Authors: Mengtao Yan, Qi Wang, Haining Wang, Ruizhi Chengze, Yi Zhang, Hongsheng Liu, Zidong Wang, Fan Yu, Qi Qi, Hao Sun
Abstract: Simulation of fluid flows is crucial for modeling physical phenomena like meteorology, aerodynamics, and biomedicine. Classical numerical solvers often require fine spatiotemporal grids to satisfy stability, consistency, and convergence conditions, leading to substantial computational costs. Although machine learning has demonstrated better efficiency, they typically suffer from issues of interpretability, generalizability, and data dependency. Hence, we propose a learnable and differentiable finite volume solver, called LDSolver, designed for efficient and accurate simulation of fluid flows on spatiotemporal coarse grids. LDSolver comprises two key components: (1) a differentiable finite volume solver, and (2) an learnable module providing equivalent approximation for fluxes (derivatives and interpolations), and temporal error correction on coarse grids. Even with limited training data (e.g., only a few trajectories), our model could accelerate the simulation while maintaining a high accuracy with superior generalizability. Experiments on different flow systems (e.g., Burgers, decaying, forced and shear flows) show that LDSolver achieves state-of-the-art performance, surpassing baseline models with notable margins.
Authors: Siqing Long, Xiangzhi Huang, Jiemin Xie, Ming Cai
Abstract: Accurate traffic demand forecasting enables transportation management departments to allocate resources more effectively, thereby improving their utilization efficiency. However, complex spatiotemporal relationships in traffic systems continue to limit the performance of demand forecasting models. To improve the accuracy of spatiotemporal traffic demand prediction, we propose a new graph convolutional network structure called DKGCM. Specifically, we first consider the spatial flow distribution of different traffic nodes and propose a novel temporal similarity-based clustering graph convolution method, DK-GCN. This method utilizes Dynamic Time Warping (DTW) and K-means clustering to group traffic nodes and more effectively capture spatial dependencies. On the temporal scale, we integrate the Fast Fourier Transform (FFT) within the bidirectional Mamba deep learning framework to capture temporal dependencies in traffic demand. To further optimize model training, we incorporate the GRPO reinforcement learning strategy to enhance the loss function feedback mechanism. Extensive experiments demonstrate that our model outperforms several advanced methods and achieves strong results on three public datasets.
Authors: Gautam Kishore Shahi
Abstract: Amid a tidal wave of misinformation flooding social media during elections and crises, extensive research has been conducted on misinformation detection, primarily focusing on text-based or image-based approaches. However, only a few studies have explored multimodal feature combinations, such as integrating text and images for building a classification model to detect misinformation. This study investigates the effectiveness of different multimodal feature combinations, incorporating text, images, and social features using an early fusion approach for the classification model. This study analyzed 1,529 tweets containing both text and images during the COVID-19 pandemic and election periods collected from Twitter (now X). A data enrichment process was applied to extract additional social features, as well as visual features, through techniques such as object detection and optical character recognition (OCR). The results show that combining unsupervised and supervised machine learning models improves classification performance by 15% compared to unimodal models and by 5% compared to bimodal models. Additionally, the study analyzes the propagation patterns of misinformation based on the characteristics of misinformation tweets and the users who disseminate them.
Authors: Hexiang Bai, Deyu Li, Jiye Liang, Yanhui Zhai
Abstract: Selecting relevant features is an important and necessary step for intelligent machines to maximize their chances of success. However, intelligent machines generally have no enough computing resources when faced with huge volume of data. This paper develops a new method based on sampling techniques and rough set theory to address the challenge of feature selection for massive data. To this end, this paper proposes using the ratio of discernible object pairs to all object pairs that should be distinguished to measure the discriminatory ability of a feature set. Based on this measure, a new feature selection method is proposed. This method constructs positive region preserved samples from massive data to find a feature subset with high discriminatory ability. Compared with other methods, the proposed method has two advantages. First, it is able to select a feature subset that can preserve the discriminatory ability of all the features of the target massive data set within an acceptable time on a personal computer. Second, the lower boundary of the probability of the object pairs that can be discerned using the feature subset selected in all object pairs that should be distinguished can be estimated before finding reducts. Furthermore, 11 data sets of different sizes were used to validate the proposed method. The results show that approximate reducts can be found in a very short period of time, and the discriminatory ability of the final reduct is larger than the estimated lower boundary. Experiments on four large-scale data sets also showed that an approximate reduct with high discriminatory ability can be obtained in reasonable time on a personal computer.
Authors: Bappaditya Dey, Daniel Sorensen, Minjin Hwang, Sandip Halder
Abstract: Semiconductor manufacturing is an extremely complex process, characterized by thousands of interdependent parameters collected across diverse tools and process steps. Multi-variate time-series (MTS) analysis has emerged as a critical methodology for enabling real-time monitoring, fault detection, and predictive maintenance in such environments. However, anomaly prediction in semiconductor fabrication presents several critical challenges, including high data dimensionality, severe class imbalance due to the rarity of true faults, noisy and missing measurements, and non-stationary behavior of production systems. Furthermore, the complex interdependencies between variables and the delayed emergence of faults across downstream stages complicate both anomaly detection and root-cause-analysis. This paper presents a novel and generic approach for anomaly detection in MTS data using machine learning. The proposed methodology consists of three main steps: a) converting MTS data into image-based representations using the Continuous Wavelet Transform, b) developing a multi-class image classifier by fine-tuning a pretrained VGG-16 architecture on custom CWT image datasets, and c) constructing a Siamese network composed of two identical sub-networks, each utilizing the fine-tuned VGG-16 as a backbone. The network takes pairs of CWT images as input -one serving as a reference or anchor (representing a known-good signal), and the other as a query (representing an unknown signal). The model then compares the embeddings of both inputs to determine whether they belong to the same class at a given time step. Our approach demonstrates high accuracy in identifying anomalies on a real FAB process time-series dataset, offering a promising solution for offline anomaly detection in process and tool trace data. Moreover, the approach is flexible and can be applied in both supervised and semi-supervised settings.
Authors: Anurag Arnab, Ahmet Iscen, Mathilde Caron, Alireza Fathi, Cordelia Schmid
Abstract: Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage this sequence length, and succumb to irrelevant distractors within the context window. We present Temporal Chain of Thought, an inference strategy for video question-answering that curates the model's input context. We use the VLM itself to iteratively identify and extract the most relevant frames from the video, which are then used for answering. We demonstrate how leveraging more computation at inference-time to select the most relevant context leads to improvements in accuracy, in agreement with recent work on inference-time scaling of LLMs. Moreover, we achieve state-of-the-art results on 4 diverse video question-answering datasets, showing consistent improvements with 3 different VLMs. In particular, our method shines on longer videos which would not otherwise fit within the model's context window: On longer videos of more than 1 hour on LVBench, our approach using a context window of 32K outperforms the same VLM using standard inference with a 700K context window by 2.8 points.
Authors: Shakya Jayakody, Youpeng Zhao, Jun Wang
Abstract: Graph convolutional networks (GCNs) are fundamental in various scientific applications, ranging from biomedical protein-protein interactions (PPI) to large-scale recommendation systems. An essential component for modeling graph structures in GCNs is sparse general matrix-matrix multiplication (SpGEMM). As the size of graph data continues to scale up, SpGEMMs are often conducted in an out-of-core fashion due to limited GPU memory space in resource-constrained systems. Albeit recent efforts that aim to alleviate the memory constraints of out-of-core SpGEMM through either GPU feature caching, hybrid CPU-GPU memory layout, or performing the computation in sparse format, current systems suffer from both high I/O latency and GPU under-utilization issues. In this paper, we first identify the problems of existing systems, where sparse format data alignment and memory allocation are the main performance bottlenecks, and propose AIRES, a novel algorithm-system co-design solution to accelerate out-of-core SpGEMM computation for GCNs. Specifically, from the algorithm angle, AIRES proposes to alleviate the data alignment issues on the block level for matrices in sparse formats and develops a tiling algorithm to facilitate row block-wise alignment. On the system level, AIRES employs a three-phase dynamic scheduling that features a dual-way data transfer strategy utilizing a tiered memory system: integrating GPU memory, GPU Direct Storage (GDS), and host memory to reduce I/O latency and improve throughput. Evaluations show that AIRES significantly outperforms the state-of-the-art methods, achieving up to 1.8x lower latency in real-world graph processing benchmarks.
Authors: Wanjia Zhao, Jiaqi Han, Siyi Gu, Mingjian Jiang, James Zou, Stefano Ermon
Abstract: Geometric diffusion models have shown remarkable success in molecular dynamics and structure generation. However, efficiently fine-tuning them for downstream tasks with varying geometric controls remains underexplored. In this work, we propose an SE(3)-equivariant adapter framework ( GeoAda) that enables flexible and parameter-efficient fine-tuning for controlled generative tasks without modifying the original model architecture. GeoAda introduces a structured adapter design: control signals are first encoded through coupling operators, then processed by a trainable copy of selected pretrained model layers, and finally projected back via decoupling operators followed by an equivariant zero-initialized convolution. By fine-tuning only these lightweight adapter modules, GeoAda preserves the model's geometric consistency while mitigating overfitting and catastrophic forgetting. We theoretically prove that the proposed adapters maintain SE(3)-equivariance, ensuring that the geometric inductive biases of the pretrained diffusion model remain intact during adaptation. We demonstrate the wide applicability of GeoAda across diverse geometric control types, including frame control, global control, subgraph control, and a broad range of application domains such as particle dynamics, molecular dynamics, human motion prediction, and molecule generation. Empirical results show that GeoAda achieves state-of-the-art fine-tuning performance while preserving original task accuracy, whereas other baselines experience significant performance degradation due to overfitting and catastrophic forgetting.
Authors: Eitan Anzenberg, Arunava Samajpati, Sivasankaran Chandrasekar, Varun Kacholia
Abstract: The use of large language models (LLMs) in hiring promises to streamline candidate screening, but it also raises serious concerns regarding accuracy and algorithmic bias where sufficient safeguards are not in place. In this work, we benchmark several state-of-the-art foundational LLMs - including models from OpenAI, Anthropic, Google, Meta, and Deepseek, and compare them with our proprietary domain-specific hiring model (Match Score) for job candidate matching. We evaluate each model's predictive accuracy (ROC AUC, Precision-Recall AUC, F1-score) and fairness (impact ratio of cut-off analysis across declared gender, race, and intersectional subgroups). Our experiments on a dataset of roughly 10,000 real-world recent candidate-job pairs show that Match Score outperforms the general-purpose LLMs on accuracy (ROC AUC 0.85 vs 0.77) and achieves significantly more equitable outcomes across demographic groups. Notably, Match Score attains a minimum race-wise impact ratio of 0.957 (near-parity), versus 0.809 or lower for the best LLMs, (0.906 vs 0.773 for the intersectionals, respectively). We discuss why pretraining biases may cause LLMs with insufficient safeguards to propagate societal biases in hiring scenarios, whereas a bespoke supervised model can more effectively mitigate these biases. Our findings highlight the importance of domain-specific modeling and bias auditing when deploying AI in high-stakes domains such as hiring, and caution against relying on off-the-shelf LLMs for such tasks without extensive fairness safeguards. Furthermore, we show with empirical evidence that there shouldn't be a dichotomy between choosing accuracy and fairness in hiring: a well-designed algorithm can achieve both accuracy in hiring and fairness in outcomes.
Authors: Xingtu Liu, Lin F. Yang, Sharan Vaswani
Abstract: We consider infinite-horizon $\gamma$-discounted (linear) constrained Markov decision processes (CMDPs) where the objective is to find a policy that maximizes the expected cumulative reward subject to expected cumulative constraints. Given access to a generative model, we propose to solve CMDPs with a primal-dual framework that can leverage any black-box unconstrained MDP solver. For linear CMDPs with feature dimension $d$, we instantiate the framework by using mirror descent value iteration (\texttt{MDVI})~\citep{kitamura2023regularization} an example MDP solver. We provide sample complexity bounds for the resulting CMDP algorithm in two cases: (i) relaxed feasibility, where small constraint violations are allowed, and (ii) strict feasibility, where the output policy is required to exactly satisfy the constraint. For (i), we prove that the algorithm can return an $\epsilon$-optimal policy with high probability by using $\tilde{O}\left(\frac{d^2}{(1-\gamma)^4\epsilon^2}\right)$ samples. We note that these results exhibit a near-optimal dependence on both $d$ and $\epsilon$. For (ii), we show that the algorithm requires $\tilde{O}\left(\frac{d^2}{(1-\gamma)^6\epsilon^2\zeta^2}\right)$ samples, where $\zeta$ is the problem-dependent Slater constant that characterizes the size of the feasible region. Finally, we instantiate our framework for tabular CMDPs and show that it can be used to recover near-optimal sample complexities in this setting.
Authors: Alexi Gladstone, Ganesh Nanduru, Md Mofijul Islam, Peixuan Han, Hyeonjeong Ha, Aman Chadha, Yilun Du, Heng Ji, Jundong Li, Tariq Iqbal
Abstract: Inference-time computation techniques, analogous to human System 2 Thinking, have recently become popular for improving model performances. However, most existing approaches suffer from several limitations: they are modality-specific (e.g., working only in text), problem-specific (e.g., verifiable domains like math and coding), or require additional supervision/training on top of unsupervised pretraining (e.g., verifiers or verifiable rewards). In this paper, we ask the question "Is it possible to generalize these System 2 Thinking approaches, and develop models that learn to think solely from unsupervised learning?" Interestingly, we find the answer is yes, by learning to explicitly verify the compatibility between inputs and candidate-predictions, and then re-framing prediction problems as optimization with respect to this verifier. Specifically, we train Energy-Based Transformers (EBTs) -- a new class of Energy-Based Models (EBMs) -- to assign an energy value to every input and candidate-prediction pair, enabling predictions through gradient descent-based energy minimization until convergence. Across both discrete (text) and continuous (visual) modalities, we find EBTs scale faster than the dominant Transformer++ approach during training, achieving an up to 35% higher scaling rate with respect to data, batch size, parameters, FLOPs, and depth. During inference, EBTs improve performance with System 2 Thinking by 29% more than the Transformer++ on language tasks, and EBTs outperform Diffusion Transformers on image denoising while using fewer forward passes. Further, we find that EBTs achieve better results than existing models on most downstream tasks given the same or worse pretraining performance, suggesting that EBTs generalize better than existing approaches. Consequently, EBTs are a promising new paradigm for scaling both the learning and thinking capabilities of models.
Authors: Florian Gr\"otschla, Luca A. Lanzend\"orfer, Longxiang Jiao, Roger Wattenhofer
Abstract: We introduce PANAMA, an active learning framework for the training of end-to-end parametric guitar amp models using a WaveNet-like architecture. With \model, one can create a virtual amp by recording samples that are determined by an active learning strategy to use a minimum amount of datapoints (i.e., amp knob settings). We show that gradient-based optimization algorithms can be used to determine the optimal datapoints to sample, and that the approach helps under a constrained number of samples.
Authors: Shikai Qiu, Lechao Xiao, Andrew Gordon Wilson, Jeffrey Pennington, Atish Agarwala
Abstract: What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, training algorithms, and data, compute-optimally trained models exhibit a remarkably precise universality. Specifically, loss curves from models of varying sizes collapse onto a single universal curve when training compute and loss are normalized to unity at the end of training. With learning rate decay, the collapse becomes so tight that differences in the normalized curves across models fall below the noise floor of individual loss curves across random seeds, a phenomenon we term supercollapse. We observe supercollapse across learning rate schedules, datasets, and architectures, including transformers trained on next-token prediction, and find it breaks down when hyperparameters are scaled suboptimally, providing a precise and practical indicator of good scaling. We explain these phenomena by connecting collapse to the power-law structure in typical neural scaling laws, and analyzing a simple yet surprisingly effective model of SGD noise dynamics that accurately predicts loss curves across various learning rate schedules and quantitatively explains the origin of supercollapse.
Authors: Jingyu Pan, Isaac Jacobson, Zheng Zhao, Tung-Chieh Chen, Guanglei Zhou, Chen-Chia Chang, Vineet Rashingkar, Yiran Chen
Abstract: Modern very large-scale integration (VLSI) design requires the implementation of integrated circuits using electronic design automation (EDA) tools. Due to the complexity of EDA algorithms, the vast parameter space poses a huge challenge to chip design optimization, as the combination of even moderate numbers of parameters creates an enormous solution space to explore. Manual parameter selection remains industrial practice despite being excessively laborious and limited by expert experience. To address this issue, we present CROP, the first large language model (LLM)-powered automatic VLSI design flow tuning framework. Our approach includes: (1) a scalable methodology for transforming RTL source code into dense vector representations, (2) an embedding-based retrieval system for matching designs with semantically similar circuits, and (3) a retrieval-augmented generation (RAG)-enhanced LLM-guided parameter search system that constrains the search process with prior knowledge from similar designs. Experiment results demonstrate CROP's ability to achieve superior quality-of-results (QoR) with fewer iterations than existing approaches on industrial designs, including a 9.9% reduction in power consumption.
Authors: Xiao Li, Liangji Zhu, Anand Rangarajan, Sanjay Ranka
Abstract: Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representation. However, their limited controllability and reconstruction accuracy restrict their practical application to data compression. In this work, we propose an efficient latent diffusion framework that bridges this gap by combining a variational autoencoder with a conditional diffusion model. Our method compresses only a small number of keyframes into latent space and uses them as conditioning inputs to reconstruct the remaining frames via generative interpolation, eliminating the need to store latent representations for every frame. This approach enables accurate spatiotemporal reconstruction while significantly reducing storage costs. Experimental results across multiple datasets show that our method achieves up to 10 times higher compression ratios than rule-based state-of-the-art compressors such as SZ3, and up to 63 percent better performance than leading learning-based methods under the same reconstruction error.
Authors: Tuo Wang, Jian Kang, Yujun Yan, Adithya Kulkarni, Dawei Zhou
Abstract: Conformal prediction for graph neural networks (GNNs) offers a promising framework for quantifying uncertainty, enhancing GNN reliability in high-stakes applications. However, existing methods predominantly focus on static graphs, neglecting the evolving nature of real-world graphs. Temporal dependencies in graph structure, node attributes, and ground truth labels violate the fundamental exchangeability assumption of standard conformal prediction methods, limiting their applicability. To address these challenges, in this paper, we introduce NCPNET, a novel end-to-end conformal prediction framework tailored for temporal graphs. Our approach extends conformal prediction to dynamic settings, mitigating statistical coverage violations induced by temporal dependencies. To achieve this, we propose a diffusion-based non-conformity score that captures both topological and temporal uncertainties within evolving networks. Additionally, we develop an efficiency-aware optimization algorithm that improves the conformal prediction process, enhancing computational efficiency and reducing coverage violations. Extensive experiments on diverse real-world temporal graphs, including WIKI, REDDIT, DBLP, and IBM Anti-Money Laundering dataset, demonstrate NCPNET's capability to ensure guaranteed coverage in temporal graphs, achieving up to a 31% reduction in prediction set size on the WIKI dataset, significantly improving efficiency compared to state-of-the-art methods. Our data and code are available at https://github.com/ODYSSEYWT/NCPNET.
Authors: Seung Hyun Cheon, Meredith Stewart, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun
Abstract: Many safety failures in machine learning arise when models are used to assign predictions to people (often in settings like lending, hiring, or content moderation) without accounting for how individuals can change their inputs. In this work, we introduce a formal validation procedure for the responsiveness of predictions with respect to interventions on their features. Our procedure frames responsiveness as a type of sensitivity analysis in which practitioners control a set of changes by specifying constraints over interventions and distributions over downstream effects. We describe how to estimate responsiveness for the predictions of any model and any dataset using only black-box access, and how to use these estimates to support tasks such as falsification and failure probability estimation. We develop algorithms that construct these estimates by generating a uniform sample of reachable points, and demonstrate how they can promote safety in real-world applications such as recidivism prediction, organ transplant prioritization, and content moderation.
Authors: Jiyeon Bae, Hyeon Jeon, Jinwook Seo
Abstract: Evaluating the accuracy of dimensionality reduction (DR) projections in preserving the structure of high-dimensional data is crucial for reliable visual analytics. Diverse evaluation metrics targeting different structural characteristics have thus been developed. However, evaluations of DR projections can become biased if highly correlated metrics--those measuring similar structural characteristics--are inadvertently selected, favoring DR techniques that emphasize those characteristics. To address this issue, we propose a novel workflow that reduces bias in the selection of evaluation metrics by clustering metrics based on their empirical correlations rather than on their intended design characteristics alone. Our workflow works by computing metric similarity using pairwise correlations, clustering metrics to minimize overlap, and selecting a representative metric from each cluster. Quantitative experiments demonstrate that our approach improves the stability of DR evaluation, which indicates that our workflow contributes to mitigating evaluation bias.
Authors: Xinquan Huang, Paris Perdikaris
Abstract: Neural networks have emerged as powerful surrogates for solving partial differential equations (PDEs), offering significant computational speedups over traditional methods. However, these models suffer from a critical limitation: error accumulation during long-term rollouts, where small inaccuracies compound exponentially, eventually causing complete divergence from physically valid solutions. We present PhysicsCorrect, a training-free correction framework that enforces PDE consistency at each prediction step by formulating correction as a linearized inverse problem based on PDE residuals. Our key innovation is an efficient caching strategy that precomputes the Jacobian and its pseudoinverse during an offline warm-up phase, reducing computational overhead by two orders of magnitude compared to standard correction approaches. Across three representative PDE systems -- Navier-Stokes fluid dynamics, wave equations, and the chaotic Kuramoto-Sivashinsky equation -- PhysicsCorrect reduces prediction errors by up to 100x while adding negligible inference time (under 5\%). The framework integrates seamlessly with diverse architectures including Fourier Neural Operators, UNets, and Vision Transformers, effectively transforming unstable neural surrogates into reliable simulation tools that bridge the gap between deep learning's computational efficiency and the physical fidelity demanded by practical scientific applications.
Authors: Shravan Doda, Shashidhar Reddy Javaji, Zining Zhu
Abstract: In the current machine learning landscape, we face a "model lake" phenomenon: Given a task, there is a proliferation of trained models with similar performances despite different behavior. For model users attempting to navigate and select from the models, documentation comparing model pairs is helpful. However, for every $N$ models there could be $O(N^2)$ pairwise comparisons, a number prohibitive for the model developers to manually perform pairwise comparisons and prepare documentations. To facilitate fine-grained pairwise comparisons among models, we introduced $\textbf{VERBA}$. Our approach leverages a large language model (LLM) to generate verbalizations of model differences by sampling from the two models. We established a protocol that evaluates the informativeness of the verbalizations via simulation. We also assembled a suite with a diverse set of commonly used machine learning models as a benchmark. For a pair of decision tree models with up to 5% performance difference but 20-25% behavioral differences, $\textbf{VERBA}$ effectively verbalizes their variations with up to 80% overall accuracy. When we included the models' structural information, the verbalization's accuracy further improved to 90%. $\textbf{VERBA}$ opens up new research avenues for improving the transparency and comparability of machine learning models in a post-hoc manner.
Authors: Fangzhou Shi, Xiaopeng Ke, Xinye Xiong, Kexin Meng, Chang Men, Zhengdan Zhu
Abstract: The proliferation of ride-hailing aggregator platforms presents significant growth opportunities for ride-service providers by increasing order volume and gross merchandise value (GMV). On most ride-hailing aggregator platforms, service providers that offer lower fares are ranked higher in listings and, consequently, are more likely to be selected by passengers. This competitive ranking mechanism creates a strong incentive for service providers to adopt coupon strategies that lower prices to secure a greater number of orders, as order volume directly influences their long-term viability and sustainability. Thus, designing an effective coupon strategy that can dynamically adapt to market fluctuations while optimizing order acquisition under budget constraints is a critical research challenge. However, existing studies in this area remain scarce. To bridge this gap, we propose FCA-RL, a novel reinforcement learning-based subsidy strategy framework designed to rapidly adapt to competitors' pricing adjustments. Our approach integrates two key techniques: Fast Competition Adaptation (FCA), which enables swift responses to dynamic price changes, and Reinforced Lagrangian Adjustment (RLA), which ensures adherence to budget constraints while optimizing coupon decisions on new price landscape. Furthermore, we introduce RideGym, the first dedicated simulation environment tailored for ride-hailing aggregators, facilitating comprehensive evaluation and benchmarking of different pricing strategies without compromising real-world operational efficiency. Experimental results demonstrate that our proposed method consistently outperforms baseline approaches across diverse market conditions, highlighting its effectiveness in subsidy optimization for ride-hailing service providers.
Authors: Yang Yang, Xiaolu Zhou, Bosong Ding, Miao Xin
Abstract: Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging process due to the inefficiencies and inconsistencies inherent in conventional reward engineering methodologies. Recent advances have explored leveraging large language models (LLMs) to automate reward function design. However, their suboptimal performance in numerical optimization often yields unsatisfactory reward quality, while the evolutionary search paradigm demonstrates inefficient utilization of simulation resources, resulting in prohibitively lengthy design cycles with disproportionate computational overhead. To address these challenges, we propose the Uncertainty-aware Reward Design Process (URDP), a novel framework that integrates large language models to streamline reward function design and evaluation in RL environments. URDP quantifies candidate reward function uncertainty based on self-consistency analysis, enabling simulation-free identification of ineffective reward components while discovering novel reward components. Furthermore, we introduce uncertainty-aware Bayesian optimization (UABO), which incorporates uncertainty estimation to significantly enhance hyperparameter configuration efficiency. Finally, we construct a bi-level optimization architecture by decoupling the reward component optimization and the hyperparameter tuning. URDP orchestrates synergistic collaboration between the reward logic reasoning of the LLMs and the numerical optimization strengths of the Bayesian Optimization. We conduct a comprehensive evaluation of URDP across 35 diverse tasks spanning three benchmark environments. Our experimental results demonstrate that URDP not only generates higher-quality reward functions but also achieves significant improvements in the efficiency of automated reward design compared to existing approaches.
Authors: Zhaoyu Zhang, Lingyi Wang, Wei Wu, Fuhui Zhou, Qihui Wu
Abstract: Data-driven semantic communication is based on superficial statistical patterns, thereby lacking interpretability and generalization, especially for applications with the presence of unseen data. To address these challenges, we propose a novel knowledge graph-enhanced zero-shot semantic communication (KGZS-SC) network. Guided by the structured semantic information from a knowledge graph-based semantic knowledge base (KG-SKB), our scheme provides generalized semantic representations and enables reasoning for unseen cases. Specifically, the KG-SKB aligns the semantic features in a shared category semantics embedding space and enhances the generalization ability of the transmitter through aligned semantic features, thus reducing communication overhead by selectively transmitting compact visual semantics. At the receiver, zero-shot learning (ZSL) is leveraged to enable direct classification for unseen cases without the demand for retraining or additional computational overhead, thereby enhancing the adaptability and efficiency of the classification process in dynamic or resource-constrained environments. The simulation results conducted on the APY datasets show that the proposed KGZS-SC network exhibits robust generalization and significantly outperforms existing SC frameworks in classifying unseen categories across a range of SNR levels.
Authors: Alif Ashrafee, Jedrzej Kozal, Michal Wozniak, Bartosz Krawczyk
Abstract: Traditional continual learning methods prioritize knowledge retention and focus primarily on mitigating catastrophic forgetting, implicitly assuming that the data distribution of previously learned tasks remains static. This overlooks the dynamic nature of real-world data streams, where concept drift permanently alters previously seen data and demands both stability and rapid adaptation. We introduce a holistic framework for continual learning under concept drift that simulates realistic scenarios by evolving task distributions. As a baseline, we consider Full Relearning (FR), in which the model is retrained from scratch on newly labeled samples from the drifted distribution. While effective, this approach incurs substantial annotation and computational overhead. To address these limitations, we propose Adaptive Memory Realignment (AMR), a lightweight alternative that equips rehearsal-based learners with a drift-aware adaptation mechanism. AMR selectively removes outdated samples of drifted classes from the replay buffer and repopulates it with a small number of up-to-date instances, effectively realigning memory with the new distribution. This targeted resampling matches the performance of FR while reducing the need for labeled data and computation by orders of magnitude. To enable reproducible evaluation, we introduce four concept-drift variants of standard vision benchmarks: Fashion-MNIST-CD, CIFAR10-CD, CIFAR100-CD, and Tiny-ImageNet-CD, where previously seen classes reappear with shifted representations. Comprehensive experiments on these datasets using several rehearsal-based baselines show that AMR consistently counters concept drift, maintaining high accuracy with minimal overhead. These results position AMR as a scalable solution that reconciles stability and plasticity in non-stationary continual learning environments.
Authors: Sooyeon Kim, Giung Nam, Juho Lee
Abstract: Recent work has framed constrained text generation with autoregressive language models as a probabilistic inference problem. Among these, Zhao et al. (2024) introduced a promising approach based on twisted Sequential Monte Carlo, which incorporates learned twist functions and twist-induced proposals to guide the generation process. However, in constrained generation settings where the target distribution concentrates on outputs that are unlikely under the base model, learning becomes challenging due to sparse and uninformative reward signals. We show that iteratively refining the base model through self-distillation alleviates this issue by making the model progressively more aligned with the target, leading to substantial gains in generation quality.
Authors: Haodong Zhang, Hongqi Li
Abstract: Electroencephalography (EEG) is one of the most common signals used to capture the electrical activity of the brain, and the decoding of EEG, to acquire the user intents, has been at the forefront of brain-computer/machine interfaces (BCIs/BMIs) research. Compared to traditional EEG analysis methods with machine learning, the advent of deep learning approaches have gradually revolutionized the field by providing an end-to-end long-cascaded architecture, which can learn more discriminative features automatically. Among these, Transformer is renowned for its strong handling capability of sequential data by the attention mechanism, and the application of Transformers in various EEG processing tasks is increasingly prevalent. This article delves into a relevant survey, summarizing the latest application of Transformer models in EEG decoding since it appeared. The evolution of the model architecture is followed to sort and organize the related advances, in which we first elucidate the fundamentals of the Transformer that benefits EEG decoding and its direct application. Then, the common hybrid architectures by integrating basic Transformer with other deep learning techniques (convolutional/recurrent/graph/spiking neural netwo-rks, generative adversarial networks, diffusion models, etc.) is overviewed in detail. The research advances of applying the modified intrinsic structures of customized Transformer have also been introduced. Finally, the current challenges and future development prospects in this rapidly evolving field are discussed. This paper aims to help readers gain a clear understanding of the current state of Transformer applications in EEG decoding and to provide valuable insights for future research endeavors.
Authors: Changhun Kim, Yechan Mun, Sangchul Hahn, Eunho Yang
Abstract: This study proposes DeltaSHAP, a novel explainable artificial intelligence (XAI) algorithm specifically designed for online patient monitoring systems. In clinical environments, discovering the causes driving patient risk evolution is critical for timely intervention, yet existing XAI methods fail to address the unique requirements of clinical time series explanation tasks. To this end, DeltaSHAP addresses three key clinical needs: explaining the changes in the consecutive predictions rather than isolated prediction scores, providing both magnitude and direction of feature attributions, and delivering these insights in real time. By adapting Shapley values to temporal settings, our approach accurately captures feature coalition effects. It further attributes prediction changes using only the actually observed feature combinations, making it efficient and practical for time-sensitive clinical applications. We also introduce new evaluation metrics to evaluate the faithfulness of the attributions for online time series, and demonstrate through experiments on online patient monitoring tasks that DeltaSHAP outperforms state-of-the-art XAI methods in both explanation quality as 62% and computational efficiency as 33% time reduction on the MIMIC-III decompensation benchmark. We release our code at https://github.com/AITRICS/DeltaSHAP.
Authors: JunHyeok Oh, Byung-Jun Lee
Abstract: Offline reinforcement learning (RL) optimizes a policy using only a fixed dataset, making it a practical approach in scenarios where interaction with the environment is costly. Due to this limitation, generalization ability is key to improving the performance of offline RL algorithms, as demonstrated by recent successes of offline RL with diffusion models. However, it remains questionable whether such diffusion models are necessary for highly performing offline RL algorithms, given their significant computational requirements during inference. In this paper, we propose Penalized Action Noise Injection (PANI), a method that simply enhances offline learning by utilizing noise-injected actions to cover the entire action space, while penalizing according to the amount of noise injected. This approach is inspired by how diffusion models have worked in offline RL algorithms. We provide a theoretical foundation for this method, showing that offline RL algorithms with such noise-injected actions solve a modified Markov Decision Process (MDP), which we call the noisy action MDP. PANI is compatible with a wide range of existing off-policy and offline RL algorithms, and despite its simplicity, it demonstrates significant performance improvements across various benchmarks.
Authors: Muhammad Usama, Dong Eui Chang
Abstract: Equalizer parameter optimization for signal integrity in high-speed Dynamic Random Access Memory systems is crucial but often computationally demanding or model-reliant. This paper introduces a data-driven framework employing learned latent signal representations for efficient signal integrity evaluation, coupled with a model-free Advantage Actor-Critic reinforcement learning agent for parameter optimization. The latent representation captures vital signal integrity features, offering a fast alternative to direct eye diagram analysis during optimization, while the reinforcement learning agent derives optimal equalizer settings without explicit system models. Applied to industry-standard Dynamic Random Access Memory waveforms, the method achieved significant eye-opening window area improvements: 42.7\% for cascaded Continuous-Time Linear Equalizer and Decision Feedback Equalizer structures, and 36.8\% for Decision Feedback Equalizer-only configurations. These results demonstrate superior performance, computational efficiency, and robust generalization across diverse Dynamic Random Access Memory units compared to existing techniques. Core contributions include an efficient latent signal integrity metric for optimization, a robust model-free reinforcement learning strategy, and validated superior performance for complex equalizer architectures.
Authors: Caio Azevedo, Lina Achaji, Stefano Sabatini, Nicola Poerio, Grzegorz Bartyzel, Sascha Hornauer, Fabien Moutarde
Abstract: Trajectory prediction is an essential step in the pipeline of an autonomous vehicle. Inaccurate or inconsistent predictions regarding the movement of agents in its surroundings lead to poorly planned maneuvers and potentially dangerous situations for the end-user. Current state-of-the-art deep-learning-based trajectory prediction models can achieve excellent accuracy on public datasets. However, when used in more complex, interactive scenarios, they often fail to capture important interdependencies between agents, leading to inconsistent predictions among agents in the traffic scene. Inspired by the efficacy of incorporating human preference into large language models, this work fine-tunes trajectory prediction models in multi-agent settings using preference optimization. By taking as input automatically calculated preference rankings among predicted futures in the fine-tuning process, our experiments--using state-of-the-art models on three separate datasets--show that we are able to significantly improve scene consistency while minimally sacrificing trajectory prediction accuracy and without adding any excess computational requirements at inference time.
Authors: Zihan Tan, Suyuan Huang, Guancheng Wan, Wenke Huang, He Li, Mang Ye
Abstract: Federated Graph Learning (FGL) combines the privacy-preserving capabilities of federated learning (FL) with the strong graph modeling capability of Graph Neural Networks (GNNs). Current research addresses subgraph-FL only from the structural perspective, neglecting the propagation of graph signals on spatial and spectral domains of the structure. From a spatial perspective, subgraph-FL introduces edge disconnections between clients, leading to disruptions in label signals and a degradation in the class knowledge of the global GNN. From a spectral perspective, spectral heterogeneity causes inconsistencies in signal frequencies across subgraphs, which makes local GNNs overfit the local signal propagation schemes. As a result, spectral client drifts occur, undermining global generalizability. To tackle the challenges, we propose a global knowledge repository to mitigate label signal disruption and a frequency alignment to address spectral client drifts. The combination of spatial and spectral strategies forms our framework S2FGL. Extensive experiments on multiple datasets demonstrate the superiority of S2FGL. The code is available at https://github.com/Wonder7racer/S2FGL.git.
Authors: Francesco Alesiani, Henrik Christiansen, Federico Errica
Abstract: Kolmogorov Arnold Networks (KANs) are an emerging architecture for building machine learning models. KANs are based on the theoretical foundation of the Kolmogorov-Arnold Theorem and its expansions, which provide an exact representation of a multi-variate continuous bounded function as the composition of a limited number of univariate continuous functions. While such theoretical results are powerful, their use as a representation learning alternative to a multi-layer perceptron (MLP) hinges on the ad-hoc choice of the number of bases modeling each of the univariate functions. In this work, we show how to address this problem by adaptively learning a potentially infinite number of bases for each univariate function during training. We therefore model the problem as a variational inference optimization problem. Our proposal, called InfinityKAN, which uses backpropagation, extends the potential applicability of KANs by treating an important hyperparameter as part of the learning process.
Authors: Vaidehi Srinivas
Abstract: We study the problem of conformal prediction in a novel online framework that directly optimizes efficiency. In our problem, we are given a target miscoverage rate $\alpha > 0$, and a time horizon $T$. On each day $t \le T$ an algorithm must output an interval $I_t \subseteq [0, 1]$, then a point $y_t \in [0, 1]$ is revealed. The goal of the algorithm is to achieve coverage, that is, $y_t \in I_t$ on (close to) a $(1 - \alpha)$-fraction of days, while maintaining efficiency, that is, minimizing the average volume (length) of the intervals played. This problem is an online analogue to the problem of constructing efficient confidence intervals. We study this problem over arbitrary and exchangeable (random order) input sequences. For exchangeable sequences, we show that it is possible to construct intervals that achieve coverage $(1 - \alpha) - o(1)$, while having length upper bounded by the best fixed interval that achieves coverage in hindsight. For arbitrary sequences however, we show that any algorithm that achieves a $\mu$-approximation in average length compared to the best fixed interval achieving coverage in hindsight, must make a multiplicative factor more mistakes than $\alpha T$, where the multiplicative factor depends on $\mu$ and the aspect ratio of the problem. Our main algorithmic result is a matching algorithm that can recover all Pareto-optimal settings of $\mu$ and number of mistakes. Furthermore, our algorithm is deterministic and therefore robust to an adaptive adversary. This gap between the exchangeable and arbitrary settings is in contrast to the classical online learning problem. In fact, we show that no single algorithm can simultaneously be Pareto-optimal for arbitrary sequences and optimal for exchangeable sequences. On the algorithmic side, we give an algorithm that achieves the near-optimal tradeoff between the two cases.
Authors: Chenxu Wang, Yilin Lyu, Zicheng Sun, Liping Jing
Abstract: Continual fine-tuning of Large Language Models (LLMs) is hampered by the trade-off between efficiency and expressiveness. Low-Rank Adaptation (LoRA) offers efficiency but constrains the model's ability to learn new tasks and transfer knowledge due to its low-rank nature and reliance on explicit parameter constraints. We propose GORP (Gradient LOw Rank Projection) for Continual Learning, a novel training strategy that overcomes these limitations by synergistically combining full and low-rank parameters and jointly updating within a unified low-rank gradient subspace. GORP expands the optimization space while preserving efficiency and mitigating catastrophic forgetting. Extensive experiments on continual learning benchmarks demonstrate GORP's superior performance compared to existing state-of-the-art approaches. Code is available at https://github.com/Wcxwcxw/GORP.
Authors: Ahmed G. Habashi, Ahmed M. Azab, Seif Eldawlatly, Gamal M. Aly
Abstract: Cross-subject motor imagery (CS-MI) classification in brain-computer interfaces (BCIs) is a challenging task due to the significant variability in Electroencephalography (EEG) patterns across different individuals. This variability often results in lower classification accuracy compared to subject-specific models, presenting a major barrier to developing calibration-free BCIs suitable for real-world applications. In this paper, we introduce a novel approach that significantly enhances cross-subject MI classification performance through optimized preprocessing and deep learning techniques. Our approach involves direct classification of Short-Time Fourier Transform (STFT)-transformed EEG data, optimized STFT parameters, and a balanced batching strategy during training of a Convolutional Neural Network (CNN). This approach is uniquely validated across four different datasets, including three widely-used benchmark datasets leading to substantial improvements in cross-subject classification, achieving 67.60% on the BCI Competition IV Dataset 1 (IV-1), 65.96% on Dataset 2A (IV-2A), and 80.22% on Dataset 2B (IV-2B), outperforming state-of-the-art techniques. Additionally, we systematically investigate the classification performance using MI windows ranging from the full 4-second window to 1-second windows. These results establish a new benchmark for generalizable, calibration-free MI classification in addition to contributing a robust open-access dataset to advance research in this domain.
Authors: Alicja R\k{a}czkowska, Riccardo Belluzzo, Piotr Zieli\'nski, Joanna Baran, Pawe{\l} Olszewski
Abstract: The text-to-SQL task is an active challenge in Natural Language Processing. Many existing solutions focus on using black-box language models extended with specialized components within customized end-to-end text-to-SQL pipelines. While these solutions use both closed-source proprietary language models and coding-oriented open-source models, there is a lack of research regarding SQL-specific generative models. At the same time, recent advancements in self-correcting generation strategies show promise for improving the capabilities of existing architectures. The application of these concepts to the text-to-SQL task remains unexplored. In this paper, we introduce RetrySQL, a new approach to training text-to-SQL generation models. We prepare reasoning steps for reference SQL queries and then corrupt them to create retry data that contains both incorrect and corrected steps, divided with a special token. We continuously pre-train an open-source coding model with this data and demonstrate that retry steps yield an improvement of up to 4 percentage points in both overall and challenging execution accuracy metrics, compared to pre-training without retry data. Additionally, we confirm that supervised fine-tuning with LoRA is ineffective for learning from retry data and that full-parameter pre-training is a necessary requirement for that task. We showcase that the self-correcting behavior is learned by the model and the increase in downstream accuracy metrics is a result of this additional skill. Finally, we incorporate RetrySQL-trained models into the full text-to-SQL pipeline and showcase that they are competitive in terms of execution accuracy with proprietary models that contain orders of magnitude more parameters. RetrySQL demonstrates that self-correction can be learned in the text-to-SQL task and provides a novel way of improving generation accuracy for SQL-oriented language models.
Authors: David A. Danhofer, Davide D'Ascenzo, Rafael Dubach, Tomaso Poggio
Abstract: Overparametrized Deep Neural Networks (DNNs) have demonstrated remarkable success in a wide variety of domains too high-dimensional for classical shallow networks subject to the curse of dimensionality. However, open questions about fundamental principles, that govern the learning dynamics of DNNs, remain. In this position paper we argue that it is the ability of DNNs to exploit the compositionally sparse structure of the target function driving their success. As such, DNNs can leverage the property that most practically relevant functions can be composed from a small set of constituent functions, each of which relies only on a low-dimensional subset of all inputs. We show that this property is shared by all efficiently Turing-computable functions and is therefore highly likely present in all current learning problems. While some promising theoretical insights on questions concerned with approximation and generalization exist in the setting of compositionally sparse functions, several important questions on the learnability and optimization of DNNs remain. Completing the picture of the role of compositional sparsity in deep learning is essential to a comprehensive theory of artificial, and even general, intelligence.
Authors: Luca Baroni, Galvin Khara, Joachim Schaeffer, Marat Subkhankulov, Stefan Heimersheim
Abstract: Layer-wise normalization (LN) is an essential component of virtually all transformer-based large language models. While its effects on training stability are well documented, its role at inference time is poorly understood. Additionally, LN layers hinder mechanistic interpretability by introducing additional nonlinearities and increasing the interconnectedness of individual model components. Here, we show that all LN layers can be removed from every GPT-2 model with only a small increase in validation loss (e.g. +0.03 cross-entropy loss for GPT-2 XL). Thus, LN cannot play a substantial role in language modeling. We find that the amount of fine-tuning data needed for LN removal grows sublinearly with model parameters, suggesting scaling to larger models is feasible. We release a suite of LN-free GPT-2 models on Hugging Face. Furthermore, we test interpretability techniques on LN-free models. Direct logit attribution now gives the exact direct effect of individual components, while the accuracy of attribution patching does not significantly improve. We also confirm that GPT-2's "confidence neurons" are inactive in the LN-free models. Our work clarifies the role of LN layers in language modeling, showing that GPT-2-class models can function without LN layers. We hope that our LN-free analogs of the GPT-2 family of models will enable more precise interpretability research and improve our understanding of language models.
Authors: Fabian Kresse, Emily Yu, Christoph H. Lampert
Abstract: Learned Differentiable Boolean Logic Networks (DBNs) already deliver efficient inference on resource-constrained hardware. We extend them with a trainable, differentiable interconnect whose parameter count remains constant as input width grows, allowing DBNs to scale to far wider layers than earlier learnable-interconnect designs while preserving their advantageous accuracy. To further reduce model size, we propose two complementary pruning stages: an SAT-based logic equivalence pass that removes redundant gates without affecting performance, and a similarity-based, data-driven pass that outperforms a magnitude-style greedy baseline and offers a superior compression-accuracy trade-off.
Authors: Sertac Kilickaya, Levent Eren
Abstract: Purpose: The primary aim of this study is to enhance fault diagnosis in induction machines by leveraging the Pad\'e Approximant Neuron (PAON) model. While accelerometers and microphones are standard in motor condition monitoring, deep learning models with nonlinear neuron architectures offer promising improvements in diagnostic performance. This research addresses the question: Can Pad\'e Approximant Neural Networks (Pad\'eNets) outperform conventional Convolutional Neural Networks (CNNs) and Self-Organized Operational Neural Networks (Self-ONNs) in diagnosing electrical and mechanical faults using vibration and acoustic data? Methods: We evaluate and compare the diagnostic capabilities of three deep learning architectures: one-dimensional CNNs, Self-ONNs, and Pad\'eNets. These models are tested on the University of Ottawa's publicly available constant-speed induction motor datasets, which include both vibration and acoustic sensor data. The Pad\'eNet model is designed to introduce enhanced nonlinearity and is compatible with unbounded activation functions such as Leaky ReLU. Results and Conclusion: Pad\'eNets consistently outperformed the baseline models, achieving diagnostic accuracies of 99.96%, 98.26%, 97.61%, and 98.33% for accelerometers 1, 2, 3, and the acoustic sensor, respectively. The enhanced nonlinearity of Pad\'eNets, together with their compatibility with unbounded activation functions, significantly improves fault diagnosis performance in induction motor condition monitoring.
Authors: Fran\c{c}ois Rozet, Ruben Ohana, Michael McCabe, Gilles Louppe, Fran\c{c}ois Lanusse, Shirley Ho
Abstract: The steep computational cost of diffusion models at inference hinders their use as fast physics emulators. In the context of image and video generation, this computational drawback has been addressed by generating in the latent space of an autoencoder instead of the pixel space. In this work, we investigate whether a similar strategy can be effectively applied to the emulation of dynamical systems and at what cost. We find that the accuracy of latent-space emulation is surprisingly robust to a wide range of compression rates (up to 1000x). We also show that diffusion-based emulators are consistently more accurate than non-generative counterparts and compensate for uncertainty in their predictions with greater diversity. Finally, we cover practical design choices, spanning from architectures to optimizers, that we found critical to train latent-space emulators.
Authors: Hazal Mogultay Ozcan, Sinan Kalkan, Fatos T. Yarman-Vural
Abstract: In this paper, we propose a novel model called Learnable VAE (L-VAE), which learns a disentangled representation together with the hyperparameters of the cost function. L-VAE can be considered as an extension of \b{eta}-VAE, wherein the hyperparameter, \b{eta}, is empirically adjusted. L-VAE mitigates the limitations of \b{eta}-VAE by learning the relative weights of the terms in the loss function to control the dynamic trade-off between disentanglement and reconstruction losses. In the proposed model, the weight of the loss terms and the parameters of the model architecture are learned concurrently. An additional regularization term is added to the loss function to prevent bias towards either reconstruction or disentanglement losses. Experimental analyses show that the proposed L-VAE finds an effective balance between reconstruction fidelity and disentangling the latent dimensions. Comparisons of the proposed L-VAE against \b{eta}-VAE, VAE, ControlVAE, DynamicVAE, and {\sigma}-VAE on datasets, such as dSprites, MPI3D-complex, Falcor3D, and Isaac3D reveals that L-VAE consistently provides the best or the second best performances measured by a set of disentanglement metrics. Moreover, qualitative experiments on CelebA dataset, confirm the success of the L-VAE model for disentangling the facial attributes.
Authors: Antoine Honor\'e, Borja Rodr\'iguez G\'alvez, Yoomi Park, Yitian Zhou, Volker M. Lauschke, Ming Xiao
Abstract: Variant effect predictors (VEPs) aim to assess the functional impact of protein variants, traditionally relying on multiple sequence alignments (MSAs). This approach assumes that naturally occurring variants are fit, an assumption challenged by pharmacogenomics, where some pharmacogenes experience low evolutionary pressure. Deep mutational scanning (DMS) datasets provide an alternative by offering quantitative fitness scores for variants. In this work, we propose a transformer-based matrix variational auto-encoder (matVAE) with a structured prior and evaluate its performance on 33 DMS datasets corresponding to 26 drug target and ADME proteins from the ProteinGym benchmark. Our model trained on MSAs (matVAE-MSA) outperforms the state-of-the-art DeepSequence model in zero-shot prediction on DMS datasets, despite using an order of magnitude fewer parameters and requiring less computation at inference time. We also compare matVAE-MSA to matENC-DMS, a model of similar capacity trained on DMS data, and find that the latter performs better on supervised prediction tasks. Additionally, incorporating AlphaFold-generated structures into our transformer model further improves performance, achieving results comparable to DeepSequence trained on MSAs and finetuned on DMS. These findings highlight the potential of DMS datasets to replace MSAs without significant loss in predictive performance, motivating further development of DMS datasets and exploration of their relationships to enhance variant effect prediction.
Authors: Irena Girshovitz, Atai Ambus, Moni Shahar, Ran Gilad-Bachrach
Abstract: Background: The use of Electronic Health Records (EHRs) for epidemiological studies and artificial intelligence (AI) training is increasing rapidly. The reliability of the results depends on the accuracy and completeness of EHR data. However, EHR data often contain significant quality issues, including misrepresentations of subpopulations, biases, and systematic errors, as they are primarily collected for clinical and billing purposes. Existing quality assessment methods remain insufficient, lacking systematic procedures to assess data fitness for research. Methods: We present the Medical Data Pecking approach, which adapts unit testing and coverage concepts from software engineering to identify data quality concerns. We demonstrate our approach using the Medical Data Pecking Tool (MDPT), which consists of two main components: (1) an automated test generator that uses large language models and grounding techniques to create a test suite from data and study descriptions, and (2) a data testing framework that executes these tests, reporting potential errors and coverage. Results: We evaluated MDPT on three datasets: All of Us (AoU), MIMIC-III, and SyntheticMass, generating 55-73 tests per cohort across four conditions. These tests correctly identified 20-43 non-aligned or non-conforming data issues. We present a detailed analysis of the LLM-generated test suites in terms of reference grounding and value accuracy. Conclusion: Our approach incorporates external medical knowledge to enable context-sensitive data quality testing as part of the data analysis workflow to improve the validity of its outcomes. Our approach tackles these challenges from a quality assurance perspective, laying the foundation for further development such as additional data modalities and improved grounding methods.
Authors: David H. Mguni
Abstract: We introduce a new hierarchical deep learning framework for recursive higher-order meta-learning that enables neural networks (NNs) to construct, solve, and generalise across hierarchies of tasks. Central to this approach is a generative mechanism that creates \emph{virtual tasks} -- synthetic problem instances designed to enable the meta-learner to learn \emph{soft constraints} and unknown generalisable rules across related tasks. Crucially, this enables the framework to generate its own informative, task-grounded datasets thereby freeing machine learning (ML) training from the limitations of relying entirely on human-generated data. By actively exploring the virtual point landscape and seeking out tasks lower-level learners find difficult, the meta-learner iteratively refines constraint regions. This enhances inductive biases, regularises the adaptation process, and produces novel, unanticipated tasks and constraints required for generalisation. Each meta-level of the hierarchy corresponds to a progressively abstracted generalisation of problems solved at lower levels, enabling a structured and interpretable learning progression. By interpreting meta-learners as category-theoretic \emph{functors} that generate and condition a hierarchy of subordinate learners, we establish a compositional structure that supports abstraction and knowledge transfer across progressively generalised tasks. The category-theoretic perspective unifies existing meta-learning models and reveals how learning processes can be transformed and compared through functorial relationships, while offering practical design principles for structuring meta-learning. We speculate this architecture may underpin the next generation of NNs capable of autonomously generating novel, instructive tasks and their solutions, thereby advancing ML towards general artificial intelligence.
Authors: Alberto Caron, Chris Hicks, Vasilios Mavroudis
Abstract: In this work, we address the challenge of data-efficient exploration in reinforcement learning by examining existing principled, information-theoretic approaches to intrinsic motivation. Specifically, we focus on a class of exploration bonuses that targets epistemic uncertainty rather than the aleatoric noise inherent in the environment. We prove that these bonuses naturally signal epistemic information gains and converge to zero once the agent becomes sufficiently certain about the environment's dynamics and rewards, thereby aligning exploration with genuine knowledge gaps. Our analysis provides formal guarantees for IG-based approaches, which previously lacked theoretical grounding. To enable practical use, we also discuss tractable approximations via sparse variational Gaussian Processes, Deep Kernels and Deep Ensemble models. We then outline a general framework - Predictive Trajectory Sampling with Bayesian Exploration (PTS-BE) - which integrates model-based planning with information-theoretic bonuses to achieve sample-efficient deep exploration. We empirically demonstrate that PTS-BE substantially outperforms other baselines across a variety of environments characterized by sparse rewards and/or purely exploratory tasks.
Authors: Harry Cheng, Ming-Hui Liu, Yangyang Guo, Tianyi Wang, Liqiang Nie, Mohan Kankanhalli
Abstract: Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often demonstrate that these two objectives are inherently conflicting, revealing a trade-off between them. In this paper, we, for the first time, uncover and formally define a causal relationship between fairness and generalization. Building on the back-door adjustment, we show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions. Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals. Across three cross-domain benchmarks, DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art detectors, validating both its theoretical foundation and practical effectiveness.
Authors: Ramchalam Kinattinkara Ramakrishnan, Zhaocong Yuan, Shaojie Zhuo, Chen Feng, Yicheng Lin, Chenzheng Su, Xiaopeng Zhang
Abstract: Speculative decoding generally dictates having a small, efficient draft model that is either pretrained or distilled offline to a particular target model series, for instance, Llama or Qwen models. However, within online deployment settings, there are two major challenges: 1) usage of a target model that is incompatible with the draft model; 2) expectation of latency improvements over usage and time. In this work, we propose OmniDraft, a unified framework that enables a single draft model to operate with any target model and adapt dynamically to user data. We introduce an online n-gram cache with hybrid distillation fine-tuning to address the cross-vocabulary mismatch across draft and target models; and further improve decoding speed by leveraging adaptive drafting techniques. OmniDraft is particularly suitable for on-device LLM applications where model cost, efficiency and user customization are the major points of contention. This further highlights the need to tackle the above challenges and motivates the \textit{``one drafter for all''} paradigm. We showcase the proficiency of the OmniDraft framework by performing online learning on math reasoning, coding and text generation tasks. Notably, OmniDraft enables a single Llama-68M model to pair with various target models including Vicuna-7B, Qwen2-7B and Llama3-8B models for speculative decoding; and additionally provides up to 1.5-2x speedup.
Authors: Siqi Zhao, Joshua Moller, Porfi Quintero-Cadena, Lood van Niekerk
Abstract: Therapeutic antibodies require not only high-affinity target engagement, but also favorable manufacturability, stability, and safety profiles for clinical effectiveness. These properties are collectively called `developability'. To enable a computational framework for optimizing antibody sequences for favorable developability, we introduce a guided discrete diffusion model trained on natural paired heavy- and light-chain sequences from the Observed Antibody Space (OAS) and quantitative developability measurements for 246 clinical-stage antibodies. To steer generation toward biophysically viable candidates, we integrate a Soft Value-based Decoding in Diffusion (SVDD) Module that biases sampling without compromising naturalness. In unconstrained sampling, our model reproduces global features of both the natural repertoire and approved therapeutics, and under SVDD guidance we achieve significant enrichment in predicted developability scores over unguided baselines. When combined with high-throughput developability assays, this framework enables an iterative, ML-driven pipeline for designing antibodies that satisfy binding and biophysical criteria in tandem.
Authors: Francesco Di Salvo, Hanh Huyen My Nguyen, Christian Ledig
Abstract: Deep Learning (DL) has revolutionized medical imaging, yet its adoption is constrained by data scarcity and privacy regulations, limiting access to diverse datasets. Federated Learning (FL) enables decentralized training but suffers from high communication costs and is often restricted to a single downstream task, reducing flexibility. We propose a data-sharing method via Differentially Private (DP) generative models. By adopting foundation models, we extract compact, informative embeddings, reducing redundancy and lowering computational overhead. Clients collaboratively train a Differentially Private Conditional Variational Autoencoder (DP-CVAE) to model a global, privacy-aware data distribution, supporting diverse downstream tasks. Our approach, validated across multiple feature extractors, enhances privacy, scalability, and efficiency, outperforming traditional FL classifiers while ensuring differential privacy. Additionally, DP-CVAE produces higher-fidelity embeddings than DP-CGAN while requiring $5{\times}$ fewer parameters.
Authors: Thomas Hazenberg, Yao Ma, Seyed Sahand Mohammadi Ziabari, Marijn van Rijswijk
Abstract: This study investigates how Multi-Agent Reinforcement Learning (MARL) can improve dynamic pricing strategies in supply chains, particularly in contexts where traditional ERP systems rely on static, rule-based approaches that overlook strategic interactions among market actors. While recent research has applied reinforcement learning to pricing, most implementations remain single-agent and fail to model the interdependent nature of real-world supply chains. This study addresses that gap by evaluating the performance of three MARL algorithms: MADDPG, MADQN, and QMIX against static rule-based baselines, within a simulated environment informed by real e-commerce transaction data and a LightGBM demand prediction model. Results show that rule-based agents achieve near-perfect fairness (Jain's Index: 0.9896) and the highest price stability (volatility: 0.024), but they fully lack competitive dynamics. Among MARL agents, MADQN exhibits the most aggressive pricing behaviour, with the highest volatility and the lowest fairness (0.5844). MADDPG provides a more balanced approach, supporting market competition (share volatility: 9.5 pp) while maintaining relatively high fairness (0.8819) and stable pricing. These findings suggest that MARL introduces emergent strategic behaviour not captured by static pricing rules and may inform future developments in dynamic pricing.
Authors: Aditya Vema Reddy Kesari, Krishna Reddy Kesari
Abstract: Federated learning (FL) mechanisms typically require each client to transfer their weights to a central server, irrespective of how useful they are. In order to avoid wasteful data transfer costs from clients to the central server, we propose the use of consensus based protocols to identify a subset of clients with most useful model weights at each data transfer step. First, we explore the application of existing fluid democracy protocols to FL from a performance standpoint, comparing them with traditional one-person-one-vote (also known as 1p1v or FedAvg). We propose a new fluid democracy protocol named viscous-retained democracy that always does better than 1p1v under the same assumptions as existing fluid democracy protocols while also not allowing for influence accumulation. Secondly, we identify weaknesses of fluid democracy protocols from an adversarial lens in terms of their dependence on topology and/ or number of adversaries required to negatively impact the global model weights. To this effect, we propose an algorithm (FedVRD) that dynamically limits the effect of adversaries while minimizing cost by leveraging the delegation topology.
Authors: Zilin Kang, Chenyuan Hu, Yu Luo, Zhecheng Yuan, Ruijie Zheng, Huazhe Xu
Abstract: Deep reinforcement learning for continuous control has recently achieved impressive progress. However, existing methods often suffer from primacy bias, a tendency to overfit early experiences stored in the replay buffer, which limits an RL agent's sample efficiency and generalizability. In contrast, humans are less susceptible to such bias, partly due to infantile amnesia, where the formation of new neurons disrupts early memory traces, leading to the forgetting of initial experiences. Inspired by this dual processes of forgetting and growing in neuroscience, in this paper, we propose Forget and Grow (FoG), a new deep RL algorithm with two mechanisms introduced. First, Experience Replay Decay (ER Decay) "forgetting early experience", which balances memory by gradually reducing the influence of early experiences. Second, Network Expansion, "growing neural capacity", which enhances agents' capability to exploit the patterns of existing data by dynamically adding new parameters during training. Empirical results on four major continuous control benchmarks with more than 40 tasks demonstrate the superior performance of FoG against SoTA existing deep RL algorithms, including BRO, SimBa, and TD-MPC2.
Authors: Omri Porat, Michael Fire, Eran Ben-Elia
Abstract: Dockless e-scooters, a key micromobility service, have emerged as eco-friendly and flexible urban transport alternatives. These services improve first and last-mile connectivity, reduce congestion and emissions, and complement public transport for short-distance travel. However, effective management of these services depends on accurate demand prediction, which is crucial for optimal fleet distribution and infrastructure planning. While previous studies have focused on analyzing spatial or temporal factors in isolation, this study introduces a framework that integrates spatial, temporal, and network dependencies for improved micromobility demand forecasting. This integration enhances accuracy while providing deeper insights into urban micromobility usage patterns. Our framework improves demand prediction accuracy by 27 to 49% over baseline models, demonstrating its effectiveness in capturing micromobility demand patterns. These findings support data-driven micromobility management, enabling optimized fleet distribution, cost reduction, and sustainable urban planning.
Authors: Shiyi Liu, Buwen Liang, Yuetong Fang, Zixuan Jiang, Renjing Xu
Abstract: Recent advances in AI for science have highlighted the power of contrastive learning in bridging heterogeneous biological data modalities. Building on this paradigm, we propose HIPPO (HIerarchical Protein-Protein interaction prediction across Organisms), a hierarchical contrastive framework for protein-protein interaction(PPI) prediction, where protein sequences and their hierarchical attributes are aligned through multi-tiered biological representation matching. The proposed approach incorporates hierarchical contrastive loss functions that emulate the structured relationship among functional classes of proteins. The framework adaptively incorporates domain and family knowledge through a data-driven penalty mechanism, enforcing consistency between the learned embedding space and the intrinsic hierarchy of protein functions. Experiments on benchmark datasets demonstrate that HIPPO achieves state-of-the-art performance, outperforming existing methods and showing robustness in low-data regimes. Notably, the model demonstrates strong zero-shot transferability to other species without retraining, enabling reliable PPI prediction and functional inference even in less characterized or rare organisms where experimental data are limited. Further analysis reveals that hierarchical feature fusion is critical for capturing conserved interaction determinants, such as binding motifs and functional annotations. This work advances cross-species PPI prediction and provides a unified framework for interaction prediction in scenarios with sparse or imbalanced multi-species data.
Authors: Argimiro Arratia, Mahmoud El Daou, Henryk Gzyl
Abstract: We consider the following classification problem: Given a population of individuals characterized by a set of attributes represented as a vector in ${\mathbb R}^N$, the goal is to find a hyperplane in ${\mathbb R}^N$ that separates two sets of points corresponding to two distinct classes. This problem, with a history dating back to the perceptron model, remains central to machine learning. In this paper we propose a novel approach by searching for a vector of parameters in a bounded $N$-dimensional hypercube centered at the origin and a positive vector in ${\mathbb R}^M$, obtained through the minimization of an entropy-based function defined over the space of unknown variables. The method extends to polynomial surfaces, allowing the separation of data points by more complex decision boundaries. This provides a robust alternative to traditional linear or quadratic optimization techniques, such as support vector machines and gradient descent. Numerical experiments demonstrate the efficiency and versatility of the method in handling diverse classification tasks, including linear and non-linear separability.
Authors: Aurko Roy, Timothy Chou, Sai Surya Duvvuri, Sijia Chen, Jiecao Yu, Xiaodong Wang, Manzil Zaheer, Rohan Anil
Abstract: Recent work has shown that training loss scales as a power law with both model size and the number of tokens, and that achieving compute-optimal models requires scaling model size and token count together. However, these scaling laws assume an infinite supply of data and apply primarily in compute-bound settings. As modern large language models increasingly rely on massive internet-scale datasets, the assumption that they are compute-bound is becoming less valid. This shift highlights the need for architectures that prioritize token efficiency. In this work, we investigate the use of the 2-simplicial Transformer, an architecture that generalizes standard dot-product attention to trilinear functions through an efficient Triton kernel implementation. We demonstrate that the 2-simplicial Transformer achieves better token efficiency than standard Transformers: for a fixed token budget, similarly sized models outperform their dot-product counterparts on tasks involving mathematics, coding, reasoning, and logic. We quantify these gains by demonstrating that $2$-simplicial attention changes the exponent in the scaling laws for knowledge and reasoning tasks compared to dot product attention.
Authors: Yixuan Zhang, Ruihao Zhu, Qiaomin Xie
Abstract: We study contextual online pricing with biased offline data. For the scalar price elasticity case, we identify the instance-dependent quantity $\delta^2$ that measures how far the offline data lies from the (unknown) online optimum. We show that the time length $T$, bias bound $V$, size $N$ and dispersion $\lambda_{\min}(\hat{\Sigma})$ of the offline data, and $\delta^2$ jointly determine the statistical complexity. An Optimism-in-the-Face-of-Uncertainty (OFU) policy achieves a minimax-optimal, instance-dependent regret bound $\tilde{\mathcal{O}}\big(d\sqrt{T} \wedge (V^2T + \frac{dT}{\lambda_{\min}(\hat{\Sigma}) + (N \wedge T) \delta^2})\big)$. For general price elasticity, we establish a worst-case, minimax-optimal rate $\tilde{\mathcal{O}}\big(d\sqrt{T} \wedge (V^2T + \frac{dT }{\lambda_{\min}(\hat{\Sigma})})\big)$ and provide a generalized OFU algorithm that attains it. When the bias bound $V$ is unknown, we design a robust variant that always guarantees sub-linear regret and strictly improves on purely online methods whenever the exact bias is small. These results deliver the first tight regret guarantees for contextual pricing in the presence of biased offline data. Our techniques also transfer verbatim to stochastic linear bandits with biased offline data, yielding analogous bounds.
Authors: Ricardo Buitrago Ruiz, Albert Gu
Abstract: Recently, recurrent models such as state space models and linear attention have become popular due to their linear complexity in the sequence length. Thanks to their recurrent nature, in principle they can process arbitrarily long sequences, but their performance sometimes drops considerably beyond their training context lengths-i.e. they fail to length generalize. In this work, we provide comprehensive empirical and theoretical analysis to support the unexplored states hypothesis, which posits that models fail to length generalize when during training they are only exposed to a limited subset of the distribution of all attainable states (i.e. states that would be attained if the recurrence was applied to long sequences). Furthermore, we investigate simple training interventions that aim to increase the coverage of the states that the model is trained on, e.g. by initializing the state with Gaussian noise or with the final state of a different input sequence. With only 500 post-training steps ($\sim 0.1\%$ of the pre-training budget), these interventions enable length generalization for sequences that are orders of magnitude longer than the training context (e.g. $2k\longrightarrow 128k$) and show improved performance in long context tasks, thus presenting a simple and efficient way to enable robust length generalization in general recurrent models.
Authors: Thiti Suttaket, Stanley Kok
Abstract: Survival analysis is an important problem in healthcare because it models the relationship between an individual's covariates and the onset time of an event of interest (e.g., death). It is important for survival models to be well-calibrated (i.e., for their predicted probabilities to be close to ground-truth probabilities) because badly calibrated systems can result in erroneous clinical decisions. Existing survival models are typically calibrated at the population level only, and thus run the risk of being poorly calibrated for one or more minority subpopulations. We propose a model called GRADUATE that achieves multicalibration by ensuring that all subpopulations are well-calibrated too. GRADUATE frames multicalibration as a constrained optimization problem, and optimizes both calibration and discrimination in-training to achieve a good balance between them. We mathematically prove that the optimization method used yields a solution that is both near-optimal and feasible with high probability. Empirical comparisons against state-of-the-art baselines on real-world clinical datasets demonstrate GRADUATE's efficacy. In a detailed analysis, we elucidate the shortcomings of the baselines vis-a-vis GRADUATE's strengths.
Authors: Ilias Diakonikolas, Jingyi Gao, Daniel Kane, Sihan Liu, Christopher Ye
Abstract: We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probability distributions, the goal is to characterize the sample complexity of replicably testing natural properties of the underlying distributions. On the algorithmic front, we develop new replicable algorithms for testing closeness and independence of discrete distributions. On the lower bound front, we develop a new methodology for proving sample complexity lower bounds for replicable testing that may be of broader interest. As an application of our technique, we establish near-optimal sample complexity lower bounds for replicable uniformity testing -- answering an open question from prior work -- and closeness testing.
Authors: Ruiyang Zhou, Shuozhe Li, Amy Zhang, Liu Leqi
Abstract: Recent advances in large language models have been driven by reinforcement learning (RL)-style post-training, which improves reasoning by optimizing model outputs based on reward or preference signals. GRPO-style approaches implement this by using self-generated samples labeled by an outcome-based verifier. However, these methods depend heavily on the model's initial ability to produce positive samples. They primarily refine what the model already knows (distribution sharpening) rather than enabling the model to solve problems where it initially fails. This limitation is especially problematic in early-stage RL training and on challenging reasoning tasks, where positive samples are unlikely to be generated. To unlock reasoning ability in such settings, the model must explore new reasoning trajectories beyond its current output distribution. Such exploration requires access to sufficiently good positive samples to guide the learning. While expert demonstrations seem like a natural solution, we find that they are often ineffective in RL post-training. Instead, we identify two key properties of effective positive samples: they should (1) be likely under the current policy, and (2) increase the model's likelihood of predicting the correct answer. Based on these insights, we propose $\textbf{Self-Explanation Policy Optimization (ExPO)}$-a simple and modular framework that generates such samples by conditioning on the ground-truth answer. ExPO enables efficient exploration and guides the model to produce reasoning trajectories more aligned with its policy than expert-written CoTs, while ensuring higher quality than its own (incorrect) samples. Experiments show that ExPO improves both learning efficiency and final performance on reasoning benchmarks, surpassing expert-demonstration-based methods in challenging settings such as MATH level-5, where the model initially struggles the most.
Authors: Yuchen Ma, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel
Abstract: Estimating treatment effects is crucial for personalized decision-making in medicine, but this task faces unique challenges in clinical practice. At training time, models for estimating treatment effects are typically trained on well-structured medical datasets that contain detailed patient information. However, at inference time, predictions are often made using textual descriptions (e.g., descriptions with self-reported symptoms), which are incomplete representations of the original patient information. In this work, we make three contributions. (1) We show that the discrepancy between the data available during training time and inference time can lead to biased estimates of treatment effects. We formalize this issue as an inference time text confounding problem, where confounders are fully observed during training time but only partially available through text at inference time. (2) To address this problem, we propose a novel framework for estimating treatment effects that explicitly accounts for inference time text confounding. Our framework leverages large language models together with a custom doubly robust learner to mitigate biases caused by the inference time text confounding. (3) Through a series of experiments, we demonstrate the effectiveness of our framework in real-world applications.
Authors: Kunyu Zhang, Qiang Li, Shujian Yu
Abstract: Recent evidence suggests that modeling higher-order interactions (HOIs) in functional magnetic resonance imaging (fMRI) data can enhance the diagnostic accuracy of machine learning systems. However, effectively extracting and utilizing HOIs remains a significant challenge. In this work, we propose MvHo-IB, a novel multi-view learning framework that integrates both pairwise interactions and HOIs for diagnostic decision-making, while automatically compressing task-irrelevant redundant information. MvHo-IB introduces several key innovations: (1) a principled method that combines O-information from information theory with a matrix-based Renyi alpha-order entropy estimator to quantify and extract HOIs, (2) a purpose-built Brain3DCNN encoder to effectively utilize these interactions, and (3) a new multi-view learning information bottleneck objective to enhance representation learning. Experiments on three benchmark fMRI datasets demonstrate that MvHo-IB achieves state-of-the-art performance, significantly outperforming previous methods, including recent hypergraph-based techniques. The implementation of MvHo-IB is available at https://github.com/zky04/MvHo-IB.
Authors: Qun Su, Kai Zhu, Qiaolin Gou, Jintu Zhang, Renling Hu, Yurong Li, Yongze Wang, Hui Zhang, Ziyi You, Linlong Jiang, Yu Kang, Jike Wang, Chang-Yu Hsieh, Tingjun Hou
Abstract: Accurate atomistic biomolecular simulations are vital for disease mechanism understanding, drug discovery, and biomaterial design, but existing simulation methods exhibit significant limitations. Classical force fields are efficient but lack accuracy for transition states and fine conformational details critical in many chemical and biological processes. Quantum Mechanics (QM) methods are highly accurate but computationally infeasible for large-scale or long-time simulations. AI-based force fields (AIFFs) aim to achieve QM-level accuracy with efficiency but struggle to balance many-body modeling complexity, accuracy, and speed, often constrained by limited training data and insufficient validation for generalizability. To overcome these challenges, we introduce LiTEN, a novel equivariant neural network with Tensorized Quadrangle Attention (TQA). TQA efficiently models three- and four-body interactions with linear complexity by reparameterizing high-order tensor features via vector operations, avoiding costly spherical harmonics. Building on LiTEN, LiTEN-FF is a robust AIFF foundation model, pre-trained on the extensive nablaDFT dataset for broad chemical generalization and fine-tuned on SPICE for accurate solvated system simulations. LiTEN achieves state-of-the-art (SOTA) performance across most evaluation subsets of rMD17, MD22, and Chignolin, outperforming leading models such as MACE, NequIP, and EquiFormer. LiTEN-FF enables the most comprehensive suite of downstream biomolecular modeling tasks to date, including QM-level conformer searches, geometry optimization, and free energy surface construction, while offering 10x faster inference than MACE-OFF for large biomolecules (~1000 atoms). In summary, we present a physically grounded, highly efficient framework that advances complex biomolecular modeling, providing a versatile foundation for drug discovery and related applications.
Authors: Adebola K. Ojo, Ifechukwude Jude Okafor
Abstract: Investors and stock market analysts face major challenges in predicting stock returns and making wise investment decisions. The predictability of equity stock returns can boost investor confidence, but it remains a difficult task. To address this issue, a study was conducted using a Long Short-term Memory (LSTM) model to predict future stock market movements. The study used a historical dataset from the Nigerian Stock Exchange (NSE), which was cleaned and normalized to design the LSTM model. The model was evaluated using performance metrics and compared with other deep learning models like Artificial and Convolutional Neural Networks (CNN). The experimental results showed that the LSTM model can predict future stock market prices and returns with over 90% accuracy when trained with a reliable dataset. The study concludes that LSTM models can be useful in predicting financial time-series-related problems if well-trained. Future studies should explore combining LSTM models with other deep learning techniques like CNN to create hybrid models that mitigate the risks associated with relying on a single model for future equity stock predictions.
Authors: Ayaan Qayyum
Abstract: This paper will discuss how headline data can be used to predict stock prices. The stock price in question is the SPDR S&P 500 ETF Trust, also known as SPY that tracks the performance of the largest 500 publicly traded corporations in the United States. A key focus is to use news headlines from the Wall Street Journal (WSJ) to predict the movement of stock prices on a daily timescale with OpenAI-based text embedding models used to create vector encodings of each headline with principal component analysis (PCA) to exact the key features. The challenge of this work is to capture the time-dependent and time-independent, nuanced impacts of news on stock prices while handling potential lag effects and market noise. Financial and economic data were collected to improve model performance; such sources include the U.S. Dollar Index (DXY) and Treasury Interest Yields. Over 390 machine-learning inference models were trained. The preliminary results show that headline data embeddings greatly benefit stock price prediction by at least 40% compared to training and optimizing a machine learning system without headline data embeddings.
Authors: Boris Kriuk, Logic Ng, Zarif Al Hossain
Abstract: Support and resistance (SR) levels are central to technical analysis, guiding traders in entry, exit, and risk management. Despite widespread use, traditional SR identification methods often fail to adapt to the complexities of modern, volatile markets. Recent research has introduced machine learning techniques to address the following challenges, yet most focus on price prediction rather than structural level identification. This paper presents DeepSupp, a new deep learning approach for detecting financial support levels using multi-head attention mechanisms to analyze spatial correlations and market microstructure relationships. DeepSupp integrates advanced feature engineering, constructing dynamic correlation matrices that capture evolving market relationships, and employs an attention-based autoencoder for robust representation learning. The final support levels are extracted through unsupervised clustering, leveraging DBSCAN to identify significant price thresholds. Comprehensive evaluations on S&P 500 tickers demonstrate that DeepSupp outperforms six baseline methods, achieving state-of-the-art performance across six financial metrics, including essential support accuracy and market regime sensitivity. With consistent results across diverse market conditions, DeepSupp addresses critical gaps in SR level detection, offering a scalable and reliable solution for modern financial analysis. Our approach highlights the potential of attention-based architectures to uncover nuanced market patterns and improve technical trading strategies.
Authors: Hadi Keramati, Samaneh Jazayeri
Abstract: We present a reinforcement learning (RL)-driven framework for optimizing block-preconditioner sizes in iterative solvers used in portfolio optimization and option pricing. The covariance matrix in portfolio optimization or the discretization of differential operators in option pricing models lead to large linear systems of the form $\mathbf{A}\textbf{x}=\textbf{b}$. Direct inversion of high-dimensional portfolio or fine-grid option pricing incurs a significant computational cost. Therefore, iterative methods are usually used for portfolios in real-world situations. Ill-conditioned systems, however, suffer from slow convergence. Traditional preconditioning techniques often require problem-specific parameter tuning. To overcome this limitation, we rely on RL to dynamically adjust the block-preconditioner sizes and accelerate iterative solver convergence. Evaluations on a suite of real-world portfolio optimization matrices demonstrate that our RL framework can be used to adjust preconditioning and significantly accelerate convergence and reduce computational cost. The proposed accelerated solver supports faster decision-making in dynamic portfolio allocation and real-time option pricing.
Authors: J\'er\'emy Rouch (CRNL-ENES), M Ducrettet (CRNL-ENES, ISYEB), S Haupert (ISYEB), R Emonet (LabHC), F S\`ebe (CRNL-ENES, OFB - DRAS)
Abstract: The accessibility of long-duration recorders, adapted to sometimes demanding field conditions, has enabled the deployment of extensive animal population monitoring campaigns through ecoacoustics. The effectiveness of automatic signal detection methods, increasingly based on neural approaches, is frequently evaluated solely through machine learning metrics, while acoustic analysis of performance remains rare. As part of the acoustic monitoring of Rock Ptarmigan populations, we propose here a simple method for acoustic analysis of the detection system's performance. The proposed measure is based on relating the signal-to-noise ratio of synthetic signals to their probability of detection. We show how this measure provides information about the system and allows optimisation of its training. We also show how it enables modelling of the detection distance, thus offering the possibility of evaluating its dynamics according to the sound environment and accessing an estimation of the spatial density of calls.
Authors: Nirhoshan Sivaroopan, Kaushitha Silva, Chamara Madarasingha, Thilini Dahanayaka, Guillaume Jourjon, Anura Jayasumana, Kanchana Thilakarathna
Abstract: Synthetic network traffic generation has emerged as a promising alternative for various data-driven applications in the networking domain. It enables the creation of synthetic data that preserves real-world characteristics while addressing key challenges such as data scarcity, privacy concerns, and purity constraints associated with real data. In this survey, we provide a comprehensive review of synthetic network traffic generation approaches, covering essential aspects such as data types, generation models, and evaluation methods. With the rapid advancements in AI and machine learning, we focus particularly on deep learning-based techniques while also providing a detailed discussion of statistical methods and their extensions, including commercially available tools. Furthermore, we highlight open challenges in this domain and discuss potential future directions for further research and development. This survey serves as a foundational resource for researchers and practitioners, offering a structured analysis of existing methods, challenges, and opportunities in synthetic network traffic generation.
Authors: Adam Nelson-Archer, Aleia Sen, Meena Al Hasani, Sofia Davila, Jessica Le, Omar Abbouchi
Abstract: We present a deep learning approach for forecasting short-term employment changes and assessing long-term industry health using labor market data from the U.S. Bureau of Labor Statistics. Our system leverages a Long- and Short-Term Time-series Network (LSTNet) to process multivariate time series data, including employment levels, wages, turnover rates, and job openings. The model outputs both 7-day employment forecasts and an interpretable Industry Employment Health Index (IEHI). Our approach outperforms baseline models across most sectors, particularly in stable industries, and demonstrates strong alignment between IEHI rankings and actual employment volatility. We discuss error patterns, sector-specific performance, and future directions for improving interpretability and generalization.
Authors: Linh Nguyen, Marcel Boersma, Erman Acar
Abstract: Fraudulent activity in the financial industry costs billions annually. Detecting fraud, therefore, is an essential yet technically challenging task that requires carefully analyzing large volumes of data. While machine learning (ML) approaches seem like a viable solution, applying them successfully is not so easy due to two main challenges: (1) the sparsely labeled data, which makes the training of such approaches challenging (with inherent labeling costs), and (2) lack of explainability for the flagged items posed by the opacity of ML models, that is often required by business regulations. This article proposes SAGE-FIN, a semi-supervised graph neural network (GNN) based approach with Granger causal explanations for Financial Interaction Networks. SAGE-FIN learns to flag fraudulent items based on weakly labeled (or unlabelled) data points. To adhere to regulatory requirements, the flagged items are explained by highlighting related items in the network using Granger causality. We empirically validate the favorable performance of SAGE-FIN on a real-world dataset, Bipartite Edge-And-Node Attributed financial network (Elliptic++), with Granger-causal explanations for the identified fraudulent items without any prior assumption on the network structure.
Authors: Jo\~ao B. G. de Brito, Rodrigo Heldt, Cleo S. Silveira, Matthias Bogaert, Guilherme B. Bucco, Fernando B. Luce, Jo\~ao L. Becker, Filipe J. Zabala, Michel J. Anzanello
Abstract: The emergence of Open Banking represents a significant shift in financial data management, influencing financial institutions' market dynamics and marketing strategies. This increased competition creates opportunities and challenges, as institutions manage data inflow to improve products and services while mitigating data outflow that could aid competitors. This study introduces a framework to predict customers' propensity to share data via Open Banking and interprets this behavior through Explanatory Model Analysis (EMA). Using data from a large Brazilian financial institution with approximately 3.2 million customers, a hybrid data balancing strategy incorporating ADASYN and NEARMISS techniques was employed to address the infrequency of data sharing and enhance the training of XGBoost models. These models accurately predicted customer data sharing, achieving 91.39% accuracy for inflow and 91.53% for outflow. The EMA phase combined the Shapley Additive Explanations (SHAP) method with the Classification and Regression Tree (CART) technique, revealing the most influential features on customer decisions. Key features included the number of transactions and purchases in mobile channels, interactions within these channels, and credit-related features, particularly credit card usage across the national banking system. These results highlight the critical role of mobile engagement and credit in driving customer data-sharing behaviors, providing financial institutions with strategic insights to enhance competitiveness and innovation in the Open Banking environment.
Authors: Sedigheh Mahdavi (Kristin), Jiating (Kristin), Chen, Pradeep Kumar Joshi, Lina Huertas Guativa, Upmanyu Singh
Abstract: Large Language Models (LLMs) have been employed in financial decision making, enhancing analytical capabilities for investment strategies. Traditional investment strategies often utilize quantitative models, fundamental analysis, and technical indicators. However, LLMs have introduced new capabilities to process and analyze large volumes of structured and unstructured data, extract meaningful insights, and enhance decision-making in real-time. This survey provides a structured overview of recent research on LLMs within the financial domain, categorizing research contributions into four main frameworks: LLM-based Frameworks and Pipelines, Hybrid Integration Methods, Fine-Tuning and Adaptation Approaches, and Agent-Based Architectures. This study provides a structured review of recent LLMs research on applications in stock selection, risk assessment, sentiment analysis, trading, and financial forecasting. By reviewing the existing literature, this study highlights the capabilities, challenges, and potential directions of LLMs in financial markets.
Authors: Vidya Sagar G, Shifat Ali, Siddhartha P. Chakrabarty
Abstract: This paper presents a machine learning driven framework for sectoral stress testing in the Indian financial market, focusing on financial services, information technology, energy, consumer goods, and pharmaceuticals. Initially, we address the limitations observed in conventional stress testing through dimensionality reduction and latent factor modeling via Principal Component Analysis and Autoencoders. Building on this, we extend the methodology using Variational Autoencoders, which introduces a probabilistic structure to the latent space. This enables Monte Carlo-based scenario generation, allowing for more nuanced, distribution-aware simulation of stressed market conditions. The proposed framework captures complex non-linear dependencies and supports risk estimation through Value-at-Risk and Expected Shortfall. Together, these pipelines demonstrate the potential of Machine Learning approaches to improve the flexibility, robustness, and realism of financial stress testing.
Authors: Anoushka Harit, Zhongtian Sun, Suncica Hadzidedic
Abstract: We introduce ManifoldMind, a probabilistic geometric recommender system for exploratory reasoning over semantic hierarchies in hyperbolic space. Unlike prior methods with fixed curvature and rigid embeddings, ManifoldMind represents users, items, and tags as adaptive-curvature probabilistic spheres, enabling personalised uncertainty modeling and geometry-aware semantic exploration. A curvature-aware semantic kernel supports soft, multi-hop inference, allowing the model to explore diverse conceptual paths instead of overfitting to shallow or direct interactions. Experiments on four public benchmarks show superior NDCG, calibration, and diversity compared to strong baselines. ManifoldMind produces explicit reasoning traces, enabling transparent, trustworthy, and exploration-driven recommendations in sparse or abstract domains.
Authors: Yingjie Niu, Mingchuan Zhao, Valerio Poti, Ruihai Dong
Abstract: Graph representation learning methods have been widely adopted in financial applications to enhance company representations by leveraging inter-firm relationships. However, current approaches face three key challenges: (1) The advantages of relational information are obscured by limitations in downstream task designs; (2) Existing graph models specifically designed for stock prediction often suffer from excessive complexity and poor generalization; (3) Experience-based construction of corporate relationship graphs lacks effective comparison of different graph structures. To address these limitations, we propose a long-term stock prediction task and develop a Node-level Graph Attention Network (NGAT) specifically tailored for corporate relationship graphs. Furthermore, we experimentally demonstrate the limitations of existing graph comparison methods based on model downstream task performance. Experimental results across two datasets consistently demonstrate the effectiveness of our proposed task and model. The project is publicly available on GitHub to encourage reproducibility and future research.
Authors: Nikita Bhedasgaonkar, Rushikesh K. Joshi
Abstract: In this paper, we propose HCVR (Hybrid approach with Correlation-aware Voting Rules), a lightweight rule-based feature selection method that combines Parameter-to-Parameter (P2P) and Parameter-to-Target (P2T) correlations to eliminate redundant features and retain relevant ones. This method is a hybrid of non-iterative and iterative filtering approaches for dimensionality reduction. It is a greedy method, which works by backward elimination, eliminating possibly multiple features at every step. The rules contribute to voting for features, and a decision to keep or discard is made by majority voting. The rules make use of correlation thresholds between every pair of features, and between features and the target. We provide the results from the application of HCVR to the SPAMBASE dataset. The results showed improvement performance as compared to traditional non-iterative (CFS, mRMR and MI) and iterative (RFE, SFS and Genetic Algorithm) techniques. The effectiveness was assessed based on the performance of different classifiers after applying filtering.
Authors: Mohammad Ali Alomrani, Yingxue Zhang, Derek Li, Qianyi Sun, Soumyasundar Pal, Zhanguang Zhang, Yaochen Hu, Rohan Deepak Ajwani, Antonios Valkanas, Raika Karimi, Peng Cheng, Yunzhou Wang, Pengyi Liao, Hanrui Huang, Bin Wang, Jianye Hao, Mark Coates
Abstract: Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of task complexity, often overthinking simple problems while underthinking hard ones. This survey presents a comprehensive review of efficient test-time compute (TTC) strategies, which aim to improve the computational efficiency of LLM reasoning. We introduce a two-tiered taxonomy that distinguishes between L1-controllability, methods that operate under fixed compute budgets, and L2-adaptiveness, methods that dynamically scale inference based on input difficulty or model confidence. We benchmark leading proprietary LLMs across diverse datasets, highlighting critical trade-offs between reasoning performance and token usage. Compared to prior surveys on efficient reasoning, our review emphasizes the practical control, adaptability, and scalability of TTC methods. Finally, we discuss emerging trends such as hybrid thinking models and identify key challenges for future work towards making LLMs more computationally efficient, robust, and responsive to user constraints.
Authors: Yining Feng, Ivan Selesnick
Abstract: The adaptive Iterative Soft-Thresholding Algorithm (ISTA) has been a popular algorithm for finding a desirable solution to the LASSO problem without explicitly tuning the regularization parameter $\lambda$. Despite that the adaptive ISTA is a successful practical algorithm, few theoretical results exist. In this paper, we present the theoretical analysis on the adaptive ISTA with the thresholding strategy of estimating noise level by median absolute deviation. We show properties of the fixed points of the algorithm, including scale equivariance, non-uniqueness, and local stability, prove the local linear convergence guarantee, and show its global convergence behavior.
Authors: Shaswata Mahernob Sarkar, Sheikh Iftekhar Ahmed, Jishnu Mahmud, Shaikh Anowarul Fattah, Gaurav Sharma
Abstract: Quantum Machine Learning (QML) has seen significant advancements, driven by recent improvements in Noisy Intermediate-Scale Quantum (NISQ) devices. Leveraging quantum principles such as entanglement and superposition, quantum convolutional neural networks (QCNNs) have demonstrated promising results in classifying both quantum and classical data. This study examines QCNNs in the context of image classification and proposes a novel strategy to enhance feature processing and a QCNN architecture for improved classification accuracy. First, a selective feature re-encoding strategy is proposed, which directs the quantum circuits to prioritize the most informative features, thereby effectively navigating the crucial regions of the Hilbert space to find the optimal solution space. Secondly, a novel parallel-mode QCNN architecture is designed to simultaneously incorporate features extracted by two classical methods, Principal Component Analysis (PCA) and Autoencoders, within a unified training scheme. The joint optimization involved in the training process allows the QCNN to benefit from complementary feature representations, enabling better mutual readjustment of model parameters. To assess these methodologies, comprehensive experiments have been performed using the widely used MNIST and Fashion MNIST datasets for binary classification tasks. Experimental findings reveal that the selective feature re-encoding method significantly improves the quantum circuit's feature processing capability and performance. Furthermore, the jointly optimized parallel QCNN architecture consistently outperforms the individual QCNN models and the traditional ensemble approach involving independent learning followed by decision fusion, confirming its superior accuracy and generalization capabilities.
Authors: Mathieu Dubied, Amon Lahr, Melanie N. Zeilinger, Johannes K\"ohler
Abstract: In this paper, we present a robust and adaptive model predictive control (MPC) framework for uncertain nonlinear systems affected by bounded disturbances and unmodeled nonlinearities. We use Gaussian Processes (GPs) to learn the uncertain dynamics based on noisy measurements, including those collected during system operation. As a key contribution, we derive robust predictions for GP models using contraction metrics, which are incorporated in the MPC formulation. The proposed design guarantees recursive feasibility, robust constraint satisfaction and convergence to a reference state, with high probability. We provide a numerical example of a planar quadrotor subject to difficult-to-model ground effects, which highlights significant improvements achieved through the proposed robust prediction method and through online learning.
Authors: Semih Kacmaz, E. A. Huerta, Roland Haas
Abstract: We present a hybrid machine learning framework that combines Physics-Informed Neural Operators (PINOs) with score-based generative diffusion models to simulate the full spatio-temporal evolution of two-dimensional, incompressible, resistive magnetohydrodynamic (MHD) turbulence across a broad range of Reynolds numbers ($\mathrm{Re}$). The framework leverages the equation-constrained generalization capabilities of PINOs to predict coherent, low-frequency dynamics, while a conditional diffusion model stochastically corrects high-frequency residuals, enabling accurate modeling of fully developed turbulence. Trained on a comprehensive ensemble of high-fidelity simulations with $\mathrm{Re} \in \{100, 250, 500, 750, 1000, 3000, 10000\}$, the approach achieves state-of-the-art accuracy in regimes previously inaccessible to deterministic surrogates. At $\mathrm{Re}=1000$ and $3000$, the model faithfully reconstructs the full spectral energy distributions of both velocity and magnetic fields late into the simulation, capturing non-Gaussian statistics, intermittent structures, and cross-field correlations with high fidelity. At extreme turbulence levels ($\mathrm{Re}=10000$), it remains the first surrogate capable of recovering the high-wavenumber evolution of the magnetic field, preserving large-scale morphology and enabling statistically meaningful predictions.
Authors: Giulio Caldarelli
Abstract: The blockchain oracle problem, which refers to the challenge of injecting reliable external data into decentralized systems, remains a fundamental limitation to the development of trustless applications. While recent years have seen a proliferation of architectural, cryptographic, and economic strategies to mitigate this issue, no one has yet fully resolved the fundamental question of how a blockchain can gain knowledge about the off-chain world. In this position paper, we critically assess the role artificial intelligence (AI) can play in tackling the oracle problem. Drawing from both academic literature and practitioner implementations, we examine how AI techniques such as anomaly detection, language-based fact extraction, dynamic reputation modeling, and adversarial resistance can enhance oracle systems. We observe that while AI introduces powerful tools for improving data quality, source selection, and system resilience, it cannot eliminate the reliance on unverifiable off-chain inputs. Therefore, this study supports the idea that AI should be understood as a complementary layer of inference and filtering within a broader oracle design, not a substitute for trust assumptions.
Authors: Miroslav Cibula, Krist\'ina Malinovsk\'a, Matthias Kerzel
Abstract: Trajectory planning in robotics is understood as generating a sequence of joint configurations that will lead a robotic agent, or its manipulator, from an initial state to the desired final state, thus completing a manipulation task while considering constraints like robot kinematics and the environment. Typically, this is achieved via sampling-based planners, which are computationally intensive. Recent advances demonstrate that trajectory planning can also be performed by supervised sequence learning of trajectories, often requiring only a single or fixed number of passes through a neural architecture, thus ensuring a bounded computation time. Such fully supervised approaches, however, perform imitation learning; they do not learn based on whether the trajectories can successfully reach a goal, but try to reproduce observed trajectories. In our work, we build on this approach and propose a cognitively inspired self-supervised learning scheme based on a recurrent architecture for building a trajectory model. We evaluate the feasibility of the proposed method on a task of kinematic planning for a robotic arm. The results suggest that the model is able to learn to generate trajectories only using given paired forward and inverse kinematics models, and indicate that this novel method could facilitate planning for more complex manipulation tasks requiring adaptive solutions.
Authors: Marc-Andr\'e Carbonneau, Benjamin van Niekerk, Hugo Seut\'e, Jean-Philippe Letendre, Herman Kamper, Julian Za\"idi
Abstract: Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embeddings, designed for discrimination rather than characterizing identity. This paper investigates which aspects of a voice are captured in such representations. We find that widely used ASV embeddings focus mainly on static features like timbre and pitch range, while neglecting dynamic elements such as rhythm. We also identify confounding factors that compromise speaker similarity measurements and suggest mitigation strategies. To address these gaps, we propose U3D, a metric that evaluates speakers' dynamic rhythm patterns. This work contributes to the ongoing challenge of assessing speaker identity consistency in the context of ever-better voice cloning systems. We publicly release our code.
Authors: Max Argus, Jelena Bratulic, Houman Masnavi, Maxim Velikanov, Nick Heppert, Abhinav Valada, Thomas Brox
Abstract: Vision-Language-Action (VLA) models offer a compelling framework for tackling complex robotic manipulation tasks, but they are often expensive to train. In this paper, we propose a novel VLA approach that leverages the competitive performance of Vision Language Models (VLMs) on 2D images to directly infer robot end-effector poses in image frame coordinates. Unlike prior VLA models that output low-level controls, our model predicts trajectory waypoints, making it both more efficient to train and robot embodiment agnostic. Despite its lightweight design, our next-token prediction architecture effectively learns meaningful and executable robot trajectories. We further explore the underutilized potential of incorporating depth images, inference-time techniques such as decoding strategies, and demonstration-conditioned action generation. Our model is trained on a simulated dataset and exhibits strong sim-to-real transfer capabilities. We evaluate our approach using a combination of simulated and real data, demonstrating its effectiveness on a real robotic system.
Authors: Wenquan Lu, Yuechuan Yang, Kyle Lee, Yanshu Li, Enqi Liu
Abstract: Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning. However, in standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency. To capture reasoning that is not easily represented in words, many works have explored recurrent architectures that aim to internalize reasoning in latent space, potentially supporting latent CoT. In this paper, we investigate whether such reasoning structures emerge in Huginn-3.5B, a depth-recurrent Transformer that reuses layers at inference time without increasing parameter count. We examine the model's internal behavior on arithmetic tasks using a suite of probing techniques including the Logit Lens and Coda Lens. Our findings reveal limited evidence of interpretable latent CoT by tracking rank trajectories of final and intermediate result tokens. Furthermore, we uncover significant probing inconsistencies across recurrent blocks, where the interpretability of hidden states depends heavily on both the layer index and the decoding method. Finally, we empirically show that increasing recurrence depth yields only marginal gains and falls well short of models that explicitly externalize reasoning steps. The code is available at https://github.com/wenquanlu/huginn-latent-cot.
Authors: Takuro Kawada, Shunsuke Kitada, Sota Nemoto, Hitoshi Iyatomi
Abstract: Graphical Abstracts (GAs) play a crucial role in visually conveying the key findings of scientific papers. While recent research has increasingly incorporated visual materials such as Figure 1 as de facto GAs, their potential to enhance scientific communication remains largely unexplored. Moreover, designing effective GAs requires advanced visualization skills, creating a barrier to their widespread adoption. To tackle these challenges, we introduce SciGA-145k, a large-scale dataset comprising approximately 145,000 scientific papers and 1.14 million figures, explicitly designed for supporting GA selection and recommendation as well as facilitating research in automated GA generation. As a preliminary step toward GA design support, we define two tasks: 1) Intra-GA recommendation, which identifies figures within a given paper that are well-suited to serve as GAs, and 2) Inter-GA recommendation, which retrieves GAs from other papers to inspire the creation of new GAs. We provide reasonable baseline models for these tasks. Furthermore, we propose Confidence Adjusted top-1 ground truth Ratio (CAR), a novel recommendation metric that offers a fine-grained analysis of model behavior. CAR addresses limitations in traditional ranking-based metrics by considering cases where multiple figures within a paper, beyond the explicitly labeled GA, may also serve as GAs. By unifying these tasks and metrics, our SciGA-145k establishes a foundation for advancing visual scientific communication while contributing to the development of AI for Science.
Authors: Ben Adcock, Bernhard Hientzsch, Akil Narayan, Yiming Xu
Abstract: Motivated by the need for efficient estimation of conditional expectations, we consider a least-squares function approximation problem with heavily polluted data. Existing methods that are powerful in the small noise regime are suboptimal when large noise is present. We propose a hybrid approach that combines Christoffel sampling with certain types of optimal experimental design to address this issue. We show that the proposed algorithm enjoys appropriate optimality properties for both sample point generation and noise mollification, leading to improved computational efficiency and sample complexity compared to existing methods. We also extend the algorithm to convex-constrained settings with similar theoretical guarantees. When the target function is defined as the expectation of a random field, we extend our approach to leverage adaptive random subspaces and establish results on the approximation capacity of the adaptive procedure. Our theoretical findings are supported by numerical studies on both synthetic data and on a more challenging stochastic simulation problem in computational finance.
Authors: Mohammad Akyash, Kimia Azar, Hadi Kamali
Abstract: As one of their many applications, large language models (LLMs) have recently shown promise in automating register transfer level (RTL) code generation. However, conventional LLM decoding strategies, originally designed for natural language, often fail to meet the structural and semantic demands of RTL, leading to hallucinated, repetitive, or invalid code outputs. In this paper, we first investigate the root causes of these decoding failures through an empirical analysis of token-level entropy during RTL generation. Our findings reveal that LLMs exhibit low confidence in regions of structural ambiguity or semantic complexity, showing that standard decoding strategies fail to differentiate between regions requiring determinism (syntax-critical regions) and those that benefit from creative exploratory variability (design-critical regions). Then, to overcome this, we introduce DecoRTL, a novel run-time decoding strategy, that is both syntax-aware and contrastive for RTL code generation. DecoRTL integrates two complementary components: (i) self-consistency sampling, which generates multiple candidates and re-ranks them based on token-level agreement to promote correctness while maintaining diversity; and (ii) syntax-aware temperature adaptation, which classifies tokens by their syntactical and functional roles and adjusts the sampling temperature accordingly, enforcing low temperature for syntax-critical tokens and higher temperature for exploratory ones. Our approach operates entirely at inference time without requiring any additional model fine-tuning. Through evaluations on multiple open-source LLMs using the VerilogEval benchmark, we demonstrate significant improvements in syntactic validity, functional correctness, and output diversity, while the execution overhead (performance overhead) is imperceptible.
Authors: Dali Liu, Haolei Weng
Abstract: In this paper, we explore the knowledge transfer under the setting of matrix completion, which aims to enhance the estimation of a low-rank target matrix with auxiliary data available. We propose a transfer learning procedure given prior information on which source datasets are favorable. We study its convergence rates and prove its minimax optimality. Our analysis reveals that with the source matrices close enough to the target matrix, out method outperforms the traditional method using the single target data. In particular, we leverage the advanced sharp concentration inequalities introduced in \cite{brailovskaya2024universality} to eliminate a logarithmic factor in the convergence rate, which is crucial for proving the minimax optimality. When the relevance of source datasets is unknown, we develop an efficient detection procedure to identify informative sources and establish its selection consistency. Simulations and real data analysis are conducted to support the validity of our methodology.
Authors: Zihao Li, Chao Yang, Tong Zhang, Yakun Chen, Xianzhi Wang, Guandong Xu, Daoyi Dong
Abstract: Preference alignment has achieved greater success on Large Language Models (LLMs) and drawn broad interest in recommendation research. Existing preference alignment methods for recommendation either require explicit reward modeling or only support pairwise preference comparison. The former directly increases substantial computational costs, while the latter hinders training efficiency on negative samples. Moreover, no existing effort has explored preference alignment solutions for tail-item recommendation. To bridge the above gaps, we propose LPO4Rec, which extends the Bradley-Terry model from pairwise comparison to listwise comparison, to improve the efficiency of model training. Specifically, we derive a closed form optimal policy to enable more efficient and effective training without explicit reward modeling. We also present an adaptive negative sampling and reweighting strategy to prioritize tail items during optimization and enhance performance in tail-item recommendations. Besides, we theoretically prove that optimizing the listwise preference optimization (LPO) loss is equivalent to maximizing the upper bound of the optimal reward. Our experiments on three public datasets show that our method outperforms 10 baselines by a large margin, achieving up to 50% performance improvement while reducing 17.9% GPU memory usage when compared with direct preference optimization (DPO) in tail-item recommendation. Our code is available at https://github.com/Yuhanleeee/LPO4Rec.
Authors: Hongli Yu, Tinghong Chen, Jiangtao Feng, Jiangjie Chen, Weinan Dai, Qiying Yu, Ya-Qin Zhang, Wei-Ying Ma, Jingjing Liu, Mingxuan Wang, Hao Zhou
Abstract: Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents with linear complexity without performance degradation during extrapolation remains the ultimate challenge in long-text processing. We directly optimize for long-text tasks in an end-to-end fashion and introduce a novel agent workflow, MemAgent, which reads text in segments and updates the memory using an overwrite strategy. We extend the DAPO algorithm to facilitate training via independent-context multi-conversation generation. MemAgent has demonstrated superb long-context capabilities, being able to extrapolate from an 8K context trained on 32K text to a 3.5M QA task with performance loss < 5% and achieves 95%+ in 512K RULER test.
Authors: Jacob J. Morra, Kaitlyn E. Fouke, Kexin Hang, Zichen He, Owen Traubert, Timothy W. Dunn, Eva A. Naumann
Abstract: Delineating how animal behavior arises from neural activity is a foundational goal of neuroscience. However, as the computations underlying behavior unfold in networks of thousands of individual neurons across the entire brain, this presents challenges for investigating neural roles and computational mechanisms in large, densely wired mammalian brains during behavior. Transformers, the backbones of modern large language models (LLMs), have become powerful tools for neural decoding from smaller neural populations. These modern LLMs have benefited from extensive pre-training, and their sequence-to-sequence learning has been shown to generalize to novel tasks and data modalities, which may also confer advantages for neural decoding from larger, brain-wide activity recordings. Here, we present a systematic evaluation of off-the-shelf LLMs to decode behavior from brain-wide populations, termed NLP4Neuro, which we used to test LLMs on simultaneous calcium imaging and behavior recordings in larval zebrafish exposed to visual motion stimuli. Through NLP4Neuro, we found that LLMs become better at neural decoding when they use pre-trained weights learned from textual natural language data. Moreover, we found that a recent mixture-of-experts LLM, DeepSeek Coder-7b, significantly improved behavioral decoding accuracy, predicted tail movements over long timescales, and provided anatomically consistent highly interpretable readouts of neuron salience. NLP4Neuro demonstrates that LLMs are highly capable of informing brain-wide neural circuit dissection.
Authors: Jikai Jin, Lester Mackey, Vasilis Syrgkanis
Abstract: Structure-agnostic causal inference studies how well one can estimate a treatment effect given black-box machine learning estimates of nuisance functions (like the impact of confounders on treatment and outcomes). Here, we find that the answer depends in a surprising way on the distribution of the treatment noise. Focusing on the partially linear model of \citet{robinson1988root}, we first show that the widely adopted double machine learning (DML) estimator is minimax rate-optimal for Gaussian treatment noise, resolving an open problem of \citet{mackey2018orthogonal}. Meanwhile, for independent non-Gaussian treatment noise, we show that DML is always suboptimal by constructing new practical procedures with higher-order robustness to nuisance errors. These \emph{ACE} procedures use structure-agnostic cumulant estimators to achieve $r$-th order insensitivity to nuisance errors whenever the $(r+1)$-st treatment cumulant is non-zero. We complement these core results with novel minimax guarantees for binary treatments in the partially linear model. Finally, using synthetic demand estimation experiments, we demonstrate the practical benefits of our higher-order robust estimators.
Authors: Terence Zeng, Abhishek K. Umrawal
Abstract: Recommendation systems have become essential in modern music streaming platforms, shaping how users discover and engage with songs. One common approach in recommendation systems is collaborative filtering, which suggests content based on the preferences of users with similar listening patterns to the target user. However, this method is less effective on media where interactions are sparse. Music is one such medium, since the average user of a music streaming service will never listen to the vast majority of tracks. Due to this sparsity, there are several challenges that have to be addressed with other methods. This review examines the current state of research in addressing these challenges, with an emphasis on the role of content filtering in mitigating biases inherent in collaborative filtering approaches. We explore various methods of song classification for content filtering, including lyrical analysis using Large Language Models (LLMs) and audio signal processing techniques. Additionally, we discuss the potential conflicts between these different analysis methods and propose avenues for resolving such discrepancies.
Authors: De Cheng, Zhipeng Xu, Xinyang Jiang, Dongsheng Li, Nannan Wang, Xinbo Gao
Abstract: Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains. Notably, recent advances in pre-trained Visual Foundation Models (VFMs), such as CLIP, have demonstrated considerable potential in enhancing the generalization capabilities of deep learning models. Despite the increasing attention toward VFM-based domain prompt tuning within DG, the effective design of prompts capable of disentangling invariant features across diverse domains remains a critical challenge. In this paper, we propose addressing this challenge by leveraging the controllable and flexible language prompt of the VFM. Noting that the text modality of VFMs is naturally easier to disentangle, we introduce a novel framework for text feature-guided visual prompt tuning. This framework first automatically disentangles the text prompt using a large language model (LLM) and then learns domain-invariant visual representation guided by the disentangled text feature. However, relying solely on language to guide visual feature disentanglement has limitations, as visual features can sometimes be too complex or nuanced to be fully captured by descriptive text. To address this, we introduce Worst Explicit Representation Alignment (WERA), which extends text-guided visual prompts by incorporating an additional set of abstract prompts. These prompts enhance source domain diversity through stylized image augmentations, while alignment constraints ensure that visual representations remain consistent across both the original and augmented distributions. Experiments conducted on major DG datasets, including PACS, VLCS, OfficeHome, DomainNet, and TerraInc, demonstrate that our proposed method outperforms state-of-the-art DG methods.
Authors: Dohoon Kim, Donghun Kang, Taesup Moon
Abstract: Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating different domain datasets. However, existing continual DAP methods face several limitations: (1) high computational cost and GPU memory usage during training; (2) sensitivity to incremental data order; and (3) providing a single, generalized model for all end tasks, which contradicts the essence of DAP. In this paper, we propose DoMIX, a novel approach that addresses these challenges by leveraging LoRA modules, a representative parameter-efficient fine-tuning (PEFT) method. Our approach enables efficient and parallel domain-adaptive pre-training that is robust to domain order and effectively utilizes accumulated knowledge to provide tailored pre-trained models for specific tasks. We also demonstrate that our method can be extended beyond the DAP setting to standard LLM fine-tuning scenarios. Code is available at https://github.com/dohoonkim-ai/DoMIX.
Authors: Gabriel O. Flores-Aquino, Octavio Gutierrez-Frias, Juan Irving Vasquez
Abstract: Path planning algorithms aim to compute a collision-free path, and many works focus on finding the optimal distance path. However, for some applications, a more suitable approach is to balance response time, safety of the paths, and path length. In this context, a skeleton map is a useful tool in graph-based schemes, as it provides an intrinsic representation of free configuration space. However, skeletonization algorithms are very resource-intensive, being primarily oriented towards image processing tasks. We propose an efficient path-planning methodology that finds safe paths within an acceptable processing time. This methodology leverages a Deep Denoising Auto-Encoder (DDAE) based on U-Net architecture to compute a skeletonized version of the navigation map, which we refer to as SkelUnet. The SkelUnet network facilitates exploration of the entire workspace through one-shot sampling (OSS), as opposed to the iterative process used by exact algorithms or the probabilistic sampling process. SkelUnet is trained and tested on a dataset consisting of 12,500 bi-dimensional dungeon maps. The motion planning methodology is evaluated in a simulation environment for an Unmanned Aerial Vehicle (UAV) using 250 previously unseen maps, and assessed with various navigation metrics to quantify the navigability of the computed paths. The results demonstrate that using SkelUnet to construct a roadmap offers significant advantages, such as connecting all regions of free workspace, providing safer paths, and reducing processing times. These characteristics make this method particularly suitable for mobile service robots in structured environments.
Authors: Thang D. Bui, Michalis K. Titsias
Abstract: Inducing-point-based sparse variational Gaussian processes have become the standard workhorse for scaling up GP models. Recent advances show that these methods can be improved by introducing a diagonal scaling matrix to the conditional posterior density given the inducing points. This paper first considers an extension that employs a block-diagonal structure for the scaling matrix, provably tightening the variational lower bound. We then revisit the unifying framework of sparse GPs based on Power Expectation Propagation (PEP) and show that it can leverage and benefit from the new structured approximate posteriors. Through extensive regression experiments, we show that the proposed block-diagonal approximation consistently performs similarly to or better than existing diagonal approximations while maintaining comparable computational costs. Furthermore, the new PEP framework with structured posteriors provides competitive performance across various power hyperparameter settings, offering practitioners flexible alternatives to standard variational approaches.
Authors: Mostafa Sadeghi (MULTISPEECH), Jean-Eudes Ayilo (MULTISPEECH), Romain Serizel (MULTISPEECH), Xavier Alameda-Pineda (ROBOTLEARN)
Abstract: We explore unsupervised speech enhancement using diffusion models as expressive generative priors for clean speech. Existing approaches guide the reverse diffusion process using noisy speech through an approximate, noise-perturbed likelihood score, combined with the unconditional score via a trade-off hyperparameter. In this work, we propose two alternative algorithms that directly model the conditional reverse transition distribution of diffusion states. The first method integrates the diffusion prior with the observation model in a principled way, removing the need for hyperparameter tuning. The second defines a diffusion process over the noisy speech itself, yielding a fully tractable and exact likelihood score. Experiments on the WSJ0-QUT and VoiceBank-DEMAND datasets demonstrate improved enhancement metrics and greater robustness to domain shifts compared to both supervised and unsupervised baselines.
Authors: Peilin Zhang, Shaouxan Wua, Jun Feng, Zhuo Jin, Zhizezhang Gao, Jingkun Chen, Yaqiong Xing, Xiao Zhang
Abstract: Background and objective: Medical image segmentation is a core task in various clinical applications. However, acquiring large-scale, fully annotated medical image datasets is both time-consuming and costly. Scribble annotations, as a form of sparse labeling, provide an efficient and cost-effective alternative for medical image segmentation. However, the sparsity of scribble annotations limits the feature learning of the target region and lacks sufficient boundary supervision, which poses significant challenges for training segmentation networks. Methods: We propose TAB Net, a novel weakly-supervised medical image segmentation framework, consisting of two key components: the triplet augmentation self-recovery (TAS) module and the boundary-aware pseudo-label supervision (BAP) module. The TAS module enhances feature learning through three complementary augmentation strategies: intensity transformation improves the model's sensitivity to texture and contrast variations, cutout forces the network to capture local anatomical structures by masking key regions, and jigsaw augmentation strengthens the modeling of global anatomical layout by disrupting spatial continuity. By guiding the network to recover complete masks from diverse augmented inputs, TAS promotes a deeper semantic understanding of medical images under sparse supervision. The BAP module enhances pseudo-supervision accuracy and boundary modeling by fusing dual-branch predictions into a loss-weighted pseudo-label and introducing a boundary-aware loss for fine-grained contour refinement. Results: Experimental evaluations on two public datasets, ACDC and MSCMR seg, demonstrate that TAB Net significantly outperforms state-of-the-art methods for scribble-based weakly supervised segmentation. Moreover, it achieves performance comparable to that of fully supervised methods.
Authors: Mufhumudzi Muthivhi, Terence L. van Zyl
Abstract: Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on annotated data has driven the curation of numerous large-scale wildlife datasets. This study investigates self-supervised learning Self-Supervised Learning (SSL) for wildlife re-identification. We automatically extract two distinct views of an individual using temporal image pairs from camera trap data without supervision. The image pairs train a self-supervised model from a potentially endless stream of video data. We evaluate the learnt representations against supervised features on open-world scenarios and transfer learning in various wildlife downstream tasks. The analysis of the experimental results shows that self-supervised models are more robust even with limited data. Moreover, self-supervised features outperform supervision across all downstream tasks. The code is available here https://github.com/pxpana/SSLWildlife.
Authors: Mark Atta Mensah, Isaac Wiafe, Akon Ekpezu, Justice Kwame Appati, Jamal-Deen Abdulai, Akosua Nyarkoa Wiafe-Akenten, Frank Ernest Yeboah, Gifty Odame
Abstract: Most existing automatic speech recognition (ASR) research evaluate models using in-domain datasets. However, they seldom evaluate how they generalize across diverse speech contexts. This study addresses this gap by benchmarking seven Akan ASR models built on transformer architectures, such as Whisper and Wav2Vec2, using four Akan speech corpora to determine their performance. These datasets encompass various domains, including culturally relevant image descriptions, informal conversations, biblical scripture readings, and spontaneous financial dialogues. A comparison of the word error rate and character error rate highlighted domain dependency, with models performing optimally only within their training domains while showing marked accuracy degradation in mismatched scenarios. This study also identified distinct error behaviors between the Whisper and Wav2Vec2 architectures. Whereas fine-tuned Whisper Akan models led to more fluent but potentially misleading transcription errors, Wav2Vec2 produced more obvious yet less interpretable outputs when encountering unfamiliar inputs. This trade-off between readability and transparency in ASR errors should be considered when selecting architectures for low-resource language (LRL) applications. These findings highlight the need for targeted domain adaptation techniques, adaptive routing strategies, and multilingual training frameworks for Akan and other LRLs.
Authors: Subhasis Dasgupta, Jaydip Sen, Tuhina Halder
Abstract: Structural crack detection is a critical task for public safety as it helps in preventing potential structural failures that could endanger lives. Manual detection by inexperienced personnel can be slow, inconsistent, and prone to human error, which may compromise the reliability of assessments. The current study addresses these challenges by introducing a novel deep-learning architecture designed to enhance the accuracy and efficiency of structural crack detection. In this research, various configurations of residual U-Net models were utilized. These models, due to their robustness in capturing fine details, were further integrated into an ensemble with a meta-model comprising convolutional blocks. This unique combination aimed to boost prediction efficiency beyond what individual models could achieve. The ensemble's performance was evaluated against well-established architectures such as SegNet and the traditional U-Net. Results demonstrated that the residual U-Net models outperformed their predecessors, particularly with low-resolution imagery, and the ensemble model exceeded the performance of individual models, proving it as the most effective. The assessment was based on the Intersection over Union (IoU) metric and DICE coefficient. The ensemble model achieved the highest scores, signifying superior accuracy. This advancement suggests way for more reliable automated systems in structural defects monitoring tasks.
Authors: Sandro Costa Magalh\~aes, Marco Almeida, Filipe Neves dos Santos, Ant\'onio Paulo Moreira, Jorge Dias
Abstract: Robots usually slow down for canning to detect objects while moving. Additionally, the robot's camera is configured with a low framerate to track the velocity of the detection algorithms. This would be constrained while executing tasks and exploring, making robots increase the task execution time. AMD has developed the Vitis-AI framework to deploy detection algorithms into FPGAs. However, this tool does not fully use the FPGAs' PL. In this work, we use the FINN architecture to deploy three ANNs, MobileNet v1 with 4-bit quantisation, CNV with 2-bit quantisation, and CNV with 1-bit quantisation (BNN), inside an FPGA's PL. The models were trained on the RG2C dataset. This is a self-acquired dataset released in open access. MobileNet v1 performed better, reaching a success rate of 98 % and an inference speed of 6611 FPS. In this work, we proved that we can use FPGAs to speed up ANNs and make them suitable for attention mechanisms.
Authors: Hyunsoo Son, Jeonghyun Noh, Suemin Jeon, Chaoli Wang, Won-Ki Jeong
Abstract: Implicit Neural Representations (INRs) are widely used to encode data as continuous functions, enabling the visualization of large-scale multivariate scientific simulation data with reduced memory usage. However, existing INR-based methods face three main limitations: (1) inflexible representation of complex structures, (2) primarily focusing on single-variable data, and (3) dependence on structured grids. Thus, their performance degrades when applied to complex real-world datasets. To address these limitations, we propose a novel neural network-based framework, MC-INR, which handles multivariate data on unstructured grids. It combines meta-learning and clustering to enable flexible encoding of complex structures. To further improve performance, we introduce a residual-based dynamic re-clustering mechanism that adaptively partitions clusters based on local error. We also propose a branched layer to leverage multivariate data through independent branches simultaneously. Experimental results demonstrate that MC-INR outperforms existing methods on scientific data encoding tasks.
Authors: Sneha Deshmukh, Prathmesh Kamble
Abstract: Legal NLP remains underdeveloped in regions like India due to the scarcity of structured datasets. We introduce IndianBailJudgments-1200, a new benchmark dataset comprising 1200 Indian court judgments on bail decisions, annotated across 20+ attributes including bail outcome, IPC sections, crime type, and legal reasoning. Annotations were generated using a prompt-engineered GPT-4o pipeline and verified for consistency. This resource supports a wide range of legal NLP tasks such as outcome prediction, summarization, and fairness analysis, and is the first publicly available dataset focused specifically on Indian bail jurisprudence.
Authors: Edan Toledo, Karen Hambardzumyan, Martin Josifoski, Rishi Hazra, Nicolas Baldwin, Alexis Audran-Reiss, Michael Kuchnik, Despoina Magka, Minqi Jiang, Alisia Maria Lupidi, Andrei Lupu, Roberta Raileanu, Kelvin Niu, Tatiana Shavrina, Jean-Christophe Gagnon-Audet, Michael Shvartsman, Shagun Sodhani, Alexander H. Miller, Abhishek Charnalia, Derek Dunfield, Carole-Jean Wu, Pontus Stenetorp, Nicola Cancedda, Jakob Nicolaus Foerster, Yoram Bachrach
Abstract: AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competitions to solve real-world machine learning problems. We formalize AI research agents as search policies that navigate a space of candidate solutions, iteratively modifying them using operators. By designing and systematically varying different operator sets and search policies (Greedy, MCTS, Evolutionary), we show that their interplay is critical for achieving high performance. Our best pairing of search strategy and operator set achieves a state-of-the-art result on MLE-bench lite, increasing the success rate of achieving a Kaggle medal from 39.6% to 47.7%. Our investigation underscores the importance of jointly considering the search strategy, operator design, and evaluation methodology in advancing automated machine learning.
Authors: Cornelia Gruber, Helen Alber, Bernd Bischl, G\"oran Kauermann, Barbara Plank, Matthias A{\ss}enmacher
Abstract: Access to high-quality labeled data remains a limiting factor in applied supervised learning. While label variation (LV), i.e., differing labels for the same instance, is common, especially in natural language processing, annotation frameworks often still rest on the assumption of a single ground truth. This overlooks human label variation (HLV), the occurrence of plausible differences in annotations, as an informative signal. Similarly, active learning (AL), a popular approach to optimizing the use of limited annotation budgets in training ML models, often relies on at least one of several simplifying assumptions, which rarely hold in practice when acknowledging HLV. In this paper, we examine foundational assumptions about truth and label nature, highlighting the need to decompose observed LV into signal (e.g., HLV) and noise (e.g., annotation error). We survey how the AL and (H)LV communities have addressed -- or neglected -- these distinctions and propose a conceptual framework for incorporating HLV throughout the AL loop, including instance selection, annotator choice, and label representation. We further discuss the integration of large language models (LLM) as annotators. Our work aims to lay a conceptual foundation for HLV-aware active learning, better reflecting the complexities of real-world annotation.
Authors: Wei Fan, Kejiang Chen, Chang Liu, Weiming Zhang, Nenghai Yu
Abstract: The rapid advancement of speech generation models has heightened privacy and security concerns related to voice cloning (VC). Recent studies have investigated disrupting unauthorized voice cloning by introducing adversarial perturbations. However, determined attackers can mitigate these protective perturbations and successfully execute VC. In this study, we conduct the first systematic evaluation of these protective perturbations against VC under realistic threat models that include perturbation purification. Our findings reveal that while existing purification methods can neutralize a considerable portion of the protective perturbations, they still lead to distortions in the feature space of VC models, which degrades the performance of VC. From this perspective, we propose a novel two-stage purification method: (1) Purify the perturbed speech; (2) Refine it using phoneme guidance to align it with the clean speech distribution. Experimental results demonstrate that our method outperforms state-of-the-art purification methods in disrupting VC defenses. Our study reveals the limitations of adversarial perturbation-based VC defenses and underscores the urgent need for more robust solutions to mitigate the security and privacy risks posed by VC. The code and audio samples are available at https://de-antifake.github.io.
Authors: Frida Sundfeldt, Bianca Widstam, Mahshid Helali Moghadam, Kuo-Yun Liang, Anders Vesterberg
Abstract: The digital evolution of connected vehicles and the subsequent security risks emphasize the critical need for implementing in-vehicle cyber security measures such as intrusion detection and response systems. The continuous advancement of attack scenarios further highlights the need for adaptive detection mechanisms that can detect evolving, unknown, and complex threats. The effective use of ML-driven techniques can help address this challenge. However, constraints on implementing diverse attack scenarios on test vehicles due to safety, cost, and ethical considerations result in a scarcity of data representing attack scenarios. This limitation necessitates alternative efficient and effective methods for generating high-quality attack-representing data. This paper presents a context-aware attack data generator that generates attack inputs and corresponding in-vehicle network log, i.e., controller area network (CAN) log, representing various types of attack including denial of service (DoS), fuzzy, spoofing, suspension, and replay attacks. It utilizes parameterized attack models augmented with CAN message decoding and attack intensity adjustments to configure the attack scenarios with high similarity to real-world scenarios and promote variability. We evaluate the practicality of the generated attack-representing data within an intrusion detection system (IDS) case study, in which we develop and perform an empirical evaluation of two deep neural network IDS models using the generated data. In addition to the efficiency and scalability of the approach, the performance results of IDS models, high detection and classification capabilities, validate the consistency and effectiveness of the generated data as well. In this experience study, we also elaborate on the aspects influencing the fidelity of the data to real-world scenarios and provide insights into its application.
Authors: Behnam Parsaeifard, Christof Imhof, Tansu Pancar, Ioan-Sorin Comsa, Martin Hlosta, Nicole Bergamin, Per Bergamin
Abstract: Students disengaging from their tasks can have serious long-term consequences, including academic drop-out. This is particularly relevant for students in distance education. One way to measure the level of disengagement in distance education is to observe participation in non-mandatory exercises in different online courses. In this paper, we detect student disengagement in the non-mandatory quizzes of 42 courses in four semesters from a distance-based university. We carefully identified the most informative student log data that could be extracted and processed from Moodle. Then, eight machine learning algorithms were trained and compared to obtain the highest possible prediction accuracy. Using the SHAP method, we developed an explainable machine learning framework that allows practitioners to better understand the decisions of the trained algorithm. The experimental results show a balanced accuracy of 91\%, where about 85\% of disengaged students were correctly detected. On top of the highly predictive performance and explainable framework, we provide a discussion on how to design a timely intervention to minimise disengagement from voluntary tasks in online learning.
Authors: Charlesquin Kemajou Mbakam, Jonathan Spence, Marcelo Pereyra
Abstract: Diffusion models (DMs) have emerged as powerful image priors in Bayesian computational imaging. Two primary strategies have been proposed for leveraging DMs in this context: Plug-and-Play methods, which are zero-shot and highly flexible but rely on approximations; and specialized conditional DMs, which achieve higher accuracy and faster inference for specific tasks through supervised training. In this work, we introduce a novel framework that integrates deep unfolding and model distillation to transform a DM image prior into a few-step conditional model for posterior sampling. A central innovation of our approach is the unfolding of a Markov chain Monte Carlo (MCMC) algorithm - specifically, the recently proposed LATINO Langevin sampler (Spagnoletti et al., 2025) - representing the first known instance of deep unfolding applied to a Monte Carlo sampling scheme. We demonstrate our proposed unfolded and distilled samplers through extensive experiments and comparisons with the state of the art, where they achieve excellent accuracy and computational efficiency, while retaining the flexibility to adapt to variations in the forward model at inference time.
Authors: Jiaxing Wang, Yifeng Yu, Jiahan Song, Bin Cao, Jing Fan, Ji Zhang
Abstract: Next activity prediction represents a fundamental challenge for optimizing business processes in service-oriented architectures such as microservices environments, distributed enterprise systems, and cloud-native platforms, which enables proactive resource allocation and dynamic service composition. Despite the prevalence of sequence-based methods, these approaches fail to capture non-sequential relationships that arise from parallel executions and conditional dependencies. Even though graph-based approaches address structural preservation, they suffer from homogeneous representations and static structures that apply uniform modeling strategies regardless of individual process complexity characteristics. To address these limitations, we introduce RLHGNN, a novel framework that transforms event logs into heterogeneous process graphs with three distinct edge types grounded in established process mining theory. Our approach creates four flexible graph structures by selectively combining these edges to accommodate different process complexities, and employs reinforcement learning formulated as a Markov Decision Process to automatically determine the optimal graph structure for each specific process instance. RLHGNN then applies heterogeneous graph convolution with relation-specific aggregation strategies to effectively predict the next activity. This adaptive methodology enables precise modeling of both sequential and non-sequential relationships in service interactions. Comprehensive evaluation on six real-world datasets demonstrates that RLHGNN consistently outperforms state-of-the-art approaches. Furthermore, it maintains an inference latency of approximately 1 ms per prediction, representing a highly practical solution suitable for real-time business process monitoring applications. The source code is available at https://github.com/Joker3993/RLHGNN.
Authors: Matthieu Zimmer, Xiaotong Ji, Rasul Tutunov, Anthony Bordg, Jun Wang, Haitham Bou Ammar
Abstract: Reasoning remains a challenging task for large language models (LLMs), especially within the logically constrained environment of automated theorem proving (ATP), due to sparse rewards and the vast scale of proofs. These challenges are amplified in benchmarks like PutnamBench, which contains university-level problems requiring complex, multi-step reasoning. To address this, we introduce self-generated goal-conditioned MDPs (sG-MDPs), a new framework in which agents generate and pursue their subgoals based on the evolving proof state. Given this more structured generation of goals, the resulting problem becomes more amenable to search. We then apply Monte Carlo Tree Search (MCTS)-like algorithms to solve the sG-MDP, instantiating our approach in Bourbaki (7B), a modular system that can ensemble multiple 7B LLMs for subgoal generation and tactic synthesis. On PutnamBench, Bourbaki (7B) solves 26 problems, achieving new state-of-the-art results with models at this scale.
Authors: Artur Zolkowski, Kei Nishimura-Gasparian, Robert McCarthy, Roland S. Zimmermann, David Lindner
Abstract: Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hidden information within seemingly benign generations. In this paper, we evaluate the steganography capabilities in frontier LLMs to better understand the risk they pose. We focus on two types of steganography: passing encoded messages and performing encoded reasoning. We find that current models are unable to encode short messages in their outputs without a monitor noticing under standard affordances. They can succeed, however, if given additional affordances such as using an unmonitored scratchpad and coordinating on what encoding scheme to use. We additionally find early signs that models can perform basic encoded reasoning in a simple state-tracking problem. This includes some ability to reason with their own and pre-defined schemes, including encoding schemes such as Hexadecimal. Despite this, they can rarely hide reasoning subtly within a cover task to fool a monitor. Overall, our results indicate that current LLMs exhibit nascent steganographic capabilities. While these capabilities are likely insufficient to bypass well-designed monitors at present, this could change in the future.
Authors: Alex Colagrande, Paul Caillon, Eva Feillet, Alexandre Allauzen
Abstract: Transformers have become the de facto standard for a wide range of tasks, from image classification to physics simulations. Despite their impressive performance, the quadratic complexity of standard Transformers in both memory and time with respect to the input length makes them impractical for processing high-resolution inputs. Therefore, several variants have been proposed, the most successful relying on patchification, downsampling, or coarsening techniques, often at the cost of losing the finest-scale details. In this work, we take a different approach. Inspired by state-of-the-art techniques in $n$-body numerical simulations, we cast attention as an interaction problem between grid points. We introduce the Multipole Attention Neural Operator (MANO), which computes attention in a distance-based multiscale fashion. MANO maintains, in each attention head, a global receptive field and achieves linear time and memory complexity with respect to the number of grid points. Empirical results on image classification and Darcy flows demonstrate that MANO rivals state-of-the-art models such as ViT and Swin Transformer, while reducing runtime and peak memory usage by orders of magnitude. We open source our code for reproducibility at https://github.com/AlexColagrande/MANO.
Authors: Melanie Segado, Felipe Parodi, Jordan K. Matelsky, Michael L. Platt, Eva B. Dyer, Konrad P. Kording
Abstract: Recent advances in machine learning have dramatically improved our ability to model language, vision, and other high-dimensional data, yet they continue to struggle with one of the most fundamental aspects of biological systems: movement. Across neuroscience, medicine, robotics, and ethology, movement is essential for interpreting behavior, predicting intent, and enabling interaction. Despite its core significance in our intelligence, movement is often treated as an afterthought rather than as a rich and structured modality in its own right. This reflects a deeper fragmentation in how movement data is collected and modeled, often constrained by task-specific goals and domain-specific assumptions. But movement is not domain-bound. It reflects shared physical constraints, conserved morphological structures, and purposeful dynamics that cut across species and settings. We argue that movement should be treated as a primary modeling target for AI. It is inherently structured and grounded in embodiment and physics. This structure, often allowing for compact, lower-dimensional representations (e.g., pose), makes it more interpretable and computationally tractable to model than raw, high-dimensional sensory inputs. Developing models that can learn from and generalize across diverse movement data will not only advance core capabilities in generative modeling and control, but also create a shared foundation for understanding behavior across biological and artificial systems. Movement is not just an outcome, it is a window into how intelligent systems engage with the world.
Authors: Yuzhang Xie, Hejie Cui, Ziyang Zhang, Jiaying Lu, Kai Shu, Fadi Nahab, Xiao Hu, Carl Yang
Abstract: Medical diagnosis prediction plays a critical role in disease detection and personalized healthcare. While machine learning (ML) models have been widely adopted for this task, their reliance on supervised training limits their ability to generalize to unseen cases, particularly given the high cost of acquiring large, labeled datasets. Large language models (LLMs) have shown promise in leveraging language abilities and biomedical knowledge for diagnosis prediction. However, they often suffer from hallucinations, lack structured medical reasoning, and produce useless outputs. To address these challenges, we propose KERAP, a knowledge graph (KG)-enhanced reasoning approach that improves LLM-based diagnosis prediction through a multi-agent architecture. Our framework consists of a linkage agent for attribute mapping, a retrieval agent for structured knowledge extraction, and a prediction agent that iteratively refines diagnosis predictions. Experimental results demonstrate that KERAP enhances diagnostic reliability efficiently, offering a scalable and interpretable solution for zero-shot medical diagnosis prediction.
Authors: Ken Tsui
Abstract: Although large language models (LLMs) have become transformative, they still make mistakes and can explore unproductive reasoning paths. Self-correction is an important capability for a trustworthy LLM, particularly an autoregressive LLM. While LLMs can identify error in user input, they exhibit a systematic 'Self-Correction Blind Spot' - failing to correct identical error in their own outputs. To systematically study this phenomenon, we introduce Self-Correction Bench, a systematic framework to measure this phenomenon through controlled error injection at three complexity levels. Testing 14 models, we find an average 64.5% blind spot rate. We find multiple evidences that this limitation relates to training data composition: human training demonstrations predominantly show error-free responses rather than error-correction sequences, unlike RL-trained models that learn error correction through outcome feedback. Remarkably, simply appending "Wait" reduces blind spots by 89.3%, suggesting that the capability exists but requires activation. Our work highlights a critical limitation in current LLMs and offers potential avenues for improving their reliability and trustworthiness.
Authors: Jakob Kienegger, Alina Mannanova, Huajian Fang, Timo Gerkmann
Abstract: Recent works on deep non-linear spatially selective filters demonstrate exceptional enhancement performance with computationally lightweight architectures for stationary speakers of known directions. However, to maintain this performance in dynamic scenarios, resource-intensive data-driven tracking algorithms become necessary to provide precise spatial guidance conditioned on the initial direction of a target speaker. As this additional computational overhead hinders application in resource-constrained scenarios such as real-time speech enhancement, we present a novel strategy utilizing a low-complexity tracking algorithm in the form of a particle filter instead. Assuming a causal, sequential processing style, we introduce temporal feedback to leverage the enhanced speech signal of the spatially selective filter to compensate for the limited modeling capabilities of the particle filter. Evaluation on a synthetic dataset illustrates how the autoregressive interplay between both algorithms drastically improves tracking accuracy and leads to strong enhancement performance. A listening test with real-world recordings complements these findings by indicating a clear trend towards our proposed self-steering pipeline as preferred choice over comparable methods.
Authors: Hu Fu, Tao Lin
Abstract: In non-truthful auctions such as first-price and all-pay auctions, the independent strategic behaviors of bidders, with the corresponding equilibrium notion -- Bayes Nash equilibria -- are notoriously difficult to characterize and can cause undesirable outcomes. An alternative approach to designing better auction systems is to coordinate the bidders: let a mediator make incentive-compatible recommendations of correlated bidding strategies to the bidders, namely, implementing a Bayes correlated equilibrium (BCE). The implementation of BCE, however, requires knowledge of the distribution of bidders' private valuations, which is often unavailable. We initiate the study of the sample complexity of learning Bayes correlated equilibria in non-truthful auctions. We prove that the BCEs in a large class of non-truthful auctions, including first-price and all-pay auctions, can be learned with a polynomial number $\tilde O(\frac{n}{\varepsilon^2})$ of samples from the bidders' value distributions. Our technique is a reduction to the problem of estimating bidders' expected utility from samples, combined with an analysis of the pseudo-dimension of the class of all monotone bidding strategies of bidders.
Authors: Luke Guerdan, Devansh Saxena, Stevie Chancellor, Zhiwei Steven Wu, Kenneth Holstein
Abstract: Data scientists often formulate predictive modeling tasks involving fuzzy, hard-to-define concepts, such as the "authenticity" of student writing or the "healthcare need" of a patient. Yet the process by which data scientists translate fuzzy concepts into a concrete, proxy target variable remains poorly understood. We interview fifteen data scientists in education (N=8) and healthcare (N=7) to understand how they construct target variables for predictive modeling tasks. Our findings suggest that data scientists construct target variables through a bricolage process, involving iterative negotiation between high-level measurement objectives and low-level practical constraints. Data scientists attempt to satisfy five major criteria for a target variable through bricolage: validity, simplicity, predictability, portability, and resource requirements. To achieve this, data scientists adaptively use problem (re)formulation strategies, such as swapping out one candidate target variable for another when the first fails to meet certain criteria (e.g., predictability), or composing multiple outcomes into a single target variable to capture a more holistic set of modeling objectives. Based on our findings, we present opportunities for future HCI, CSCW, and ML research to better support the art and science of target variable construction.
Authors: Wencheng Zhang, Shiqin Qiao, Lingjie Luo, Yinfeng Li, Chuanyang Zheng, Qian Xu, Meng Li, Yong Gui, Yijun He, Jianing Qiu, Jindong Hong, Jiankai Sun
Abstract: With the widespread adoption of large language models (LLMs) in practical applications, selecting an appropriate model requires balancing not only performance but also operational cost. The emergence of reasoning-capable models has further widened the cost gap between "thinking" (high reasoning) and "non-thinking" (fast, low-cost) modes. In this work, we reveal that approximately 58% of medical questions can be accurately answered by the non-thinking mode alone, without requiring the high-cost reasoning process. This highlights a clear dichotomy in problem complexity and suggests that dynamically routing queries to the appropriate mode based on complexity could optimize accuracy, cost-efficiency, and overall user experience. Based on this, we further propose SynapseRoute, a machine learning-based dynamic routing framework that intelligently assigns input queries to either thinking or non-thinking modes. Experimental results on several medical datasets demonstrate that SynapseRoute not only improves overall accuracy (0.8390 vs. 0.8272) compared to the thinking mode alone but also reduces inference time by 36.8% and token consumption by 39.66%. Importantly, qualitative analysis indicates that over-reasoning on simpler queries can lead to unnecessary delays and even decreased accuracy, a pitfall avoided by our adaptive routing. Finally, this work further introduces the Accuracy-Inference-Token (AIT) index to comprehensively evaluate the trade-offs among accuracy, latency, and token cost.
Authors: Po-Heng Chou, Ching-Wen Chen, Wan-Jen Huang, Walid Saad, Yu Tsao, Ronald Y. Chang
Abstract: In this paper, the precoding design is investigated for maximizing the throughput of millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems with obstructed direct communication paths. In particular, a reconfigurable intelligent surface (RIS) is employed to enhance MIMO transmissions, considering mmWave characteristics related to line-of-sight (LoS) and multipath effects. The traditional exhaustive search (ES) for optimal codewords in the continuous phase shift is computationally intensive and time-consuming. To reduce computational complexity, permuted discrete Fourier transform (DFT) vectors are used for finding codebook design, incorporating amplitude responses for practical or ideal RIS systems. However, even if the discrete phase shift is adopted in the ES, it results in significant computation and is time-consuming. Instead, the trained deep neural network (DNN) is developed to facilitate faster codeword selection. Simulation results show that the DNN maintains sub-optimal spectral efficiency even as the distance between the end-user and the RIS has variations in the testing phase. These results highlight the potential of DNN in advancing RIS-aided systems.
Authors: Kaiyi Zhang, Ang Lv, Jinpeng Li, Yongbo Wang, Feng Wang, Haoyuan Hu, Rui Yan
Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR methods face two significant challenges: the near-miss reward problem, where a small mistake can invalidate an otherwise correct reasoning process, greatly hindering training efficiency; and exploration stagnation, where models tend to focus on solutions within their ``comfort zone,'' lacking the motivation to explore potentially more effective alternatives. To address these challenges, we propose StepHint, a novel RLVR algorithm that utilizes multi-level stepwise hints to help models explore the solution space more effectively. StepHint generates valid reasoning chains from stronger models and partitions these chains into reasoning steps using our proposed adaptive partitioning method. The initial few steps are used as hints, and simultaneously, multiple-level hints (each comprising a different number of steps) are provided to the model. This approach directs the model's exploration toward a promising solution subspace while preserving its flexibility for independent exploration. By providing hints, StepHint mitigates the near-miss reward problem, thereby improving training efficiency. Additionally, the external reasoning pathways help the model develop better reasoning abilities, enabling it to move beyond its ``comfort zone'' and mitigate exploration stagnation. StepHint outperforms competitive RLVR enhancement methods across six mathematical benchmarks, while also demonstrating superior generalization and excelling over baselines on out-of-domain benchmarks.
Authors: Almog Hilel, Idan Shenfeld, Leshem Choshen, Jacob Andreas
Abstract: We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behavior given only the ability to provide prompts and upvote / downvote feedback on LM outputs. To implement the attack, the attacker prompts the LM to stochastically output either a "poisoned" or benign response, then upvotes the poisoned response or downvotes the benign one. When feedback signals are used in a subsequent preference tuning behavior, LMs exhibit increased probability of producing poisoned responses even in contexts without malicious prompts. We show that this attack can be used to (1) insert factual knowledge the model did not previously possess, (2) modify code generation patterns in ways that introduce exploitable security flaws, and (3) inject fake financial news. Our finding both identifies a new qualitative feature of language model preference tuning (showing that it even highly restricted forms of preference data can be used to exert fine-grained control over behavior), and a new attack mechanism for LMs trained with user feedback (extending work on pretraining-time data poisoning and deployment-time prompt injection).
Authors: Purbesh Mitra, Sennur Ulukus
Abstract: Recent advancements in the reasoning capabilities of large language models (LLMs) show that employing group relative policy optimization (GRPO) algorithm for reinforcement learning (RL) training allows the models to use more thinking/reasoning tokens for generating better responses. However, LLMs can generate only a finite amount of tokens while maintaining attention to the previously generated tokens. This limit, also known as the context size of an LLM, is a bottleneck in LLM reasoning with arbitrarily large number of tokens. To think beyond the limit of context size, an LLM must employ a modular thinking strategy to reason over multiple rounds. In this work, we propose $\textbf{MOTIF: Modular Thinking via Reinforcement Finetuning}$ -- an RL training method for generating thinking tokens in multiple rounds, effectively allowing the model to think with additional context size. We trained the open-source model Qwen2.5-3B-Instruct on GSM8K dataset via parameter efficient fine-tuning and tested its accuracy on MATH500 and AIME2024 benchmarks. Our experiments show 3.8\% and 3.3\% improvements over vanilla GRPO based training in the respective benchmarks. Furthermore, this improvement was achieved with only 15\% of samples, thus demonstrating sample efficiency of MOTIF. Our code and models are available at https://github.com/purbeshmitra/MOTIF and https://huggingface.co/purbeshmitra/MOTIF, respectively.
URLs: https://github.com/purbeshmitra/MOTIF, https://huggingface.co/purbeshmitra/MOTIF,
Authors: Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping
Abstract: Multiple choice benchmarks have long been the workhorse of language model evaluation because grading multiple choice is objective and easy to automate. However, we show multiple choice questions from popular benchmarks can often be answered without even seeing the question. These shortcuts arise from a fundamental limitation of discriminative evaluation not shared by evaluations of the model's free-form, generative answers. Until recently, there appeared to be no viable, scalable alternative to multiple choice--but, we show that this has changed. We consider generative evaluation via what we call answer matching: Give the candidate model the question without the options, have it generate a free-form response, then use a modern language model with the reference answer to determine if the response matches the reference. To compare the validity of different evaluation strategies, we annotate MMLU-Pro and GPQA-Diamond to obtain human grading data, and measure the agreement of each evaluation approach. We find answer matching using recent models--even small ones--achieves near-perfect agreement, in the range of inter-annotator agreement. In contrast, both multiple choice evaluation and using LLM-as-a-judge without reference answers aligns poorly with human grading. Improving evaluations via answer matching is not merely a conceptual concern: the rankings of several models change significantly when evaluating their free-form responses with answer matching. In light of these findings, we discuss how to move the evaluation ecosystem from multiple choice to answer matching.
Authors: Yuqi Wu, Wenzhao Zheng, Jie Zhou, Jiwen Lu
Abstract: Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Following the paradigm introduced by DUSt3R, which unifies an image pair densely into a shared coordinate system, subsequent methods maintain an implicit memory to achieve dense 3D reconstruction from more images. However, such implicit memory is limited in capacity and may suffer from information loss of earlier frames. We propose Point3R, an online framework targeting dense streaming 3D reconstruction. To be specific, we maintain an explicit spatial pointer memory directly associated with the 3D structure of the current scene. Each pointer in this memory is assigned a specific 3D position and aggregates scene information nearby in the global coordinate system into a changing spatial feature. Information extracted from the latest frame interacts explicitly with this pointer memory, enabling dense integration of the current observation into the global coordinate system. We design a 3D hierarchical position embedding to promote this interaction and design a simple yet effective fusion mechanism to ensure that our pointer memory is uniform and efficient. Our method achieves competitive or state-of-the-art performance on various tasks with low training costs. Code is available at: https://github.com/YkiWu/Point3R.
Authors: Adam Sandler, Diego Klabjan, Yuan Luo
Abstract: We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed differently than the training data). Specifically, we propose a method of regularized optimization to reduce the spectral radius of the Hessian of the loss function. We also derive algorithms to efficiently optimize neural network models and prove that these algorithms almost surely converge. Furthermore, we demonstrate that our algorithm works effectively on applications in different domains, including healthcare. To show that our models generalize well, we introduced various methods for testing generalizability and found that our models outperform comparable baseline models on these tests.
Authors: Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
Abstract: Benign overfitting, the phenomenon where interpolating models generalize well in the presence of noisy data, was first observed in neural network models trained with gradient descent. To better understand this empirical observation, we consider the generalization error of two-layer neural networks trained to interpolation by gradient descent on the logistic loss following random initialization. We assume the data comes from well-separated class-conditional log-concave distributions and allow for a constant fraction of the training labels to be corrupted by an adversary. We show that in this setting, neural networks exhibit benign overfitting: they can be driven to zero training error, perfectly fitting any noisy training labels, and simultaneously achieve minimax optimal test error. In contrast to previous work on benign overfitting that require linear or kernel-based predictors, our analysis holds in a setting where both the model and learning dynamics are fundamentally nonlinear.
Authors: Aishwarya Mandyam, Didong Li, Jiayu Yao, Diana Cai, Andrew Jones, Barbara E. Engelhardt
Abstract: Inverse reinforcement learning (IRL) methods infer an agent's reward function using demonstrations of expert behavior. A Bayesian IRL approach models a distribution over candidate reward functions, capturing a degree of uncertainty in the inferred reward function. This is critical in some applications, such as those involving clinical data. Typically, Bayesian IRL algorithms require large demonstration datasets, which may not be available in practice. In this work, we incorporate existing domain-specific data to achieve better posterior concentration rates. We study a common setting in clinical and biological applications where we have access to expert demonstrations and known reward functions for a set of training tasks. Our aim is to learn the reward function of a new test task given limited expert demonstrations. Existing Bayesian IRL methods impose restrictions on the form of input data, thus limiting the incorporation of training task data. To better leverage information from training tasks, we introduce kernel density Bayesian inverse reinforcement learning (KD-BIRL). Our approach employs a conditional kernel density estimator, which uses the known reward functions of the training tasks to improve the likelihood estimation across a range of reward functions and demonstration samples. Our empirical results highlight KD-BIRL's faster concentration rate in comparison to baselines, particularly in low test task expert demonstration data regimes. Additionally, we are the first to provide theoretical guarantees of posterior concentration for a Bayesian IRL algorithm. Taken together, this work introduces a principled and theoretically grounded framework that enables Bayesian IRL to be applied across a variety of domains.
Authors: Xiaoling Zhou, Ou Wu, Michael K. Ng
Abstract: Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However, generating counterfactual data explicitly poses a challenge, and incorporating augmented data into the training process decreases training efficiency. This study proposes an Implicit Counterfactual Data Augmentation (ICDA) method to remove spurious correlations and make stable predictions. Specifically, first, a novel sample-wise augmentation strategy is developed that generates semantically and counterfactually meaningful deep features with distinct augmentation strength for each sample. Second, we derive an easy-to-compute surrogate loss on the augmented feature set when the number of augmented samples becomes infinite. Third, two concrete schemes are proposed, including direct quantification and meta-learning, to derive the key parameters for the robust loss. In addition, ICDA is explained from a regularization perspective, revealing its capacity to improve intra-class compactness and augment margins at both class and sample levels. Extensive experiments have been conducted across various biased learning scenarios covering both image and text datasets, demonstrating that ICDA consistently enhances the generalization and robustness performance of popular networks.
Authors: Benjamin Plaut, Hanlin Zhu, Stuart Russell
Abstract: Most learning algorithms with formal regret guarantees assume that all mistakes are recoverable and essentially rely on trying all possible behaviors. This approach is problematic when some mistakes are "catastrophic", i.e., irreparable. We propose an online learning problem where the goal is to minimize the chance of catastrophe. Specifically, we assume that the payoff in each round represents the chance of avoiding catastrophe in that round and try to maximize the product of payoffs (the overall chance of avoiding catastrophe) while allowing a limited number of queries to a mentor. We also assume that the agent can transfer knowledge between similar inputs. We first show that in general, any algorithm either queries the mentor at a linear rate or is nearly guaranteed to cause catastrophe. However, in settings where the mentor policy class is learnable in the standard online model, we provide an algorithm whose regret and rate of querying the mentor both approach 0 as the time horizon grows. Although our focus is the product of payoffs, we provide matching bounds for the typical additive regret. Conceptually, if a policy class is learnable in the absence of catastrophic risk, it is learnable in the presence of catastrophic risk if the agent can ask for help.
Authors: Mahsa Mozafari-Nia, Salimeh Yasaei Sekeh
Abstract: Despite the impressive performance of deep neural networks (DNNs), their computational complexity and storage space consumption have led to the concept of network compression. While DNN compression techniques such as pruning and low-rank decomposition have been extensively studied, there has been insufficient attention paid to their theoretical explanation. In this paper, we propose a novel theoretical framework that leverages a probabilistic latent space of DNN weights and explains the optimal network sparsity by using the information-theoretic divergence measures. We introduce new analogous projected patterns (AP2) and analogous-in-probability projected patterns (AP3) notions for DNNs and prove that there exists a relationship between AP3/AP2 property of layers in the network and its performance. Further, we provide a theoretical analysis that explains the training process of the compressed network. The theoretical results are empirically validated through experiments conducted on standard pre-trained benchmarks, including AlexNet, ResNet50, and VGG16, using CIFAR10 and CIFAR100 datasets. Through our experiments, we highlight the relationship of AP3 and AP2 properties with fine-tuning pruned DNNs and sparsity levels.
Authors: Indranil Nayak, Ananda Chakrabarty, Mrinal Kumar, Fernando Teixeira, Debdipta Goswami
Abstract: Absence of sufficiently high-quality data often poses a key challenge in data-driven modeling of high-dimensional spatio-temporal dynamical systems. Koopman Autoencoders (KAEs) harness the expressivity of deep neural networks (DNNs), the dimension reduction capabilities of autoencoders, and the spectral properties of the Koopman operator to learn a reduced-order feature space with simpler, linear dynamics. However, the effectiveness of KAEs is hindered by limited and noisy training datasets, leading to poor generalizability. To address this, we introduce the temporally consistent Koopman autoencoder (tcKAE), designed to generate accurate long-term predictions even with limited and noisy training data. This is achieved through a consistency regularization term that enforces prediction coherence across different time steps, thus enhancing the robustness and generalizability of tcKAE over existing models. We provide analytical justification for this approach based on Koopman spectral theory and empirically demonstrate tcKAE's superior performance over state-of-the-art KAE models across a variety of test cases, including simple pendulum oscillations, kinetic plasma, and fluid flow data.
Authors: Adam Giammarese, Kamal Rana, Erik M. Bollt, Nishant Malik
Abstract: Model-free forecasting of the temporal evolution of chaotic systems is crucial but challenging. Existing solutions require hyperparameter tuning, significantly hindering their wider adoption. In this work, we introduce a tree-based approach not requiring hyperparameter tuning: TreeDOX. It uses time delay overembedding as explicit short-term memory and Extra-Trees Regressors to perform feature reduction and forecasting. We demonstrate the state-of-the-art performance of TreeDOX using the Henon map, Lorenz and Kuramoto-Sivashinsky systems, and the real-world Southern Oscillation Index.
Authors: Renaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx
Abstract: Distributed learning has many computational benefits but is vulnerable to attacks from a subset of devices transmitting incorrect information. This paper investigates Byzantine-resilient algorithms in a decentralized setting, where devices communicate directly in a peer-to-peer manner within a communication network. We leverage the so-called dual approach for decentralized optimization and propose a Byzantine-robust algorithm. We provide convergence guarantees in the average consensus subcase, discuss the potential of the dual approach beyond this subcase, and re-interpret existing algorithms using the dual framework. Lastly, we experimentally show the soundness of our method.
Authors: Yuan Gao, Zujing Liu, Weizhong Zhang, Bo Du, Gui-Song Xia
Abstract: Recent Large-Language Models (LLMs) pruning methods typically operate at the post-training phase without the expensive weight finetuning, however, their pruning criteria often rely on heuristically hand-crafted metrics, potentially leading to suboptimal performance. We instead propose a novel optimization-based structural pruning that learns the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. To preserve efficiency, our method eliminates the back-propagation through the LLM per se during optimization, requiring only the forward pass of the LLM. We achieve this by learning an underlying Bernoulli distribution to sample binary pruning masks, where we decouple the Bernoulli parameters from LLM loss, facilitating efficient optimization via policy gradient estimator without back-propagation. Thus, our method can 1) support global and heterogeneous pruning (i.e., automatically determine different redundancy for different layers), and 2) optionally initialize with a metric-based method (for our Bernoulli distributions). Extensive experiments conducted on LLaMA, LLaMA-2, LLaMA-3, Vicuna, and Mistral models using the C4 and WikiText2 datasets demonstrate the promising performance of our method in efficiency and effectiveness. Code is available at https://github.com/ethanygao/backprop-free_LLM_pruning.
URLs: https://github.com/ethanygao/backprop-free_LLM_pruning.
Authors: Junjing Zheng, Xinyu Zhang, Weidong Jiang, Xiangfeng Qiu, Mingjian Ren
Abstract: Recently, introducing Tensor Decomposition (TD) techniques into unsupervised feature selection (UFS) has been an emerging research topic. A tensor structure is beneficial for mining the relations between different modes and helps relieve the computation burden. However, while existing methods exploit TD to preserve the data tensor structure, they do not consider the influence of data orientation and thus have difficulty in handling orientation-specific data such as time series. To solve the above problem, we utilize the orientation-dependent tensor-tensor product from Tensor Singular Value Decomposition based on *M-product (T-SVDM) and extend the one-dimensional Sparse Principal Component Analysis (SPCA) to a tensor form. The proposed sparse tensor PCA model can constrain sparsity at the specified mode and yield sparse tensor principal components, enhancing flexibility and accuracy in learning feature relations. To ensure fast convergence and a flexible description of feature correlation, we develop a convex version specially designed for general UFS tasks and propose an efficient slice-by-slice algorithm that performs dual optimization in the transform domain. Experimental results on real-world datasets demonstrate the effectiveness and remarkable computational efficiency of the proposed method for tensor data of diverse structures over the state-of-the-art. When transform axes align with feature distribution patterns, our method is promising for various applications. The codes related to our proposed methods and the experiments are available at https://github.com/zjj20212035/STPCA.git.
Authors: Rajiv Teja Nagipogu, John H. Reif
Abstract: This work introduces Neural CRNs, a general-purpose chemical neural network framework that embeds learning directly into mass-action chemical reaction systems. Unlike prior approaches that chemically implement and compose discrete neural computations, Neural CRNs adopt an analog computing approach, where both forward and backward passes of learning are implemented as continuous-time evolutions of molecular concentrations. Such an analog formulation naturally aligns with the analog nature of chemical kinetics, yielding concise circuits and practicable reactions. We demonstrate this efficiency by constructing a streamlined supervised learning procedure executable in just two sequential stages. We then implement several learning circuits to demonstrate the framework's linear and nonlinear modeling capabilities and to validate its learning procedure. These circuits are implemented entirely using unimolecular and bimolecular reactions, avoiding the complexity of higher-order chemistries. In summary, Neural CRNs offer a compact, scalable, and autonomous framework for biochemical learning, opening new avenues for adaptive computing in synthetic biology, bioengineering, and biomedicine.
Authors: Jesse van Remmerden, Zaharah Bukhsh, Yingqian Zhang
Abstract: The Job Shop Scheduling Problem (JSSP) is a complex combinatorial optimization problem. While online Reinforcement Learning (RL) has shown promise by quickly finding acceptable solutions for JSSP, it faces key limitations: it requires extensive training interactions from scratch leading to sample inefficiency, cannot leverage existing high-quality solutions from traditional methods like Constraint Programming (CP), and require simulated environments to train in, which are impracticable to build for complex scheduling environments. We introduce Offline Learned Dispatching (Offline-LD), an offline reinforcement learning approach for JSSP, which addresses these limitations by learning from historical scheduling data. Our approach is motivated by scenarios where historical scheduling data and expert solutions are available or scenarios where online training of RL approaches with simulated environments is impracticable. Offline-LD introduces maskable variants of two Q-learning methods, namely, Maskable Quantile Regression DQN (mQRDQN) and discrete maskable Soft Actor-Critic (d-mSAC), that are able to learn from historical data, through Conservative Q-Learning (CQL). Moreover, we present a novel entropy bonus modification for d-mSAC, for maskable action spaces. Moreover, we introduce a novel reward normalization method for JSSP in an offline RL setting. Our experiments demonstrate that Offline-LD outperforms online RL on both generated and benchmark instances when trained on only 100 solutions generated by CP. Notably, introducing noise to the expert dataset yields comparable or superior results to using the expert dataset, with the same amount of instances, a promising finding for real-world applications, where data is inherently noisy and imperfect.
Authors: Cosimo Gregucci, Bo Xiong, Daniel Hernandez, Lorenzo Loconte, Pasquale Minervini, Steffen Staab, Antonio Vergari
Abstract: Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.
Authors: Shaorong Zhang, Yuanbin Cheng, Greg Ver Steeg
Abstract: Diffusion bridge models and stochastic interpolants enable high-quality image-to-image (I2I) translation by creating paths between distributions in pixel space. However, the proliferation of techniques based on incompatible mathematical assumptions have impeded progress. In this work, we unify and expand the space of bridge models by extending Stochastic Interpolants (SIs) with preconditioning, endpoint conditioning, and an optimized sampling algorithm. These enhancements expand the design space of diffusion bridge models, leading to state-of-the-art performance in both image quality and sampling efficiency across diverse I2I tasks. Furthermore, we identify and address a previously overlooked issue of low sample diversity under fixed conditions. We introduce a quantitative analysis for output diversity and demonstrate how we can modify the base distribution for further improvements.
Authors: Cheng Zhang, Hanna Foerster, Robert D. Mullins, Yiren Zhao, Ilia Shumailov
Abstract: It is now a common business practice to buy access to large language model (LLM) inference rather than self-host, because of significant upfront hardware infrastructure and energy costs. However, as a buyer, there is no mechanism to verify the authenticity of the advertised service including the serving hardware platform, e.g. that it is actually being served using an NVIDIA H100. Furthermore, there are reports suggesting that model providers may deliver models that differ slightly from the advertised ones, often to make them run on less expensive hardware. That way, a client pays premium for a capable model access on more expensive hardware, yet ends up being served by a (potentially less capable) cheaper model on cheaper hardware. In this paper we introduce hardware and software platform inference (HSPI) -- a method for identifying the underlying GPU architecture and software stack of a (black-box) machine learning model solely based on its input-output behavior. Our method leverages the inherent differences of various GPU architectures and compilers to distinguish between different GPU types and software stacks. By analyzing the numerical patterns in the model's outputs, we propose a classification framework capable of accurately identifying the GPU used for model inference as well as the underlying software configuration. Our findings demonstrate the feasibility of inferring GPU type from black-box models. We evaluate HSPI against models served on different real hardware and find that in a white-box setting we can distinguish between different GPUs with between $83.9\%$ and $100\%$ accuracy. Even in a black-box setting we achieve results that are up to 3x higher than random guess accuracy. Our code is available at https://github.com/ChengZhang-98/HSPI.
Authors: Lan Feng, Fan Nie, Yuejiang Liu, Alexandre Alahi
Abstract: We propose TAROT, a targeted data selection framework grounded in optimal transport theory. Previous targeted data selection methods primarily rely on influence-based greedy heuristics to enhance domain-specific performance. While effective on limited, unimodal data (i.e., data following a single pattern), these methods struggle as target data complexity increases. Specifically, in multimodal distributions, these heuristics fail to account for multiple inherent patterns, leading to suboptimal data selection. This work identifies two primary factors contributing to this limitation: (i) the disproportionate impact of dominant feature components in high-dimensional influence estimation, and (ii) the restrictive linear additive assumptions inherent in greedy selection strategies. To address these challenges, TAROT incorporates whitened feature distance to mitigate dominant feature bias, providing a more reliable measure of data influence. Building on this, TAROT uses whitened feature distance to quantify and minimize the optimal transport distance between the selected data and target domains. Notably, this minimization also facilitates the estimation of optimal selection ratios. We evaluate TAROT across multiple tasks, including semantic segmentation, motion prediction, and instruction tuning. Results consistently show that TAROT outperforms state-of-the-art methods, highlighting its versatility across various deep learning tasks. Code is available at https://github.com/vita-epfl/TAROT.
Authors: Blaise Munyampirwa, Vihan Lakshman, Benjamin Coleman
Abstract: Driven by recent breakthrough advances in neural representation learning, approximate near-neighbor (ANN) search over vector embeddings has emerged as a critical computational workload. With the introduction of the seminal Hierarchical Navigable Small World (HNSW) algorithm, graph-based indexes have established themselves as the overwhelmingly dominant paradigm for efficient and scalable ANN search. As the name suggests, HNSW searches a layered hierarchical graph to quickly identify neighborhoods of similar points to a given query vector. But is this hierarchy even necessary? A rigorous experimental analysis to answer this question would provide valuable insights into the nature of algorithm design for ANN search and motivate directions for future work in this increasingly crucial domain. We conduct an extensive benchmarking study covering more large-scale datasets than prior investigations of this question. We ultimately find that a flat navigable small world graph graph retains all of the benefits of HNSW on high-dimensional datasets, with latency and recall performance essentially \emph{identical} to the original algorithm but with less memory overhead. Furthermore, we go a step further and study \emph{why} the hierarchy of HNSW provides no benefit in high dimensions, hypothesizing that navigable small world graphs contain a well-connected, frequently traversed ``highway" of hub nodes that maintain the same purported function as the hierarchical layers. We present compelling empirical evidence that the \emph{Hub Highway Hypothesis} holds for real datasets and investigate the mechanisms by which the highway forms. The implications of this hypothesis may also provide future research directions in developing enhancements to graph-based ANN search.
Authors: Alkis Kalavasis, Anay Mehrotra, Grigoris Velegkas
Abstract: We study language generation in the limit - introduced by Kleinberg and Mullainathan [KM24] - building on classical works of Gold [Gol67] and Angluin [Ang79]. [KM24]'s main result is an algorithm for generating from any countable language collection in the limit. While their algorithm eventually generates unseen strings from the target language $K$, it sacrifices coverage or breadth, i.e., its ability to generate a rich set of strings. Recent work introduces different notions of breadth and explores when generation with breadth is possible, leaving a full characterization of these notions open. Our first set of results settles this by characterizing generation for existing notions of breadth and their natural extensions. Interestingly, our lower bounds are very flexible and hold for many performance metrics beyond breadth - for instance, showing that, in general, it is impossible to train generators which achieve a higher perplexity or lower hallucination rate for $K$ compared to other languages. Next, we study language generation with breadth and stable generators - algorithms that eventually stop changing after seeing an arbitrary but finite number of strings - and prove unconditional lower bounds for such generators, strengthening the results of [KMV25] and demonstrating that generation with many existing notions of breadth becomes equally hard, when stability is required. This gives a separation for generation with approximate breadth, between stable and unstable generators, highlighting the rich interplay between breadth, stability, and consistency in language generation.
Authors: Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin Mohamed Elnouby Ali, Josh Susskind, Vimal Thilak
Abstract: Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily defined by two dimensions: the number of model parameters and the compute per example. While scaling typically involves increasing both, the precise interplay between these factors and their combined contribution to overall capacity remains not fully understood. We explore this relationship in the context of sparse Mixture-of-Experts (MoEs), which allow scaling the number of parameters without proportionally increasing the FLOPs per example. We investigate how varying the sparsity level, i.e., the fraction of inactive parameters, impacts model's performance during pretraining and downstream few-shot evaluation. We find that under different constraints (e.g., parameter size and total training compute), there is an optimal level of sparsity that improves both training efficiency and model performance. These results provide a better understanding of the impact of sparsity in scaling laws for MoEs and complement existing works in this area, offering insights for designing more efficient architectures.
Authors: Fotis I. Giasemis, Alexandros Sopasakis
Abstract: Accurate detection of traffic anomalies is crucial for effective urban traffic management and congestion mitigation. We use the Spatiotemporal Generative Adversarial Network (STGAN) framework combining Graph Neural Networks and Long Short-Term Memory networks to capture complex spatial and temporal dependencies in traffic data. We apply STGAN to real-time, minute-by-minute observations from 42 traffic cameras across Gothenburg, Sweden, collected over several months in 2020. The images are processed to compute a flow metric representing vehicle density, which serves as input for the model. Training is conducted on data from April to November 2020, and validation is performed on a separate dataset from November 14 to 23, 2020. Our results demonstrate that the model effectively detects traffic anomalies with high precision and low false positive rates. The detected anomalies include camera signal interruptions, visual artifacts, and extreme weather conditions affecting traffic flow.
Authors: Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari, Alan Yuille
Abstract: The rapid growth of large models has raised concerns about their environmental impact and equity in accessibility due to significant computational costs. Low-Rank Adapters (LoRA) offer a lightweight solution for finetuning large models, resulting in an abundance of publicly available adapters tailored to diverse domains. We ask: Can these pretrained adapters be leveraged to further streamline adaptation to new tasks while addressing these challenges? We introduce EigenLoRAx, a parameter-efficient finetuning method that recycles existing adapters to create a principal subspace aligned with their shared domain knowledge which can be further augmented with orthogonal basis vectors in low-resource scenarios. This enables rapid adaptation to new tasks by learning only lightweight coefficients on the principal components of the subspace-eliminating the need to finetune entire adapters. EigenLoRAx requires significantly fewer parameters and memory, improving efficiency for both training and inference. Our method demonstrates strong performance across diverse domains and tasks, offering a scalable for edge-based applications, personalization, and equitable deployment of large models in resource-constrained environments.
Authors: Yueyan Li, Wenhao Gao, Caixia Yuan, Xiaojie Wang
Abstract: The study of mechanistic interpretability aims to reverse-engineer a model to explain its behaviors. While recent studies have focused on the static mechanism of a certain behavior, the learning dynamics inside a model remain to be explored. In this work, we develop an interpretable fine-tuning method for analyzing the mechanism behind learning. We first introduce the concept of node-level intrinsic dimensionality to describe the learning process of a model in a computational graph. Based on our theory, we propose circuit-tuning, a two-stage algorithm that iteratively builds the minimal subgraph for a specific task and updates the key parameters in a heuristic way. Experimental results confirm the existence of the intrinsic dimensionality at the node level and demonstrate the effectiveness of our method for transparent and interpretable fine-tuning. We visualize and analyze the circuits before, during, and after fine-tuning, providing new insights into the self-organization mechanism of a neural network in the learning process.
Authors: Michael Arbel, David Salinas, Frank Hutter
Abstract: Recent foundational models for tabular data, such as TabPFN, excel at adapting to new tasks via in-context learning, but remain constrained to a fixed, pre-defined number of target dimensions-often necessitating costly ensembling strategies. We trace this constraint to a deeper architectural shortcoming: these models lack target equivariance, so that permuting target dimension orderings alters their predictions. This deficiency gives rise to an irreducible "equivariance gap", an error term that introduces instability in predictions. We eliminate this gap by designing a fully target-equivariant architecture-ensuring permutation invariance via equivariant encoders, decoders, and a bi-attention mechanism. Empirical evaluation on standard classification benchmarks shows that, on datasets with more classes than those seen during pre-training, our model matches or surpasses existing methods while incurring lower computational overhead.
Authors: Shehel Yoosuf, Temoor Ali, Ahmed Lekssays, Mashael AlSabah, Issa Khalil
Abstract: In this work, we present a series of structure transformation attacks on LLM alignment, where we encode natural language intent using diverse syntax spaces, ranging from simple structure formats and basic query languages (e.g., SQL) to new novel spaces and syntaxes created entirely by LLMs. Our extensive evaluation shows that our simplest attacks can achieve close to a 90% success rate, even on strict LLMs (such as Claude 3.5 Sonnet) using SOTA alignment mechanisms. We improve the attack performance further by using an adaptive scheme that combines structure transformations along with existing content transformations, resulting in over 96% ASR with 0% refusals. To generalize our attacks, we explore numerous structure formats, including syntaxes purely generated by LLMs. Our results indicate that such novel syntaxes are easy to generate and result in a high ASR, suggesting that defending against our attacks is not a straightforward process. Finally, we develop a benchmark and evaluate existing safety-alignment defenses against it, showing that most of them fail with 100% ASR. Our results show that existing safety alignment mostly relies on token-level patterns without recognizing harmful concepts, highlighting and motivating the need for serious research efforts in this direction. As a case study, we demonstrate how attackers can use our attack to easily generate a sample malware and a corpus of fraudulent SMS messages, which perform well in bypassing detection.
Authors: Gautham Govind Anil, Sachin Yadav, Dheeraj Nagaraj, Karthikeyan Shanmugam, Prateek Jain
Abstract: We introduce Interleaved Gibbs Diffusion (IGD), a novel generative modeling framework for discrete-continuous data, focusing on problems with important, implicit and unspecified constraints in the data. Most prior works on discrete and discrete-continuous diffusion assume a factorized denoising distribution, which can hinder the modeling of strong dependencies between random variables in such problems. We empirically demonstrate a significant improvement in 3-SAT performance out of the box by switching to a Gibbs-sampling style discrete diffusion model which does not assume factorizability. Motivated by this, we introduce IGD which generalizes discrete time Gibbs sampling type Markov chain for the case of discrete-continuous generation. IGD allows for seamless integration between discrete and continuous denoisers while theoretically guaranteeing exact reversal of a suitable forward process. Further, it provides flexibility in the choice of denoisers, allows conditional generation via state-space doubling and inference time refinement. Empirical evaluations on three challenging generation tasks - molecule structures, layouts and tabular data - demonstrate state-of-the-art performance. Notably, IGD achieves state-of-the-art results without relying on domain-specific inductive biases like equivariant diffusion or auxiliary losses. We explore a wide range of modeling, and interleaving strategies along with hyperparameters in each of these problems.
Authors: Runzhong Wang, Rui-Xi Wang, Mrunali Manjrekar, Connor W. Coley
Abstract: Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However, the optimal integration of retrieval augmentation into molecular machine learning remains unclear. Graph neural networks stand to benefit from clever matching to understand the structural alignment of retrieved molecules to a query molecule. Neural graph matching offers a compelling solution by explicitly modeling node and edge affinities between two structural graphs while employing a noise-robust, end-to-end neural network to learn affinity metrics. We apply this approach to mass spectrum simulation and introduce MARASON, a novel model that incorporates neural graph matching to enhance a fragmentation-based neural network. Experimental results highlight the effectiveness of our design, with MARASON achieving 28% top-1 accuracy, a substantial improvement over the non-retrieval state-of-the-art accuracy of 19%. Moreover, MARASON outperforms both naive retrieval-augmented generation methods and traditional graph matching approaches. Code is publicly available at https://github.com/coleygroup/ms-pred
Authors: Abdullah Mamun, Asiful Arefeen, Susan B. Racette, Dorothy D. Sears, Corrie M. Whisner, Matthew P. Buman, Hassan Ghasemzadeh
Abstract: Postprandial hyperglycemia, marked by the blood glucose level exceeding the normal range after consuming a meal, is a critical indicator of progression toward type 2 diabetes in people with prediabetes and in healthy individuals. A key metric for understanding blood glucose dynamics after eating is the postprandial area under the curve (AUC). Predicting postprandial AUC in advance based on a person's lifestyle factors, such as diet and physical activity level, and explaining the factors that affect postprandial blood glucose could allow an individual to adjust their lifestyle accordingly to maintain normal glucose levels. In this study, we developed an explainable machine learning solution, GlucoLens, that takes sensor-driven inputs and uses advanced data processing, large language models, and trainable machine learning models to predict postprandial AUC and hyperglycemia from diet, physical activity, and recent glucose patterns. We used data obtained from wearables in a five-week clinical trial of 10 adults who worked full-time to develop and evaluate the proposed computational model that integrates wearable sensing, multimodal data, and machine learning. Our machine learning model takes multimodal data from wearable activity and glucose monitoring sensors, along with food and work logs, and provides an interpretable prediction of the postprandial glucose pattern. Our GlucoLens system achieves a normalized root mean squared error (NRMSE) of 0.123 in its best configuration. On average, the proposed technology provides a 16% better performance level compared to the comparison models. Additionally, our technique predicts hyperglycemia with an accuracy of 73.3% and an F1 score of 0.716 and recommends different treatment options to help avoid hyperglycemia through diverse counterfactual explanations. Code available: https://github.com/ab9mamun/GlucoLens.
Authors: Clara Fannjiang, Ji Won Park
Abstract: Algorithms for machine learning-guided design, or design algorithms, use machine learning-based predictions to propose novel objects with desired property values. Given a new design task -- for example, to design novel proteins with high binding affinity to a therapeutic target -- one must choose a design algorithm and specify any hyperparameters and predictive and/or generative models involved. How can these decisions be made such that the resulting designs are successful? This paper proposes a method for design algorithm selection, which aims to select design algorithms that will produce a distribution of design labels satisfying a user-specified success criterion -- for example, that at least ten percent of designs' labels exceed a threshold. It does so by combining designs' predicted property values with held-out labeled data to reliably forecast characteristics of the label distributions produced by different design algorithms, building upon techniques from prediction-powered inference. The method is guaranteed with high probability to return design algorithms that yield successful label distributions (or the null set if none exist), if the density ratios between the design and labeled data distributions are known. We demonstrate the method's effectiveness in simulated protein and RNA design tasks, in settings with either known or estimated density ratios.
Authors: Shiguang Sun, Hanbo Zhang, Zeyang Liu, Xinrui Yang, Lipeng Wan, Xingyu Chen, Xuguang Lan
Abstract: Existing visual model-based reinforcement learning (MBRL) algorithms with observation reconstruction often suffer from information conflicts, making it difficult to learn compact representations and hence result in less robust policies, especially in the presence of task-irrelevant visual distractions. In this paper, we first reveal that the information conflicts in current visual MBRL algorithms stem from visual representation learning and latent dynamics modeling with an information-theoretic perspective. Based on this finding, we present a new algorithm to resolve information conflicts for visual MBRL, named MInCo, which mitigates information conflicts by leveraging negative-free contrastive learning, aiding in learning invariant representation and robust policies despite noisy observations. To prevent the dominance of visual representation learning, we introduce time-varying reweighting to bias the learning towards dynamics modeling as training proceeds. We evaluate our method on several robotic control tasks with dynamic background distractions. Our experiments demonstrate that MInCo learns invariant representations against background noise and consistently outperforms current state-of-the-art visual MBRL methods. Code is available at https://github.com/ShiguangSun/minco.
Authors: Kapil Chawla, William Holmes
Abstract: In this article we develop a Physics Informed Neural Network (PINN) approach to simulate ice sheet dynamics governed by the Shallow Ice Approximation. This problem takes the form of a time-dependent parabolic obstacle problem. Prior work has used this approach to address the stationary obstacle problem and here we extend it to the time dependent problem. Through comprehensive 1D and 2D simulations, we validate the model's effectiveness in capturing complex free-boundary conditions. By merging traditional mathematical modeling with cutting-edge deep learning methods, this approach provides a scalable and robust solution for predicting temporal variations in ice thickness. To illustrate this approach in a real world setting, we simulate the dynamics of the Devon Ice Cap, incorporating aerogeophysical data from 2000 and 2018.
Authors: Shiwen Qin, Gabriela Kadlecov\'a, Martin Pil\'at, Shay B. Cohen, Roman Neruda, Elliot J. Crowley, Jovita Lukasik, Linus Ericsson
Abstract: Neural architecture search (NAS) faces a challenge in balancing the exploration of expressive, broad search spaces that enable architectural innovation with the need for efficient evaluation of architectures to effectively search such spaces. We investigate surrogate model training for improving search in highly expressive NAS search spaces based on context-free grammars. We show that i) surrogate models trained either using zero-cost-proxy metrics and neural graph features (GRAF) or by fine-tuning an off-the-shelf LM have high predictive power for the performance of architectures both within and across datasets, ii) these surrogates can be used to filter out bad architectures when searching on novel datasets, thereby significantly speeding up search and achieving better final performances, and iii) the surrogates can be further used directly as the search objective for huge speed-ups.
Authors: Alberto Casagrande, Francesco Fabris, Rossano Girometti, Roberto Pagliarini
Abstract: Agreement measures, such as Cohen's kappa or intraclass correlation, gauge the matching between two or more classifiers. They are used in a wide range of contexts from medicine, where they evaluate the effectiveness of medical treatments and clinical trials, to artificial intelligence, where they can quantify the approximation due to the reduction of a classifier. The consistency of different classifiers to a golden standard can be compared simply by using the order induced by their agreement measure with respect to the golden standard itself. Nevertheless, labelling an approach as good or bad exclusively by using the value of an agreement measure requires a scale or a significativity index. Some quality scales have been proposed in the literature for Cohen's kappa, but they are mainly na\"ive, and their boundaries are arbitrary. This work proposes a general approach to evaluate the significativity of any agreement value between two classifiers and introduces two significativity indices: one dealing with finite data sets, the other one handling classification probability distributions. Moreover, this manuscript addresses the computational challenges of evaluating such indices and proposes some efficient algorithms for their evaluation.
Authors: AJ Miller, Fangzhou Yu, Michael Brauckmann, Farbod Farshidian
Abstract: This work presents an overview of the technical details behind a high performance reinforcement learning policy deployment with the Spot RL Researcher Development Kit for low level motor access on Boston Dynamics Spot. This represents the first public demonstration of an end to end end reinforcement learning policy deployed on Spot hardware with training code publicly available through Nvidia IsaacLab and deployment code available through Boston Dynamics. We utilize Wasserstein Distance and Maximum Mean Discrepancy to quantify the distributional dissimilarity of data collected on hardware and in simulation to measure our sim2real gap. We use these measures as a scoring function for the Covariance Matrix Adaptation Evolution Strategy to optimize simulated parameters that are unknown or difficult to measure from Spot. Our procedure for modeling and training produces high quality reinforcement learning policies capable of multiple gaits, including a flight phase. We deploy policies capable of over 5.2ms locomotion, more than triple Spots default controller maximum speed, robustness to slippery surfaces, disturbance rejection, and overall agility previously unseen on Spot. We detail our method and release our code to support future work on Spot with the low level API.
Authors: Yu-Hsiang Lan, Eric K. Oermann
Abstract: There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal (cross-time) and variate (cross-variate) dependencies. While Transformer-based models have gained popularity for their flexibility in capturing both sequential and cross-variate relationships, it is unclear how to best integrate these two sources of information in the context of the Transformer architecture while optimizing for both performance and efficiency. We re-purpose the Transformer architecture to effectively model both cross-time and cross-variate dependencies. Our approach begins by embedding each variate independently into a variate-wise representation that captures its cross-time dynamics, and then models cross-variate dependencies through attention mechanisms on these learned embeddings. Gating operations in both cross-time and cross-variate modeling phases regulate information flow, allowing the model to focus on the most relevant features for accurate predictions. Our method achieves state-of-the-art performance across 13 real-world datasets and can be seamlessly integrated into other Transformer-based and LLM-based forecasters, delivering performance improvements up to 20.7\% over original models. Code is available at this repository: https://github.com/nyuolab/Gateformer.
Authors: Mary Phuong, Roland S. Zimmermann, Ziyue Wang, David Lindner, Victoria Krakovna, Sarah Cogan, Allan Dafoe, Lewis Ho, Rohin Shah
Abstract: Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future advanced systems, could pose severe loss of control risk. It is therefore important for AI developers to rule out harm from scheming prior to model deployment. In this paper, we present a suite of scheming reasoning evaluations measuring two types of reasoning capabilities that we believe are prerequisites for successful scheming: First, we propose five evaluations of ability to reason about and circumvent oversight (stealth). Second, we present eleven evaluations for measuring a model's ability to instrumentally reason about itself, its environment and its deployment (situational awareness). We demonstrate how these evaluations can be used as part of a scheming inability safety case: a model that does not succeed on these evaluations is almost certainly incapable of causing severe harm via scheming in real deployment. We run our evaluations on current frontier models and find that none of them show concerning levels of either situational awareness or stealth.
Authors: Dazhuo Qiu, Haolai Che, Arijit Khan, Yinghui Wu
Abstract: Inference queries have been routinely issued to graph machine learning models such as graph neural networks (GNNs) for various network analytical tasks. Nevertheless, GNNs outputs are often hard to interpret comprehensively. Existing methods typically compromise to individual pre-defined explainability measures (such as fidelity), which often leads to biased, ``one-sided'' interpretations. This paper introduces skyline explanation, a new paradigm that interprets GNN output by simultaneously optimizing multiple explainability measures of users' interests. (1) We propose skyline explanations as a Pareto set of explanatory subgraphs that dominate others over multiple explanatory measures. We formulate skyline explanation as a multi-criteria optimization problem, and establish its hardness results. (2) We design efficient algorithms with an onion-peeling approach, which strategically prioritizes nodes and removes unpromising edges to incrementally assemble skyline explanations. (3) We also develop an algorithm to diversify the skyline explanations to enrich the comprehensive interpretation. (4) We introduce efficient parallel algorithms with load-balancing strategies to scale skyline explanation for large-scale GNN-based inference. Using real-world and synthetic graphs, we experimentally verify our algorithms' effectiveness and scalability.
Authors: Yaxin Hou, Yuheng Jia
Abstract: This paper studies the long-tailed semi-supervised learning (LTSSL) with distribution mismatch, where the class distribution of the labeled training data follows a long-tailed distribution and mismatches with that of the unlabeled training data. Most existing methods introduce auxiliary classifiers (experts) to model various unlabeled data distributions and produce pseudo-labels, but the expertises of various experts are not fully utilized. We observe that different experts are good at predicting different intervals of samples, e.g., long-tailed expert is skilled in samples located in the head interval and uniform expert excels in samples located in the medium interval. Therefore, we propose a dynamic expert assignment module that can estimate the class membership (i.e., head, medium, or tail class) of samples, and dynamically assigns suitable expert to each sample based on the estimated membership to produce high-quality pseudo-label in the training phase and produce prediction in the testing phase. We also theoretically reveal that integrating different experts' strengths will lead to a smaller generalization error bound. Moreover, we find that the deeper features are more biased toward the head class but with more discriminative ability, while the shallower features are less biased but also with less discriminative ability. We, therefore, propose a multi-depth feature fusion module to utilize different depth features to mitigate the model bias. Our method demonstrates its effectiveness through comprehensive experiments on the CIFAR-10-LT, STL-10-LT, and SVHN-LT datasets across various settings. The code is available at https://github.com/yaxinhou/Meta-Expert.
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: Mert Onur Cakiroglu, Idil Bilge Altun, Mehmet Dalkilic, Elham Buxton, Hasan Kurban
Abstract: Time series forecasting remains a challenging task for foundation models due to temporal heterogeneity, high dimensionality, and the lack of inherent symbolic structure. In this work, we propose DRAGON (Discrete Representation and Augmented Graph encoding Over de BruijN Graphs), a novel encoder that introduces Multivariate de Bruijn Graphs (MdBGs) to bridge the gap between symbolic representations and neural modeling. DRAGON discretizes continuous input sequences and maps them onto a fixed graph structure, enabling dynamic context recovery via graph-based attention. Integrated as an auxiliary module within a dual-branch architecture, DRAGON augments conventional CNN-based encoders with symbolic, structure-aware representations. All code developed for this study is available at: https://github.com/KurbanIntelligenceLab/MultdBG-Time-Series-Library
URLs: https://github.com/KurbanIntelligenceLab/MultdBG-Time-Series-Library
Authors: Zehao Wu, Yanjie Zhao, Haoyu Wang
Abstract: As Large Language Models (LLMs) become integral software components in modern applications, unauthorized model derivations through fine-tuning, merging, and redistribution have emerged as critical software engineering challenges. Unlike traditional software where clone detection and license compliance are well-established, the LLM ecosystem lacks effective mechanisms to detect model lineage and enforce licensing agreements. This gap is particularly problematic when open-source model creators, such as Meta's LLaMA, require derivative works to maintain naming conventions for attribution, yet no technical means exist to verify compliance. To fill this gap, treating LLMs as software artifacts requiring provenance tracking, we present TensorGuard, a gradient-based fingerprinting framework for LLM similarity detection and family classification. Our approach extracts model-intrinsic behavioral signatures by analyzing gradient responses to random input perturbations across tensor layers, operating independently of training data, watermarks, or specific model formats. TensorGuard supports the widely-adopted safetensors format and constructs high-dimensional fingerprints through statistical analysis of gradient features. These fingerprints enable two complementary capabilities: direct pairwise similarity assessment between arbitrary models through distance computation, and systematic family classification of unknown models via the K-Means clustering algorithm with domain-informed centroid initialization using known base models. Experimental evaluation on 58 models comprising 8 base models and 50 derivatives across five model families (Llama, Qwen, Gemma, Phi, Mistral) demonstrates 94% classification accuracy under our centroid-initialized K-Means clustering.
Authors: Mohammad Jalali, Bahar Dibaei Nia, Farzan Farnia
Abstract: While several feature embedding models have been developed in the literature, comparisons of these embeddings have largely focused on their numerical performance in classification-related downstream applications. However, an interpretable comparison of different embeddings requires identifying and analyzing mismatches between sample groups clustered within the embedding spaces. In this work, we propose the \emph{Spectral Pairwise Embedding Comparison (SPEC)} framework to compare embeddings and identify their differences in clustering a reference dataset. Our approach examines the kernel matrices derived from two embeddings and leverages the eigendecomposition of the difference kernel matrix to detect sample clusters that are captured differently by the two embeddings. We present a scalable implementation of this kernel-based approach, with computational complexity that grows linearly with the sample size. Furthermore, we introduce an optimization problem using this framework to align two embeddings, ensuring that clusters identified in one embedding are also captured in the other model. We provide numerical results demonstrating the SPEC's application to compare and align embeddings on large-scale datasets such as ImageNet and MS-COCO. The project page is available at https://mjalali.github.io/SPEC/.
Authors: Zhiqi Wang, Chengyu Zhang, Yuetian Chen, Nathalie Baracaldo, Swanand Kadhe, Lei Yu
Abstract: Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on performance metrics such as AUC, accuracy, and TPR@low FPR - either by developing new methods to enhance these metrics or using them to evaluate privacy solutions - we found that it overlooks the disparities among different attacks. These disparities, both between distinct attack methods and between multiple instantiations of the same method, have crucial implications for the reliability and completeness of MIAs as privacy evaluation tools. In this paper, we systematically investigate these disparities through a novel framework based on coverage and stability analysis. Extensive experiments reveal significant disparities in MIAs, their potential causes, and their broader implications for privacy evaluation. To address these challenges, we propose an ensemble framework with three distinct strategies to harness the strengths of state-of-the-art MIAs while accounting for their disparities. This framework not only enables the construction of more powerful attacks but also provides a more robust and comprehensive methodology for privacy evaluation.
Authors: Xinnan Zhang, Chenliang Li, Siliang Zeng, Jiaxiang Li, Zhongruo Wang, Kaixiang Lin, Songtao Lu, Alfredo Garcia, Mingyi Hong
Abstract: Aligning large language models (LLMs) with human preferences usually requires fine-tuning methods such as RLHF and DPO. These methods directly optimize the model parameters, so they cannot be used in test-time to improve model performance, nor are they applicable when the model weights are not accessible. In contrast, test-time methods sidestep weight updates by leveraging reward functions to guide and improve output quality. However, they incur high inference costs, and their one-shot guidance is often based on imperfect reward or value functions, leading to suboptimal outputs. In this work, we present a method named Iterative Reweight-then-Optimize (IRO), a reinforcement learning (RL) framework that performs RL-style alignment of the (frozen) base model without touching its parameters. During training, each iteration (i) samples candidates from the base model, (ii) resamples using current value functions, and (iii) trains a new lightweight value function that guides the next decoding pass. At test time, the value functions are used to guide the base model generation via a search-based optimization process. Notably, users can apply IRO to align a model on their own dataset, similar to OpenAI's reinforcement fine-tuning (RFT), but without requiring access to the model weights.
Authors: Leonard S. Pleiss, Tobias Sutter, Maximilian Schiffer
Abstract: Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific learning potential. In an effort to sample more efficiently, researchers introduced Prioritized Experience Replay (PER). In this paper, we propose an extension to PER by introducing a novel measure of temporal difference error reliability. We theoretically show that the resulting transition selection algorithm, Reliability-adjusted Prioritized Experience Replay (ReaPER), enables more efficient learning than PER. We further present empirical results showing that ReaPER outperforms PER across various environment types, including the Atari-10 benchmark.
Authors: Ziyue Li, Chenrui Fan, Tianyi Zhou
Abstract: Grokking, i.e., test performance keeps improving long after training loss converged, has been recently witnessed in neural network training, making the mechanism of generalization and other emerging capabilities such as reasoning mysterious. While prior studies usually train small models on a few toy or highly-specific tasks for thousands of epochs, we conduct the first study of grokking on checkpoints during one-pass pretraining of a 7B large language model (LLM), i.e., OLMoE. We compute the training loss and evaluate generalization on diverse benchmark tasks, including math reasoning, code generation, and commonsense/domain-specific knowledge retrieval tasks. Our study, for the first time, verifies that grokking still happens in the pretraining of large-scale foundation models, though different data may enter grokking stages asynchronously. We further demystify grokking's "emergence of generalization" by investigating LLM internal dynamics. Specifically, we find that training samples' pathways (i.e., expert choices across layers) evolve from random, instance-specific to more structured and shareable between samples. Also, the complexity of a sample's pathway reduces despite the converged loss. These indicate a memorization-to-generalization "knowledge digestion", providing a mechanistic explanation of delayed generalization. In the study, we develop two novel metrics to quantify pathway distance and the complexity of a single pathway. We show their ability to predict the generalization improvement on diverse downstream tasks. They are efficient, simple to compute and solely dependent on training data. Hence, they have practical value for pretraining, enabling us to monitor the generalization performance without finetuning and test. Theoretically, we show that more structured pathways reduce model complexity and improve the generalization bound.
Authors: Denis Gudovskiy, Wenzhao Zheng, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer
Abstract: Recently, continuous normalizing flows (CNFs) and diffusion models (DMs) have been studied using the unified theoretical framework. Although such models can generate high-quality data points from a noise distribution, the sampling demands multiple iterations to solve an ordinary differential equation (ODE) with high computational complexity. Most existing methods focus on reducing the number of time steps during the sampling process to improve efficiency. In this work, we explore a complementary direction in which the quality-complexity tradeoff can be dynamically controlled in terms of time steps and in the length of the neural network. We achieve this by rewiring the blocks in the transformer-based architecture to solve an inner discretized ODE w.r.t. its length. Then, we employ time- and length-wise consistency terms during flow matching training, and as a result, the sampling can be performed with an arbitrary number of time steps and transformer blocks. Unlike others, our ODE$_t$(ODE$_l$) approach is solver-agnostic in time dimension and decreases both latency and memory usage. Compared to the previous state of the art, image generation experiments on CelebA-HQ and ImageNet show a latency reduction of up to 3$\times$ in the most efficient sampling mode, and a FID score improvement of up to 3.5 points for high-quality sampling. We release our code and model weights with fully reproducible experiments.
Authors: Tianhao Chen, Xin Xu, Zijing Liu, Pengxiang Li, Xinyuan Song, Ajay Kumar Jaiswal, Fan Zhang, Jishan Hu, Yang Wang, Hao Chen, Shizhe Diao, Shiwei Liu, Yu Li, Lu Yin, Can Yang
Abstract: Modern Large Language Models, such as the LLaMA, Qwen and DeepSeek series, predominantly adopt the Pre-LayerNorm (Pre-LN) Transformer architecture. While being stable during pretraining and scalable to large model sizes, Pre-LN suffers from an exponential growth in activation variance across layers, causing the shortcut to dominate over sub-layer outputs in the residual connection and limiting the learning capacity of deeper layers. To mitigate this issue, we propose Gradient-Preserving Activation Scaling (GPAS), a simple technique that can be used in combination with existing approaches. GPAS works by scaling down the intermediate activations while keeping their gradients unchanged. This leaves information in the activations intact, and avoids the gradient vanishing problem associated with gradient downscaling. Extensive experiments across various model sizes from 71M to 1B show that GPAS achieves consistent performance gains. Beyond enhancing Pre-LN Transformers, GPAS also shows promise in improving alternative architectures such as Sandwich-LN and DeepNorm, demonstrating its versatility and potential for improving training dynamics in a wide range of settings. Our code is available at https://github.com/dandingsky/GPAS.
Authors: Thomas Gaskin, Guy J. Abel
Abstract: We present a novel and detailed dataset on origin-destination annual migration flows and stocks between 230 countries and regions, spanning the period from 1990 to the present. Our flow estimates are further disaggregated by country of birth, providing a comprehensive picture of migration over the last 35 years. The estimates are obtained by training a deep recurrent neural network to learn flow patterns from 18 covariates for all countries, including geographic, economic, cultural, societal, and political information. The recurrent architecture of the neural network means that the entire past can influence current migration patterns, allowing us to learn long-range temporal correlations. By training an ensemble of neural networks and additionally pushing uncertainty on the covariates through the trained network, we obtain confidence bounds for all our estimates, allowing researchers to pinpoint the geographic regions most in need of additional data collection. We validate our approach on various test sets of unseen data, demonstrating that it significantly outperforms traditional methods estimating five-year flows while delivering a significant increase in temporal resolution. The model is fully open source: all training data, neural network weights, and training code are made public alongside the migration estimates, providing a valuable resource for future studies of human migration.
Authors: Jiongli Zhu, Parjanya Prajakta Prashant, Alex Cloninger, Babak Salimi
Abstract: Training data increasingly shapes not only model accuracy but also regulatory compliance and market valuation of AI assets. Yet existing valuation methods remain inadequate: model-based techniques depend on a single fitted model and inherit its biases, while algorithm-based approaches such as Data Shapley require costly retrainings at web scale. Recent Wasserstein-based model-agnostic methods rely on approximations that misrank examples relative to their true leave-one-out (LOO) utility. We introduce KAIROS, a scalable, model-agnostic valuation framework that assigns each example a distributional influence score: its contribution to the Maximum Mean Discrepancy (MMD) between the empirical training distribution and a clean reference set. Unlike Wasserstein surrogates, our MMD-based influence admits a closed-form solution that faithfully approximates the exact LOO ranking within $O(1/N^2)$ error, requires no retraining, and naturally extends to conditional kernels for unified label- and feature-error detection. Moreover, KAIROS supports efficient online updates: when a new batch of size m arrives, all scores can be updated in $O(mN)$ time, delivering up to 50x speedup without compromising ranking quality. Empirical evaluations on noise, mislabeling, and poisoning benchmarks show that KAIROS consistently outperforms state-of-the-art model-, Shapley-, and Wasserstein-based baselines in both accuracy and runtime. We provide rigorous theoretical guarantees, including symmetry for reproducible rankings and density-separation for interpretable thresholds.
Authors: Arthur Thuy, Ekaterina Loginova, Dries F. Benoit
Abstract: Recent years have seen growing interest in Question Difficulty Estimation (QDE) using natural language processing techniques. Question difficulty is often represented using discrete levels, framing the task as ordinal regression due to the inherent ordering from easiest to hardest. However, the literature has neglected the ordinal nature of the task, relying on classification or discretized regression models, with specialized ordinal regression methods remaining unexplored. Furthermore, evaluation metrics are tightly coupled to the modeling paradigm, hindering cross-study comparability. While some metrics fail to account for the ordinal structure of difficulty levels, none adequately address class imbalance, resulting in biased performance assessments. This study addresses these limitations by benchmarking three types of model outputs -- discretized regression, classification, and ordinal regression -- using the balanced Discrete Ranked Probability Score (DRPS), a novel metric that jointly captures ordinality and class imbalance. In addition to using popular ordinal regression methods, we propose OrderedLogitNN, extending the ordered logit model from econometrics to neural networks. We fine-tune BERT on the RACE++ and ARC datasets and find that OrderedLogitNN performs considerably better on complex tasks. The balanced DRPS offers a robust and fair evaluation metric for discrete-level QDE, providing a principled foundation for future research.
Authors: Dang Qua Nguyen, Morteza Hashemi, Erik Perrins, Sergiy A. Vorobyov, David J. Love, Taejoon Kim
Abstract: Federated learning (FL) has emerged as a promising paradigm for distributed machine learning, enabling collaborative training of a global model across multiple local devices without requiring them to share raw data. Despite its advancements, FL is limited by factors such as: (i) privacy risks arising from the unprotected transmission of local model updates to the fusion center (FC) and (ii) decreased learning utility caused by heterogeneity in model quantization resolution across participating devices. Prior work typically addresses only one of these challenges because maintaining learning utility under both privacy risks and quantization heterogeneity is a non-trivial task. In this paper, our aim is therefore to improve the learning utility of a privacy-preserving FL that allows clusters of devices with different quantization resolutions to participate in each FL round. Specifically, we introduce a novel stochastic quantizer (SQ) that is designed to simultaneously achieve differential privacy (DP) and minimum quantization error. Notably, the proposed SQ guarantees bounded distortion, unlike other DP approaches. To address quantization heterogeneity, we introduce a cluster size optimization technique combined with a linear fusion approach to enhance model aggregation accuracy. Numerical simulations validate the benefits of our approach in terms of privacy protection and learning utility compared to the conventional LaplaceSQ-FL algorithm.
Authors: Zuguang Li (Sherman), Wen Wu (Sherman), Shaohua Wu (Sherman), Songge Zhang (Sherman), Ye Wang (Sherman), Xuemin (Sherman), Shen
Abstract: Split learning (SL) has emerged as a computationally efficient approach for artificial intelligence (AI) model training, which can alleviate device-side computational workloads. However, complex AI model architectures pose high computational complexity to obtain the optimal model splitting. In this paper, we represent an arbitrary AI model as a directed acyclic graph (DAG), and then reformulate the optimal model splitting problem as a minimum s-t cut search problem. To solve the problem, we propose a fast DAG-based model splitting algorithm, which restructures the DAG to enable the optimal model splitting identification via a maximum flow method. Theoretical analysis indicates that the proposed algorithm is optimal. Furthermore, considering AI models with block structures, we propose a block-wise model splitting algorithm to reduce computational complexity. The algorithm abstracts each block, i.e., a component consisting of multiple layers, into a single vertex, thereby obtaining the optimal model splitting via a simplified DAG. Extensive experimental results demonstrate that the proposed algorithms can determine the optimal model splitting within milliseconds, as well as reduce training delay by 24.62%-38.95% in dynamic edge networks as compared to the state-of-the-art benchmarks.
Authors: Hyoseo (Lauren), Yoon, Yisong Yue, Been Kim
Abstract: Independently trained vision and language models inhabit disjoint representational spaces, shaped by their respective modalities, objectives, and architectures. Yet an emerging hypothesis - the Platonic Representation Hypothesis - suggests that such models may nonetheless converge toward a shared statistical model of reality. This compatibility, if it exists, raises a fundamental question: can we move beyond post-hoc statistical detection of alignment and explicitly optimize for it between such disjoint representations? We cast this Platonic alignment problem as a multi-objective optimization task - preserve each modality's native structure while aligning for mutual coherence. We introduce the Joint Autoencoder Modulator (JAM) framework that jointly trains modality-specific autoencoders on the latent representations of pre-trained single modality models, encouraging alignment through both reconstruction and cross-modal objectives. By analogy, this framework serves as a method to escape Plato's Cave, enabling the emergence of shared structure from disjoint inputs. We evaluate this framework across three critical design axes: (i) the alignment objective - comparing contrastive loss (Con), its hard-negative variant (NegCon), and our Spread loss, (ii) the layer depth at which alignment is most effective, and (iii) the impact of foundation model scale on representational convergence. Our findings show that our lightweight Pareto-efficient framework reliably induces alignment, even across frozen, independently trained representations, offering both theoretical insight and practical pathways for transforming generalist unimodal foundations into specialist multimodal models.
Authors: Tong Liu, Yinuo Wang, Xujie Song, Wenjun Zou, Liangfa Chen, Likun Wang, Bin Shuai, Jingliang Duan, Shengbo Eben Li
Abstract: Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However, unimodal distribution often and easily causes bias in value function estimation, leading to poor algorithm performance. This paper proposes a distributional reinforcement learning algorithm called DSAC-D (Distributed Soft Actor Critic with Diffusion Policy) to address the challenges of estimating bias in value functions and obtaining multimodal policy representations. A multimodal distributional policy iteration framework that can converge to the optimal policy was established by introducing policy entropy and value distribution function. A diffusion value network that can accurately characterize the distribution of multi peaks was constructed by generating a set of reward samples through reverse sampling using a diffusion model. Based on this, a distributional reinforcement learning algorithm with dual diffusion of the value network and the policy network was derived. MuJoCo testing tasks demonstrate that the proposed algorithm not only learns multimodal policy, but also achieves state-of-the-art (SOTA) performance in all 9 control tasks, with significant suppression of estimation bias and total average return improvement of over 10% compared to existing mainstream algorithms. The results of real vehicle testing show that DSAC-D can accurately characterize the multimodal distribution of different driving styles, and the diffusion policy network can characterize multimodal trajectories.
Authors: Wu Fei, Hao Kong, Shuxian Liang, Yang Lin, Yibo Yang, Jing Tang, Lei Chen, Xiansheng Hua
Abstract: Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational overhead, and there is no unified theoretical framework for process-level advantage estimation. To bridge this gap, we propose \textbf{S}elf-Guided \textbf{P}rocess \textbf{R}eward \textbf{O}ptimization~(\textbf{SPRO}), a novel framework that enables process-aware RL through two key innovations: (1) we first theoretically demonstrate that process rewards can be derived intrinsically from the policy model itself, and (2) we introduce well-defined cumulative process rewards and \textbf{M}asked \textbf{S}tep \textbf{A}dvantage (\textbf{MSA}), which facilitates rigorous step-wise action advantage estimation within shared-prompt sampling groups. Our experimental results demonstrate that SPRO outperforms vaniila GRPO with 3.4x higher training efficiency and a 17.5\% test accuracy improvement. Furthermore, SPRO maintains a stable and elevated policy entropy throughout training while reducing the average response length by approximately $1/3$, evidencing sufficient exploration and prevention of reward hacking. Notably, SPRO incurs no additional computational overhead compared to outcome-supervised RL methods such as GRPO, which benefit industrial implementation.
Authors: Peter Carbonetto, Abhishek Sarkar, Zihao Wang, Matthew Stephens
Abstract: We report on the potential for using algorithms for non-negative matrix factorization (NMF) to improve parameter estimation in topic models. While several papers have studied connections between NMF and topic models, none have suggested leveraging these connections to develop new algorithms for fitting topic models. NMF avoids the "sum-to-one" constraints on the topic model parameters, resulting in an optimization problem with simpler structure and more efficient computations. Building on recent advances in optimization algorithms for NMF, we show that first solving the NMF problem then recovering the topic model fit can produce remarkably better fits, and in less time, than standard algorithms for topic models. While we focus primarily on maximum likelihood estimation, we show that this approach also has the potential to improve variational inference for topic models. Our methods are implemented in the R package fastTopics.
Authors: Kui Ren, Lu Zhang
Abstract: The task of simultaneously reconstructing multiple physical coefficients in partial differential equations (PDEs) from observed data is ubiquitous in applications. In this work, we propose an integrated data-driven and model-based iterative reconstruction framework for such joint inversion problems where additional data on the unknown coefficients are supplemented for better reconstructions. Our method couples the supplementary data with the PDE model to make the data-driven modeling process consistent with the model-based reconstruction procedure. We characterize the impact of learning uncertainty on the joint inversion results for two typical inverse problems. Numerical evidence is provided to demonstrate the feasibility of using data-driven models to improve the joint inversion of multiple coefficients in PDEs.
Authors: Maryanthe Malliaris, Shay Moran
Abstract: This paper is about the surprising interaction of a foundational result from model theory, about stability of theories, with algorithmic stability in learning. First, in response to gaps in existing learning models, we introduce a new statistical learning model, called ``Probably Eventually Correct'' or PEC. We characterize Littlestone (stable) classes in terms of this model. As a corollary, Littlestone classes have frequent short definitions in a natural statistical sense. In order to obtain a characterization of Littlestone classes in terms of frequent definitions, we build an equivalence theorem highlighting what is common to many existing approximation algorithms, and to the new PEC. This is guided by an analogy to definability of types in model theory, but has its own character. Drawing on these theorems and on other recent work, we present a complete algorithmic analogue of Shelah's celebrated Unstable Formula Theorem, with algorithmic properties taking the place of the infinite.
Authors: Brando Miranda, Alycia Lee, Sudharsan Sundar, Allison Casasola, Rylan Schaeffer, Elyas Obbad, Sanmi Koyejo
Abstract: Current trends in pre-training Large Language Models (LLMs) primarily focus on the scaling of model and dataset size. While the quality of pre-training data is considered an important factor for training powerful LLMs, it remains a nebulous concept that has not been rigorously characterized. To this end, we propose a formalization of one key aspect of data quality -- measuring the variability of natural language data -- specifically via a measure we call the diversity coefficient. Our empirical analysis shows that the proposed diversity coefficient aligns with the intuitive properties of diversity and variability, e.g., it increases as the number of latent concepts increases. Then, we measure the diversity coefficient of publicly available pre-training datasets and demonstrate that their formal diversity is high compared to theoretical lower and upper bounds. Finally, we conduct a comprehensive set of controlled interventional experiments with GPT-2 and LLaMAv2 that demonstrate the diversity coefficient of pre-training data characterizes useful aspects of downstream model evaluation performance -- totaling 44 models of various sizes (51M to 7B parameters). We conclude that our formal notion of diversity is an important aspect of data quality that captures variability and causally leads to improved evaluation performance.
Authors: Fredy Vides, Idelfonso B. R. Nogueira, Gabriela Lopez Gutierrez, Lendy Banegas, Evelyn Flores
Abstract: The investigation reported in this document focuses on identifying systems with symmetries using equivariant autoregressive reservoir computers. General results in structured matrix approximation theory are presented, exploring a two-fold approach. Firstly, a comprehensive examination of generic symmetry-preserving nonlinear time delay embedding is conducted. This involves analyzing time series data sampled from an equivariant system under study. Secondly, sparse least-squares methods are applied to discern approximate representations of the output coupling matrices. These matrices play a critical role in determining the nonlinear autoregressive representation of an equivariant system. The structural characteristics of these matrices are dictated by the set of symmetries inherent in the system. The document outlines prototypical algorithms derived from the described techniques, offering insight into their practical applications. Emphasis is placed on the significant improvement on structured identification precision when compared to classical reservoir computing methods for the simulation of equivariant dynamical systems.
Authors: Maxime Masson, Rodrigo Agerri, Christian Sallaberry, Marie-Noelle Bessagnet, Annig Le Parc Lacayrelle, Philippe Roose
Abstract: The rising influence of social media platforms in various domains, including tourism, has highlighted the growing need for efficient and automated Natural Language Processing (NLP) strategies to take advantage of this valuable resource. However, the transformation of multilingual, unstructured, and informal texts into structured knowledge still poses significant challenges, most notably the never-ending requirement for manually annotated data to train deep learning classifiers. In this work, we study different NLP techniques to establish the best ones to obtain competitive performances while keeping the need for training annotated data to a minimum. To do so, we built the first publicly available multilingual dataset (French, English, and Spanish) for the tourism domain, composed of tourism-related tweets. The dataset includes multilayered, manually revised annotations for Named Entity Recognition (NER) for Locations and Fine-grained Thematic Concepts Extraction mapped to the Thesaurus of Tourism and Leisure Activities of the World Tourism Organization, as well as for Sentiment Analysis at the tweet level. Extensive experimentation comparing various few-shot and fine-tuning techniques with modern language models demonstrate that modern few-shot techniques allow us to obtain competitive results for all three tasks with very little annotation data: 5 tweets per label (15 in total) for Sentiment Analysis, 30 tweets for Named Entity Recognition of Locations and 1K tweets annotated with fine-grained thematic concepts, a highly fine-grained sequence labeling task based on an inventory of 315 classes. We believe that our results, grounded in a novel dataset, pave the way for applying NLP to new domain-specific applications, reducing the need for manual annotations and circumventing the complexities of rule-based, ad-hoc solutions.
Authors: Miquel Mir\'o-Nicolau, Gabriel Moy\`a-Alcover, Antoni Jaume-i-Cap\'o, Manuel Gonz\'alez-Hidalgo, Adel Ghazel, Maria Gemma Sempere Campello, Juan Antonio Palmer Sancho
Abstract: The increasing reliance on Deep Learning models, combined with their inherent lack of transparency, has spurred the development of a novel field of study known as eXplainable AI (XAI) methods. These methods seek to enhance the trust of end-users in automated systems by providing insights into the rationale behind their decisions. This paper presents a novel trust measure in XAI systems, allowing their refinement. Our proposed metric combines both performance metrics and trust indicators from an objective perspective. To validate this novel methodology, we conducted three case studies showing an improvement respect the state-of-the-art, with an increased sensitiviy to different scenarios.
Authors: Yingfang Yuan, Kefan Chen, Mehdi Rizvi, Lynne Baillie, Wei Pang
Abstract: The growing interest in fair AI development is evident. The ''Leave No One Behind'' initiative urges us to address multiple and intersecting forms of inequality in accessing services, resources, and opportunities, emphasising the significance of fairness in AI. This is particularly relevant as an increasing number of AI tools are applied to decision-making processes, such as resource allocation and service scheme development, across various sectors such as health, energy, and housing. Therefore, exploring joint inequalities in these sectors is significant and valuable for thoroughly understanding overall inequality and unfairness. This research introduces an innovative approach to quantify cross-sectoral intersecting discrepancies among user-defined groups using latent class analysis. These discrepancies can be used to approximate inequality and provide valuable insights to fairness issues. We validate our approach using both proprietary and public datasets, including both EVENS and Census 2021 (England & Wales) datasets, to examine cross-sectoral intersecting discrepancies among different ethnic groups. We also verify the reliability of the quantified discrepancy by conducting a correlation analysis with a government public metric. Our findings reveal significant discrepancies both among minority ethnic groups and between minority ethnic groups and non-minority ethnic groups, emphasising the need for targeted interventions in policy-making processes. Furthermore, we demonstrate how the proposed approach can provide valuable insights into ensuring fairness in machine learning systems.
Authors: Shahana Ibrahim, Panagiotis A. Traganitis, Xiao Fu, Georgios B. Giannakis
Abstract: One of the primary catalysts fueling advances in artificial intelligence (AI) and machine learning (ML) is the availability of massive, curated datasets. A commonly used technique to curate such massive datasets is crowdsourcing, where data are dispatched to multiple annotators. The annotator-produced labels are then fused to serve downstream learning and inference tasks. This annotation process often creates noisy labels due to various reasons, such as the limited expertise, or unreliability of annotators, among others. Therefore, a core objective in crowdsourcing is to develop methods that effectively mitigate the negative impact of such label noise on learning tasks. This feature article introduces advances in learning from noisy crowdsourced labels. The focus is on key crowdsourcing models and their methodological treatments, from classical statistical models to recent deep learning-based approaches, emphasizing analytical insights and algorithmic developments. In particular, this article reviews the connections between signal processing (SP) theory and methods, such as identifiability of tensor and nonnegative matrix factorization, and novel, principled solutions of longstanding challenges in crowdsourcing -- showing how SP perspectives drive the advancements of this field. Furthermore, this article touches upon emerging topics that are critical for developing cutting-edge AI/ML systems, such as crowdsourcing in reinforcement learning with human feedback (RLHF) and direct preference optimization (DPO) that are key techniques for fine-tuning large language models (LLMs).
Authors: Yassine Habchi, Hamza Kheddar, Yassine Himeur, Mohamed Chahine Ghanem, Abdelkrim Boukabou, Shadi Atalla, Wathiq Mansoor, Hussain Al-Ahmad
Abstract: Incurable diseases continue to pose major challenges to global healthcare systems, with their prevalence shaped by lifestyle, economic, social, and genetic factors. Among these, kidney disease remains a critical global health issue, requiring ongoing research to improve early diagnosis and treatment. In recent years, deep learning (DL) has shown promise in medical imaging and diagnostics, driving significant progress in automatic kidney cancer (KC) detection. However, the success of DL models depends heavily on the availability of high-quality, domain-specific datasets, which are often limited and expensive to acquire. Moreover, DL models demand substantial computational power and storage, restricting their real-world clinical use. To overcome these barriers, transfer learning (TL) has emerged as an effective approach, enabling the reuse of pre-trained models from related domains to enhance KC diagnosis. This paper presents a comprehensive survey of DL-based TL frameworks for KC detection, systematically reviewing key methodologies, their advantages, and limitations, and analyzing their practical performance. It further discusses challenges in applying TL to medical imaging and highlights emerging trends that could influence future research. This review demonstrates the transformative role of TL in precision medicine, particularly oncology, by improving diagnostic accuracy, lowering computational demands, and supporting the integration of AI-powered tools in healthcare. The insights provided offer valuable guidance for researchers and practitioners, paving the way for future advances in KC diagnostics and personalized treatment strategies.
Authors: Jiahui Jin, Yifan Song, Dong Kan, Haojia Zhu, Xiangguo Sun, Zhicheng Li, Xigang Sun, Jinghui Zhang
Abstract: Urban region representation is crucial for various urban downstream tasks. However, despite the proliferation of methods and their success, acquiring general urban region knowledge and adapting to different tasks remains challenging. Existing work pays limited attention to the fine-grained functional layout semantics in urban regions, limiting their ability to capture transferable knowledge across regions. Further, inadequate handling of the unique features and relationships required for different downstream tasks may also hinder effective task adaptation. In this paper, we propose a $\textbf{G}$raph-based $\textbf{U}$rban $\textbf{R}$egion $\textbf{P}$re-training and $\textbf{P}$rompting framework ($\textbf{GURPP}$) for region representation learning. Specifically, we first construct an urban region graph and develop a subgraph-centric urban region pre-training model to capture the heterogeneous and transferable patterns of entity interactions. This model pre-trains knowledge-rich region embeddings using contrastive learning and multi-view learning methods. To further refine these representations, we design two graph-based prompting methods: a manually-defined prompt to incorporate explicit task knowledge and a task-learnable prompt to discover hidden knowledge, which enhances the adaptability of these embeddings to different tasks. Extensive experiments on various urban region prediction tasks and different cities demonstrate the superior performance of our framework.
Authors: Carlo Alberto Barbano, Matteo Brunello, Benoit Dufumier, Marco Grangetto
Abstract: Deep Learning (DL) in neuroimaging has become increasingly relevant for detecting neurological conditions and neurodegenerative disorders. One of the most predominant biomarkers in neuroimaging is represented by brain age, which has been shown to be a good indicator for different conditions, such as Alzheimer's Disease. Using brain age for weakly supervised pre-training of DL models in transfer learning settings has also recently shown promising results, especially when dealing with data scarcity of different conditions. On the other hand, anatomical information of brain MRIs (e.g. cortical thickness) can provide important information for learning good representations that can be transferred to many downstream tasks. In this work, we propose AnatCL, an anatomical foundation model for brain MRIs that i.) leverages anatomical information in a weakly contrastive learning approach, and ii.) achieves state-of-the-art performances across many different downstream tasks. To validate our approach we consider 12 different downstream tasks for the diagnosis of different conditions such as Alzheimer's Disease, autism spectrum disorder, and schizophrenia. Furthermore, we also target the prediction of 10 different clinical assessment scores using structural MRI data. Our findings show that incorporating anatomical information during pre-training leads to more robust and generalizable representations. Pre-trained models can be found at: https://github.com/EIDOSLAB/AnatCL.
Authors: Juan-Pablo Ortega, Florian Rossmannek
Abstract: Several topological and analytical notions of continuity and fading memory for causal and time-invariant filters are introduced, and the relations between them are analyzed. A significant generalization of the convolution theorem that establishes the equivalence between the fading memory property and the availability of convolution representations of linear filters is proved. This result extends a previous similar characterization to a complete array of weighted norms in the definition of the fading memory property. Additionally, the main theorem shows that the availability of convolution representations can be characterized, at least when the codomain is finite-dimensional, not only by the fading memory property but also by the reunion of two purely topological notions that are called minimal continuity and minimal fading memory property. Finally, when the input space and the codomain of a linear functional are Hilbert spaces, it is shown that minimal continuity and the minimal fading memory property guarantee the existence of interesting embeddings of the associated reproducing kernel Hilbert spaces.
Authors: Zhe Xiong, Qiaoqiao Ding, Xiaoqun Zhang
Abstract: Recently, medical image synthesis gains more and more popularity, along with the rapid development of generative models. Medical image synthesis aims to generate an unacquired image modality, often from other observed data modalities. Synthesized images can be used for clinical diagnostic assistance, data augmentation for model training and validation or image quality improving. In the meanwhile, the flow-based models are among the successful generative models for the ability of generating realistic and high-quality synthetic images. However, most flow-based models require to calculate flow ordinary different equation (ODE) evolution steps in synthesis process, for which the performances are significantly limited by heavy computation time due to a large number of time iterations. In this paper, we propose a novel flow-based model, namely bi-directional Discrete Process Matching (Bi-DPM) to accomplish the bi-modality image synthesis tasks. Different to other flow matching based models, we propose to utilize both forward and backward ODE flows and enhance the consistency on the intermediate images over a few discrete time steps, resulting in a synthesis process maintaining high-quality generations for both modalities under the guidance of paired data. Our experiments on three datasets of MRI T1/T2 and CT/MRI demonstrate that Bi-DPM outperforms other state-of-the-art flow-based methods for bi-modality image synthesis, delivering higher image quality with accurate anatomical regions.
Authors: Jingxiong Liu, Ludvig Lemner, Linnea Wahlgren, Gregory Gay, Nasser Mohammadiha, Joakim Wennerberg
Abstract: Much of the cost and effort required during the software testing process is invested in performing test maintenance - the addition, removal, or modification of test cases to keep the test suite in sync with the system-under-test or to otherwise improve its quality. Tool support could reduce the cost - and improve the quality - of test maintenance by automating aspects of the process or by providing guidance and support to developers. In this study, we explore the capabilities and applications of large language models (LLMs) - complex machine learning models adapted to textual analysis - to support test maintenance. We conducted a case study at Ericsson AB where we explore the triggers that indicate the need for test maintenance, the actions that LLMs can take, and the considerations that must be made when deploying LLMs in an industrial setting. We also propose and demonstrate a multi-agent architecture that can predict which tests require maintenance following a change to the source code. Collectively, these contributions advance our theoretical and practical understanding of how LLMs can be deployed to benefit industrial test maintenance processes.
Authors: Zhanglu Yan, Zhenyu Bai, Weng-Fai Wong
Abstract: Spiking Neural Networks (SNNs) promise higher energy efficiency over conventional Quantized Artificial Neural Networks (QNNs) due to their event-driven, spike-based computation. However, prevailing energy evaluations often oversimplify, focusing on computational aspects while neglecting critical overheads like comprehensive data movement and memory access. Such simplifications can lead to misleading conclusions regarding the true energy benefits of SNNs. This paper presents a rigorous re-evaluation. We establish a fair baseline by mapping rate-encoded SNNs with $T$ timesteps to functionally equivalent QNNs with $\lceil \log_2(T+1) \rceil$ bits. This ensures both models have comparable representational capacities, as well has similar hardware requirement, enabling meaningful energy comparisons. We introduce a detailed analytical energy model encompassing core computation and data movement (sparse and dense activations, weights). Using this model, we systematically explore a wide parameter space, including intrinsic network characteristics ($T$, spike rate $s_r$, QNN sparsity $\gamma$, model size $N$, weight bit-level) and hardware characteristics (memory system and network-on-chip). Our analysis identifies specific operational regimes where SNNs genuinely offer superior energy efficiency. For example, under typical neuromorphic hardware conditions, SNNs with moderate time windows ($T \in [5,10]$) require an average spike rate ($s_r$) below 6.4% to outperform equivalent QNNs. These insights guide the design of genuinely energy-efficient neural network solutions.
Authors: Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
Abstract: Machine learning models are often brittle under distribution shift, i.e., when data distributions at test time differ from those during training. Understanding this failure mode is central to identifying and mitigating safety risks of mass adoption of machine learning. Here we analyze ridge regression under concept shift -- a form of distribution shift in which the input-label relationship changes at test time. We derive an exact expression for prediction risk in the thermodynamic limit. Our results reveal nontrivial effects of concept shift on generalization performance, including a phase transition between weak and strong concept shift regimes and nonmonotonic data dependence of test performance even when double descent is absent. Our theoretical results are in good agreement with experiments based on transformers pretrained to solve linear regression; under concept shift, too long context length can be detrimental to generalization performance of next token prediction. Finally, our experiments on MNIST and FashionMNIST suggest that this intriguing behavior is present also in classification problems.
Authors: Alfredo Ibias, Hector Antona, Guillem Ramirez-Miranda, Enric Guinovart, Eduard Alarcon
Abstract: Unsupervised learning methods have a soft inspiration in cognition models. To this day, the most successful unsupervised learning methods revolve around clustering samples in a mathematical space. In this paper we propose a primitive-based, unsupervised learning approach for decision-making inspired by a novel cognition framework. This representation-centric approach models the input space constructively as a distributed hierarchical structure in an input-agnostic way. We compared our approach with both current state-of-the-art unsupervised learning classification, with current state-of-the-art small and incomplete datasets classification, and with current state-of-the-art cancer type classification. We show how our proposal outperforms previous state-of-the-art. We also evaluate some cognition-like properties of our proposal where it not only outperforms the compared algorithms (even supervised learning ones), but it also shows a different, more cognition-like, behaviour.
Authors: Kosuke Imai, Kentaro Nakamura
Abstract: In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence (GenAI). Specifically, we propose to use a deep generative model such as large language models (LLMs) to efficiently generate treatments and use their internal representation for subsequent causal effect estimation. We show that the knowledge of this true internal representation helps disentangle the treatment features of interest, such as specific sentiments and certain topics, from other possibly unknown confounding features. Unlike existing methods, the proposed GenAI-Powered Inference (GPI) methodology eliminates the need to learn causal representation from the data, and hence produces more accurate and efficient estimates. We formally establish the conditions required for the nonparametric identification of the average treatment effect, propose an estimation strategy that avoids the violation of the overlap assumption, and derive the asymptotic properties of the proposed estimator through the application of double machine learning. Finally, using an instrumental variables approach, we extend the proposed methodology to the settings in which the treatment feature is based on human perception. The proposed GPI methodology is also applicable to text reuse where an LLM is used to regenerate existing texts. We conduct simulation and empirical studies, using the generated text data from an open-source LLM, Llama 3, to illustrate the advantages of our estimator over state-of-the-art causal representation learning algorithms.
Authors: Sizhe Chen, Arman Zharmagambetov, Saeed Mahloujifar, Kamalika Chaudhuri, David Wagner, Chuan Guo
Abstract: Large language models (LLMs) are becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advanced language understanding. To accomplish these tasks, the LLM often uses external data sources such as user documents, web retrieval, results from API calls, etc. This opens up new avenues for attackers to manipulate the LLM via prompt injection. Adversarial prompts can be injected into external data sources to override the system's intended instruction and instead execute a malicious instruction. To mitigate this vulnerability, we propose a new defense called SecAlign based on the technique of preference optimization. Our defense first constructs a preference dataset with prompt-injected inputs, secure outputs (ones that respond to the legitimate instruction), and insecure outputs (ones that respond to the injection). We then perform preference optimization on this dataset to teach the LLM to prefer the secure output over the insecure one. This provides the first known method that reduces the success rates of various prompt injections to <10%, even against attacks much more sophisticated than ones seen during training. This indicates our defense generalizes well against unknown and yet-to-come attacks. Also, SecAlign models are still practical with similar utility to the one before defensive training in our evaluations. Our code is at https://github.com/facebookresearch/SecAlign
Authors: Nicholas Kr\"amer
Abstract: Despite substantial progress in recent years, probabilistic solvers with adaptive step sizes can still not solve memory-demanding differential equations -- unless we care only about a single point in time (which is far too restrictive; we want the whole time series). Counterintuitively, the culprit is the adaptivity itself: Its unpredictable memory demands easily exceed our machine's capabilities, making our simulations fail unexpectedly and without warning. Still, dropping adaptivity would abandon years of progress, which can't be the answer. In this work, we solve this conundrum. We develop an adaptive probabilistic solver with fixed memory demands building on recent developments in robust state estimation. Switching to our method (i) eliminates memory issues for long time series, (ii) accelerates simulations by orders of magnitude through unlocking just-in-time compilation, and (iii) makes adaptive probabilistic solvers compatible with scientific computing in JAX.
Authors: Kim-Celine Kahl, Selen Erkan, Jeremias Traub, Carsten T. L\"uth, Klaus Maier-Hein, Lena Maier-Hein, Paul F. Jaeger
Abstract: Vision-Language Models (VLMs) have great potential in medical tasks, like Visual Question Answering (VQA), where they could act as interactive assistants for both patients and clinicians. Yet their robustness to distribution shifts on unseen data remains a key concern for safe deployment. Evaluating such robustness requires a controlled experimental setup that allows for systematic insights into the model's behavior. However, we demonstrate that current setups fail to offer sufficiently thorough evaluations. To address this gap, we introduce a novel framework, called SURE-VQA, centered around three key requirements to overcome current pitfalls and systematically analyze VLM robustness: 1) Since robustness on synthetic shifts does not necessarily translate to real-world shifts, it should be measured on real-world shifts that are inherent to the VQA data; 2) Traditional token-matching metrics often fail to capture underlying semantics, necessitating the use of large language models (LLMs) for more accurate semantic evaluation; 3) Model performance often lacks interpretability due to missing sanity baselines, thus meaningful baselines should be reported that allow assessing the multimodal impact on the VLM. To demonstrate the relevance of this framework, we conduct a study on the robustness of various Fine-Tuning (FT) methods across three medical datasets with four types of distribution shifts. Our study highlights key insights into robustness: 1) No FT method consistently outperforms others in robustness, and 2) robustness trends are more stable across FT methods than across distribution shifts. Additionally, we find that simple sanity baselines that do not use the image data can perform surprisingly well and confirm LoRA as the best-performing FT method on in-distribution data. Code is provided at https://github.com/IML-DKFZ/sure-vqa.
Authors: Osvaldo Gramaxo Freitas, Anastasios Theodoropoulos, Nino Villanueva, Tiago Fernandes, Solange Nunes, Jos\'e A. Font, Antonio Onofre, Alejandro Torres-Forn\'e, Jos\'e D. Martin-Guerrero
Abstract: Gravitational-wave approximants are essential for gravitational-wave astronomy, allowing the coverage binary black hole parameter space for inference or match filtering without costly numerical relativity (NR) simulations, but generally trading some accuracy for computational efficiency. To reduce this trade-off, NR surrogate models can be constructed using interpolation within NR waveform space. We present a 2-stage training approach for neural network-based NR surrogate models. Initially trained on approximant-generated waveforms and then fine-tuned with NR data, these dual-stage artificial neural surrogate (\texttt{DANSur}) models offer rapid and competitively accurate waveform generation, generating millions in under 20ms on a GPU while keeping mean mismatches with NR around $10^{-4}$. Implemented in the \textsc{bilby} framework, we show they can be used for parameter estimation tasks.
Authors: Pranava Seth, Vishal Upendran, Megha Anand, Janmejoy Sarkar, Soumya Roy, Priyadarshan Chaki, Pratyay Chowdhury, Borishan Ghosh, Durgesh Tripathi
Abstract: The Solar Ultraviolet Imaging Telescope(SUIT) onboard Aditya-L1 is an imager that observes the solar photosphere and chromosphere through observations in the wavelength range of 200-400 nm. A comprehensive understanding of the plasma and thermodynamic properties of chromospheric and photospheric morphological structures requires a large sample statistical study, necessitating the development of automatic feature detection methods. To this end, we develop the feature detection algorithm SPACE-SUIT: Solar Phenomena Analysis and Classification using Enhanced vision techniques for SUIT, to detect and classify the solar chromospheric features to be observed from SUIT's Mg II k filter. Specifically, we target plage regions, sunspots, filaments, and off-limb structures. SPACE uses YOLO, a neural network-based model to identify regions of interest. We train and validate SPACE using mock-SUIT images developed from Interface Region Imaging Spectrometer(IRIS) full-disk mosaic images in Mg II k line, while we also perform detection on Level-1 SUIT data. SPACE achieves an approximate precision of 0.788, recall 0.863 and MAP of 0.874 on the validation mock SUIT FITS dataset. Given the manual labeling of our dataset, we perform "self-validation" by applying statistical measures and Tamura features on the ground truth and predicted bounding boxes. We find the distributions of entropy, contrast, dissimilarity, and energy to show differences in the features. These differences are qualitatively captured by the detected regions predicted by SPACE and validated with the observed SUIT images, even in the absence of labeled ground truth. This work not only develops a chromospheric feature extractor but also demonstrates the effectiveness of statistical metrics and Tamura features for distinguishing chromospheric features, offering independent validation for future detection schemes.
Authors: Baocai Yin, Ji Zhao, Huajie Jiang, Ningning Hou, Yongli Hu, Amin Beheshti, Ming-Hsuan Yang, Yuankai Qi
Abstract: Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data for replay or add additional branches in the model to learn new knowledge, which has high memory requirements. In this paper, we propose a novel lightweight CL framework, Adapter-Enhanced Semantic Prompting (AESP), which integrates prompt tuning and adapter techniques. Specifically, we design semantic-guided prompts to enhance the generalization ability of visual features and utilize adapters to efficiently fuse the semantic information, aiming to learn more adaptive features for the continual learning task. Furthermore, to choose the right task prompt for feature adaptation, we have developed a novel matching mechanism for prompt selection. Extensive experiments on three CL datasets demonstrate that our approach achieves favorable performance across multiple metrics, showing its potential for advancing CL.
Authors: Sungdong Lee, Joshua Bang, Youngrae Kim, Hyungwon Choi, Sang-Yun Oh, Joong-Ho Won
Abstract: Graphical model estimation from multi-omics data requires a balance between statistical estimation performance and computational scalability. We introduce a novel pseudolikelihood-based graphical model framework that reparameterizes the target precision matrix while preserving the sparsity pattern and estimates it by minimizing an $\ell_1$-penalized empirical risk based on a new loss function. The proposed estimator maintains estimation and selection consistency in various metrics under high-dimensional assumptions. The associated optimization problem allows for a provably fast computation algorithm using a novel operator-splitting approach and communication-avoiding distributed matrix multiplication. A high-performance computing implementation of our framework was tested using simulated data with up to one million variables, demonstrating complex dependency structures similar to those found in biological networks. Leveraging this scalability, we estimated a partial correlation network from a dual-omic liver cancer data set. The co-expression network estimated from the ultrahigh-dimensional data demonstrated superior specificity in prioritizing key transcription factors and co-activators by excluding the impact of epigenetic regulation, thereby highlighting the value of computational scalability in multi-omic data analysis.
Authors: Jian Hu, Xibin Wu, Wei Shen, Jason Klein Liu, Zilin Zhu, Weixun Wang, Songlin Jiang, Haoran Wang, Hao Chen, Bin Chen, Weikai Fang, Xianyu, Yu Cao, Haotian Xu
Abstract: Large Language Models (LLMs) fine-tuned via Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) significantly improve the alignment of human-AI values and further raise the upper bound of AI capabilities, particularly in reasoning-intensive, long-context Chain-of-Thought (long-CoT) tasks. However, existing RLHF (or RLVR) frameworks commonly face challenges such as inference bottlenecks and complexity barriers, restricting their accessibility for newcomers. To bridge this gap, we introduce \textbf{OpenRLHF}, a user-friendly, scalable, and easy-to-learn open-source RLHF framework built upon Ray, vLLM, DeepSpeed, and HuggingFace Transformers, featuring a simplified design, clear code structure, and comprehensive documentation to facilitate entry for researchers and practitioners. Experimental results show that OpenRLHF achieves superior training efficiency with speedups ranging from 1.22x to 1.68x across different model sizes compared to state-of-the-art frameworks, while requiring significantly fewer lines of code for implementation. OpenRLHF is publicly available at https://github.com/OpenRLHF/OpenRLHF, and has already been adopted by leading institutions to accelerate RLHF research and learning.
Authors: Jeffrey Kelling, Vicente Bolea, Michael Bussmann, Ankush Checkervarty, Alexander Debus, Jan Ebert, Greg Eisenhauer, Vineeth Gutta, Stefan Kesselheim, Scott Klasky, Vedhas Pandit, Richard Pausch, Norbert Podhorszki, Franz Poschel, David Rogers, Jeyhun Rustamov, Steve Schmerler, Ulrich Schramm, Klaus Steiniger, Rene Widera, Anna Willmann, Sunita Chandrasekaran
Abstract: Increasing HPC cluster sizes and large-scale simulations that produce petabytes of data per run, create massive IO and storage challenges for analysis. Deep learning-based techniques, in particular, make use of these amounts of domain data to extract patterns that help build scientific understanding. Here, we demonstrate a streaming workflow in which simulation data is streamed directly to a machine-learning (ML) framework, circumventing the file system bottleneck. Data is transformed in transit, asynchronously to the simulation and the training of the model. With the presented workflow, data operations can be performed in common and easy-to-use programming languages, freeing the application user from adapting the application output routines. As a proof-of-concept we consider a GPU accelerated particle-in-cell (PIConGPU) simulation of the Kelvin- Helmholtz instability (KHI). We employ experience replay to avoid catastrophic forgetting in learning from this non-steady process in a continual manner. We detail challenges addressed while porting and scaling to Frontier exascale system.
Authors: Johan Larsson, Jonas Wallin
Abstract: Regularized models are often sensitive to the scales of the features in the data and it has therefore become standard practice to normalize (center and scale) the features before fitting the model. But there are many different ways to normalize the features and the choice may have dramatic effects on the resulting model. In spite of this, there has so far been no research on this topic. In this paper, we begin to bridge this knowledge gap by studying normalization in the context of lasso, ridge, and elastic net regression. We focus on binary features and show that their class balances (proportions of ones) directly influences the regression coefficients and that this effect depends on the combination of normalization and regularization methods used. We demonstrate that this effect can be mitigated by scaling binary features with their variance in the case of the lasso and standard deviation in the case of ridge regression, but that this comes at the cost of increased variance of the coefficient estimates. For the elastic net, we show that scaling the penalty weights, rather than the features, can achieve the same effect. Finally, we also tackle mixes of binary and normal features as well as interactions and provide some initial results on how to normalize features in these cases.
Authors: Daniele Molino, Francesco Di Feola, Eliodoro Faiella, Deborah Fazzini, Domiziana Santucci, Linlin Shen, Valerio Guarrasi, Paolo Soda
Abstract: The adoption of Artificial Intelligence in medical imaging holds great promise, yet it remains hindered by challenges such as data scarcity, privacy concerns, and the need for robust multimodal integration. While recent advances in generative modeling have enabled high-quality synthetic data generation, existing approaches are often limited to unimodal, unidirectional synthesis and therefore lack the ability to jointly synthesize multiple modalities while preserving clinical consistency. To address this challenge, we introduce XGeM, a 6.77-billion-parameter multimodal generative model designed to support flexible, any-to-any synthesis between medical data modalities. XGeM constructs a shared latent space via contrastive learning and introduces a novel Multi-Prompt Training strategy, enabling conditioning on arbitrary subsets of input modalities. This design allows the model to adapt to heterogeneous clinical inputs and generate multiple outputs jointly, preserving both semantic and structural coherence. We extensively validate XGeM: first we benchmark it against five competitors on the MIMIC-CXR dataset, a state-of-the-art dataset for multi-view Chest X-ray and radiological report generation. Secondly, we perform a Visual Turing Test with expert radiologists to assess the realism and clinical relevance of the generated data, ensuring alignment with real-world scenarios. Finally, we show how XGeM can support key medical data challenges such as anonymization, class imbalance, and data scarcity, underscoring its utility as a foundation model for medical data synthesis. Project page is at https://cosbidev.github.io/XGeM/.
Authors: Yu Terada, Ken Arai, Yu Tanaka, Yota Maeda, Hiroshi Ueno, Hiroyuki Tezuka
Abstract: The discovery of causal relations from observed data has attracted significant interest from disciplines such as economics, social sciences, and biology. In practical applications, considerable knowledge of the underlying systems is often unavailable, and real data are usually associated with nonlinear causal structures, which makes the direct use of most conventional causality analysis methods difficult. This study proposes a novel quantum Peter-Clark (qPC) algorithm for causal discovery that does not require any assumptions about the underlying model structures. Based on conditional independence tests in a class of reproducing kernel Hilbert spaces characterized by quantum circuits, the proposed algorithm can explore causal relations from the observed data drawn from arbitrary distributions. We conducted systematic experiments on fundamental graphs of causal structures, demonstrating that the qPC algorithm exhibits better performance, particularly with smaller sample sizes compared to its classical counterpart. Furthermore, we proposed a novel optimization approach based on Kernel Target Alignment (KTA) for determining hyperparameters of quantum kernels. This method effectively reduced the risk of false positives in causal discovery, enabling more reliable inference. Our theoretical and experimental results demonstrate that the quantum algorithm can empower classical algorithms for accurate inference in causal discovery, supporting them in regimes where classical algorithms typically fail. In addition, the effectiveness of this method was validated using the datasets on Boston housing prices, heart disease, and biological signaling systems as real-world applications. These findings highlight the potential of quantum-based causal discovery methods in addressing practical challenges, particularly in small-sample scenarios, where traditional approaches have shown significant limitations.
Authors: Krrish Chawla, Aryan Sahai, Mario DePavia, Sudharsan Sundar, Brando Miranda, Elyas Obbad, Sanmi Koyejo
Abstract: Contrary to the conventional emphasis on dataset size, we explore the role of data alignment -- an often overlooked aspect of data quality -- in training capable Large Language Models (LLMs). To do so, we use the Task2Vec-based alignment coefficient, a quantitative measure of the similarity between two datasets, to quantify the impact of alignment between training data and evaluation data on downstream performance. In particular, we conduct controlled \textit{interventional} experiments for two settings: 1. the impact of increased alignment coefficients between various pre-training (pt) against evaluation datasets, and 2. the impact of increased alignment coefficients between domain specific fine-tuning (ft) against domain specific evaluation. The domain specific task we explore is Autoformalization -- the machine translation task between natural language and code for formal verification. In both settings, we find a strong, predictable negative correlation between the alignment coefficient of a model's training and evaluation data and the model's loss/perplexity on the respective downstream task. These findings suggest a re-evaluation of LLM training approaches, demonstrating the relevance of data alignment compared to data quantity, especially in specialized downstream tasks such as Autoformalization.
Authors: Theo Lepage, Reda Dehak
Abstract: Recent developments in Self-Supervised Learning (SSL) have demonstrated significant potential for Speaker Verification (SV), but closing the performance gap with supervised systems remains an ongoing challenge. SSL frameworks rely on anchor-positive pairs, constructed from segments of the same audio utterance. Hence, positives have channel characteristics similar to those of their corresponding anchors, even with extensive data-augmentation. Therefore, this positive sampling strategy is a fundamental limitation as it encodes too much information regarding the recording source in the learned representations. This article introduces Self-Supervised Positive Sampling (SSPS), a bootstrapped technique for sampling appropriate and diverse positives in SSL frameworks for SV. SSPS samples positives close to their anchor in the representation space, assuming that these pseudo-positives belong to the same speaker identity but correspond to different recording conditions. This method consistently demonstrates improvements in SV performance on VoxCeleb benchmarks when applied to major SSL frameworks, including SimCLR, SwAV, VICReg, and DINO. Using SSPS, SimCLR and DINO achieve 2.57% and 2.53% EER on VoxCeleb1-O, respectively. SimCLR yields a 58% relative reduction in EER, getting comparable performance to DINO with a simpler training framework. Furthermore, SSPS lowers intra-class variance and reduces channel information in speaker representations while exhibiting greater robustness without data-augmentation.
Authors: Swadhin Das, Saarthak Gupta, Kamal Kumar, Raksha Sharma
Abstract: Remote Sensing Image Captioning (RSIC) is the process of generating meaningful descriptions from remote sensing images. Recently, it has gained significant attention, with encoder-decoder models serving as the backbone for generating meaningful captions. The encoder extracts essential visual features from the input image, transforming them into a compact representation, while the decoder utilizes this representation to generate coherent textual descriptions. Recently, transformer-based models have gained significant popularity due to their ability to capture long-range dependencies and contextual information. The decoder has been well explored for text generation, whereas the encoder remains relatively unexplored. However, optimizing the encoder is crucial as it directly influences the richness of extracted features, which in turn affects the quality of generated captions. To address this gap, we systematically evaluate twelve different convolutional neural network (CNN) architectures within a transformer-based encoder framework to assess their effectiveness in RSIC. The evaluation consists of two stages: first, a numerical analysis categorizes CNNs into different clusters, based on their performance. The best performing CNNs are then subjected to human evaluation from a human-centric perspective by a human annotator. Additionally, we analyze the impact of different search strategies, namely greedy search and beam search, to ensure the best caption. The results highlight the critical role of encoder selection in improving captioning performance, demonstrating that specific CNN architectures significantly enhance the quality of generated descriptions for remote sensing images. By providing a detailed comparison of multiple encoders, this study offers valuable insights to guide advances in transformer-based image captioning models.
Authors: M. P. Bento, H. B. C\^amara, J. F. Seabra
Abstract: We parametrically solve the Boltzmann equations governing freeze-in dark matter (DM) in alternative cosmologies with Physics-Informed Neural Networks (PINNs), a mesh-free method. Through inverse PINNs, using a single DM experimental point -- observed relic density -- we determine the physical attributes of the theory, namely power-law cosmologies, inspired by braneworld scenarios, and particle interaction cross sections. The expansion of the Universe in such alternative cosmologies has been parameterized through a switch-like function reproducing the Hubble law at later times. Without loss of generality, we model more realistically this transition with a smooth function. We predict a distinct pair-wise relationship between power-law exponent and particle interactions: for a given cosmology with negative (positive) exponent, smaller (larger) cross sections are required to reproduce the data. Lastly, via Bayesian methods, we quantify the epistemic uncertainty of theoretical parameters found in inverse problems.
Authors: Binghui Wu, Dinil Mon Divakaran, Mohan Gurusamy
Abstract: As modern networks grow increasingly complex--driven by diverse devices, encrypted protocols, and evolving threats--network traffic analysis has become critically important. Existing machine learning models often rely only on a single representation of packets or flows, limiting their ability to capture the contextual relationships essential for robust analysis. Furthermore, task-specific architectures for supervised, semi-supervised, and unsupervised learning lead to inefficiencies in adapting to varying data formats and security tasks. To address these gaps, we propose UniNet, a unified framework that introduces a novel multi-granular traffic representation (T-Matrix), integrating session, flow, and packet-level features to provide comprehensive contextual information. Combined with T-Attent, a lightweight attention-based model, UniNet efficiently learns latent embeddings for diverse security tasks. Extensive evaluations across four key network security and privacy problems--anomaly detection, attack classification, IoT device identification, and encrypted website fingerprinting--demonstrate UniNet's significant performance gain over state-of-the-art methods, achieving higher accuracy, lower false positive rates, and improved scalability. By addressing the limitations of single-level models and unifying traffic analysis paradigms, UniNet sets a new benchmark for modern network security.
Authors: Elvis Kimara, Mozhgan Hadadi, Jackson Godbersen, Aditya Balu, Talukder Jubery, Yawei Li, Adarsh Krishnamurthy, Patrick S. Schnable, Baskar Ganapathysubramanian
Abstract: The development of artificial intelligence (AI) and machine learning (ML) based tools for 3D phenotyping, especially for maize, has been limited due to the lack of large and diverse 3D datasets. 2D image datasets fail to capture essential structural details such as leaf architecture, plant volume, and spatial arrangements that 3D data provide. To address this limitation, we present MaizeField3D (https://baskargroup.github.io/MaizeField3D/), a curated dataset of 3D point clouds of field-grown maize plants from a diverse genetic panel, designed to be AI-ready for advancing agricultural research. Our dataset includes 1,045 high-quality point clouds of field-grown maize collected using a terrestrial laser scanner (TLS). Point clouds of 520 plants from this dataset were segmented and annotated using a graph-based segmentation method to isolate individual leaves and stalks, ensuring consistent labeling across all samples. This labeled data was then used for fitting procedural models that provide a structured parametric representation of the maize plants. The leaves of the maize plants in the procedural models are represented using Non-Uniform Rational B-Spline (NURBS) surfaces that were generated using a two-step optimization process combining gradient-free and gradient-based methods. We conducted rigorous manual quality control on all datasets, correcting errors in segmentation, ensuring accurate leaf ordering, and validating metadata annotations. The dataset also includes metadata detailing plant morphology and quality, alongside multi-resolution subsampled point cloud data (100k, 50k, 10k points), which can be readily used for different downstream computational tasks. MaizeField3D will serve as a comprehensive foundational dataset for AI-driven phenotyping, plant structural analysis, and 3D applications in agricultural research.
Authors: DongHeun Han, Byungmin Kim, RoUn Lee, KyeongMin Kim, Hyoseok Hwang, HyeongYeop Kang
Abstract: Realistic Hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact forces and finger torques. Consequently, these approaches prioritize tight, one-size-fits-all grips rather than reflecting users' intended force levels. We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions, faithfully reflecting the user's grip force intention. Instead of mimicking predefined motion datasets, ForceGrip uses generated training scenarios-randomizing object shapes, wrist movements, and trigger input flows-to challenge the agent with a broad spectrum of physical interactions. To effectively learn from these complex tasks, we employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization. This progressive strategy ensures stable hand-object contact, adaptive force control based on user inputs, and robust handling under dynamic conditions. Additionally, a proximity reward function enhances natural finger motions and accelerates training convergence. Quantitative and qualitative evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods. Demo videos are available as supplementary material and the code is provided at https://han-dongheun.github.io/ForceGrip.
Authors: Dongsheng Yang, Qianying Liu, Wataru Sato, Takashi Minato, Chaoran Liu, Shin'ya Nishida
Abstract: Automatic robotic facial expression generation is crucial for human-robot interaction, as handcrafted methods based on fixed joint configurations often yield rigid and unnatural behaviors. Although recent automated techniques reduce the need for manual tuning, they tend to fall short by not adequately bridging the gap between human preferences and model predictions-resulting in a deficiency of nuanced and realistic expressions due to limited degrees of freedom and insufficient perceptual integration. In this work, we propose a novel learning-to-rank framework that leverages human feedback to address this discrepancy and enhanced the expressiveness of robotic faces. Specifically, we conduct pairwise comparison annotations to collect human preference data and develop the Human Affective Pairwise Impressions (HAPI) model, a Siamese RankNet-based approach that refines expression evaluation. Results obtained via Bayesian Optimization and online expression survey on a 35-DOF android platform demonstrate that our approach produces significantly more realistic and socially resonant expressions of Anger, Happiness, and Surprise than those generated by baseline and expert-designed methods. This confirms that our framework effectively bridges the gap between human preferences and model predictions while robustly aligning robotic expression generation with human affective responses.
Authors: Finn M. Sherry, Bart M. N. Smets
Abstract: Flow Matching (FM) is a recent generative modelling technique: we aim to learn how to sample from distribution $\mathfrak{X}_1$ by flowing samples from some distribution $\mathfrak{X}_0$ that is easy to sample from. The key trick is that this flow field can be trained while conditioning on the end point in $\mathfrak{X}_1$: given an end point, simply move along a straight line segment to the end point (Lipman et al. 2022). However, straight line segments are only well-defined on Euclidean space. Consequently, Chen and Lipman (2023) generalised the method to FM on Riemannian manifolds, replacing line segments with geodesics or their spectral approximations. We take an alternative point of view: we generalise to FM on Lie groups by instead substituting exponential curves for line segments. This leads to a simple, intrinsic, and fast implementation for many matrix Lie groups, since the required Lie group operations (products, inverses, exponentials, logarithms) are simply given by the corresponding matrix operations. FM on Lie groups could then be used for generative modelling with data consisting of sets of features (in $\mathbb{R}^n$) and poses (in some Lie group), e.g. the latent codes of Equivariant Neural Fields (Wessels et al. 2025).
Authors: Gijs Bellaard, Bart M. N. Smets, Remco Duits
Abstract: Euclidean E(3) equivariant neural networks that employ scalar fields on position-orientation space M(3) have been effectively applied to tasks such as predicting molecular dynamics and properties. To perform equivariant convolutional-like operations in these architectures one needs Euclidean invariant kernels on M(3) x M(3). In practice, a handcrafted collection of invariants is selected, and this collection is then fed into multilayer perceptrons to parametrize the kernels. We rigorously describe an optimal collection of 4 smooth scalar invariants on the whole of M(3) x M(3). With optimal we mean that the collection is independent and universal, meaning that all invariants are pertinent, and any invariant kernel is a function of them. We evaluate two collections of invariants, one universal and one not, using the PONITA neural network architecture. Our experiments show that using a collection of invariants that is universal positively impacts the accuracy of PONITA significantly.
Authors: Gijs Bellaard, Bart M. N. Smets
Abstract: Riemannian metrics on the position-orientation space M(3) that are roto-translation group SE(3) invariant play a key role in image analysis tasks like enhancement, denoising, and segmentation. These metrics enable roto-translation equivariant algorithms, with the associated Riemannian distance often used in implementation. However, computing the Riemannian distance is costly, which makes it unsuitable in situations where constant recomputation is needed. We propose the mav (minimal angular velocity) distance, defined as the Riemannian length of a geometrically meaningful curve, as a practical alternative. We see an application of the mav distance in geometric deep learning. Namely, neural networks architectures such as PONITA, relies on geometric invariants to create their roto-translation equivariant model. The mav distance offers a trainable invariant, with the parameters that determine the Riemannian metric acting as learnable weights. In this paper we: 1) classify and parametrize all SE(3) invariant metrics on M(3), 2) describes how to efficiently calculate the mav distance, and 3) investigate if including the mav distance within PONITA can positively impact its accuracy in predicting molecular properties.
Authors: Alejandra Perez, Han Zhang, Yu-Chun Ku, Lalithkumar Seenivasan, Roger Soberanis, Jose L. Porras, Richard Day, Jeff Jopling, Peter Najjar, Mathias Unberath
Abstract: The operating room (OR) is a complex environment where optimizing workflows is critical to reduce costs and improve patient outcomes. While computer vision approaches for automatic recognition of perioperative events can identify bottlenecks for OR optimization, privacy concerns limit the use of OR videos for automated event detection. We propose a two-stage pipeline for privacy-preserving OR video analysis and event detection. First, we leverage vision foundation models for depth estimation and semantic segmentation to generate de-identified Digital Twins (DT) of the OR from conventional RGB videos. Second, we employ the SafeOR model, a fused two-stream approach that processes segmentation masks and depth maps for OR event detection. Evaluation on an internal dataset of 38 simulated surgical trials with five event classes shows that our DT-based approach achieves performance on par with -- and sometimes better than -- raw RGB video-based models for OR event detection. Digital Twins enable privacy-preserving OR workflow analysis, facilitating the sharing of de-identified data across institutions and potentially enhancing model generalizability by mitigating domain-specific appearance differences.
Authors: Florian Vahl, J\"orn Griepenburg, Jan Gutsche, Jasper G\"uldenstein, Jianwei Zhang
Abstract: This paper introduces SoccerDiffusion, a transformer-based diffusion model designed to learn end-to-end control policies for humanoid robot soccer directly from real-world gameplay recordings. Using data collected from RoboCup competitions, the model predicts joint command trajectories from multi-modal sensor inputs, including vision, proprioception, and game state. We employ a distillation technique to enable real-time inference on embedded platforms that reduces the multi-step diffusion process to a single step. Our results demonstrate the model's ability to replicate complex motion behaviors such as walking, kicking, and fall recovery both in simulation and on physical robots. Although high-level tactical behavior remains limited, this work provides a robust foundation for subsequent reinforcement learning or preference optimization methods. We release the dataset, pretrained models, and code under: https://bit-bots.github.io/SoccerDiffusion
Authors: Rodrigo Maulen-Soto (SU, LPSM), Claire Boyer (IUF), Pierre Marion (EPFL)
Abstract: Transformers have emerged as a powerful neural network architecture capable of tackling a wide range of learning tasks. In this work, we provide a theoretical analysis of their ability to automatically extract structure from data in an unsupervised setting. In particular, we demonstrate their suitability for clustering when the input data is generated from a Gaussian mixture model. To this end, we study a simplified two-head attention layer and define a population risk whose minimization with unlabeled data drives the head parameters to align with the true mixture centroids. This phenomenon highlights the ability of attention-based layers to capture underlying distributional structure. We further examine an attention layer with key, query, and value matrices fixed to the identity, and show that, even without any trainable parameters, it can perform in-context quantization, revealing the surprising capacity of transformer-based methods to adapt dynamically to input-specific distributions.
Authors: Hao Wang, Pinzhi Huang, Jihan Yang, Saining Xie, Daisuke Kawahara
Abstract: The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages, especially when integrating cultural knowledge, remains a significant challenge. To better assess this issue, we introduce two new benchmarks: KnowRecall and VisRecall, which evaluate cross-lingual consistency in MLLMs. KnowRecall is a visual question answering benchmark designed to measure factual knowledge consistency in 15 languages, focusing on cultural and historical questions about global landmarks. VisRecall assesses visual memory consistency by asking models to describe landmark appearances in 9 languages without access to images. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, still struggle to achieve cross-lingual consistency. This underscores the need for more robust approaches that produce truly multilingual and culturally aware models.
Authors: Dominic Lowe, M. S. Kim, Roberto Bondesan
Abstract: Gaussian Process Regression is a well-known machine learning technique for which several quantum algorithms have been proposed. We show here that in a wide range of scenarios these algorithms show no exponential speedup. We achieve this by rigorously proving that the condition number of a kernel matrix scales at least linearly with the matrix size under general assumptions on the data and kernel. We additionally prove that the sparsity and Frobenius norm of a kernel matrix scale linearly under similar assumptions. The implications for the quantum algorithms runtime are independent of the complexity of loading classical data on a quantum computer and also apply to dequantised algorithms. We supplement our theoretical analysis with numerical verification for popular kernels in machine learning.
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: R\'ois\'in Luo, James McDermott, Colm O'Riordan
Abstract: We present a theoretical framework for deriving the general $n$-th order Fr\'echet derivatives of singular values in real rectangular matrices, by leveraging reduced resolvent operators from Kato's analytic perturbation theory for self-adjoint operators. Deriving closed-form expressions for higher-order derivatives of singular values is notoriously challenging through standard matrix-analysis techniques. To overcome this, we treat a real rectangular matrix as a compact operator on a finite-dimensional Hilbert space, and embed the rectangular matrix into a block self-adjoint operator so that non-symmetric perturbations are captured. Applying Kato's asymptotic eigenvalue expansion to this construction, we obtain a general, closed-form expression for the infinitesimal $n$-th order spectral variations. Specializing to $n=2$ and deploying on a Kronecker-product representation with matrix convention yield the Hessian of a singular value, not found in literature. By bridging abstract operator-theoretic perturbation theory with matrices, our framework equips researchers with a practical toolkit for higher-order spectral sensitivity studies in random matrix applications (e.g., adversarial perturbation in deep learning).
Authors: Jaewon Min, Jin Hyeon Kim, Paul Hyunbin Cho, Jaeeun Lee, Jihye Park, Minkyu Park, Sangpil Kim, Hyunhee Park, Seungryong Kim
Abstract: Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those methods frequently generate plausible but incorrect text-like patterns, a phenomenon we refer to as text-image hallucination. In this paper, we introduce Text-Aware Image Restoration (TAIR), a novel restoration task that requires the simultaneous recovery of visual contents and textual fidelity. To tackle this task, we present SA-Text, a large-scale benchmark of 100K high-quality scene images densely annotated with diverse and complex text instances. Furthermore, we propose a multi-task diffusion framework, called TeReDiff, that integrates internal features from diffusion models into a text-spotting module, enabling both components to benefit from joint training. This allows for the extraction of rich text representations, which are utilized as prompts in subsequent denoising steps. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art restoration methods, achieving significant gains in text recognition accuracy. See our project page: https://cvlab-kaist.github.io/TAIR/
Authors: Abdolazim Rezaei, Mehdi Sookhak, Ahmad Patooghy
Abstract: Connected and Autonomous Vehicles (CAVs) rely on a range of devices that often process privacy-sensitive data. Among these, roadside units play a critical role particularly through the use of AI-equipped (AIE) cameras for applications such as violation detection. However, the privacy risks associated with captured imagery remain a major concern, as such data can be misused for identity theft, profiling, or unauthorized commercial purposes. While traditional techniques such as face blurring and obfuscation have been applied to mitigate privacy risks, individual privacy remains at risk, as individuals can still be tracked using other features such as their clothing. This paper introduces a novel privacy-preserving framework that leverages feedback-based reinforcement learning (RL) and vision-language models (VLMs) to protect sensitive visual information captured by AIE cameras. The main idea is to convert images into semantically equivalent textual descriptions, ensuring that scene-relevant information is retained while visual privacy is preserved. A hierarchical RL strategy is employed to iteratively refine the generated text, enhancing both semantic accuracy and privacy. Evaluation results demonstrate significant improvements in both privacy protection and textual quality, with the Unique Word Count increasing by approximately 77\% and Detail Density by around 50\% compared to existing approaches.
Authors: Weizhi Zhang, Yangning Li, Yuanchen Bei, Junyu Luo, Guancheng Wan, Liangwei Yang, Chenxuan Xie, Yuyao Yang, Wei-Chieh Huang, Chunyu Miao, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Yankai Chen, Chunkit Chan, Peilin Zhou, Xinyang Zhang, Chenwei Zhang, Jingbo Shang, Ming Zhang, Yangqiu Song, Irwin King, Philip S. Yu
Abstract: Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.
Authors: Luhuan Wu, Mingzhang Yin, Yixin Wang, John P. Cunningham, David M. Blei
Abstract: Invariant prediction [Peters et al., 2016] analyzes feature/outcome data from multiple environments to identify invariant features - those with a stable predictive relationship to the outcome. Such features support generalization to new environments and help reveal causal mechanisms. Previous methods have primarily tackled this problem through hypothesis testing or regularized optimization. Here we develop Bayesian Invariant Prediction (BIP), a probabilistic model for invariant prediction. BIP encodes the indices of invariant features as a latent variable and recover them by posterior inference. Under the assumptions of Peters et al. [2016], the BIP posterior targets the true invariant features. We prove that the posterior is consistent and that greater environment heterogeneity leads to faster posterior contraction. To handle many features, we design an efficient variational approximation called VI-BIP. In simulations and real data, we find that BIP and VI-BIP are more accurate and scalable than existing methods for invariant prediction.
Authors: Tianxing Chen, Kaixuan Wang, Zhaohui Yang, Yuhao Zhang, Zanxin Chen, Baijun Chen, Wanxi Dong, Ziyuan Liu, Dong Chen, Tianshuo Yang, Haibao Yu, Xiaokang Yang, Yusen Qin, Zhiqiang Xie, Yao Mu, Ping Luo, Tian Nian, Weiliang Deng, Yiheng Ge, Yibin Liu, Zixuan Li, Dehui Wang, Zhixuan Liang, Haohui Xie, Rijie Zeng, Yunfei Ge, Peiqing Cong, Guannan He, Zhaoming Han, Ruocheng Yin, Jingxiang Guo, Lunkai Lin, Tianling Xu, Hongzhe Bi, Xuewu Lin, Tianwei Lin, Shujie Luo, Keyu Li, Ziyan Zhao, Ke Fan, Heyang Xu, Bo Peng, Wenlong Gao, Dongjiang Li, Feng Jin, Hui Shen, Jinming Li, Chaowei Cui, Yu Chen, Yaxin Peng, Lingdong Zeng, Wenlong Dong, Tengfei Li, Weijie Ke, Jun Chen, Erdemt Bao, Tian Lan, Tenglong Liu, Jin Yang, Huiping Zhuang, Baozhi Jia, Shuai Zhang, Zhengfeng Zou, Fangheng Guan, Tianyi Jia, Ke Zhou, Hongjiu Zhang, Yating Han, Cheng Fang, Yixian Zou, Chongyang Xu, Qinglun Zhang, Shen Cheng, Xiaohe Wang, Ping Tan, Haoqiang Fan, Shuaicheng Liu, Jiaheng Chen, Chuxuan Huang, Chengliang Lin, Kaijun Luo, Boyu Yue, Yi Liu, Jinyu Chen, Zichang Tan, Liming Deng, Shuo Xu, Zijian Cai, Shilong Yin, Hao Wang, Hongshan Liu, Tianyang Li, Long Shi, Ran Xu, Huilin Xu, Zhengquan Zhang, Congsheng Xu, Jinchang Yang, Feng Xu
Abstract: Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To advance this goal, we launched the RoboTwin Dual-Arm Collaboration Challenge at the 2nd MEIS Workshop, CVPR 2025. Built on the RoboTwin Simulation platform (1.0 and 2.0) and the AgileX COBOT-Magic Robot platform, the competition consisted of three stages: Simulation Round 1, Simulation Round 2, and a final Real-World Round. Participants totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios. The challenge attracted 64 global teams and over 400 participants, producing top-performing solutions like SEM and AnchorDP3 and generating valuable insights into generalizable bimanual policy learning. This report outlines the competition setup, task design, evaluation methodology, key findings and future direction, aiming to support future research on robust and generalizable bimanual manipulation policies. The Challenge Webpage is available at https://robotwin-benchmark.github.io/cvpr-2025-challenge/.
URLs: https://robotwin-benchmark.github.io/cvpr-2025-challenge/.
Authors: Xue Wen Tan, Stanley Kok
Abstract: Every publicly traded U.S. company files an annual 10-K report containing critical insights into financial health and risk. We propose Tiny eXplainable Risk Assessor (TinyXRA), a lightweight and explainable transformer-based model that automatically assesses company risk from these reports. Unlike prior work that relies solely on the standard deviation of excess returns (adjusted for the Fama-French model), which indiscriminately penalizes both upside and downside risk, TinyXRA incorporates skewness, kurtosis, and the Sortino ratio for more comprehensive risk assessment. We leverage TinyBERT as our encoder to efficiently process lengthy financial documents, coupled with a novel dynamic, attention-based word cloud mechanism that provides intuitive risk visualization while filtering irrelevant terms. This lightweight design ensures scalable deployment across diverse computing environments with real-time processing capabilities for thousands of financial documents which is essential for production systems with constrained computational resources. We employ triplet loss for risk quartile classification, improving over pairwise loss approaches in existing literature by capturing both the direction and magnitude of risk differences. Our TinyXRA achieves state-of-the-art predictive accuracy across seven test years on a dataset spanning 2013-2024, while providing transparent and interpretable risk assessments. We conduct comprehensive ablation studies to evaluate our contributions and assess model explanations both quantitatively by systematically removing highly attended words and sentences, and qualitatively by examining explanation coherence. The paper concludes with findings, practical implications, limitations, and future research directions. Our code is available at https://github.com/Chen-XueWen/TinyXRA.
Authors: Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao, Jujie He, Jiacai Liu, Chaojie Wang, Rui Yan, Wei Shen, Fuxiang Zhang, Jiacheng Xu, Yang Liu, Yahui Zhou
Abstract: Despite the critical role of reward models (RMs) in reinforcement learning from human feedback (RLHF), current state-of-the-art open RMs perform poorly on most existing evaluation benchmarks, failing to capture the spectrum of nuanced and sophisticated human preferences. Even approaches that incorporate advanced training techniques have not yielded meaningful performance improvements. We hypothesize that this brittleness stems primarily from limitations in preference datasets, which are often narrowly scoped, synthetically labeled, or lack rigorous quality control. To address these challenges, we present a large-scale preference dataset comprising 40 million preference pairs, named SynPref-40M. To enable data curation at scale, we design a human-AI synergistic two-stage pipeline that leverages the complementary strengths of human annotation quality and AI scalability. In this pipeline, humans provide verified annotations, while large language models perform automatic curation based on human guidance. Training on this preference mixture, we introduce Skywork-Reward-V2, a suite of eight reward models ranging from 0.6B to 8B parameters, trained on a carefully curated subset of 26 million preference pairs from SynPref-40M. We demonstrate that Skywork-Reward-V2 is versatile across a wide range of capabilities, including alignment with human preferences, objective correctness, safety, resistance to stylistic biases, and best-of-N scaling, achieving state-of-the-art performance across seven major reward model benchmarks. Ablation studies confirm that the effectiveness of our approach stems not only from data scale but also from high-quality curation. The Skywork-Reward-V2 series represents substantial progress in open reward models, highlighting the untapped potential of existing preference datasets and demonstrating how human-AI curation synergy can unlock significantly higher data quality.