen
Abstract: Public model repositories now contain millions of models, yet most models remain undocumented and effectively lost. In this position paper, we advocate for charting the world's model population in a unified structure we call the Model Atlas: a graph that captures models, their attributes, and the weight transformations that connect them. The Model Atlas enables applications in model forensics, meta-ML research, and model discovery, challenging tasks given today's unstructured model repositories. However, because most models lack documentation, large atlas regions remain uncharted. Addressing this gap motivates new machine learning methods that treat models themselves as data, inferring properties such as functionality, performance, and lineage directly from their weights. We argue that a scalable path forward is to bypass the unique parameter symmetries that plague model weights. Charting all the world's models will require a community effort, and we hope its broad utility will rally researchers toward this goal.
Authors: Selim Jerad, Anej Svete, Jiaoda Li, Ryan Cotterell
Abstract: Understanding the expressive power of transformers has recently attracted attention, as it offers insights into their abilities and limitations. Many studies analyze unique hard attention transformers, where attention selects a single position that maximizes the attention scores. When multiple positions achieve the maximum score, either the rightmost or the leftmost of those is chosen. In this paper, we highlight the importance of this seeming triviality. Recently, finite-precision transformers with both leftmost- and rightmost-hard attention were shown to be equivalent to Linear Temporal Logic (LTL). We show that this no longer holds with only leftmost-hard attention -- in that case, they correspond to a \emph{strictly weaker} fragment of LTL. Furthermore, we show that models with leftmost-hard attention are equivalent to \emph{soft} attention, suggesting they may better approximate real-world transformers than right-attention models. These findings refine the landscape of transformer expressivity and underscore the role of attention directionality.
Authors: Onno Eberhard, Michael Muehlebach, Claire Vernade
Abstract: Partially observable environments present a considerable computational challenge in reinforcement learning due to the need to consider long histories. Learning with a finite window of observations quickly becomes intractable as the window length grows. In this work, we introduce memory traces. Inspired by eligibility traces, these are compact representations of the history of observations in the form of exponential moving averages. We prove sample complexity bounds for the problem of offline on-policy evaluation that quantify the return errors achieved with memory traces for the class of Lipschitz continuous value estimates. We establish a close connection to the window approach, and demonstrate that, in certain environments, learning with memory traces is significantly more sample efficient. Finally, we underline the effectiveness of memory traces empirically in online reinforcement learning experiments for both value prediction and control.
Authors: Hyunjun Lee, Hyunsoo Lee, Sookwan Han
Abstract: There have been many attempts to leverage multiple diffusion models for collaborative generation, extending beyond the original domain. A prominent approach involves synchronizing multiple diffusion trajectories by mixing the estimated scores to artificially correlate the generation processes. However, existing methods rely on naive heuristics, such as averaging, without considering task specificity. These approaches do not clarify why such methods work and often produce suboptimal results when a heuristic suitable for one task is blindly applied to others. In this paper, we present a probabilistic framework for analyzing why diffusion synchronization works and reveal where heuristics should be focused; modeling correlations between multiple trajectories and adapting them to each specific task. We further identify optimal correlation models per task, achieving better results than previous approaches that apply a single heuristic across all tasks without justification.
Authors: Agnimitra Dasgupta, Alexsander Marciano da Cunha, Ali Fardisi, Mehrnegar Aminy, Brianna Binder, Bryan Shaddy, Assad A Oberai
Abstract: Diffusion models have emerged as powerful generative tools with applications in computer vision and scientific machine learning (SciML), where they have been used to solve large-scale probabilistic inverse problems. Traditionally, these models have been derived using principles of variational inference, denoising, statistical signal processing, and stochastic differential equations. In contrast to the conventional presentation, in this study we derive diffusion models using ideas from linear partial differential equations and demonstrate that this approach has several benefits that include a constructive derivation of the forward and reverse processes, a unified derivation of multiple formulations and sampling strategies, and the discovery of a new class of variance preserving models. We also apply the conditional version of these models to solve canonical conditional density estimation problems and challenging inverse problems. These problems help establish benchmarks for systematically quantifying the performance of different formulations and sampling strategies in this study and for future studies. Finally, we identify and implement a mechanism through which a single diffusion model can be applied to measurements obtained from multiple measurement operators. Taken together, the contents of this manuscript provide a new understanding of and several new directions in the application of diffusion models to solving physics-based inverse problems.
Authors: Junming Liu, Guosun Zeng, Ding Wang, Yanting Gao, Yufei Jin
Abstract: Multimodal data are often incomplete and exhibit Non-Independent and Identically Distributed (Non-IID) characteristics in real-world scenarios. These inherent limitations lead to both modality heterogeneity through partial modality absence and data heterogeneity from distribution divergence, creating fundamental challenges for effective federated learning (FL). To address these coupled challenges, we propose FedRecon, the first method targeting simultaneous missing modality reconstruction and Non-IID adaptation in multimodal FL. Our approach first employs a lightweight Multimodal Variational Autoencoder (MVAE) to reconstruct missing modalities while preserving cross-modal consistency. Distinct from conventional imputation methods, we achieve sample-level alignment through a novel distribution mapping mechanism that guarantees both data consistency and completeness. Additionally, we introduce a strategy employing global generator freezing to prevent catastrophic forgetting, which in turn mitigates Non-IID fluctuations. Extensive evaluations on multimodal datasets demonstrate FedRecon's superior performance in modality reconstruction under Non-IID conditions, surpassing state-of-the-art methods.
Authors: Deyu Cao, Samin Aref
Abstract: The growing use of large language models has raised environmental and economic concerns about their intensity of resource usage during inference. Serving these models to each user requires substantial energy and water for cooling. Model compression techniques like quantization can shrink large language models and make them more resource efficient at the cost of potential performance degradation. Quantization methods compress model size through replacing their high-precision parameters by quantized values of lower precision. Among existing methods, the ApiQ method achieves superior accuracy preservation at minimal memory and time overhead. We investigate two ideas to extend performance in ultra-low-bit quantization beyond ApiQ's level. First, we look into combining existing quantization-aware training techniques with ApiQ's partial training. We show that this does not outperform the baseline ApiQ method with limited training data and frozen weights. This leads to two key insights: (1) The substantial representational capacity that is gained through full retraining is unlikely to be feasible through partial training. (2) This gain may depend on using a large and diverse dataset in quantization-aware training. Second, through a novel approach informed by the two insights, we propose an ultra-low-bit quantization method that builds upon ApiQ and extends its performance without the need for full retraining. This publicly available method relies on a saliency-aware regularization term that prioritizes preserving the most impactful parameters during quantization. Our experiments on LLaMA 7B and 13B benchmarks demonstrate that our method reduces the ApiQ's accuracy degradation by 10.85\% and 7.54\% respectively.
Authors: Huanyu Zhang, Chengzu Li, Wenshan Wu, Shaoguang Mao, Yifan Zhang, Haochen Tian, Ivan Vuli\'c, Zhang Zhang, Liang Wang, Tieniu Tan, Furu Wei
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks. However, recent studies have exposed critical limitations in their spatial reasoning capabilities. This deficiency in spatial reasoning significantly constrains MLLMs' ability to interact effectively with the physical world, thereby limiting their broader applications. We argue that spatial reasoning capabilities will not naturally emerge from merely scaling existing architectures and training methodologies. Instead, this challenge demands dedicated attention to fundamental modifications in the current MLLM development approach. In this position paper, we first establish a comprehensive framework for spatial reasoning within the context of MLLMs. We then elaborate on its pivotal role in real-world applications. Through systematic analysis, we examine how individual components of the current methodology, from training data to reasoning mechanisms, influence spatial reasoning capabilities. This examination reveals critical limitations while simultaneously identifying promising avenues for advancement. Our work aims to direct the AI research community's attention toward these crucial yet underexplored aspects. By highlighting these challenges and opportunities, we seek to catalyze progress toward achieving human-like spatial reasoning capabilities in MLLMs.
Authors: Ignacio Peis, Batuhan Koyuncu, Isabel Valera, Jes Frellsen
Abstract: We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlike prior approaches that rely on MLP-based hypernetworks with scalability limitations, our method employs a Transformer-based decoder to generate INR parameters from latent variables, addressing both representation capacity and computational efficiency. Our framework extends latent diffusion models (LDMs) to INR generation by replacing standard decoders with a Transformer-based hypernetwork, which can be trained either from scratch or via hyper-transforming: a strategy that fine-tunes only the decoder while freezing the pre-trained latent space. This enables efficient adaptation of existing generative models to INR-based representations without requiring full retraining. We validate our approach across multiple modalities, demonstrating improved scalability, expressiveness, and generalization over existing INR-based generative models. Our findings establish a unified and flexible framework for learning structured function representations.
Authors: Hossein Ahmadi, Sajjad Emdadi Mahdimahalleh, Arman Farahat, Banafsheh Saffari
Abstract: The rapid growth of unlabeled time-series data in domains such as wireless communications, radar, biomedical engineering, and the Internet of Things (IoT) has driven advancements in unsupervised learning. This review synthesizes recent progress in applying autoencoders and vision transformers for unsupervised signal analysis, focusing on their architectures, applications, and emerging trends. We explore how these models enable feature extraction, anomaly detection, and classification across diverse signal types, including electrocardiograms, radar waveforms, and IoT sensor data. The review highlights the strengths of hybrid architectures and self-supervised learning, while identifying challenges in interpretability, scalability, and domain generalization. By bridging methodological innovations and practical applications, this work offers a roadmap for developing robust, adaptive models for signal intelligence.
Authors: Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang, Linchao Zhang, Xiaochun Cao, Qingming Huang
Abstract: Real-world datasets often follow a long-tailed distribution, making generalization to tail classes difficult. Recent methods resorted to long-tail variants of Sharpness-Aware Minimization (SAM), such as ImbSAM and CC-SAM, to improve generalization by flattening the loss landscape. However, these attempts face a trade-off between computational efficiency and control over the loss landscape. On the one hand, ImbSAM is efficient but offers only coarse control as it excludes head classes from the SAM process. On the other hand, CC-SAM provides fine-grained control through class-dependent perturbations but at the cost of efficiency due to multiple backpropagations. Seeing this dilemma, we introduce Focal-SAM, which assigns different penalties to class-wise sharpness, achieving fine-grained control without extra backpropagations, thus maintaining efficiency. Furthermore, we theoretically analyze Focal-SAM's generalization ability and derive a sharper generalization bound. Extensive experiments on both traditional and foundation models validate the effectiveness of Focal-SAM.
Authors: Lang Feng, Weihao Tan, Zhiyi Lyu, Longtao Zheng, Haiyang Xu, Ming Yan, Fei Huang, Bo An
Abstract: Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments. However, their open-ended textual action space and non-end-to-end nature of action generation present significant challenges to effective online exploration in RL, e.g., explosion of the exploration space. We propose a novel online fine-tuning method, Counterfactual Soft Reinforcement Learning (CoSo), better suited to the textual output space of VLM agents. Compared to prior methods that assign uniform uncertainty to all tokens, CoSo leverages counterfactual reasoning to dynamically assess the causal influence of individual tokens on post-processed actions. By prioritizing the exploration of action-critical tokens while reducing the impact of semantically redundant or low-impact tokens, CoSo enables a more targeted and efficient online rollout process. We provide theoretical analysis proving CoSo's convergence and policy improvement guarantees, and extensive empirical evaluations supporting CoSo's effectiveness. Our results across a diverse set of agent tasks, including Android device control, card gaming, and embodied AI, highlight its remarkable ability to enhance exploration efficiency and deliver consistent performance gains. The code is available at https://github.com/langfengQ/CoSo.
Authors: Guanghui Wang, Zhiyong Yang, Zitai Wang, Shi Wang, Qianqian Xu, Qingming Huang
Abstract: Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically using forward Kullback-Leibler divergence (FKLD) or reverse KLD (RKLD). It has become an effective training paradigm due to the broader supervision information provided by the teacher distribution compared to one-hot labels. We identify that the core challenge in KD lies in balancing two mode-concentration effects: the \textbf{\textit{Hardness-Concentration}} effect, which refers to focusing on modes with large errors, and the \textbf{\textit{Confidence-Concentration}} effect, which refers to focusing on modes with high student confidence. Through an analysis of how probabilities are reassigned during gradient updates, we observe that these two effects are entangled in FKLD and RKLD, but in extreme forms. Specifically, both are too weak in FKLD, causing the student to fail to concentrate on the target class. In contrast, both are too strong in RKLD, causing the student to overly emphasize the target class while ignoring the broader distributional information from the teacher. To address this imbalance, we propose ABKD, a generic framework with $\alpha$-$\beta$-divergence. Our theoretical results show that ABKD offers a smooth interpolation between FKLD and RKLD, achieving an effective trade-off between these effects. Extensive experiments on 17 language/vision datasets with 12 teacher-student settings confirm its efficacy. The code is available at https://github.com/ghwang-s/abkd.
Authors: Zara Siddique, Liam D. Turner, Luis Espinosa-Anke
Abstract: We introduce Dialz, a framework for advancing research on steering vectors for open-source LLMs, implemented in Python. Steering vectors allow users to modify activations at inference time to amplify or weaken a 'concept', e.g. honesty or positivity, providing a more powerful alternative to prompting or fine-tuning. Dialz supports a diverse set of tasks, including creating contrastive pair datasets, computing and applying steering vectors, and visualizations. Unlike existing libraries, Dialz emphasizes modularity and usability, enabling both rapid prototyping and in-depth analysis. We demonstrate how Dialz can be used to reduce harmful outputs such as stereotypes, while also providing insights into model behaviour across different layers. We release Dialz with full documentation, tutorials, and support for popular open-source models to encourage further research in safe and controllable language generation. Dialz enables faster research cycles and facilitates insights into model interpretability, paving the way for safer, more transparent, and more reliable AI systems.
Authors: Zhen Liu, Yicheng Luo, Boyuan Li, Emadeldeen Eldele, Min Wu, Qianli Ma
Abstract: Shapelets are discriminative subsequences (or shapes) with high interpretability in time series classification. Due to the time-intensive nature of shapelet discovery, existing shapelet-based methods mainly focus on selecting discriminative shapes while discarding others to achieve candidate subsequence sparsification. However, this approach may exclude beneficial shapes and overlook the varying contributions of shapelets to classification performance. To this end, we propose a Soft sparse Shapes (SoftShape) model for efficient time series classification. Our approach mainly introduces soft shape sparsification and soft shape learning blocks. The former transforms shapes into soft representations based on classification contribution scores, merging lower-scored ones into a single shape to retain and differentiate all subsequence information. The latter facilitates intra- and inter-shape temporal pattern learning, improving model efficiency by using sparsified soft shapes as inputs. Specifically, we employ a learnable router to activate a subset of class-specific expert networks for intra-shape pattern learning. Meanwhile, a shared expert network learns inter-shape patterns by converting sparsified shapes into sequences. Extensive experiments show that SoftShape outperforms state-of-the-art methods and produces interpretable results.
Authors: Yuhao Li, Ling Luo, Uwe Aickelin
Abstract: Medical research, particularly in predicting patient outcomes, heavily relies on medical time series data extracted from Electronic Health Records (EHR), which provide extensive information on patient histories. Despite rigorous examination, labeling errors are inevitable and can significantly impede accurate predictions of patient outcome. To address this challenge, we propose an \textbf{A}ttention-based Learning Framework with Dynamic \textbf{C}alibration and Augmentation for \textbf{T}ime series Noisy \textbf{L}abel \textbf{L}earning (ACTLL). This framework leverages a two-component Beta mixture model to identify the certain and uncertain sets of instances based on the fitness distribution of each class, and it captures global temporal dynamics while dynamically calibrating labels from the uncertain set or augmenting confident instances from the certain set. Experimental results on large-scale EHR datasets eICU and MIMIC-IV-ED, and several benchmark datasets from the UCR and UEA repositories, demonstrate that our model ACTLL has achieved state-of-the-art performance, especially under high noise levels.
Authors: Yanxin Liu, Yunqi Zhang
Abstract: Currently, the scaling law of Large Language Models (LLMs) faces challenges and bottlenecks. This paper posits that noise effects, stemming from changes in the signal-to-noise ratio under diminishing marginal returns, are the root cause of these issues. To control this noise, we investigated the differences between models with performance advantages and disadvantages, introducing the concept of "relative overfitting." Based on their complementary strengths, we have proposed an application framework, Accept-Reject (AR), and the associated AR Law, which operates within this framework to elucidate the patterns of performance changes after model integration. In Natural Language Processing (NLP), we use LLMs and Small Language Models (SLMs) as the medium for discussion. This framework enables SLMs to exert a universal positive influence on LLM decision outputs, rather than the intuitively expected potential negative influence. We validated our approach using self-built models based on mainstream architectures and pre-trained mainstream models across multiple datasets, including basic language modeling, long-context tasks, subject examination, and question-answering (QA) benchmarks. The results demonstrate that through our framework, compared to increasing the LLM's parameters, we can achieve better performance improvements with significantly lower parameter and computational costs in many scenarios. These improvements are universal, stable, and effective. Furthermore, we explore the potential of "relative overfitting" and the AR framework in other machine learning domains, such as computer vision (CV) and AI for science. We hope the proposed approach can help scale laws overcome existing bottlenecks.
Authors: Gabriel Malikal, Ismail Alkhouri, Alvaro Velasquez, Adam M Alessio, Saiprasad Ravishankar
Abstract: The Maximum Cut (MaxCut) problem is NP-Complete, and obtaining its optimal solution is NP-hard in the worst case. As a result, heuristic-based algorithms are commonly used, though their design often requires significant domain expertise. More recently, learning-based methods trained on large (un)labeled datasets have been proposed; however, these approaches often struggle with generalizability and scalability. A well-known approximation algorithm for MaxCut is the Goemans-Williamson (GW) algorithm, which relaxes the Quadratic Unconstrained Binary Optimization (QUBO) formulation into a semidefinite program (SDP). The GW algorithm then applies hyperplane rounding by uniformly sampling a random hyperplane to convert the SDP solution into binary node assignments. In this paper, we propose a training-data-free approach based on a non-episodic reinforcement learning formulation, in which an agent learns to select improved rounding hyperplanes that yield better cuts than those produced by the GW algorithm. By optimizing over a Markov Decision Process (MDP), our method consistently achieves better cuts across large-scale graphs with varying densities and degree distributions.
Authors: Shpresim Sadiku, Kartikeya Chitranshi, Hiroshi Kera, Sebastian Pokutta
Abstract: Plausible counterfactual explanations (p-CFEs) are perturbations that minimally modify inputs to change classifier decisions while remaining plausible under the data distribution. In this study, we demonstrate that classifiers can be trained on p-CFEs labeled with induced \emph{incorrect} target classes to classify unperturbed inputs with the original labels. While previous studies have shown that such learning is possible with adversarial perturbations, we extend this paradigm to p-CFEs. Interestingly, our experiments reveal that learning from p-CFEs is even more effective: the resulting classifiers achieve not only high in-distribution accuracy but also exhibit significantly reduced bias with respect to spurious correlations.
Authors: Noah Amsel, David Persson, Christopher Musco, Robert M. Gower
Abstract: Computing the polar decomposition and the related matrix sign function, has been a well-studied problem in numerical analysis for decades. More recently, it has emerged as an important subroutine in deep learning, particularly within the Muon optimization framework. However, the requirements in this setting differ significantly from those of traditional numerical analysis. In deep learning, methods must be highly efficient and GPU-compatible, but high accuracy is often unnecessary. As a result, classical algorithms like Newton-Schulz (which suffers from slow initial convergence) and methods based on rational functions (which rely on QR decompositions or matrix inverses) are poorly suited to this context. In this work, we introduce Polar Express, a GPU-friendly algorithm for computing the polar decomposition. Like classical polynomial methods such as Newton-Schulz, our approach uses only matrix-matrix multiplications, making it GPU-compatible. Motivated by earlier work of Chen & Chow and Nakatsukasa & Freund, Polar Express adapts the polynomial update rule at each iteration by solving a minimax optimization problem, and we prove that it enjoys a strong worst-case optimality guarantee. This property ensures both rapid early convergence and fast asymptotic convergence. We also address finite-precision issues, making it stable in bfloat16 in practice. We apply Polar Express within the Muon optimization framework and show consistent improvements in validation loss on large-scale models such as GPT-2, outperforming recent alternatives across a range of learning rates.
Authors: Qihao Duan, Bingding Huang, Zhenqiao Song, Irina Lehmann, Lei Gu, Roland Eils, Benjamin Wild
Abstract: Large language models (LLMs) have revolutionized natural language processing and are increasingly applied to other sequential data types, including genetic sequences. However, adapting LLMs to genomics presents significant challenges. Capturing complex genomic interactions requires modeling long-range dependencies within DNA sequences, where interactions often span over 10,000 base pairs, even within a single gene, posing substantial computational burdens under conventional model architectures and training paradigms. Moreover, standard LLM training approaches are suboptimal for DNA: autoregressive training, while efficient, supports only unidirectional understanding. However, DNA is inherently bidirectional, e.g., bidirectional promoters regulate transcription in both directions and account for nearly 11% of human gene expression. Masked language models (MLMs) allow bidirectional understanding but are inefficient, as only masked tokens contribute to the loss per step. To address these limitations, we introduce JanusDNA, the first bidirectional DNA foundation model built upon a novel pretraining paradigm that combines the optimization efficiency of autoregressive modeling with the bidirectional comprehension of masked modeling. JanusDNA adopts a hybrid Mamba, Attention and Mixture of Experts (MoE) architecture, combining long-range modeling of Attention with efficient sequential learning of Mamba. MoE layers further scale model capacity via sparse activation while keeping computational cost low. Notably, JanusDNA processes up to 1 million base pairs at single nucleotide resolution on a single 80GB GPU. Extensive experiments and ablations show JanusDNA achieves new SOTA results on three genomic representation benchmarks, outperforming models with 250x more activated parameters. Code: https://github.com/Qihao-Duan/JanusDNA
Authors: Shaghayegh Hosseinpour, Sanchari Das
Abstract: Smishing, or SMS-based phishing, poses an increasing threat to mobile users by mimicking legitimate communications through culturally adapted, concise, and deceptive messages, which can result in the loss of sensitive data or financial resources. In such, we present a multi-channel smishing detection model that combines country-specific semantic tagging, structural pattern tagging, character-level stylistic cues, and contextual phrase embeddings. We curated and relabeled over 84,000 messages across five datasets, including 24,086 smishing samples. Our unified architecture achieves 97.89% accuracy, an F1 score of 0.963, and an AUC of 99.73%, outperforming single-stream models by capturing diverse linguistic and structural cues. This work demonstrates the effectiveness of multi-signal learning in robust and region-aware phishing.
Authors: Xiaojun Guo, Ang Li, Yifei Wang, Stefanie Jegelka, Yisen Wang
Abstract: Although Large Language Models (LLMs) have demonstrated remarkable progress, their proficiency in graph-related tasks remains notably limited, hindering the development of truly general-purpose models. Previous attempts, including pretraining graph foundation models or employing supervised fine-tuning, often face challenges such as the scarcity of large-scale, universally represented graph data. We introduce G1, a simple yet effective approach demonstrating that Reinforcement Learning (RL) on synthetic graph-theoretic tasks can significantly scale LLMs' graph reasoning abilities. To enable RL training, we curate Erd\~os, the largest graph reasoning dataset to date comprising 50 diverse graph-theoretic tasks of varying difficulty levels, 100k training data and 5k test data, all drived from real-world graphs. With RL on Erd\~os, G1 obtains substantial improvements in graph reasoning, where our finetuned 3B model even outperforms Qwen2.5-72B-Instruct (24x size). RL-trained models also show strong zero-shot generalization to unseen tasks, domains, and graph encoding schemes, including other graph-theoretic benchmarks as well as real-world node classification and link prediction tasks, without compromising general reasoning abilities. Our findings offer an efficient, scalable path for building strong graph reasoners by finetuning LLMs with RL on graph-theoretic tasks, which combines the strengths of pretrained LLM capabilities with abundant, automatically generated synthetic data, suggesting that LLMs possess graph understanding abilities that RL can elicit successfully. Our implementation is open-sourced at https://github.com/PKU-ML/G1, with models and datasets hosted on Hugging Face collections https://huggingface.co/collections/PKU-ML/g1-683d659e992794fc99618cf2 for broader accessibility.
URLs: https://github.com/PKU-ML/G1,, https://huggingface.co/collections/PKU-ML/g1-683d659e992794fc99618cf2
Authors: Zachary C. Brown, David Carlson
Abstract: The field of hypothesis generation promises to reduce costs in neuroscience by narrowing the range of interventional studies needed to study various phenomena. Existing machine learning methods can generate scientific hypotheses from complex datasets, but many approaches assume causal relationships are static over time, limiting their applicability to systems with dynamic, state-dependent behavior, such as the brain. While some techniques attempt dynamic causal discovery through factor models, they often restrict relationships to linear patterns or impose other simplifying assumptions. We propose a novel method that models dynamic graphs as a conditionally weighted superposition of static graphs, where each static graph can capture nonlinear relationships. This approach enables the detection of complex, time-varying interactions between variables beyond linear limitations. Our method improves f1-scores of predicted dynamic causal patterns by roughly 22-28% on average over baselines in some of our experiments, with some improvements reaching well over 60%. A case study on real brain data demonstrates our method's ability to uncover relationships linked to specific behavioral states, offering valuable insights into neural dynamics.
Authors: Zijing Wang, Xingle Xu, Yongkang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Xiaocui Yang, Daling Wang, Hinrich Sch\"utze
Abstract: Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model. Although recent model merging methods have shown promising results, they struggle to maintain performance gains as the number of merged models increases. In this paper, we investigate the key obstacles that limit the scalability of model merging when integrating a large number of expert models. First, we prove that there is an upper bound on model merging. Further theoretical analysis reveals that the limited effective parameter space imposes a strict constraint on the number of models that can be successfully merged. Gaussian Width shows that the marginal benefit of merging additional models diminishes according to a strictly concave function. This implies that the effective parameter space becomes rapidly saturated as the number of merged models increases. Furthermore, using Approximate Kinematics Theory, we prove the existence of a unique optimal threshold beyond which adding more models does not yield significant performance improvements. At the same time, we introduce a straightforward Reparameterized Heavy-Tailed method (RHT) to extend the coverage of the merged model, thereby enhancing its performance. Empirical results on 12 benchmarks, including both knowledge-intensive and general-purpose tasks, validate our theoretical analysis. We believe that these results spark further research beyond the current scope of model merging. The source code is in the Github repository: https://github.com/wzj1718/ModelMergingAnalysis.
Authors: Yekun Zhu, Min Tang, Zheng Ma
Abstract: In this paper, we propose a novel neural network approach, termed DeepRTE, to address the steady-state Radiative Transfer Equation (RTE). The RTE is a differential-integral equation that governs the propagation of radiation through a participating medium, with applications spanning diverse domains such as neutron transport, atmospheric radiative transfer, heat transfer, and optical imaging. Our DeepRTE framework demonstrates superior computational efficiency for solving the steady-state RTE, surpassing traditional methods and existing neural network approaches. This efficiency is achieved by embedding physical information through derivation of the RTE and mathematically-informed network architecture. Concurrently, DeepRTE achieves high accuracy with significantly fewer parameters, largely due to its incorporation of mechanisms such as multi-head attention. Furthermore, DeepRTE is a mesh-free neural operator framework with inherent zero-shot capability. This is achieved by incorporating Green's function theory and pre-training with delta-function inflow boundary conditions into both its architecture design and training data construction. The efficacy of the proposed approach is substantiated through comprehensive numerical experiments.
Authors: Sean Current, Ziqi Chen, Daniel Adu-Ampratwum, Xia Ning, Srinivasan Parthasarathy
Abstract: Methods for automatic chemical retrosynthesis have found recent success through the application of models traditionally built for natural language processing, primarily through transformer neural networks. These models have demonstrated significant ability to translate between the SMILES encodings of chemical products and reactants, but are constrained as a result of their autoregressive nature. We propose DiffER, an alternative template-free method for retrosynthesis prediction in the form of categorical diffusion, which allows the entire output SMILES sequence to be predicted in unison. We construct an ensemble of diffusion models which achieves state-of-the-art performance for top-1 accuracy and competitive performance for top-3, top-5, and top-10 accuracy among template-free methods. We prove that DiffER is a strong baseline for a new class of template-free model, capable of learning a variety of synthetic techniques used in laboratory settings and outperforming a variety of other template-free methods on top-k accuracy metrics. By constructing an ensemble of categorical diffusion models with a novel length prediction component with variance, our method is able to approximately sample from the posterior distribution of reactants, producing results with strong metrics of confidence and likelihood. Furthermore, our analyses demonstrate that accurate prediction of the SMILES sequence length is key to further boosting the performance of categorical diffusion models.
Authors: Zhaokun Wang, Jinyu Guo, Jingwen Pu, Lingfeng Chen, Hongli Pu, Jie Ou, Libo Qin, Wenhong Tian
Abstract: Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustness to noise only with generated noisy data. Drawing inspiration from the mixture-of-experts architecture, LoPE strategically integrates a dedicated poisoning expert in an asymmetric LoRA configuration. Through a two-stage paradigm, LoPE performs noise injection on the poisoning expert during fine-tuning to enhance its noise discrimination and processing ability. During inference, we selectively mask the dedicated poisoning expert to leverage purified knowledge acquired by normal experts for noise-robust output. Extensive experiments demonstrate that LoPE achieves strong performance and robustness purely through the low-cost noise injection, which completely eliminates the requirement of data cleaning.
Authors: Stepan Shabalin, Ayush Panda, Dmitrii Kharlapenko, Abdur Raheem Ali, Yixiong Hao, Arthur Conmy
Abstract: Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models. Inference-Time Decomposition of Activations (ITDA) is a recently proposed variant of dictionary learning that takes the dictionary to be a set of data points from the activation distribution and reconstructs them with gradient pursuit. We apply Sparse Autoencoders (SAEs) and ITDA to a large text-to-image diffusion model, Flux 1, and consider the interpretability of embeddings of both by introducing a visual automated interpretation pipeline. We find that SAEs accurately reconstruct residual stream embeddings and beat MLP neurons on interpretability. We are able to use SAE features to steer image generation through activation addition. We find that ITDA has comparable interpretability to SAEs.
Authors: Andrei Chernov, Vitaliy Pozdnyakov, Ilya Makarov
Abstract: Recent studies in time series forecasting have explored formulating regression via classification task. By discretizing the continuous target space into bins and predicting over a fixed set of classes, these approaches benefit from stable training, robust uncertainty modeling, and compatibility with modern deep learning architectures. However, most existing methods rely on one-hot encoding that ignores the inherent ordinal structure of the underlying values. As a result, they fail to provide information about the relative distance between predicted and true values during training. In this paper, we propose to address this limitation by introducing binary cumulative encoding (BCE), that represents scalar targets into monotonic binary vectors. This encoding implicitly preserves order and magnitude information, allowing the model to learn distance-aware representations while still operating within a classification framework. We propose a convolutional neural network architecture specifically designed for BCE, incorporating residual and dilated convolutions to enable fast and expressive temporal modeling. Through extensive experiments on benchmark forecasting datasets, we show that our approach outperforms widely used methods in both point and probabilistic forecasting, while requiring fewer parameters and enabling faster training.
Authors: Yidong Luo, Chenguang Wang, Jiahao Yang, Fanzeng Xia, Tianshu Yu
Abstract: Mixed-Integer Linear Programming (MILP) is fundamental to solving complex decision-making problems. The proliferation of MILP instance generation methods, driven by machine learning's demand for diverse optimization datasets and the limitations of static benchmarks, has significantly outpaced standardized evaluation techniques. Consequently, assessing the fidelity and utility of synthetic MILP instances remains a critical, multifaceted challenge. This paper introduces a comprehensive benchmark framework designed for the systematic and objective evaluation of MILP instance generation methods. Our framework provides a unified and extensible methodology, assessing instance quality across crucial dimensions: mathematical validity, structural similarity, computational hardness, and utility in downstream machine learning tasks. A key innovation is its in-depth analysis of solver-internal features -- particularly by comparing distributions of key solver outputs including root node gap, heuristic success rates, and cut plane usage -- leveraging the solver's dynamic solution behavior as an `expert assessment' to reveal nuanced computational resemblances. By offering a structured approach with clearly defined solver-independent and solver-dependent metrics, our benchmark aims to facilitate robust comparisons among diverse generation techniques, spur the development of higher-quality instance generators, and ultimately enhance the reliability of research reliant on synthetic MILP data. The framework's effectiveness in systematically comparing the fidelity of instance sets is demonstrated using contemporary generative models.
Authors: Jun Wu, Yirong Xiong, Jiangtao Wen, Yuxing Han
Abstract: Despite rapid advancements in the research and deployment of large language models (LLMs), the statistical distribution of model parameters, as well as their influence on initialization, training dynamics, and downstream efficiency, has received surprisingly little attention. A recent work introduced BackSlash, a training-time compression algorithm. It first demonstrated that pre-trained LLM parameters follow generalized Gaussian distributions (GGDs) better. By optimizing GG priors during training, BackSlash can reduce parameters by up to 90\% with minimal performance loss. Building on this foundational insight, we propose a unified, end-to-end framework for LLM optimization based on the GG model. Our contributions are threefold: (1) GG-based initialization scheme that aligns with the statistical structure of trained models, resulting in faster convergence and improved accuracy; (2) DeepShape, a post-training regularization method that reshapes weight distributions to match a GG profile, improving compressibility with minimized degradation in performance; and (3) RF8, a compact and hardware-efficient 8-bit floating-point format designed for GG-distributed-initialized BackSlash training, enabling low-cost inference without compromising accuracy. Experiments across diverse model architectures show that our framework consistently yields smaller and faster models that match or outperform standard training baselines. By grounding LLM development in principled statistical modeling, this work forges a new path toward efficient, scalable, and hardware-aware AI systems. The code is available on our project page: https://huggingface.co/spaces/shifeng3711/gg_prior.
Authors: Femi Bello, Anubrata Das, Fanzhi Zeng, Fangcong Yin, Liu Leqi
Abstract: It has been hypothesized that neural networks with similar architectures trained on similar data learn shared representations relevant to the learning task. We build on this idea by extending the conceptual framework where representations learned across models trained on the same data can be expressed as linear combinations of a \emph{universal} set of basis features. These basis features underlie the learning task itself and remain consistent across models, regardless of scale. From this framework, we propose the \textbf{Linear Representation Transferability (LRT)} Hypothesis -- that there exists an affine transformation between the representation spaces of different models. To test this hypothesis, we learn affine mappings between the hidden states of models of different sizes and evaluate whether steering vectors -- directions in hidden state space associated with specific model behaviors -- retain their semantic effect when transferred from small to large language models using the learned mappings. We find strong empirical evidence that such affine mappings can preserve steering behaviors. These findings suggest that representations learned by small models can be used to guide the behavior of large models, and that the LRT hypothesis may be a promising direction on understanding representation alignment across model scales.
Authors: Ning Zhang, Henry Kenlay, Li Zhang, Mihai Cucuringu, Xiaowen Dong
Abstract: Graph convolutional neural networks (GCNNs) have emerged as powerful tools for analyzing graph-structured data, achieving remarkable success across diverse applications. However, the theoretical understanding of the stability of these models, i.e., their sensitivity to small changes in the graph structure, remains in rather limited settings, hampering the development and deployment of robust and trustworthy models in practice. To fill this gap, we study how perturbations in the graph topology affect GCNN outputs and propose a novel formulation for analyzing model stability. Unlike prior studies that focus only on worst-case perturbations, our distribution-aware formulation characterizes output perturbations across a broad range of input data. This way, our framework enables, for the first time, a probabilistic perspective on the interplay between the statistical properties of the node data and perturbations in the graph topology. We conduct extensive experiments to validate our theoretical findings and demonstrate their benefits over existing baselines, in terms of both representation stability and adversarial attacks on downstream tasks. Our results demonstrate the practical significance of the proposed formulation and highlight the importance of incorporating data distribution into stability analysis.
Authors: SeungBum Ha, Saerom Park, Sung Whan Yoon
Abstract: Machine unlearning (MU) aims to expunge a designated forget set from a trained model without costly retraining, yet the existing techniques overlook two critical blind spots: "over-unlearning" that deteriorates retained data near the forget set, and post-hoc "relearning" attacks that aim to resurrect the forgotten knowledge. We first derive the over-unlearning metric OU@{\epsilon}, which represents the collateral damage to the nearby region of the forget set, where the over-unlearning mainly appears. Next, we expose an unforeseen relearning threat on MU, i.e., the Prototypical Relearning Attack, which exploits the per-class prototype of the forget class with just a few samples, and easily restores the pre-unlearning performance. To counter both blind spots, we introduce Spotter, a plug-and-play objective that combines (i) a masked knowledge-distillation penalty on the nearby region of forget set to suppress OU@{\epsilon}, and (ii) an intra-class dispersion loss that scatters forget-class embeddings, neutralizing prototypical relearning attacks. On CIFAR-10, as one of validations, Spotter reduces OU@{\epsilon}by below the 0.05X of the baseline, drives forget accuracy to 0%, preserves accuracy of the retain set within 1% of difference with the original, and denies the prototype-attack by keeping the forget set accuracy within <1%, without accessing retained data. It confirms that Spotter is a practical remedy of the unlearning's blind spots.
Authors: Genta Indra Winata, David Anugraha, Emmy Liu, Alham Fikri Aji, Shou-Yi Hung, Aditya Parashar, Patrick Amadeus Irawan, Ruochen Zhang, Zheng-Xin Yong, Jan Christian Blaise Cruz, Niklas Muennighoff, Seungone Kim, Hanyang Zhao, Sudipta Kar, Kezia Erina Suryoraharjo, M. Farid Adilazuarda, En-Shiun Annie Lee, Ayu Purwarianti, Derry Tanti Wijaya, Monojit Choudhury
Abstract: High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant challenge. Many dataset paper submissions lack originality, diversity, or rigorous quality control, and these shortcomings are often overlooked during peer review. Submissions also frequently omit essential details about dataset construction and properties. While existing tools such as datasheets aim to promote transparency, they are largely descriptive and do not provide standardized, measurable methods for evaluating data quality. Similarly, metadata requirements at conferences promote accountability but are inconsistently enforced. To address these limitations, this position paper advocates for the integration of systematic, rubric-based evaluation metrics into the dataset review process-particularly as submission volumes continue to grow. We also explore scalable, cost-effective methods for synthetic data generation, including dedicated tools and LLM-as-a-judge approaches, to support more efficient evaluation. As a call to action, we introduce DataRubrics, a structured framework for assessing the quality of both human- and model-generated datasets. Leveraging recent advances in LLM-based evaluation, DataRubrics offers a reproducible, scalable, and actionable solution for dataset quality assessment, enabling both authors and reviewers to uphold higher standards in data-centric research. We also release code to support reproducibility of LLM-based evaluations at https://github.com/datarubrics/datarubrics.
Authors: Wei Shen, Zhang Yaxiang, Minhui Huang, Mengfan Xu, Jiawei Zhang, Cong Shen
Abstract: With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a novel memory-efficient training paradigm called Momentum Low-rank compression (MLorc). By directly compressing and reconstructing momentum rather than gradients, MLorc avoids imposing a fixed-rank constraint on weight update matrices and better preserves the training dynamics of full-parameter fine-tuning, in contrast to existing low-rank approaches such as LoRA and GaLore. Empirically, MLorc consistently outperforms other memory-efficient training methods, matches or even exceeds the performance of full fine-tuning with a small rank (e.g., $r=4$), and generalizes well across different optimizers -- all while not compromising time or memory efficiency. Furthermore, we provide a theoretical guarantee for its convergence under reasonable assumptions.
Authors: Arij Riabi, Beno\^it Sagot, Djam\'e Seddah
Abstract: Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high-resource languages. Building language models and, more generally, NLP systems for non-standardized and low-resource languages remains a challenging task. In this work, we focus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi, found mostly on social media and messaging communication. In this low-resource scenario with data displaying a high level of variability, we compare the downstream performance of a character-based language model on part-of-speech tagging and dependency parsing to that of monolingual and multilingual models. We show that a character-based model trained on only 99k sentences of NArabizi and fined-tuned on a small treebank of this language leads to performance close to those obtained with the same architecture pre-trained on large multilingual and monolingual models. Confirming these results a on much larger data set of noisy French user-generated content, we argue that such character-based language models can be an asset for NLP in low-resource and high language variability set-tings.
Authors: Lezhi Tan, Jianfeng Lu
Abstract: Sampling a probability distribution with known likelihood is a fundamental task in computational science and engineering. Aiming at multimodality, we propose a new sampling method that takes advantage of both birth-death process and exploration component. The main idea of this method is look before you leap. We keep two sets of samplers, one at warmer temperature and one at original temperature. The former one serves as pioneer in exploring new modes and passing useful information to the other, while the latter one samples the target distribution after receiving the information. We derive a mean-field limit and show how the exploration component accelerates the sampling process. Moreover, we prove exponential asymptotic convergence under mild assumption. Finally, we test on experiments from previous literature and compare our methodology to previous ones.
Authors: Pengkun Yang, Jingzhao Zhang
Abstract: We study the scaling of classification error rates with respect to the size of the training dataset. In contrast to classical results where rates are minimax optimal for a problem class, this work starts with the empirical observation that, even for a fixed data distribution, the error scaling can have \emph{diverse} rates across different ranges of sample size. To understand when and why the error rate is non-uniform, we theoretically analyze nearest neighbor classifiers. We show that an error scaling law can have fine-grained rates: in the early phase, the test error depends polynomially on the data dimension and decreases fast; whereas in the later phase, the error depends exponentially on the data dimension and decreases slowly. Our analysis highlights the complexity of the data distribution in determining the test error. When the data are distributed benignly, we show that the generalization error of nearest neighbor classifier can depend polynomially, instead of exponentially, on the data dimension.
Authors: Estelle Ruellan, Masarah Paquet-Clouston, Sebastian Garcia
Abstract: Ransomware-as-a-service (RaaS) is increasing the scale and complexity of ransomware attacks. Understanding the internal operations behind RaaS has been a challenge due to the illegality of such activities. The recent chat leak of the Conti RaaS operator, one of the most infamous ransomware operators on the international scene, offers a key opportunity to better understand the inner workings of such organizations. This paper analyzes the main topic discussions in the Conti chat leak using machine learning techniques such as Natural Language Processing (NLP) and Latent Dirichlet Allocation (LDA), as well as visualization strategies. Five discussion topics are found: 1) Business, 2) Technical, 3) Internal tasking/Management, 4) Malware, and 5) Customer Service/Problem Solving. Moreover, the distribution of topics among Conti members shows that only 4% of individuals have specialized discussions while almost all individuals (96%) are all-rounders, meaning that their discussions revolve around the five topics. The results also indicate that a significant proportion of Conti discussions are non-tech related. This study thus highlights that running such large RaaS operations requires a workforce skilled beyond technical abilities, with individuals involved in various tasks, from management to customer service or problem solving. The discussion topics also show that the organization behind the Conti RaaS oper5086933ator shares similarities with a large firm. We conclude that, although RaaS represents an example of specialization in the cybercrime industry, only a few members are specialized in one topic, while the rest runs and coordinates the RaaS operation.
Authors: Xinyue Zheng, Haowei Lin, Kaichen He, Zihao Wang, Zilong Zheng, Yitao Liang
Abstract: Developing AI agents capable of interacting with open-world environments to solve diverse tasks is a compelling challenge. However, evaluating such open-ended agents remains difficult, with current benchmarks facing scalability limitations. To address this, we introduce Minecraft Universe (MCU), a comprehensive evaluation framework set within the open-world video game Minecraft. MCU incorporates three key components: (1) an expanding collection of 3,452 composable atomic tasks that encompasses 11 major categories and 41 subcategories of challenges; (2) a task composition mechanism capable of generating infinite diverse tasks with varying difficulty; and (3) a general evaluation framework that achieves 91.5\% alignment with human ratings for open-ended task assessment. Empirical results reveal that even state-of-the-art foundation agents struggle with the increasing diversity and complexity of tasks. These findings highlight the necessity of MCU as a robust benchmark to drive progress in AI agent development within open-ended environments. Our evaluation code and scripts are available at https://github.com/CraftJarvis/MCU.
Authors: Shangdi Yu, Joshua Engels, Yihao Huang, Julian Shun
Abstract: This paper studies density-based clustering of point sets. These methods use dense regions of points to detect clusters of arbitrary shapes. In particular, we study variants of density peaks clustering, a popular type of algorithm that has been shown to work well in practice. Our goal is to cluster large high-dimensional datasets, which are prevalent in practice. Prior solutions are either sequential, and cannot scale to large data, or are specialized for low-dimensional data. This paper unifies the different variants of density peaks clustering into a single framework, PECANN, by abstracting out several key steps common to this class of algorithms. One such key step is to find nearest neighbors that satisfy a predicate function, and one of the main contributions of this paper is an efficient way to do this predicate search using graph-based approximate nearest neighbor search (ANNS). To provide ample parallelism, we propose a doubling search technique that enables points to find an approximate nearest neighbor satisfying the predicate in a small number of rounds. Our technique can be applied to many existing graph-based ANNS algorithms, which can all be plugged into PECANN. We implement five clustering algorithms with PECANN and evaluate them on synthetic and real-world datasets with up to 1.28 million points and up to 1024 dimensions on a 30-core machine with two-way hyper-threading. Compared to the state-of-the-art FASTDP algorithm for high-dimensional density peaks clustering, which is sequential, our best algorithm is 45x-734x faster while achieving competitive ARI scores. Compared to the state-of-the-art parallel DPC-based algorithm, which is optimized for low dimensions, we show that PECANN is two orders of magnitude faster. As far as we know, our work is the first to evaluate DPC variants on large high-dimensional real-world image and text embedding datasets.
Authors: Mariano V. Ntrougkas, Nikolaos Gkalelis, Vasileios Mezaris
Abstract: The development and adoption of Vision Transformers and other deep-learning architectures for image classification tasks has been rapid. However, the "black box" nature of neural networks is a barrier to adoption in applications where explainability is essential. While some techniques for generating explanations have been proposed, primarily for Convolutional Neural Networks, adapting such techniques to the new paradigm of Vision Transformers is non-trivial. This paper presents T-TAME, Transformer-compatible Trainable Attention Mechanism for Explanations, a general methodology for explaining deep neural networks used in image classification tasks. The proposed architecture and training technique can be easily applied to any convolutional or Vision Transformer-like neural network, using a streamlined training approach. After training, explanation maps can be computed in a single forward pass; these explanation maps are comparable to or outperform the outputs of computationally expensive perturbation-based explainability techniques, achieving SOTA performance. We apply T-TAME to three popular deep learning classifier architectures, VGG-16, ResNet-50, and ViT-B-16, trained on the ImageNet dataset, and we demonstrate improvements over existing state-of-the-art explainability methods. A detailed analysis of the results and an ablation study provide insights into how the T-TAME design choices affect the quality of the generated explanation maps.
Authors: Pengzhan Jin
Abstract: We point out that (continuous or discontinuous) piecewise linear functions on a convex polytope mesh can be represented by two-hidden-layer ReLU neural networks in a weak sense. In addition, the numbers of neurons of the two hidden layers required to weakly represent are accurately given based on the numbers of polytopes and hyperplanes involved in this mesh. The results naturally hold for constant and linear finite element functions. Such weak representation establishes a bridge between shallow ReLU neural networks and finite element functions, and leads to a perspective for analyzing approximation capability of ReLU neural networks in $L^p$ norm via finite element functions. Moreover, we discuss the strict representation for tensor finite element functions via the recent tensor neural networks.
Authors: Philip Charles, Deep Ray
Abstract: Entropy conditions play a crucial role in the extraction of a physically relevant solution for systems of conservation laws, thus motivating the construction of entropy stable schemes that satisfy a discrete analogue of such conditions. TeCNO schemes (Fjordholm et al. 2012) form a class of arbitrary high-order entropy stable finite difference solvers, which require specialized reconstruction algorithms satisfying the sign property at each cell interface. Third-order weighted essentially non-oscillatory (WENO) schemes called SP-WENO (Fjordholm and Ray, 2016) and SP-WENOc (Ray, 2018) have been designed to satisfy the sign property. However, these WENO algorithms can perform poorly near shocks, with the numerical solutions exhibiting large spurious oscillations. In the present work, we propose a variant of the SP-WENO, termed as Deep Sign-Preserving WENO (DSP-WENO), where a neural network is trained to learn the WENO weighting strategy. The sign property and third-order accuracy are strongly imposed in the algorithm, which constrains the WENO weight selection region to a convex polygon. Thereafter, a neural network is trained to select the WENO weights from this convex region with the goal of improving the shock-capturing capabilities without sacrificing the rate of convergence in smooth regions. The proposed synergistic approach retains the mathematical framework of the TeCNO scheme while integrating deep learning to remedy the computational issues of the WENO-based reconstruction. We present several numerical experiments to demonstrate the significant improvement with DSP-WENO over the existing variants of WENO satisfying the sign property.
Authors: Ning Zhang, Xiaowen Dong, Mihai Cucuringu
Abstract: Graph clustering is a fundamental task in unsupervised learning with broad real-world applications. While spectral clustering methods for undirected graphs are well-established and guided by a minimum cut optimization consensus, their extension to directed graphs remains relatively underexplored due to the additional complexity introduced by edge directions. In this paper, we leverage statistical inference on stochastic block models to guide the development of a spectral clustering algorithm for directed graphs. Specifically, we study the maximum likelihood estimation under a widely used directed stochastic block model, and derive a global objective function that aligns with the underlying community structure. We further establish a theoretical upper bound on the misclustering error of its spectral relaxation, and based on this relaxation, introduce a novel, self-adaptive spectral clustering method for directed graphs. Extensive experiments on synthetic and real-world datasets demonstrate significant performance gains over existing baselines.
Authors: Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, Yuandong Tian
Abstract: Large Language Models (LLMs) are vulnerable to jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search for adversarial prompts, whereas automatic adversarial prompt generation often leads to semantically meaningless attacks that do not scale well. In this paper, we present a novel method that uses another LLM, called AdvPrompter, to generate human-readable adversarial prompts in seconds. AdvPrompter, which is trained using an alternating optimization algorithm, generates suffixes that veil the input instruction without changing its meaning, such that the TargetLLM is lured to give a harmful response. Experimental results on popular open source TargetLLMs show highly competitive results on the AdvBench and HarmBench datasets, that also transfer to closed-source black-box LLMs. We also show that training on adversarial suffixes generated by AdvPrompter is a promising strategy for improving the robustness of LLMs to jailbreaking attacks.
Authors: Tim Gyger, Reinhard Furrer, Fabio Sigrist
Abstract: Gaussian processes are flexible probabilistic regression models which are widely used in statistics and machine learning. However, a drawback is their limited scalability to large data sets. To alleviate this, full-scale approximations (FSAs) combine predictive process methods and covariance tapering, thus approximating both global and local structures. We show how iterative methods can be used to reduce computational costs in calculating likelihoods, gradients, and predictive distributions with FSAs. In particular, we introduce a novel preconditioner and show theoretically and empirically that it accelerates the conjugate gradient method's convergence speed and mitigates its sensitivity with respect to the FSA parameters and the eigenvalue structure of the original covariance matrix, and we demonstrate empirically that it outperforms a state-of-the-art pivoted Cholesky preconditioner. Furthermore, we introduce an accurate and fast way to calculate predictive variances using stochastic simulation and iterative methods. In addition, we show how our newly proposed FITC preconditioner can also be used in iterative methods for Vecchia approximations. In our experiments, it outperforms existing state-of-the-art preconditioners for Vecchia approximations. All methods are implemented in a free C++ software library with high-level Python and R packages.
Authors: Xiang Li, Zebang Shen, Liang Zhang, Niao He
Abstract: Continuous-time approximation of Stochastic Gradient Descent (SGD) is a crucial tool to study its escaping behaviors from stationary points. However, existing stochastic differential equation (SDE) models fail to fully capture these behaviors, even for simple quadratic objectives. Built on a novel stochastic backward error analysis framework, we derive the Hessian-Aware Stochastic Modified Equation (HA-SME), an SDE that incorporates Hessian information of the objective function into both its drift and diffusion terms. Our analysis shows that HA-SME achieves the order-best approximation error guarantee among existing SDE models in the literature, while significantly reducing the dependence on the smoothness parameter of the objective. Empirical experiments on neural network-based loss functions further validate this improvement. Further, for quadratic objectives, under mild conditions, HA-SME is proved to be the first SDE model that recovers exactly the SGD dynamics in the distributional sense. Consequently, when the local landscape near a stationary point can be approximated by quadratics, HA-SME provides a more precise characterization of the local escaping behaviors of SGD. With the enhanced approximation guarantee, we further conduct an escape time analysis using HA-SME, showcasing how it can be employed to analytically study the escaping behavior of SGD for general function classes.
Authors: Devichand Budagam, Azamat Zhanatuly Imanbayev, Iskander Rafailovich Akhmetov, Aleksandr Sinitca, Sergey Antonov, Dmitrii Kaplun
Abstract: Teeth segmentation and recognition play a vital role in a variety of dental applications and diagnostic procedures. The integration of deep learning models has facilitated the development of precise and automated segmentation methods. Although prior research has explored teeth segmentation, not many methods have successfully performed tooth segmentation and detection simultaneously. This study presents UFBA-425, a dental dataset derived from the UFBA-UESC dataset, featuring bounding box and polygon annotations for 425 panoramic dental X-rays. Additionally, this work introduces OralBBNet, an architecture featuring distinct segmentation and detection heads as U-Net and YOLOv8, respectively. OralBBNet is designed to improve the accuracy and robustness of tooth classification and segmentation on panoramic X-rays by leveraging the complementary strengths of U-Net and YOLOv8. Our approach achieved a 1-3% improvement in mean average precision (mAP) for teeth detection compared to existing techniques and a 15-20% improvement in the dice score for teeth segmentation over U-Net over various tooth categories and 2-4% improvement in the dice score when compared with other segmentation architectures. The results of this study establish a foundation for the wider implementation of object detection models in dental diagnostics.
Authors: Shester Gueuwou, Xiaodan Du, Greg Shakhnarovich, Karen Livescu
Abstract: A persistent challenge in sign language video processing, including the task of sign to written language translation, is how we learn representations of sign language in an effective and efficient way that preserves the important attributes of these languages, while remaining invariant to irrelevant visual differences. Informed by the nature and linguistics of signed languages, our proposed method focuses on just the most relevant parts in a signing video: the face, hands and body pose of the signer. However, instead of fully relying on pose estimation from off-the-shelf pose tracking models, which have inconsistent performance for hands and faces, we propose to learn a representation of the complex handshapes and facial expressions of sign languages in a self-supervised fashion. Our approach is based on learning from individual frames (rather than video sequences) and is therefore much more efficient than prior work on sign language pre-training. Compared to a recent model that established a new state of the art in sign language translation on the How2Sign dataset, our approach yields similar translation performance, using less than 3\% of the compute.
Authors: Mark K. Transtrum, Gus L. W. Hart, Tyler J. Jarvis, Jared P. Whitehead
Abstract: A central problem in data science is to use potentially noisy samples of an unknown function to predict values for unseen inputs. In classical statistics, predictive error is understood as a trade-off between the bias and the variance that balances model simplicity with its ability to fit complex functions. However, over-parameterized models exhibit counterintuitive behaviors, such as "double descent" in which models of increasing complexity exhibit decreasing generalization error. Others may exhibit more complicated patterns of predictive error with multiple peaks and valleys. Neither double descent nor multiple descent phenomena are well explained by the bias-variance decomposition. We introduce a novel decomposition that we call the generalized aliasing decomposition (GAD) to explain the relationship between predictive performance and model complexity. The GAD decomposes the predictive error into three parts: 1) model insufficiency, which dominates when the number of parameters is much smaller than the number of data points, 2) data insufficiency, which dominates when the number of parameters is much greater than the number of data points, and 3) generalized aliasing, which dominates between these two extremes. We demonstrate the applicability of the GAD to diverse applications, including random feature models from machine learning, Fourier transforms from signal processing, solution methods for differential equations, and predictive formation enthalpy in materials discovery. Because key components of the GAD can be explicitly calculated from the relationship between model class and samples without seeing any data labels, it can answer questions related to experimental design and model selection before collecting data or performing experiments. We further demonstrate this approach on several examples and discuss implications for predictive modeling and data science.
Authors: Nilotpal Kakati, Etienne Dreyer, Eilam Gross
Abstract: In preparation for Higgs factories and energy-frontier facilities, future colliders are moving toward high-granularity calorimeters to improve reconstruction quality. However, the cost and construction complexity of such detectors is substantial, making software-based approaches like super-resolution an attractive alternative. This study explores integrating super-resolution techniques into an LHC-like reconstruction pipeline to effectively enhance calorimeter granularity and suppress noise. We find that this software preprocessing step significantly improves reconstruction quality without physical changes to the detector. To demonstrate its impact, we propose a novel transformer-based particle flow model that offers improved particle reconstruction quality and interpretability. Our results demonstrate that super-resolution can be readily applied at collider experiments.
Authors: Francesco Verdini, Pierfrancesco Melucci, Stefano Perna, Francesco Cariaggi, Marco Gaido, Sara Papi, Szymon Mazurek, Marek Kasztelnik, Luisa Bentivogli, S\'ebastien Brati\`eres, Paolo Merialdo, Simone Scardapane
Abstract: The remarkable performance achieved by Large Language Models (LLM) has driven research efforts to leverage them for a wide range of tasks and input modalities. In speech-to-text (S2T) tasks, the emerging solution consists of projecting the output of the encoder of a Speech Foundational Model (SFM) into the LLM embedding space through an adapter module. However, no work has yet investigated how much the downstream-task performance depends on each component (SFM, adapter, LLM) nor whether the best design of the adapter depends on the chosen SFM and LLM. To fill this gap, we evaluate the combination of 5 adapter modules, 2 LLMs (Mistral and Llama), and 2 SFMs (Whisper and SeamlessM4T) on two widespread S2T tasks, namely Automatic Speech Recognition and Speech Translation. Our results demonstrate that the SFM plays a pivotal role in downstream performance, while the adapter choice has moderate impact and depends on the SFM and LLM.
Authors: Sina Mavali, Jonas Ricker, David Pape, Asja Fischer, Lea Sch\"onherr
Abstract: The rapid advancement of Generative Artificial Intelligence (GenAI) capabilities is accompanied by a concerning rise in its misuse. In particular the generation of credible misinformation in the form of images poses a significant threat to the public trust in democratic processes. Consequently, there is an urgent need to develop tools to reliably distinguish between authentic and AI-generated content. The majority of detection methods are based on neural networks that are trained to recognize forensic artifacts. In this work, we demonstrate that current state-of-the-art classifiers are vulnerable to adversarial examples under real-world conditions. Through extensive experiments, comprising four detection methods and five attack algorithms, we show that an attacker can dramatically decrease classification performance, without internal knowledge of the detector's architecture. Notably, most attacks remain effective even when images are degraded during the upload to, e.g., social media platforms. In a case study, we demonstrate that these robustness challenges are also found in commercial tools by conducting black-box attacks on HIVE, a proprietary online GenAI media detector. In addition, we evaluate the robustness of using generated features of a robust pre-trained model and showed that this increases the robustness, while not reaching the performance on benign inputs. These results, along with the increasing potential of GenAI to erode public trust, underscore the need for more research and new perspectives on methods to prevent its misuse.
Authors: Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
Abstract: Robust, diverse, and challenging cultural knowledge benchmarks are essential for measuring our progress towards making LMs that are helpful across diverse cultures. We introduce CulturalBench: a set of 1,696 human-written and human-verified questions to assess LMs' cultural knowledge, covering 45 global regions including underrepresented ones like Bangladesh, Zimbabwe, and Peru. Questions are each verified by five independent annotators and span 17 diverse topics ranging from food preferences to greeting etiquette. We construct CulturalBench using methods inspired by Human-AI Red-Teaming. Compared to human performance (92.4% accuracy), the hard version of CulturalBench is challenging even for the best-performing frontier LMs, ranging from 28.7% to 61.5% in accuracy. We find that LMs often struggle with tricky questions that have multiple correct answers (e.g., What utensils do the Chinese usually use?), revealing a tendency to overfit to a single answer. Our results indicate that GPT-4o substantially outperform other models across cultures, besting local providers (e.g., Mistral on European culture and DeepSeek on Chinese culture). Across the board, models under-perform on questions related to North Africa, South America and Middle East.
Authors: Eric Elmoznino, Thomas Jiralerspong, Yoshua Bengio, Guillaume Lajoie
Abstract: Compositionality is believed to be fundamental to intelligence. In humans, it underlies the structure of thought, language, and higher-level reasoning. In AI, compositional representations can enable a powerful form of out-of-distribution generalization, in which a model systematically adapts to novel combinations of known concepts. However, while we have strong intuitions about what compositionality is, we lack satisfying formal definitions for it that are measurable and mathematical. Here, we propose such a definition, which we call representational compositionality, that accounts for and extends our intuitions about compositionality. The definition is conceptually simple, quantitative, grounded in algorithmic information theory, and applicable to any representation. Intuitively, representational compositionality states that a compositional representation satisfies three properties. First, it must be expressive. Second, it must be possible to re-describe the representation as a function of discrete symbolic sequences with re-combinable parts, analogous to sentences in natural language. Third, the function that relates these symbolic sequences to the representation, analogous to semantics in natural language, must be simple. Through experiments on both synthetic and real world data, we validate our definition of compositionality and show how it unifies disparate intuitions from across the literature in both AI and cognitive science. We also show that representational compositionality, while theoretically intractable, can be readily estimated using standard deep learning tools. We hope that our definition can inspire the design of novel, theoretically-driven models that better capture the mechanisms of compositional thought. We make our code available at https://github.com/EricElmoznino/complexity_compositionality.
URLs: https://github.com/EricElmoznino/complexity_compositionality.
Authors: Lin Wang, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Zhitao Zhang
Abstract: Multimodal conversation, a crucial form of human communication, carries rich emotional content, making the exploration of the causes of emotions within it a research endeavor of significant importance. However, existing research on the causes of emotions typically employs an utterance selection method within a single textual modality to locate causal utterances. This approach remains limited to coarse-grained assessments, lacks nuanced explanations of emotional causation, and demonstrates inadequate capability in identifying multimodal emotional triggers. Therefore, we introduce a task-\textbf{Multimodal Emotion Cause Explanation in Conversation (MECEC)}. This task aims to generate a summary based on the multimodal context of conversations, clearly and intuitively describing the reasons that trigger a given emotion. To adapt to this task, we develop a new dataset (ECEM) based on the MELD dataset. ECEM combines video clips with detailed explanations of character emotions, helping to explore the causal factors behind emotional expression in multimodal conversations. A novel approach, FAME-Net, is further proposed, that harnesses the power of Large Language Models (LLMs) to analyze visual data and accurately interpret the emotions conveyed through facial expressions in videos. By exploiting the contagion effect of facial emotions, FAME-Net effectively captures the emotional causes of individuals engaged in conversations. Our experimental results on the newly constructed dataset show that FAME-Net outperforms several excellent baselines. Code and dataset are available at https://github.com/3222345200/FAME-Net.
Authors: Gabriele Oliaro, Zhihao Jia, Daniel Campos, Aurick Qiao
Abstract: Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present unique workload characteristics: instead of diverse independent requests, agentic frameworks typically submit repetitive inference requests, such as multi-agent pipelines performing similar subtasks or self-refinement loops iteratively enhancing outputs. These workloads result in long and highly predictable sequences, which current speculative decoding methods do not effectively exploit. To address this gap, we introduce \emph{SuffixDecoding}, a novel method that utilizes efficient suffix trees to cache long token sequences from prompts and previous outputs. By adaptively speculating more tokens when acceptance likelihood is high and fewer when it is low, SuffixDecoding effectively exploits opportunities for longer speculations while conserving computation when those opportunities are limited. Evaluations on agentic benchmarks, including SWE-Bench and Text-to-SQL, demonstrate that SuffixDecoding achieves speedups of up to 5.3$\times$, outperforming state-of-the-art methods -- 2.8$\times$ faster than model-based approaches like EAGLE-2/3 and 1.9$\times$ faster than model-free approaches such as Token Recycling. SuffixDecoding is open-sourced at https://github.com/snowflakedb/ArcticInference.
Authors: Antonio De Santis, Riccardo Campi, Matteo Bianchi, Marco Brambilla
Abstract: Convolutional Neural Networks (CNNs) have seen significant performance improvements in recent years. However, due to their size and complexity, they function as black-boxes, leading to transparency concerns. State-of-the-art saliency methods generate local explanations that highlight the area in the input image where a class is identified but cannot explain how a concept of interest contributes to the prediction, which is essential for bias mitigation. On the other hand, concept-based methods, such as TCAV (Testing with Concept Activation Vectors), provide insights into how sensitive is the network to a concept, but cannot compute its attribution in a specific prediction nor show its location within the input image. This paper introduces a novel post-hoc explainability framework, Visual-TCAV, which aims to bridge the gap between these methods by providing both local and global explanations for CNN-based image classification. Visual-TCAV uses Concept Activation Vectors (CAVs) to generate saliency maps that show where concepts are recognized by the network. Moreover, it can estimate the attribution of these concepts to the output of any class using a generalization of Integrated Gradients. This framework is evaluated on popular CNN architectures, with its validity further confirmed via experiments where ground truth for explanations is known, and a comparison with TCAV. Our code is available at https://github.com/DataSciencePolimi/Visual-TCAV.
Authors: Felix Divo, Eric Endress, Kevin Endler, Kristian Kersting, Devendra Singh Dhami
Abstract: Company fundamentals are key to assessing companies' financial and overall success and stability. Forecasting them is important in multiple fields, including investing and econometrics. While statistical and contemporary machine learning methods have been applied to many time series tasks, there is a lack of comparison of these approaches on this particularly challenging data regime. To this end, we try to bridge this gap and thoroughly evaluate the theoretical properties and practical performance of 24 deterministic and probabilistic company fundamentals forecasting models on real company data. We observe that deep learning models provide superior forecasting performance to classical models, in particular when considering uncertainty estimation. To validate the findings, we compare them to human analyst expectations and find that their accuracy is comparable to the automatic forecasts. We further show how these high-quality forecasts can benefit automated stock allocation. We close by presenting possible ways of integrating domain experts to further improve performance and increase reliability.
Authors: Reece O'Mahoney, Alexander L. Mitchell, Wanming Yu, Ingmar Posner, Ioannis Havoutis
Abstract: We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training. This is the first framework to apply classifier-free guided diffusion to quadruped locomotion and demonstrate its efficacy by extracting goal-conditioned behaviour from an originally unlabelled dataset. We show that these capabilities are compatible with a multi-skill policy and can be applied with little modification and minimal compute overhead, i.e., running entirely on the robots onboard CPU. We verify the validity of our approach with hardware experiments on the ANYmal quadruped platform.
Authors: Shuntaro Okada, Kenji Doi, Ryota Yoshihashi, Hirokatsu Kataoka, Tomohiro Tanaka
Abstract: We propose a general approach to optimize noise schedules for training and sampling in diffusion models. Our approach optimizes the noise schedules to ensure a constant rate of change in the probability distribution of diffused data throughout the diffusion process. Any distance metric for measuring the probability-distributional change is applicable to our approach, and we introduce three distance metrics. We evaluated the effectiveness of our approach on unconditional and class-conditional image-generation tasks using the LSUN (Horse, Bedroom, Church), ImageNet, FFHQ, and CIFAR10 datasets. Through extensive experiments, we confirmed that our approach broadly improves the performance of pixel-space and latent-space diffusion models regardless of the dataset, sampler, and number of function evaluations ranging from 5 to 250. Notably, by using our approach for optimizing both training and sampling schedules, we achieved a state-of-the-art FID score of 2.03 without sacrificing mode coverage on LSUN Horse 256 $\times$ 256.
Authors: Feng Chen, Chenhui Gou, Jing Liu, Yang Yang, Zhaoyang Li, Jiyuan Zhang, Zhenbang Sun, Bohan Zhuang, Qi Wu
Abstract: As multimodal large language models (MLLMs) advance rapidly, rigorous evaluation has become essential, providing further guidance for their development. In this work, we focus on a unified and robust evaluation of \textbf{vision perception} abilities, the foundational skill of MLLMs. We find that existing perception benchmarks, each focusing on different question types, domains, and evaluation metrics, introduce significant evaluation variance, complicating comprehensive assessments of perception abilities when relying on any single benchmark. To address this, we introduce \textbf{AbilityLens}, a unified benchmark designed to evaluate MLLMs in six key perception abilities (ranging from counting, OCR, to understanding structural data), focusing on both accuracy and stability, with each ability encompassing diverse types of questions, domains, and metrics. With the assistance of AbilityLens, we: (1) identify the strengths and weaknesses of current main-stream MLLMs, highlighting stability patterns and revealing a notable performance gap between state-of-the-art open-source and closed-source models; (2) uncover interesting ability conflict and early convergence phenomena during MLLM training; (3) reveal the primary reason of ability conflict is data mixing ratio and LLM model size; and (4) discuss the effectiveness of some straightforward strategies \eg, fine-tuning and model merging, to solve the ability conflict. The benchmark and online leaderboard is released in https://github.com/Chenfeng1271/AbilityLens.
Authors: Afrah Farea, Mustafa Serdar Celebi
Abstract: We investigate learnable activation functions in Physics-Informed Neural Networks (PINNs) for solving Partial Differential Equations (PDEs), comparing traditional Multilayer Perceptrons (MLPs) with fixed and trainable activations against Kolmogorov-Arnold Networks (KANs) that employ learnable basis functions. While PINNs effectively incorporate physical laws into the learning process, they suffer from convergence and spectral bias problems, which limit their applicability to problems with rapid oscillations or sharp transitions. In this work, we study and evaluate various activation and basis functions across diverse PDEs, including oscillatory, nonlinear wave, mixed-physics, and fluid dynamics problems. Using empirical Neural Tangent Kernel (NTK) analysis and Hessian eigenvalue decomposition, we assess convergence behavior, stability, and high-frequency approximation capacity. While KANs offer improved expressivity for capturing complex, high-frequency PDE solutions, they introduce new optimization challenges, especially in deeper networks. Our findings show that KANs face a curse of functional dimensionality, creating intractable optimization landscapes in deeper networks. Low spectral bias alone does not guarantee good performance; adaptive spectral bias approaches such as B-splines achieve optimal results by balancing global stability with local high-frequency resolution. Different PDE types require tailored strategies: smooth global activation functions excel for wave phenomena, while local adaptive activation functions suit problems with sharp transitions.
Authors: Sebastian Forster, Antonis Skarlatos
Abstract: Given points from an arbitrary metric space and a sequence of point updates sent by an adversary, what is the minimum recourse per update (i.e., the minimum number of changes needed to the set of centers after an update), in order to maintain a constant-factor approximation to a $k$-clustering problem? This question has received attention in recent years under the name consistent clustering. Previous works by Lattanzi and Vassilvitskii [ICLM '17] and Fichtenberger, Lattanzi, Norouzi-Fard, and Svensson [SODA '21] studied $k$-clustering objectives, including the $k$-center and the $k$-median objectives, under only point insertions. In this paper we study the $k$-center objective in the fully dynamic setting, where the update is either a point insertion or a point deletion. Before our work, {\L}\k{a}cki, Haeupler, Grunau, Rozho\v{n}, and Jayaram [SODA '24] gave a deterministic fully dynamic constant-factor approximation algorithm for the $k$-center objective with worst-case recourse of $2$ per update. In this work, we prove that the $k$-center clustering problem admits optimal recourse bounds by developing a deterministic fully dynamic constant-factor approximation algorithm with worst-case recourse of $1$ per update. Moreover our algorithm performs simple choices based on light data structures, and thus is arguably more direct and faster than the previous one which uses a sophisticated combinatorial structure. Additionally, we develop a new deterministic decremental algorithm and a new deterministic incremental algorithm, both of which maintain a $6$-approximate $k$-center solution with worst-case recourse of $1$ per update. Our incremental algorithm improves over the $8$-approximation algorithm by Charikar, Chekuri, Feder, and Motwani [STOC '97]. Finally, we remark that since all three of our algorithms are deterministic, they work against an adaptive adversary.
Authors: George Webber, Yuya Mizuno, Oliver D. Howes, Alexander Hammers, Andrew P. King, Andrew J. Reader
Abstract: Medical image reconstruction with pre-trained score-based generative models (SGMs) has advantages over other existing state-of-the-art deep-learned reconstruction methods, including improved resilience to different scanner setups and advanced image distribution modeling. SGM-based reconstruction has recently been applied to simulated positron emission tomography (PET) datasets, showing improved contrast recovery for out-of-distribution lesions relative to the state-of-the-art. However, existing methods for SGM-based reconstruction from PET data suffer from slow reconstruction, burdensome hyperparameter tuning and slice inconsistency effects (in 3D). In this work, we propose a practical methodology for fully 3D reconstruction that accelerates reconstruction and reduces the number of critical hyperparameters by matching the likelihood of an SGM's reverse diffusion process to a current iterate of the maximum-likelihood expectation maximization algorithm. Using the example of low-count reconstruction from simulated [$^{18}$F]DPA-714 datasets, we show our methodology can match or improve on the NRMSE and SSIM of existing state-of-the-art SGM-based PET reconstruction while reducing reconstruction time and the need for hyperparameter tuning. We evaluate our methodology against state-of-the-art supervised and conventional reconstruction algorithms. Finally, we demonstrate a first-ever implementation of SGM-based reconstruction for real 3D PET data, specifically [$^{18}$F]DPA-714 data, where we integrate perpendicular pre-trained SGMs to eliminate slice inconsistency issues.
Authors: Jingyao Wang, Wenwen Qiang, Changwen Zheng, Fuchun Sun
Abstract: Fine-grained emotion recognition (FER) plays a vital role in various fields, such as disease diagnosis, personalized recommendations, and multimedia mining. However, existing FER methods face three key challenges in real-world applications: (i) they rely on large amounts of continuously annotated data to ensure accuracy since emotions are complex and ambiguous in reality, which is costly and time-consuming; (ii) they cannot capture the temporal heterogeneity caused by changing emotion patterns, because they usually assume that the temporal correlation within sampling periods is the same; (iii) they do not consider the spatial heterogeneity of different FER scenarios, that is, the distribution of emotion information in different data may have bias or interference. To address these challenges, we propose a Spatio-Temporal Fuzzy-oriented Multi-modal Meta-learning framework (ST-F2M). Specifically, ST-F2M first divides the multi-modal videos into multiple views, and each view corresponds to one modality of one emotion. Multiple randomly selected views for the same emotion form a meta-training task. Next, ST-F2M uses an integrated module with spatial and temporal convolutions to encode the data of each task, reflecting the spatial and temporal heterogeneity. Then it adds fuzzy semantic information to each task based on generalized fuzzy rules, which helps handle the complexity and ambiguity of emotions. Finally, ST-F2M learns emotion-related general meta-knowledge through meta-recurrent neural networks to achieve fast and robust fine-grained emotion recognition. Extensive experiments show that ST-F2M outperforms various state-of-the-art methods in terms of accuracy and model efficiency. In addition, we construct ablation studies and further analysis to explore why ST-F2M performs well.
Authors: Wei Liu, Junlong Li, Xiwen Zhang, Fan Zhou, Yu Cheng, Junxian He
Abstract: Self-evolving trainin--where models iteratively learn from their own outputs--has emerged as a key approach for complex reasoning tasks, addressing the scarcity of high-quality chain-of-thought data. However, its effectiveness in multimodal reasoning, a domain more intricate than text-only reasoning, remains underexplored, and the understanding of critical factors in this training paradigm remains limited. Furthermore, a central challenge for this training method is performance saturation, which impedes further improvements and scalability. Inspired by reinforcement learning (RL), in this paper, we reframe self-evolving training for multimodal reasoning through the lens of RL, identifying three pivotal factors: Training Method, Reward Model, and Prompt Variation. Through systematic analysis, we establish relatively optimal design principles that significantly enhance multimodal reasoning capabilities. Moreover, delving deeper into training dynamics, we uncover the roots of saturation and propose a new automatic balancing mechanism to mitigate this limitation. Building on these insights, we propose M-STAR (Multimodal Self-evolving Training for Reasoning), a framework that achieves consistent performance gains across models of varying sizes and diverse benchmarks. All resources are made publicly available at https://mstar-lmm.github.io.
Authors: Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, Chuning Tang, Congcong Wang, Dehao Zhang, Enming Yuan, Enzhe Lu, Fengxiang Tang, Flood Sung, Guangda Wei, Guokun Lai, Haiqing Guo, Han Zhu, Hao Ding, Hao Hu, Hao Yang, Hao Zhang, Haotian Yao, Haotian Zhao, Haoyu Lu, Haoze Li, Haozhen Yu, Hongcheng Gao, Huabin Zheng, Huan Yuan, Jia Chen, Jianhang Guo, Jianlin Su, Jianzhou Wang, Jie Zhao, Jin Zhang, Jingyuan Liu, Junjie Yan, Junyan Wu, Lidong Shi, Ling Ye, Longhui Yu, Mengnan Dong, Neo Zhang, Ningchen Ma, Qiwei Pan, Qucheng Gong, Shaowei Liu, Shengling Ma, Shupeng Wei, Sihan Cao, Siying Huang, Tao Jiang, Weihao Gao, Weimin Xiong, Weiran He, Weixiao Huang, Weixin Xu, Wenhao Wu, Wenyang He, Xianghui Wei, Xianqing Jia, Xingzhe Wu, Xinran Xu, Xinxing Zu, Xinyu Zhou, Xuehai Pan, Y. Charles, Yang Li, Yangyang Hu, Yangyang Liu, Yanru Chen, Yejie Wang, Yibo Liu, Yidao Qin, Yifeng Liu, Ying Yang, Yiping Bao, Yulun Du, Yuxin Wu, Yuzhi Wang, Zaida Zhou, Zhaoji Wang, Zhaowei Li, Zhen Zhu, Zheng Zhang, Zhexu Wang, Zhilin Yang, Zhiqi Huang, Zihao Huang, Ziyao Xu, Zonghan Yang, Zongyu Lin
Abstract: Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of artificial intelligence, with the promise that large language models (LLMs) can scale their training data by learning to explore with rewards. However, prior published work has not produced competitive results. In light of this, we report on the training practice of Kimi k1.5, our latest multi-modal LLM trained with RL, including its RL training techniques, multi-modal data recipes, and infrastructure optimization. Long context scaling and improved policy optimization methods are key ingredients of our approach, which establishes a simplistic, effective RL framework without relying on more complex techniques such as Monte Carlo tree search, value functions, and process reward models. Notably, our system achieves state-of-the-art reasoning performance across multiple benchmarks and modalities -- e.g., 77.5 on AIME, 96.2 on MATH 500, 94-th percentile on Codeforces, 74.9 on MathVista -- matching OpenAI's o1. Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e.g., 60.8 on AIME, 94.6 on MATH500, 47.3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3.5 by a large margin (up to +550%).
Authors: Edoardo Cetin, Tianyu Zhao, Yujin Tang
Abstract: We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve monotonically increasing accuracy, directly translating to improved performance across downstream tasks. Furthermore, our finetuned models can expertly answer questions on specific topics by integrating powerful guidance techniques, and autonomously determine the compute required for a given problem by leveraging adaptive ODE solvers. Our method is universally applicable to any foundation model pre-trained with a cross-entropy loss and does not modify any of its original weights, fully preserving its strong single-step generation capabilities. We show our method is more effective and fully compatible with traditional finetuning approaches, introducing an orthogonal new direction to unify the strengths of the autoregressive and diffusion frameworks.
Authors: Oscar Smee, Fred Roosta, Stephen J. Wright
Abstract: Gradient descent is the primary workhorse for optimizing large-scale problems in machine learning. However, its performance is highly sensitive to the choice of the learning rate. A key limitation of gradient descent is its lack of natural scaling, which often necessitates expensive line searches or heuristic tuning to determine an appropriate step size. In this paper, we address this limitation by incorporating Hessian information to scale the gradient direction. By accounting for the curvature of the function along the gradient, our adaptive, Hessian-aware scaling method ensures a local unit step size guarantee, even in nonconvex settings. Near a local minimum that satisfies the second-order sufficient conditions, our approach achieves linear convergence with a unit step size. We show that our method converges globally under a significantly weaker version of the standard Lipschitz gradient smoothness assumption. Even when Hessian information is inexact, the local unit step size guarantee and global convergence properties remain valid under mild conditions. Finally, we validate our theoretical results empirically on a range of convex and nonconvex machine learning tasks, showcasing the effectiveness of the approach.
Authors: Yuchen He, Chihao Zhang
Abstract: We study the problem of sampling from a $d$-dimensional distribution with density $p(x)\propto e^{-f(x)}$, which does not necessarily satisfy good isoperimetric conditions. Specifically, we show that for any $L,M$ satisfying $LM\ge d\ge 5$, $\epsilon\in \left(0,\frac{1}{32}\right)$, and any algorithm with query accesses to the value of $f(x)$ and $\nabla f(x)$, there exists an $L$-log-smooth distribution with second moment at most $M$ such that the algorithm requires $\left(\frac{LM}{d\epsilon}\right)^{\Omega(d)}$ queries to compute a sample whose distribution is within $\epsilon$ in total variation distance to the target distribution. We complement the lower bound with an algorithm requiring $\left(\frac{LM}{d\epsilon}\right)^{\mathcal{O}(d)}$ queries, thereby characterizing the tight (up to the constant in the exponent) query complexity for sampling from the family of non-log-concave distributions. Our results are in sharp contrast with the recent work of Huang et al. (COLT'24), where an algorithm with quasi-polynomial query complexity was proposed for sampling from a non-log-concave distribution when $M=\mathtt{poly}(d)$. Their algorithm works under the stronger condition that all distributions along the trajectory of the Ornstein-Uhlenbeck process, starting from the target distribution, are $\mathcal{O}(1)$-log-smooth. We investigate this condition and prove that it is strictly stronger than requiring the target distribution to be $\mathcal O(1)$-log-smooth. Additionally, we study this condition in the context of mixtures of Gaussians. Finally, we place our results within the broader theme of ``sampling versus optimization'', as studied in Ma et al. (PNAS'19). We show that for a wide range of parameters, sampling is strictly easier than optimization by a super-exponential factor in the dimension $d$.
Authors: Hidde Fokkema, Tim van Erven, Sara Magliacane
Abstract: Machine learning is a vital part of many real-world systems, but several concerns remain about the lack of interpretability, explainability and robustness of black-box AI systems. Concept Bottleneck Models (CBM) address some of these challenges by learning interpretable concepts from high-dimensional data, e.g. images, which are used to predict labels. An important issue in CBMs are spurious correlation between concepts, which effectively lead to learning "wrong" concepts. Current mitigating strategies have strong assumptions, e.g., they assume that the concepts are statistically independent of each other, or require substantial interaction in terms of both interventions and labels provided by annotators. In this paper, we describe a framework that provides theoretical guarantees on the correctness of the learned concepts and on the number of required labels, without requiring any interventions. Our framework leverages causal representation learning (CRL) methods to learn latent causal variables from high-dimensional observations in a unsupervised way, and then learns to align these variables with interpretable concepts with few concept labels. We propose a linear and a non-parametric estimator for this mapping, providing a finite-sample high probability result in the linear case and an asymptotic consistency result for the non-parametric estimator. We evaluate our framework in synthetic and image benchmarks, showing that the learned concepts have less impurities and are often more accurate than other CBMs, even in settings with strong correlations between concepts.
Authors: Matt Landreman, Jong Youl Choi, Caio Alves, Prasanna Balaprakash, R. Michael Churchill, Rory Conlin, Gareth Roberg-Clark
Abstract: Magnetic geometry has a significant effect on the level of turbulent transport in fusion plasmas. Here, we model and analyze this dependence using multiple machine learning methods and a dataset of > 200,000 nonlinear simulations of ion-temperature-gradient turbulence in diverse non-axisymmetric geometries. The dataset is generated using a large collection of both optimized and randomly generated stellarator equilibria. At fixed gradients, the turbulent heat flux varies between geometries by several orders of magnitude. Trends are apparent among the configurations with particularly high or low heat flux. Regression and classification techniques from machine learning are then applied to extract patterns in the dataset. Due to a symmetry of the gyrokinetic equation, the heat flux and regressions thereof should be invariant to translations of the raw features in the parallel coordinate, similar to translation invariance in computer vision applications. Multiple regression models including convolutional neural networks (CNNs) and decision trees can achieve reasonable predictive power for the heat flux in held-out test configurations, with highest accuracy for the CNNs. Using Spearman correlation, sequential feature selection, and Shapley values to measure feature importance, it is consistently found that the most important geometric lever on the heat flux is the flux surface compression in regions of bad curvature. The second most important feature relates to the magnitude of geodesic curvature. These two features align remarkably with surrogates that have been proposed based on theory, while the methods here allow a natural extension to more features for increased accuracy. The dataset, released with this publication, may also be used to test other proposed surrogates, and we find many previously published proxies do correlate well with both the heat flux and stability boundary.
Authors: Shengguang Wu, Fan-Yun Sun, Kaiyue Wen, Nick Haber
Abstract: Recent studies have shown that Large Vision-Language Models (VLMs) tend to neglect image content and over-rely on language-model priors, resulting in errors in visually grounded tasks and hallucinations. We hypothesize that this issue arises because existing VLMs are not explicitly trained to generate texts that are accurately grounded in fine-grained image details. To enhance visual feedback during VLM training, we propose S-VCO (Symmetrical Visual Contrastive Optimization), a novel finetuning objective that steers the model toward capturing important visual details and aligning them with corresponding text tokens. To further facilitate this detailed alignment, we introduce MVC, a paired image-text dataset built by automatically filtering and augmenting visual counterfactual data to challenge the model with hard contrastive cases involving Minimal Visual Contrasts. Experiments show that our method consistently improves VLM performance across diverse benchmarks covering various abilities and domains, achieving up to a 22% reduction in hallucinations, and significant gains in vision-centric and general tasks. Notably, these improvements become increasingly pronounced in benchmarks with higher visual dependency. In short, S-VCO offers a significant enhancement of VLM's visually-dependent task performance while retaining or even improving the model's general abilities. We opensource our code at https://s-vco.github.io/
URLs: https://s-vco.github.io/
Authors: Leena Mathur, Marian Qian, Paul Pu Liang, Louis-Philippe Morency
Abstract: Social reasoning abilities are crucial for AI systems to effectively interpret and respond to multimodal human communication and interaction within social contexts. We introduce SOCIAL GENOME, the first benchmark for fine-grained, grounded social reasoning abilities of multimodal models. SOCIAL GENOME contains 272 videos of interactions and 1,486 human-annotated reasoning traces related to inferences about these interactions. These traces contain 5,777 reasoning steps that reference evidence from visual cues, verbal cues, vocal cues, and external knowledge (contextual knowledge external to videos). SOCIAL GENOME is also the first modeling challenge to study external knowledge in social reasoning. SOCIAL GENOME computes metrics to holistically evaluate semantic and structural qualities of model-generated social reasoning traces. We demonstrate the utility of SOCIAL GENOME through experiments with state-of-the-art models, identifying performance gaps and opportunities for future research to improve the grounded social reasoning abilities of multimodal models.
Authors: Yang Yao, Xuan Tong, Ruofan Wang, Yixu Wang, Lujundong Li, Liang Liu, Yan Teng, Yingchun Wang
Abstract: Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to jailbreak attacks, their ability to generate more targeted and organized content can lead to greater harm. Although some studies claim that reasoning enables safer LRMs against existing LLM attacks, they overlook the inherent flaws within the reasoning process itself. To address this gap, we propose the first jailbreak attack targeting LRMs, exploiting their unique vulnerabilities stemming from the advanced reasoning capabilities. Specifically, we introduce a Chaos Machine, a novel component to transform attack prompts with diverse one-to-one mappings. The chaos mappings iteratively generated by the machine are embedded into the reasoning chain, which strengthens the variability and complexity and also promotes a more robust attack. Based on this, we construct the Mousetrap framework, which makes attacks projected into nonlinear-like low sample spaces with mismatched generalization enhanced. Also, due to the more competing objectives, LRMs gradually maintain the inertia of unpredictable iterative reasoning and fall into our trap. Success rates of the Mousetrap attacking o1-mini, Claude-Sonnet and Gemini-Thinking are as high as 96%, 86% and 98% respectively on our toxic dataset Trotter. On benchmarks such as AdvBench, StrongREJECT, and HarmBench, attacking Claude-Sonnet, well-known for its safety, Mousetrap can astonishingly achieve success rates of 87.5%, 86.58% and 93.13% respectively. Attention: This paper contains inappropriate, offensive and harmful content.
Authors: Boxuan Zhang, Ruqi Zhang
Abstract: Large language models (LLMs) excel in many tasks but struggle to accurately quantify uncertainty in their generated responses. This limitation makes it challenging to detect misinformation and ensure reliable decision-making. Existing uncertainty quantification (UQ) methods for LLMs are primarily prompt-wise rather than response-wise, often requiring multiple response samples, which incurs high computational costs. Moreover, LLMs have been shown to be overconfident, particularly when using reasoning steps to derive their answers. In this work, we propose CoT-UQ, a response-wise UQ framework that integrates LLMs' inherent reasoning capabilities through Chain-of-Thought (CoT) into the UQ process. CoT-UQ captures critical information during inference by extracting keywords from each reasoning step and assessing their importance to the final answer. This key reasoning information is then aggregated to produce a final uncertainty estimate. We conduct extensive experiments based on Llama Family with model sizes varying from 8B to 13B across logical and mathematical reasoning tasks. Experimental results demonstrate that CoT-UQ significantly outperforms existing UQ methods, achieving an average improvement of 5.9% AUROC compared to current UQ methods. The code is available at: https://github.com/ZBox1005/CoT-UQ.
Authors: Nathan Roll
Abstract: Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel, parameter-efficient framework for enhancing the multilingual capabilities of LLMs. Our method learns a set of trigger tokens for each language through a gradient-based search, identifying the input query's language and selecting the corresponding trigger tokens which are prepended to the prompt during inference. We perform experiments on two ~1 billion parameter models, with evaluations on the global MMLU benchmark across fifteen typologically and resource diverse languages, demonstrating accuracy gains of 3.7%-19.9% compared to naive and translation-pipeline baselines.
Authors: Yifan Zhang, Wenyu Du, Dongming Jin, Jie Fu, Zhi Jin
Abstract: Chain-of-thought (CoT) significantly enhances the performance of large language models (LLMs) across a wide range of tasks, and prior research shows that CoT can theoretically increase expressiveness. However, there is limited mechanistic understanding of the algorithms that Transformer+CoT can learn. Our key contributions are: (1) We evaluate the state tracking capabilities of Transformer+CoT and its variants, confirming the effectiveness of CoT. (2) Next, we identify the circuit (a subset of model components, responsible for tracking the world state), indicating that late-layer MLP neurons play a key role. We propose two metrics, compression and distinction, and show that the neuron sets for each state achieve nearly 100% accuracy, providing evidence of an implicit finite state automaton (FSA) embedded within the model. (3) Additionally, we explore three challenging settings: skipping intermediate steps, introducing data noises, and testing length generalization. Our results demonstrate that Transformer+CoT learns robust algorithms (FSAs), highlighting its resilience in challenging scenarios. Our code is available at https://github.com/IvanChangPKU/FSA.
Authors: Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless, Dravyansh Sharma, Matthew Walter
Abstract: One of the most basic lower bounds in machine learning is that in nearly any nontrivial setting, it takes $\textit{at least}$ $1/\epsilon$ samples to learn to error $\epsilon$ (and more, if the classifier being learned is complex). However, suppose that data points are agents who have the ability to improve by a small amount if doing so will allow them to receive a (desired) positive classification. In that case, we may actually be able to achieve $\textit{zero}$ error by just being "close enough". For example, imagine a hiring test used to measure an agent's skill at some job such that for some threshold $\theta$, agents who score above $\theta$ will be successful and those who score below $\theta$ will not (i.e., learning a threshold on the line). Suppose also that by putting in effort, agents can improve their skill level by some small amount $r$. In that case, if we learn an approximation $\hat{\theta}$ of $\theta$ such that $\theta \leq \hat{\theta} \leq \theta + r$ and use it for hiring, we can actually achieve error zero, in the sense that (a) any agent classified as positive is truly qualified, and (b) any agent who truly is qualified can be classified as positive by putting in effort. Thus, the ability for agents to improve has the potential to allow for a goal one could not hope to achieve in standard models, namely zero error. In this paper, we explore this phenomenon more broadly, giving general results and examining under what conditions the ability of agents to improve can allow for a reduction in the sample complexity of learning, or alternatively, can make learning harder. We also examine both theoretically and empirically what kinds of improvement-aware algorithms can take into account agents who have the ability to improve to a limited extent when it is in their interest to do so.
Authors: Yordan P. Raykov, Hengrui Luo, Justin D. Strait, Wasiur R. KhudaBukhsh
Abstract: We propose causal effect estimators based on empirical Fr\'{e}chet means and operator-valued kernels, tailored to functional data spaces. These methods address the challenges of high-dimensionality, sequential ordering, and model complexity while preserving robustness to treatment misspecification. Using structural assumptions, we obtain compact representations of potential outcomes, enabling scalable estimation of causal effects over time and across covariates. We provide both theoretical, regarding the consistency of functional causal effects, as well as empirical comparison of a range of proposed causal effect estimators. Applications to binary treatment settings with functional outcomes illustrate the framework's utility in biomedical monitoring, where outcomes exhibit complex temporal dynamics. Our estimators accommodate scenarios with registered covariates and outcomes, aligning them to the Fr\'{e}chet means, as well as cases requiring higher-order representations to capture intricate covariate-outcome interactions. These advancements extend causal inference to dynamic and non-linear domains, offering new tools for understanding complex treatment effects in functional data settings.
Authors: Eetu Tunturi, David Diaz-Guerra, Archontis Politis, Tuomas Virtanen
Abstract: Music source separation is the task of separating a mixture of instruments into constituent tracks. Music source separation models are typically trained using only audio data, although additional information can be used to improve the model's separation capability. In this paper, we propose two ways of using musical scores to aid music source separation: a score-informed model where the score is concatenated with the magnitude spectrogram of the audio mixture as the input of the model, and a model where we use only the score to calculate the separation mask. We train our models on synthetic data in the SynthSOD dataset and evaluate our methods on the URMP and Aalto anechoic orchestra datasets, comprised of real recordings. The score-informed model improves separation results compared to a baseline approach, but struggles to generalize from synthetic to real data, whereas the score-only model shows a clear improvement in synthetic-to-real generalization.
Authors: Hai-Long Sun, Zhun Sun, Houwen Peng, Han-Jia Ye
Abstract: Recent advancements in Large Language Models (LLMs) have demonstrated enhanced reasoning capabilities, evolving from Chain-of-Thought (CoT) prompting to advanced, product-oriented solutions like OpenAI o1. During our re-implementation of this model, we noticed that in multimodal tasks requiring visual input (e.g., geometry problems), Multimodal LLMs (MLLMs) struggle to maintain focus on the visual information, in other words, MLLMs suffer from a gradual decline in attention to visual information as reasoning progresses, causing text-over-relied outputs. To investigate this, we ablate image inputs during long-chain reasoning. Concretely, we truncate the reasoning process midway, then re-complete the reasoning process with the input image removed. We observe only a ~2% accuracy drop on MathVista's test-hard subset, revealing the model's textual outputs dominate the following reasoning process. Motivated by this, we propose Take-along Visual Conditioning (TVC), a strategy that shifts image input to critical reasoning stages and compresses redundant visual tokens via dynamic pruning. This methodology helps the model retain attention to the visual components throughout the reasoning. Our approach achieves state-of-the-art performance on average across five mathematical reasoning benchmarks (+3.4 points vs previous sota), demonstrating the effectiveness of TVC in enhancing multimodal reasoning systems.
Authors: Erik G. Larsson, Nicolo Michelusi
Abstract: The decentralized gradient descent (DGD) algorithm, and its sibling, diffusion, are workhorses in decentralized machine learning, distributed inference and estimation, and multi-agent coordination. We propose a novel, principled framework for the analysis of DGD and diffusion for strongly convex, smooth objectives, and arbitrary undirected topologies, using contraction mappings coupled with a result called the mean Hessian theorem (MHT). The use of these tools yields tight convergence bounds, both in the noise-free and noisy regimes. While these bounds are qualitatively similar to results found in the literature, our approach using contractions together with the MHT decouples the algorithm dynamics (how quickly the algorithm converges to its fixed point) from its asymptotic convergence properties (how far the fixed point is from the global optimum). This yields a simple, intuitive analysis that is accessible to a broader audience. Extensions are provided to multiple local gradient updates, time-varying step sizes, noisy gradients (stochastic DGD and diffusion), communication noise, and random topologies.
Authors: Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas, Letian Chen, Rohan Paleja, Matthew Gombolay
Abstract: Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability by making the agent's decisions understandable and verifiable. Achieving this, however, requires a feature space composed of human-understandable concepts, which traditionally rely on human specification and may fail to generalize to unseen environments. We introduce interpretable Tree-based Reinforcement learning via Automated Concept Extraction (iTRACE), an automated framework that leverages pre-trained vision-language models (VLM) for semantic feature extraction and interpretable tree-based models for policy optimization. iTRACE first extracts semantically meaningful features, then maps them to policies via interpretable trees. To address the impracticality of running VLMs in RL loops, we distill their outputs into a lightweight model. By leveraging Vision-Language Models (VLMs) to automate tree-based reinforcement learning, iTRACE eliminates the need for human annotation traditionally required by interpretable models, while also addressing the limitations of VLMs alone, such as their lack of grounding in action spaces and inability to directly optimize policies. iTRACE outperforms MLP baselines that use the same interpretable features and matches the performance of CNN-based policies, producing verifiable, semantically interpretable, and human-aligned behaviors without requiring human annotation.
Authors: Owen Cook, Jake Vasilakes, Ian Roberts, Xingyi Song
Abstract: Data annotation is an essential component of the machine learning pipeline; it is also a costly and time-consuming process. With the introduction of transformer-based models, annotation at the document level is increasingly popular; however, there is no standard framework for structuring such tasks. The EffiARA annotation framework is, to our knowledge, the first project to support the whole annotation pipeline, from understanding the resources required for an annotation task to compiling the annotated dataset and gaining insights into the reliability of individual annotators as well as the dataset as a whole. The framework's efficacy is supported by two previous studies: one improving classification performance through annotator-reliability-based soft-label aggregation and sample weighting, and the other increasing the overall agreement among annotators through removing identifying and replacing an unreliable annotator. This work introduces the EffiARA Python package and its accompanying webtool, which provides an accessible graphical user interface for the system. We open-source the EffiARA Python package at https://github.com/MiniEggz/EffiARA and the webtool is publicly accessible at https://effiara.gate.ac.uk.
URLs: https://github.com/MiniEggz/EffiARA, https://effiara.gate.ac.uk.
Authors: Lucia Celli, Giovanni Peccati
Abstract: Using entropic inequalities from information theory, we provide new bounds on the total variation and 2-Wasserstein distances between a conditionally Gaussian law and a Gaussian law with invertible covariance matrix. We apply our results to quantify the speed of convergence to Gaussian of a randomly initialized fully connected neural network and its derivatives - evaluated in a finite number of inputs - when the initialization is Gaussian and the sizes of the inner layers diverge to infinity. Our results require mild assumptions on the activation function, and allow one to recover optimal rates of convergence in a variety of distances, thus improving and extending the findings of Basteri and Trevisan (2023), Favaro et al. (2023), Trevisan (2024) and Apollonio et al. (2024). One of our main tools are the quantitative cumulant estimates established in Hanin (2024). As an illustration, we apply our results to bound the total variation distance between the Bayesian posterior law of the neural network and its derivatives, and the posterior law of the corresponding Gaussian limit: this yields quantitative versions of a posterior CLT by Hron et al. (2022), and extends several estimates by Trevisan (2024) to the total variation metric.
Authors: Siyan Zhao, Devaansh Gupta, Qinqing Zheng, Aditya Grover
Abstract: Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL). These capabilities have primarily been demonstrated within the left-to-right autoregressive (AR) generation paradigm. In contrast, non-autoregressive paradigms based on diffusion generate text in a coarse-to-fine manner. Although recent diffusion-based large language models (dLLMs) have achieved competitive language modeling performance compared to their AR counterparts, it remains unclear if dLLMs can also leverage recent advances in LLM reasoning. To this end, we propose d1, a framework to adapt pre-trained masked dLLMs into reasoning models via a combination of supervised finetuning (SFT) and RL. Specifically, we develop and extend techniques to improve reasoning in pretrained dLLMs: (a) we utilize a masked SFT technique to distill knowledge and instill self-improvement behavior directly from existing datasets, and (b) we introduce a novel critic-free, policy-gradient based RL algorithm called diffu-GRPO, the first integration of policy gradient methods to masked dLLMs. Through empirical studies, we investigate the performance of different post-training recipes on multiple mathematical and planning benchmarks. We find that d1 yields the best performance and significantly improves performance of a state-of-the-art dLLM. Our code is released at https://dllm-reasoning.github.io/.
Authors: Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson, Robert Graham, Yash Vadi, Danilo Bzdok, Sebastian Lapuschkin, Lee Sharkey, Blake Aaron Richards
Abstract: Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision mechanistic interpretability has been hindered by the lack of accessible frameworks and pre-trained weights. We present Prisma (Access the codebase here: https://github.com/Prisma-Multimodal/ViT-Prisma), an open-source framework designed to accelerate vision mechanistic interpretability research, providing a unified toolkit for accessing 75+ vision and video transformers; support for sparse autoencoder (SAE), transcoder, and crosscoder training; a suite of 80+ pre-trained SAE weights; activation caching, circuit analysis tools, and visualization tools; and educational resources. Our analysis reveals surprising findings, including that effective vision SAEs can exhibit substantially lower sparsity patterns than language SAEs, and that in some instances, SAE reconstructions can decrease model loss. Prisma enables new research directions for understanding vision model internals while lowering barriers to entry in this emerging field.
Authors: Reece O'Mahoney, Wanming Yu, Ioannis Havoutis
Abstract: Generative models have shown great promise as trajectory planners, given their affinity to modeling complex distributions and guidable inference process. Previous works have successfully applied these in the context of robotic manipulation but perform poorly when the required solution does not exist as a complete trajectory within the training set. We identify that this is a result of being unable to plan via stitching, and subsequently address the architectural and dataset choices needed to remedy this. On top of this, we propose a novel addition to the training and inference procedures to both stabilize and enhance these capabilities. We demonstrate the efficacy of our approach by generating plans with out of distribution boundary conditions and performing obstacle avoidance on the Franka Panda in simulation and on real hardware. In both of these tasks our method performs significantly better than the baselines and is able to avoid obstacles up to four times as large.
Authors: Kirill Vasilevski, Benjamin Rombaut, Gopi Krishnan Rajbahadur, Gustavo A. Oliva, Keheliya Gallaba, Filipe R. Cogo, Jiahuei Lin, Dayi Lin, Haoxiang Zhang, Bouyan Chen, Kishanthan Thangarajah, Ahmed E. Hassan, Zhen Ming Jiang
Abstract: Foundation Models (FMs) such as Large Language Models (LLMs) are reshaping the software industry by enabling FMware, systems that integrate these FMs as core components. In this KDD 2025 tutorial, we present a comprehensive exploration of FMware that combines a curated catalogue of challenges with real-world production concerns. We first discuss the state of research and practice in building FMware. We further examine the difficulties in selecting suitable models, aligning high-quality domain-specific data, engineering robust prompts, and orchestrating autonomous agents. We then address the complex journey from impressive demos to production-ready systems by outlining issues in system testing, optimization, deployment, and integration with legacy software. Drawing on our industrial experience and recent research in the area, we provide actionable insights and a technology roadmap for overcoming these challenges. Attendees will gain practical strategies to enable the creation of trustworthy FMware in the evolving technology landscape.
Authors: Zijia Liu, Peixuan Han, Haofei Yu, Haoru Li, Jiaxuan You
Abstract: Large Language Models (LLMs) demonstrate impressive capabilities but lack robust temporal intelligence, struggling to integrate reasoning about the past with predictions and plausible generations of the future. Meanwhile, existing methods typically target isolated temporal skills, such as question answering about past events or basic forecasting, and exhibit poor generalization, particularly when dealing with events beyond their knowledge cutoff or requiring creative foresight. To address these limitations, we introduce \textit{Time-R1}, the first framework to endow a moderate-sized (3B-parameter) LLM with comprehensive temporal abilities: understanding, prediction, and creative generation. Our approach features a novel three-stage development path; the first two constitute a \textit{reinforcement learning (RL) curriculum} driven by a meticulously designed dynamic rule-based reward system. This framework progressively builds (1) foundational temporal understanding and logical event-time mappings from historical data, (2) future event prediction skills for events beyond its knowledge cutoff, and finally (3) enables remarkable generalization to creative future scenario generation without any fine-tuning. Strikingly, experiments demonstrate that Time-R1 outperforms models over 200 times larger, including the state-of-the-art 671B DeepSeek-R1, on highly challenging future event prediction and creative scenario generation benchmarks. This work provides strong evidence that thoughtfully engineered, progressive RL fine-tuning allows smaller, efficient models to achieve superior temporal performance, offering a practical and scalable path towards truly time-aware AI. To foster further research, we also release \textit{Time-Bench}, a large-scale multi-task temporal reasoning dataset derived from 10 years of news data, and our series of \textit{Time-R1} checkpoints.
Authors: Yiru Jiao, Simeon C. Calvert, Sander van Cranenburgh, Hans van Lint
Abstract: Accurate and timely alerts for drivers or automated systems to unfolding collisions remains a challenge in road safety, particularly in highly interactive urban traffic. Existing approaches require labour-intensive annotation of sparse risk, struggle to consider varying contextual factors, or are useful only in the scenarios they are designed for. To address these limits, this study introduces the generalised surrogate safety measure (GSSM), a new approach that learns exclusively from naturalistic driving without crash or risk labels. GSSM captures the patterns of normal driving and estimates the extent to which a traffic interaction deviates from the norm towards unsafe extreme. Utilising neural networks, normal interactions are characterised by context-conditioned distributions of multi-directional spacing between road users. In the same interaction context, a spacing closer than normal entails higher risk of potential collision. Then a context-adaptive risk score and its associated probability can be calculated based on the theory of extreme values. Any measurable factors, such as motion kinematics, weather, lighting, can serve as part of the context, allowing for diverse coverage of safety-critical interactions. Multiple public driving datasets are used to train GSSMs, which are tested with 2,591 real-world crashes and near-crashes reconstructed from the SHRP2 NDS. A vanilla GSSM using only instantaneous states achieves AUPRC of 0.9 and secures a median time advance of 2.6 seconds to prevent potential collisions. Additional data and contextual factors provide further performance gains. Across various interaction types such as rear-end, merging, and crossing, the accuracy and timeliness of GSSM consistently outperforms existing baselines. GSSM therefore establishes a scalable, context-aware, and generalisable foundation to proactively quantify collision risk in traffic interactions.
Authors: Minglu Zhao, Dehong Xu, Deqian Kong, Wen-Hao Zhang, Ying Nian Wu
Abstract: The hippocampus enables spatial navigation through place cell populations forming cognitive maps. We propose proximity-preserving neural embeddings to encode multi-scale random walk transitions, where the inner product $\langle h(x, t), h(y, t) \rangle = q(y|x, t)$ represents normalized transition probabilities, with $h(x, t)$ as the embedding at location $x$ and $q(y|x, t)$ as the transition probability at scale $\sqrt{t}$. This scale hierarchy mirrors hippocampal dorsoventral organization. The embeddings $h(x, t)$ reduce pairwise spatial proximity into an environmental map, with Euclidean distances preserving proximity information. We use gradient ascent on $q(y|x, t)$ for straight-forward path planning, employing adaptive scale selection for trap-free, smooth trajectories, equivalent to minimizing embedding space distances. Matrix squaring ($P_{2t} = P_t^2$) efficiently builds global transitions from local ones ($P_1$), enabling preplay-like shortcut prediction. Experiments demonstrate localized place fields, multi-scale tuning, adaptability, and remapping, achieving robust navigation in complex environments. Our biologically plausible framework, extensible to theta-phase precession, unifies spatial and temporal coding for scalable navigation.
Authors: Mohamed S. Elmahdy, Marius Staring, Patrick J. H. de Koning, Samer Alabed, Mahan Salehi, Faisal Alandejani, Michael Sharkey, Ziad Aldabbagh, Andrew J. Swift, Rob J. van der Geest
Abstract: Accurate and efficient quantification of cardiac function is essential for the estimation of prognosis of cardiovascular diseases (CVDs). One of the most commonly used metrics for evaluating cardiac pumping performance is left ventricular ejection fraction (LVEF). However, LVEF can be affected by factors such as inter-observer variability and varying pre-load and after-load conditions, which can reduce its reproducibility. Additionally, cardiac dysfunction may not always manifest as alterations in LVEF, such as in heart failure and cardiotoxicity diseases. An alternative measure that can provide a relatively load-independent quantitative assessment of myocardial contractility is myocardial strain and strain rate. By using LVEF in combination with myocardial strain, it is possible to obtain a thorough description of cardiac function. Automated estimation of LVEF and other volumetric measures from cine-MRI sequences can be achieved through segmentation models, while strain calculation requires the estimation of tissue displacement between sequential frames, which can be accomplished using registration models. These tasks are often performed separately, potentially limiting the assessment of cardiac function. To address this issue, in this study we propose an end-to-end deep learning (DL) model that jointly estimates groupwise (GW) registration and segmentation for cardiac cine-MRI images. The proposed anatomically-guided Deep GW network was trained and validated on a large dataset of 4-chamber view cine-MRI image series of 374 subjects. A quantitative comparison with conventional GW registration using elastix and two DL-based methods showed that the proposed model improved performance and substantially reduced computation time.
Authors: Sanjana Chalavadi, Andrei Pastor, Terry Leitch
Abstract: This study analyzes tract-level real estate ownership patterns in New York State (NYS) and New York City (NYC) to uncover racial disparities. We use an advanced race/ethnicity imputation model (LSTM+Geo with XGBoost filtering, validated at 89.2% accuracy) to compare the predicted racial composition of property owners to the resident population from census data. We examine both a Full Model (statewide) and a Name-Only LSTM Model (NYC) to assess how incorporating geospatial context affects our predictions and disparity estimates. The results reveal significant inequities: White individuals hold a disproportionate share of properties and property value relative to their population, while Black, Hispanic, and Asian communities are underrepresented as property owners. These disparities are most pronounced in minority-majority neighborhoods, where ownership is predominantly White despite a predominantly non-White population. Corporate ownership (LLCs, trusts, etc.) exacerbates these gaps by reducing owner-occupied opportunities in urban minority communities. We provide a breakdown of ownership vs. population by race for majority-White, -Black, -Hispanic, and -Asian tracts, identify those with extreme ownership disparities, and compare patterns in urban, suburban, and rural contexts. The findings underscore persistent racial inequity in property ownership, reflecting broader historical and socio-economic forces, and highlight the importance of data-driven approaches to address these issues.
Authors: Yahao Fan, Tianxiang Gui, Kaiyang Ji, Shutong Ding, Chixuan Zhang, Jiayuan Gu, Jingyi Yu, Jingya Wang, Ye Shi
Abstract: Humanoid locomotion faces a critical scalability challenge: traditional reinforcement learning (RL) methods require task-specific rewards and struggle to leverage growing datasets, even as more training terrains are introduced. We propose DreamPolicy, a unified framework that enables a single policy to master diverse terrains and generalize zero-shot to unseen scenarios by systematically integrating offline data and diffusion-driven motion synthesis. At its core, DreamPolicy introduces Humanoid Motion Imagery (HMI) - future state predictions synthesized through an autoregressive terrain-aware diffusion planner curated by aggregating rollouts from specialized policies across various distinct terrains. Unlike human motion datasets requiring laborious retargeting, our data directly captures humanoid kinematics, enabling the diffusion planner to synthesize "dreamed" trajectories that encode terrain-specific physical constraints. These trajectories act as dynamic objectives for our HMI-conditioned policy, bypassing manual reward engineering and enabling cross-terrain generalization. DreamPolicy addresses the scalability limitations of prior methods: while traditional RL fails to exploit growing datasets, our framework scales seamlessly with more offline data. As the dataset expands, the diffusion prior learns richer locomotion skills, which the policy leverages to master new terrains without retraining. Experiments demonstrate that DreamPolicy achieves average 90% success rates in training environments and an average of 20% higher success on unseen terrains than the prevalent method. It also generalizes to perturbed and composite scenarios where prior approaches collapse. By unifying offline data, diffusion-based trajectory synthesis, and policy optimization, DreamPolicy overcomes the "one task, one policy" bottleneck, establishing a paradigm for scalable, data-driven humanoid control.
Authors: Weijie Su
Abstract: Large language models (LLMs) represent a new paradigm for processing unstructured data, with applications across an unprecedented range of domains. In this paper, we address, through two arguments, whether the development and application of LLMs would genuinely benefit from foundational contributions from the statistics discipline. First, we argue affirmatively, beginning with the observation that LLMs are inherently statistical models due to their profound data dependency and stochastic generation processes, where statistical insights are naturally essential for handling variability and uncertainty. Second, we argue that the persistent black-box nature of LLMs -- stemming from their immense scale, architectural complexity, and development practices often prioritizing empirical performance over theoretical interpretability -- renders closed-form or purely mechanistic analyses generally intractable, thereby necessitating statistical approaches due to their flexibility and often demonstrated effectiveness. To substantiate these arguments, the paper outlines several research areas -- including alignment, watermarking, uncertainty quantification, evaluation, and data mixture optimization -- where statistical methodologies are critically needed and are already beginning to make valuable contributions. We conclude with a discussion suggesting that statistical research concerning LLMs will likely form a diverse ``mosaic'' of specialized topics rather than deriving from a single unifying theory, and highlighting the importance of timely engagement by our statistics community in LLM research.
Authors: Mengru Wang, Ziwen Xu, Shengyu Mao, Shumin Deng, Zhaopeng Tu, Huajun Chen, Ningyu Zhang
Abstract: Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often results in highly intertwined internal representations. This interdependency can limit control precision and sometimes lead to unintended side effects. Recent research has explored the use of sparse autoencoders (SAE) to disentangle knowledge in high-dimensional spaces for steering. However, these applications have been limited to toy tasks owing to the nontrivial issue of locating atomic knowledge components. In this paper, we propose Steering Target Atoms (STA), a novel method that isolates and manipulates disentangled knowledge components to enhance safety. Comprehensive experiments demonstrate the effectiveness of our approach. Further analysis reveals that steering exhibits superior robustness and flexibility, particularly in adversarial scenarios. We also apply the steering strategy to the large reasoning model, confirming its effectiveness in precise reasoning control.
Authors: Hemant Tyagi
Abstract: Given an undirected and connected graph $G$ on $T$ vertices, suppose each vertex $t$ has a latent signal $x_t \in \mathbb{R}^n$ associated to it. Given partial linear measurements of the signals, for a potentially small subset of the vertices, our goal is to estimate $x_t$'s. Assuming that the signals are smooth w.r.t $G$, in the sense that the quadratic variation of the signals over the graph is small, we obtain non-asymptotic bounds on the mean squared error for jointly recovering $x_t$'s, for the smoothness penalized least squares estimator. In particular, this implies for certain choices of $G$ that this estimator is weakly consistent (as $T \rightarrow \infty$) under potentially very stringent sampling, where only one coordinate is measured per vertex for a vanishingly small fraction of the vertices. The results are extended to a ``multi-layer'' ranking problem where $x_t$ corresponds to the latent strengths of a collection of $n$ items, and noisy pairwise difference measurements are obtained at each ``layer'' $t$ via a measurement graph $G_t$. Weak consistency is established for certain choices of $G$ even when the individual $G_t$'s are very sparse and disconnected.
Authors: Shenghe Zheng, Qianjia Cheng, Junchi Yao, Mengsong Wu, Haonan He, Ning Ding, Yu Cheng, Shuyue Hu, Lei Bai, Dongzhan Zhou, Ganqu Cui, Peng Ye
Abstract: Large Language Models (LLMs) have achieved remarkable progress on advanced reasoning tasks such as mathematics and coding competitions. Meanwhile, physics, despite being both reasoning-intensive and essential to real-world understanding, received limited academic and industrial attention. This paper introduces PHYSICS, a dataset containing 16,568 high-quality physics problems spanning subjects and difficulty levels, to facilitate this issue. Specifically, PHYSICS is curated with exercises from over 100 textbooks through a carefully designed pipeline for quality control. It covers five major physics domains: Mechanics, Electromagnetism, Thermodynamics, Optics, and Modern Physics. It also spans a wide range of difficulty levels, from high school to graduate-level physics courses. To utilize the data for improving and evaluating the model's physical reasoning capabilities, we split the dataset into training and test sets, and provide reasoning paths generated by powerful reasoning models for the training data to facilitate model training. In addition, for the evaluation part, we find that existing evaluation frameworks exhibit biases in aspects such as units, simplification, and precision in physics domain. To balance efficiency and accuracy, we introduce a Rule+Model evaluation framework tailored to physics problems. Our evaluations on current state-of-the-art open-source and proprietary models highlight the limitations of current models in handling physics-related tasks. We hope that our dataset and evaluation methodology will jointly advance the development of LLMs in the field of physics.
Authors: Edward L. Wang, Tianyu Wang, Avanti Athreya, Vince Lyzinski, Carey E. Priebe
Abstract: Large language models (LLMs) are a powerful tool with the ability to match human capabilities and behavior in many settings. Retrieval-augmented generation (RAG) further allows LLMs to generate diverse output depending on the contents of their RAG database. This motivates their use in the social sciences to study human behavior between individuals when large-scale experiments are infeasible. However, LLMs depend on complex, computationally expensive algorithms. In this paper, we introduce interacting Gaussian mixture models (GMMs) as an alternative to similar frameworks using LLMs. We compare a simplified model of GMMs to select experimental simulations of LLMs whose updating and response depend on feedback from other LLMs. We find that interacting GMMs capture important features of the dynamics in interacting LLMs, and we investigate key similarities and differences between interacting LLMs and GMMs. We conclude by discussing the benefits of Gaussian mixture models, potential modifications, and future research directions.
Authors: Luigi Sigillo, Shengfeng He, Danilo Comminiello
Abstract: High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a lightweight framework that enables any latent diffusion model to scale to ultra-high-resolution image generation (2K to 4K) for free. LWD introduces three key components: (1) a scale-consistent variational autoencoder objective that enhances the spectral fidelity of latent representations; (2) wavelet energy maps that identify and localize detail-rich spatial regions within the latent space; and (3) a time-dependent masking strategy that focuses denoising supervision on high-frequency components during training. LWD requires no architectural modifications and incurs no additional computational overhead. Despite its simplicity, it consistently improves perceptual quality and reduces FID in ultra-high-resolution image synthesis, outperforming strong baseline models. These results highlight the effectiveness of frequency-aware, signal-driven supervision as a principled and efficient approach for high-resolution generative modeling.
Authors: Li Zhang, Morgan Gray, Jaromir Savelka, Kevin D. Ashley
Abstract: Large Language Models (LLMs) demonstrate potential in complex legal tasks like argument generation, yet their reliability remains a concern. Building upon pilot work assessing LLM generation of 3-ply legal arguments using human evaluation, this paper introduces an automated pipeline to evaluate LLM performance on this task, specifically focusing on faithfulness (absence of hallucination), factor utilization, and appropriate abstention. We define hallucination as the generation of factors not present in the input case materials and abstention as the model's ability to refrain from generating arguments when instructed and no factual basis exists. Our automated method employs an external LLM to extract factors from generated arguments and compares them against the ground-truth factors provided in the input case triples (current case and two precedent cases). We evaluated eight distinct LLMs on three tests of increasing difficulty: 1) generating a standard 3-ply argument, 2) generating an argument with swapped precedent roles, and 3) recognizing the impossibility of argument generation due to lack of shared factors and abstaining. Our findings indicate that while current LLMs achieve high accuracy (over 90%) in avoiding hallucination on viable argument generation tests (Tests 1 & 2), they often fail to utilize the full set of relevant factors present in the cases. Critically, on the abstention test (Test 3), most models failed to follow instructions to stop, instead generating spurious arguments despite the lack of common factors. This automated pipeline provides a scalable method for assessing these crucial LLM behaviors, highlighting the need for improvements in factor utilization and robust abstention capabilities before reliable deployment in legal settings. Link: https://lizhang-aiandlaw.github.io/An-Automated-Pipeline-for-Evaluating-LLM-Generated-3-ply-Case-Based-Legal-Arguments/
Authors: Keyuan Cheng, Zijian Kan, Zhixian He, Zhuoran Zhang, Muhammad Asif Ali, Ke Xu, Lijie Hu, Di Wang
Abstract: Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge. However, we argue that these benchmarks fail to effectively evaluate how well the updated models apply this knowledge in real-life scenarios, particularly when questions require complex reasoning, involving one-to-many relationships or multi-step logical intersections. To fill in this gap, we introduce a new benchmark, COMPKE: Complex Question Answering under Knowledge Editing, which includes 11,924 complex questions that reflect real-life situations. We conduct an extensive evaluation of four knowledge editing methods on COMPKE, revealing that their effectiveness varies notably across different models. For instance, MeLLo attains an accuracy of 39.47 on GPT-4O-MINI, but this drops sharply to 3.83 on QWEN2.5-3B. We further investigate the underlying causes of these disparities from both methodological and model-specific perspectives. The datasets are available at https://github.com/kzjkzj666/CompKE.
Authors: Defne E. Ozan, Andrea N\'ovoa, Georgios Rigas, Luca Magri
Abstract: The control of spatio-temporally chaos is challenging because of high dimensionality and unpredictability. Model-free reinforcement learning (RL) discovers optimal control policies by interacting with the system, typically requiring observations of the full physical state. In practice, sensors often provide only partial and noisy measurements (observations) of the system. The objective of this paper is to develop a framework that enables the control of chaotic systems with partial and noisy observability. The proposed method, data-assimilated model-informed reinforcement learning (DA-MIRL), integrates (i) low-order models to approximate high-dimensional dynamics; (ii) sequential data assimilation to correct the model prediction when observations become available; and (iii) an off-policy actor-critic RL algorithm to adaptively learn an optimal control strategy based on the corrected state estimates. We test DA-MIRL on the spatiotemporally chaotic solutions of the Kuramoto-Sivashinsky equation. We estimate the full state of the environment with (i) a physics-based model, here, a coarse-grained model; and (ii) a data-driven model, here, the control-aware echo state network, which is proposed in this paper. We show that DA-MIRL successfully estimates and suppresses the chaotic dynamics of the environment in real time from partial observations and approximate models. This work opens opportunities for the control of partially observable chaotic systems.