Authors: Yuanbo Tang, Yan Tang, Naifan Zhang, Meixuan Chen, Yang Li
Abstract: Mixture-of-Experts based large language models (MoE LLMs) have shown significant promise in multitask adaptability by dynamically routing inputs to specialized experts. Despite their success, the collaborative mechanisms among experts are still not well understood, limiting both the interpretability and optimization of these models. In this paper, we focus on two critical issues: (1) identifying expert collaboration patterns, and (2) optimizing MoE LLMs through expert pruning. To address the first issue, we propose a hierarchical sparse dictionary learning (HSDL) method that uncovers the collaboration patterns among experts. For the second issue, we introduce the Contribution-Aware Expert Pruning (CAEP) algorithm, which effectively prunes low-contribution experts. Our extensive experiments demonstrate that expert collaboration patterns are closely linked to specific input types and exhibit semantic significance across various tasks. Moreover, pruning experiments show that our approach improves overall performance by 2.5\% on average, outperforming existing methods. These findings offer valuable insights into enhancing the efficiency and interpretability of MoE LLMs, offering a clearer understanding of expert interactions and improving model optimization.
Authors: Kristjan Greenewald, Luis Lastras, Thomas Parnell, Vraj Shah, Lucian Popa, Giulio Zizzo, Chulaka Gunasekara, Ambrish Rawat, David Cox
Abstract: Low-Rank Adaptation (LoRA) has emerged as a highly efficient framework for finetuning the weights of large foundation models, and has become the go-to method for data-driven customization of LLMs. Despite the promise of highly customized behaviors and capabilities, switching between relevant LoRAs in a multiturn setting is highly inefficient, as the key-value (KV) cache of the entire turn history must be recomputed with the LoRA weights before generation can begin. To address this problem, we propose Activated LoRA (aLoRA), which modifies the LoRA framework to only adapt weights for the tokens in the sequence \emph{after} the aLoRA is invoked. This change crucially allows aLoRA to accept the base model's KV cache of the input string, meaning that aLoRA can be instantly activated whenever needed in a chain without recomputing the cache. This enables building what we call \emph{intrinsics}, i.e. highly specialized models invoked to perform well-defined operations on portions of an input chain or conversation that otherwise uses the base model by default. We use aLoRA to train a set of intrinsics models, demonstrating competitive accuracy with standard LoRA while achieving significant inference benefits.
Authors: Loong Kuan Lee, Thore Thassilo Gerlach, Nico Piatkowski
Abstract: Multi-objective optimization involving Quadratic Unconstrained Binary Optimization (QUBO) problems arises in various domains. A fundamental challenge in this context is the effective balancing of multiple objectives, each potentially operating on very different scales. This imbalance introduces complications such as the selection of appropriate weights when scalarizing multiple objectives into a single objective function. In this paper, we propose a novel technique for scaling QUBO objectives that uses an exact computation of the variance of each individual QUBO objective. By scaling each objective to have unit variance, we align all objectives onto a common scale, thereby allowing for more balanced solutions to be found when scalarizing the objectives with equal weights, as well as potentially assisting in the search or choice of weights during scalarization. Finally, we demonstrate its advantages through empirical evaluations on various multi-objective optimization problems. Our results are noteworthy since manually selecting scalarization weights is cumbersome, and reliable, efficient solutions are scarce.
Authors: Sebastian Seidel, Uwe M. Borghoff
Abstract: Artificial intelligence (AI) has emerged as a transformative force across industries, driven by advances in deep learning and natural language processing, and fueled by large-scale data and computing resources. Despite its rapid adoption, the opacity of AI systems poses significant challenges to trust and acceptance. This work explores the intersection of connectionist and symbolic approaches to artificial intelligence, focusing on the derivation of interpretable symbolic models, such as decision trees, from feedforward neural networks (FNNs). Decision trees provide a transparent framework for elucidating the operations of neural networks while preserving their functionality. The derivation is presented in a step-by-step approach and illustrated with several examples. A systematic methodology is proposed to bridge neural and symbolic paradigms by exploiting distributed representations in FNNs to identify symbolic components, including fillers, roles, and their interrelationships. The process traces neuron activation values and input configurations across network layers, mapping activations and their underlying inputs to decision tree edges. The resulting symbolic structures effectively capture FNN decision processes and enable scalability to deeper networks through iterative refinement of subpaths for each hidden layer. To validate the theoretical framework, a prototype was developed using Keras .h5-data and emulating TensorFlow within the Java JDK/JavaFX environment. This prototype demonstrates the feasibility of extracting symbolic representations from neural networks, enhancing trust in AI systems, and promoting accountability.
Authors: Ziqi Li, Zhan Peng
Abstract: Moran Eigenvector Spatial Filtering (ESF) approaches have shown promise in accounting for spatial effects in statistical models. Can this extend to machine learning? This paper examines the effectiveness of using Moran Eigenvectors as additional spatial features in machine learning models. We generate synthetic datasets with known processes involving spatially varying and nonlinear effects across two different geometries. Moran Eigenvectors calculated from different spatial weights matrices, with and without a priori eigenvector selection, are tested. We assess the performance of popular machine learning models, including Random Forests, LightGBM, XGBoost, and TabNet, and benchmark their accuracies in terms of cross-validated R2 values against models that use only coordinates as features. We also extract coefficients and functions from the models using GeoShapley and compare them with the true processes. Results show that machine learning models using only location coordinates achieve better accuracies than eigenvector-based approaches across various experiments and datasets. Furthermore, we discuss that while these findings are relevant for spatial processes that exhibit positive spatial autocorrelation, they do not necessarily apply when modeling network autocorrelation and cases with negative spatial autocorrelation, where Moran Eigenvectors would still be useful.
Authors: Jansen S. B. Pereira, Giovani Valdrighi, Marcos Medeiros Raimundo
Abstract: In recent years, fairness in machine learning has emerged as a critical concern to ensure that developed and deployed predictive models do not have disadvantageous predictions for marginalized groups. It is essential to mitigate discrimination against individuals based on protected attributes such as gender and race. In this work, we consider applying subgroup justice concepts to gradient-boosting machines designed for supervised learning problems. Our approach expanded gradient-boosting methodologies to explore a broader range of objective functions, which combines conventional losses such as the ones from classification and regression and a min-max fairness term. We study relevant theoretical properties of the solution of the min-max optimization problem. The optimization process explored the primal-dual problems at each boosting round. This generic framework can be adapted to diverse fairness concepts. The proposed min-max primal-dual gradient boosting algorithm was theoretically shown to converge under mild conditions and empirically shown to be a powerful and flexible approach to address binary and subgroup fairness.
Authors: Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Therien, Supriyo Chakraborty, Tom Goldstein
Abstract: Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward update, leading to training instability and suboptimal performance. We present a lightweight approximation method that gives the MoE router a dense gradient update while continuing to sparsely activate its parameters. Our method, which we refer to as Default MoE, substitutes missing expert activations with default outputs consisting of an exponential moving average of expert outputs previously seen over the course of training. This allows the router to receive signals from every expert for each token, leading to significant improvements in training performance. Our Default MoE outperforms standard TopK routing in a variety of settings without requiring significant computational overhead. Code: https://github.com/vatsal0/default-moe.
Authors: Yuta Kambe, Yota Maeda, Tristan Vaccon
Abstract: The intersection of deep learning and symbolic mathematics has seen rapid progress in recent years, exemplified by the work of Lample and Charton. They demonstrated that effective training of machine learning models for solving mathematical problems critically depends on high-quality, domain-specific datasets. In this paper, we address the computation of Gr\"obner basis using Transformers. While a dataset generation method tailored to Transformer-based Gr\"obner basis computation has previously been proposed, it lacked theoretical guarantees regarding the generality or quality of the generated datasets. In this work, we prove that datasets generated by the previously proposed algorithm are sufficiently general, enabling one to ensure that Transformers can learn a sufficiently diverse range of Gr\"obner bases. Moreover, we propose an extended and generalized algorithm to systematically construct datasets of ideal generators, further enhancing the training effectiveness of Transformer. Our results provide a rigorous geometric foundation for Transformers to address a mathematical problem, which is an answer to Lample and Charton's idea of training on diverse or representative inputs.
Authors: Shiwei Ding, Lan Zhang, Zhenlin Wang, Giuseppe Ateniese, Xiaoyong Yuan
Abstract: Fine-tuning plays a crucial role in adapting models to downstream tasks with minimal training efforts. However, the rapidly increasing size of foundation models poses a daunting challenge for accommodating foundation model fine-tuning in most commercial devices, which often have limited memory bandwidth. Techniques like model sharding and tensor parallelism address this issue by distributing computation across multiple devices to meet memory requirements. Nevertheless, these methods do not fully leverage their foundation nature in facilitating the fine-tuning process, resulting in high computational costs and imbalanced workloads. We introduce a novel Distributed Dynamic Fine-Tuning (D2FT) framework that strategically orchestrates operations across attention modules based on our observation that not all attention modules are necessary for forward and backward propagation in fine-tuning foundation models. Through three innovative selection strategies, D2FT significantly reduces the computational workload required for fine-tuning foundation models. Furthermore, D2FT addresses workload imbalances in distributed computing environments by optimizing these selection strategies via multiple knapsack optimization. Our experimental results demonstrate that the proposed D2FT framework reduces the training computational costs by 40% and training communication costs by 50% with only 1% to 2% accuracy drops on the CIFAR-10, CIFAR-100, and Stanford Cars datasets. Moreover, the results show that D2FT can be effectively extended to recent LoRA, a state-of-the-art parameter-efficient fine-tuning technique. By reducing 40% computational cost or 50% communication cost, D2FT LoRA top-1 accuracy only drops 4% to 6% on Stanford Cars dataset.
Authors: Nathan Lambert
Abstract: Reinforcement learning from human feedback (RLHF) has become an important technical and storytelling tool to deploy the latest machine learning systems. In this book, we hope to give a gentle introduction to the core methods for people with some level of quantitative background. The book starts with the origins of RLHF -- both in recent literature and in a convergence of disparate fields of science in economics, philosophy, and optimal control. We then set the stage with definitions, problem formulation, data collection, and other common math used in the literature. The core of the book details every optimization stage in using RLHF, from starting with instruction tuning to training a reward model and finally all of rejection sampling, reinforcement learning, and direct alignment algorithms. The book concludes with advanced topics -- understudied research questions in synthetic data and evaluation -- and open questions for the field.
Authors: Kaira M. Samuel, Faez Ahmed
Abstract: Engineering problems that apply machine learning often involve computationally intensive methods but rely on limited datasets. As engineering data evolves with new designs and constraints, models must incorporate new knowledge over time. However, high computational costs make retraining models from scratch infeasible. Continual learning (CL) offers a promising solution by enabling models to learn from sequential data while mitigating catastrophic forgetting, where a model forgets previously learned mappings. This work introduces CL to engineering design by benchmarking several CL methods on representative regression tasks. We apply these strategies to five engineering datasets and construct nine new engineering CL benchmarks to evaluate their ability to address forgetting and improve generalization. Preliminary results show that applying existing CL methods to these tasks improves performance over naive baselines. In particular, the Replay strategy achieved performance comparable to retraining in several benchmarks while reducing training time by nearly half, demonstrating its potential for real-world engineering workflows. The code and datasets used in this work will be available at: https://github.com/kmsamuel/cl-for-engineering-release.
URLs: https://github.com/kmsamuel/cl-for-engineering-release.
Authors: Junyang Zhang, Tianyi Zhu, Cheng Luo, Anima Anandkumar
Abstract: Long-context language models exhibit impressive performance but remain challenging to deploy due to high GPU memory demands during inference. We propose Memory-efficient Offloaded Mini-sequence Inference (MOM), a method that partitions critical layers into smaller "mini-sequences" and integrates seamlessly with KV cache offloading. Experiments on various Llama, Qwen, and Mistral models demonstrate that MOM reduces peak memory usage by over 50\% on average. On Meta-Llama-3.2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU, while keeping outputs identical and not compromising accuracy. MOM also maintains highly competitive throughput due to minimal computational overhead and efficient last-layer processing. Compared to traditional chunked prefill methods, MOM achieves a 35\% greater context length extension. More importantly, our method drastically reduces prefill memory consumption, eliminating it as the longstanding dominant memory bottleneck during inference. This breakthrough fundamentally changes research priorities, redirecting future efforts from prefill-stage optimizations to improving decode-stage residual KV cache efficiency.
Authors: John J. Vastola
Abstract: How diffusion models generalize beyond their training set is not known, and is somewhat mysterious given two facts: the optimum of the denoising score matching (DSM) objective usually used to train diffusion models is the score function of the training distribution; and the networks usually used to learn the score function are expressive enough to learn this score to high accuracy. We claim that a certain feature of the DSM objective -- the fact that its target is not the training distribution's score, but a noisy quantity only equal to it in expectation -- strongly impacts whether and to what extent diffusion models generalize. In this paper, we develop a mathematical theory that partly explains this 'generalization through variance' phenomenon. Our theoretical analysis exploits a physics-inspired path integral approach to compute the distributions typically learned by a few paradigmatic under- and overparameterized diffusion models. We find that the distributions diffusion models effectively learn to sample from resemble their training distributions, but with 'gaps' filled in, and that this inductive bias is due to the covariance structure of the noisy target used during training. We also characterize how this inductive bias interacts with feature-related inductive biases.
Authors: Siow Meng Low, Akshat Kumar
Abstract: In safe reinforcement learning (RL), auxiliary safety costs are used to align the agent to safe decision making. In practice, safety constraints, including cost functions and budgets, are unknown or hard to specify, as it requires anticipation of all possible unsafe behaviors. We therefore address a general setting where the true safety definition is unknown, and has to be learned from sparsely labeled data. Our key contributions are: first, we design a safety model that performs credit assignment to estimate each decision step's impact on the overall safety using a dataset of diverse trajectories and their corresponding binary safety labels (i.e., whether the corresponding trajectory is safe/unsafe). Second, we illustrate the architecture of our safety model to demonstrate its ability to learn a separate safety score for each timestep. Third, we reformulate the safe RL problem using the proposed safety model and derive an effective algorithm to optimize a safe yet rewarding policy. Finally, our empirical results corroborate our findings and show that this approach is effective in satisfying unknown safety definition, and scalable to various continuous control tasks.
Authors: Emil Ryd, Grey Nearing
Abstract: Floods are the most common form of natural disaster and accurate flood forecasting is essential for early warning systems. Previous work has shown that machine learning (ML) models are a promising way to improve flood predictions when trained on large, geographically-diverse datasets. This requirement of global training can result in a loss of ownership for national forecasters who cannot easily adapt the models to improve performance in their region, preventing ML models from being operationally deployed. Furthermore, traditional hydrology research with physics-based models suggests that local data -- which in many cases is only accessible to local agencies -- is valuable for improving model performance. To address these concerns, we demonstrate a methodology of pre-training a model on a large, global dataset and then fine-tuning that model on data from individual basins. This results in performance increases, validating our hypothesis that there is extra information to be captured in local data. In particular, we show that performance increases are most significant in watersheds that underperform during global training. We provide a roadmap for national forecasters who wish to take ownership of global models using their own data, aiming to lower the barrier to operational deployment of ML-based hydrological forecast systems.
Authors: Akira Tamamori
Abstract: Hebbian learning limits Hopfield network capacity. While kernel methods like Kernel Logistic Regression (KLR) improve performance via iterative learning, we propose Kernel Ridge Regression (KRR) as an alternative. KRR learns dual variables non-iteratively via a closed-form solution, offering significant learning speed advantages. We show KRR achieves comparably high storage capacity (reaching ratio 1.5 shown) and noise robustness (recalling from around 80% corrupted patterns) as KLR, while drastically reducing training time, establishing KRR as an efficient method for building high-performance associative memories.
Authors: Zelal Su "Lain" Mustafaoglu, Keshav Pingali, Risto Miikkulainen
Abstract: A key challenge in reinforcement learning (RL) is managing the exploration-exploitation trade-off without sacrificing sample efficiency. Policy gradient (PG) methods excel in exploitation through fine-grained, gradient-based optimization but often struggle with exploration due to their focus on local search. In contrast, evolutionary computation (EC) methods excel in global exploration, but lack mechanisms for exploitation. To address these limitations, this paper proposes Evolutionary Policy Optimization (EPO), a hybrid algorithm that integrates neuroevolution with policy gradient methods for policy optimization. EPO leverages the exploration capabilities of EC and the exploitation strengths of PG, offering an efficient solution to the exploration-exploitation dilemma in RL. EPO is evaluated on the Atari Pong and Breakout benchmarks. Experimental results show that EPO improves both policy quality and sample efficiency compared to standard PG and EC methods, making it effective for tasks that require both exploration and local optimization.
Authors: You Rim Choi, Subeom Park, Seojun Heo, Eunchung Noh, Hyung-Sin Kim
Abstract: Open-Set Semi-Supervised Learning (OSSL) tackles the practical challenge of learning from unlabeled data that may include both in-distribution (ID) and unknown out-of-distribution (OOD) classes. However, existing OSSL methods form suboptimal feature spaces by either excluding OOD samples, interfering with them, or overtrusting their information during training. In this work, we introduce MagMatch, a novel framework that naturally isolates OOD samples through a prototype-based contrastive learning paradigm. Unlike conventional methods, MagMatch does not assign any prototypes to OOD samples; instead, it selectively aligns ID samples with class prototypes using an ID-Selective Magnetic (ISM) module, while allowing OOD samples - the "others" - to remain unaligned in the feature space. To support this process, we propose Selective Magnetic Alignment (SMA) loss for unlabeled data, which dynamically adjusts alignment based on sample confidence. Extensive experiments on diverse datasets demonstrate that MagMatch significantly outperforms existing methods in both closed-set classification accuracy and OOD detection AUROC, especially in generalizing to unseen OOD data.
Authors: Leming Wu, Yaochu Jin, Kuangrong Hao, Han Yu
Abstract: Federated learning (FL) enables collaborative training of deep learning models without requiring data to leave local clients, thereby preserving client privacy. The aggregation process on the server plays a critical role in the performance of the resulting FL model. The most commonly used aggregation method is weighted averaging based on the amount of data from each client, which is thought to reflect each client's contribution. However, this method is prone to model bias, as dishonest clients might report inaccurate training data volumes to the server, which is hard to verify. To address this issue, we propose a novel secure \underline{Fed}erated \underline{D}ata q\underline{u}antity-\underline{a}ware weighted averaging method (FedDua). It enables FL servers to accurately predict the amount of training data from each client based on their local model gradients uploaded. Furthermore, it can be seamlessly integrated into any FL algorithms that involve server-side model aggregation. Extensive experiments on three benchmarking datasets demonstrate that FedDua improves the global model performance by an average of 3.17% compared to four popular FL aggregation methods in the presence of inaccurate client data volume declarations.
Authors: Benjamin C. Koenig, Suyong Kim, Sili Deng
Abstract: Efficient chemical kinetic model inference and application for combustion problems is challenging due to large ODE systems and wideley separated time scales. Machine learning techniques have been proposed to streamline these models, though strong nonlinearity and numerical stiffness combined with noisy data sources makes their application challenging. The recently developed Kolmogorov-Arnold Networks (KANs) and KAN ordinary differential equations (KAN-ODEs) have been demonstrated as powerful tools for scientific applications thanks to their rapid neural scaling, improved interpretability, and smooth activation functions. Here, we develop ChemKANs by augmenting the KAN-ODE framework with physical knowledge of the flow of information through the relevant kinetic and thermodynamic laws, as well as an elemental conservation loss term. This novel framework encodes strong inductive bias that enables streamlined training and higher accuracy predictions, while facilitating parameter sparsity through full sharing of information across all inputs and outputs. In a model inference investigation, we find that ChemKANs exhibit no overfitting or model degradation when tasked with extracting predictive models from data that is both sparse and noisy, a task that a standard DeepONet struggles to accomplish. Next, we find that a remarkably parameter-lean ChemKAN (only 344 parameters) can accurately represent hydrogen combustion chemistry, providing a 2x acceleration over the detailed chemistry in a solver that is generalizable to larger-scale turbulent flow simulations. These demonstrations indicate potential for ChemKANs in combustion physics and chemical kinetics, and demonstrate the scalability of generic KAN-ODEs in significantly larger and more numerically challenging problems than previously studied.
Authors: Kewen Peng, Hao Zhuo, Yicheng Yang, Tim Menzies
Abstract: Discrimination-aware classification aims to make accurate predictions while satisfying fairness constraints. Traditional decision tree learners typically optimize for information gain in the target attribute alone, which can result in models that unfairly discriminate against protected social groups (e.g., gender, ethnicity). Motivated by these shortcomings, we propose GroupCART, a tree-based ensemble optimizer that avoids bias during model construction by optimizing not only for decreased entropy in the target attribute but also for increased entropy in protected attributes. Our experiments show that GroupCART achieves fairer models without data transformation and with minimal performance degradation. Furthermore, the method supports customizable weighting, offering a smooth and flexible trade-off between predictive performance and fairness based on user requirements. These results demonstrate that algorithmic bias in decision tree models can be mitigated through multi-task, fairness-aware learning. All code and datasets used in this study are available at: https://github.com/anonymous12138/groupCART.
Authors: Liheng Ma, Soumyasundar Pal, Yingxue Zhang, Philip H. S. Torr, Mark Coates
Abstract: Transformers have attained outstanding performance across various modalities, employing scaled-dot-product (SDP) attention mechanisms. Researchers have attempted to migrate Transformers to graph learning, but most advanced Graph Transformers are designed with major architectural differences, either integrating message-passing or incorporating sophisticated attention mechanisms. These complexities prevent the easy adoption of Transformer training advances. We propose three simple modifications to the plain Transformer to render it applicable to graphs without introducing major architectural distortions. Specifically, we advocate for the use of (1) simplified $L_2$ attention to measure the magnitude closeness of tokens; (2) adaptive root-mean-square normalization to preserve token magnitude information; and (3) a relative positional encoding bias with a shared encoder. Significant performance gains across a variety of graph datasets justify the effectiveness of our proposed modifications. Furthermore, empirical evaluation on the expressiveness benchmark reveals noteworthy realized expressiveness in the graph isomorphism.
Authors: Huaizhi Qu, Inyoung Choi, Zhen Tan, Song Wang, Sukwon Yun, Qi Long, Faizan Siddiqui, Kwonjoon Lee, Tianlong Chen
Abstract: LLM ensembles are widely used for LLM judges. However, how to estimate their accuracy, especially in an efficient way, is unknown. In this paper, we present a principled maximum a posteriori (MAP) framework for an economical and precise estimation of the performance of LLM ensemble judgment. We first propose a mixture of Beta-Binomial distributions to model the judgment distribution, revising from the vanilla Binomial distribution. Next, we introduce a conformal prediction-driven approach that enables adaptive stopping during iterative sampling to balance accuracy with efficiency. Furthermore, we design a prior transfer mechanism that utilizes learned distributions on open-source datasets to improve estimation on a target dataset when only scarce annotations are available. Finally, we present BetaConform, a framework that integrates our distribution assumption, adaptive stopping, and the prior transfer mechanism to deliver a theoretically guaranteed distribution estimation of LLM ensemble judgment with minimum labeled samples. BetaConform is also validated empirically. For instance, with only 10 samples from the TruthfulQA dataset, for a Llama ensembled judge, BetaConform gauges its performance with error margin as small as 3.37%.
Authors: Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler
Abstract: Constraint-based causal discovery algorithms utilize many statistical tests for conditional independence to uncover networks of causal dependencies. These approaches to causal discovery rely on an assumed correspondence between the graphical properties of a causal structure and the conditional independence properties of observed variables, known as the causal Markov condition and faithfulness. Finite data yields an empirical distribution that is "close" to the actual distribution. Across these many possible empirical distributions, the correspondence to the graphical properties can break down for different conditional independencies, and multiple violations can occur at the same time. We study this "meta-dependence" between conditional independence properties using the following geometric intuition: each conditional independence property constrains the space of possible joint distributions to a manifold. The "meta-dependence" between conditional independences is informed by the position of these manifolds relative to the true probability distribution. We provide a simple-to-compute measure of this meta-dependence using information projections and consolidate our findings empirically using both synthetic and real-world data.
Authors: Ruinan Jin, Difei Cheng, Hong Qiao, Xin Shi, Shaodong Liu, Bo Zhang
Abstract: Stochastic Gradient Descent (SGD) is widely used in machine learning research. Previous convergence analyses of SGD under the vanishing step-size setting typically require Robbins-Monro conditions. However, in practice, a wider variety of step-size schemes are frequently employed, yet existing convergence results remain limited and often rely on strong assumptions. This paper bridges this gap by introducing a novel analytical framework based on a stopping-time method, enabling asymptotic convergence analysis of SGD under more relaxed step-size conditions and weaker assumptions. In the non-convex setting, we prove the almost sure convergence of SGD iterates for step-sizes $ \{ \epsilon_t \}_{t \geq 1} $ satisfying $\sum_{t=1}^{+\infty} \epsilon_t = +\infty$ and $\sum_{t=1}^{+\infty} \epsilon_t^p < +\infty$ for some $p > 2$. Compared with previous studies, our analysis eliminates the global Lipschitz continuity assumption on the loss function and relaxes the boundedness requirements for higher-order moments of stochastic gradients. Building upon the almost sure convergence results, we further establish $L_2$ convergence. These significantly relaxed assumptions make our theoretical results more general, thereby enhancing their applicability in practical scenarios.
Authors: Akshata Hegde, Tom Nguyen, Jianlin Cheng
Abstract: Gene Regulatory Networks (GRNs) are intricate biological systems that control gene expression and regulation in response to environmental and developmental cues. Advances in computational biology, coupled with high throughput sequencing technologies, have significantly improved the accuracy of GRN inference and modeling. Modern approaches increasingly leverage artificial intelligence (AI), particularly machine learning techniques including supervised, unsupervised, semi-supervised, and contrastive learning to analyze large scale omics data and uncover regulatory gene interactions. To support both the application of GRN inference in studying gene regulation and the development of novel machine learning methods, we present a comprehensive review of machine learning based GRN inference methodologies, along with the datasets and evaluation metrics commonly used. Special emphasis is placed on the emerging role of cutting edge deep learning techniques in enhancing inference performance. The potential future directions for improving GRN inference are also discussed.
Authors: Tirtha Vinchurkar, Kareem Abdelmaqsoud, John R. Kitchin
Abstract: Machine-learned potentials (MLPs) have revolutionized materials discovery by providing accurate and efficient predictions of molecular and material properties. Graph Neural Networks (GNNs) have emerged as a state-of-the-art approach due to their ability to capture complex atomic interactions. However, GNNs often produce unreliable predictions when encountering out-of-domain data and it is difficult to identify when that happens. To address this challenge, we explore Uncertainty Quantification (UQ) techniques, focusing on Direct Propagation of Shallow Ensembles (DPOSE) as a computationally efficient alternative to deep ensembles. By integrating DPOSE into the SchNet model, we assess its ability to provide reliable uncertainty estimates across diverse Density Functional Theory datasets, including QM9, OC20, and Gold Molecular Dynamics. Our findings often demonstrate that DPOSE successfully distinguishes between in-domain and out-of-domain samples, exhibiting higher uncertainty for unobserved molecule and material classes. This work highlights the potential of lightweight UQ methods in improving the robustness of GNN-based materials modeling and lays the foundation for future integration with active learning strategies.
Authors: Reek Majumder, Mashrur Chowdhury, Sakib Mahmud Khan, Zadid Khan, Fahim Ahmad, Frank Ngeni, Gurcan Comert, Judith Mwakalonge, Dimitra Michalaka
Abstract: Deep learning (DL)-based image classification models are essential for autonomous vehicle (AV) perception modules since incorrect categorization might have severe repercussions. Adversarial attacks are widely studied cyberattacks that can lead DL models to predict inaccurate output, such as incorrectly classified traffic signs by the perception module of an autonomous vehicle. In this study, we create and compare hybrid classical-quantum deep learning (HCQ-DL) models with classical deep learning (C-DL) models to demonstrate robustness against adversarial attacks for perception modules. Before feeding them into the quantum system, we used transfer learning models, alexnet and vgg-16, as feature extractors. We tested over 1000 quantum circuits in our HCQ-DL models for projected gradient descent (PGD), fast gradient sign attack (FGSA), and gradient attack (GA), which are three well-known untargeted adversarial approaches. We evaluated the performance of all models during adversarial attacks and no-attack scenarios. Our HCQ-DL models maintain accuracy above 95\% during a no-attack scenario and above 91\% for GA and FGSA attacks, which is higher than C-DL models. During the PGD attack, our alexnet-based HCQ-DL model maintained an accuracy of 85\% compared to C-DL models that achieved accuracies below 21\%. Our results highlight that the HCQ-DL models provide improved accuracy for traffic sign classification under adversarial settings compared to their classical counterparts.
Authors: Motonobu Uchikoshi, Youhei Akimoto
Abstract: Feature selection is essential for efficient data mining and sometimes encounters the positive-unlabeled (PU) learning scenario, where only a few positive labels are available, while most data remains unlabeled. In certain real-world PU learning tasks, data subjected to adequate feature selection often form clusters with concentrated positive labels. Conventional feature selection methods that treat unlabeled data as negative may fail to capture the statistical characteristics of positive data in such scenarios, leading to suboptimal performance. To address this, we propose a novel feature selection method based on the cluster assumption in PU learning, called FSCPU. FSCPU formulates the feature selection problem as a binary optimization task, with an objective function explicitly designed to incorporate the cluster assumption in the PU learning setting. Experiments on synthetic datasets demonstrate the effectiveness of FSCPU across various data conditions. Moreover, comparisons with 10 conventional algorithms on three open datasets show that FSCPU achieves competitive performance in downstream classification tasks, even when the cluster assumption does not strictly hold.
Authors: Menglan Chen, Xianghe Pang, Jingjing Dong, WenHao Wang, Yaxin Du, Siheng Chen
Abstract: Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards. Inspired by the insight that reasoning across modalities is key to preempting intricate vulnerabilities, we propose a novel direction for VLM safety: multimodal reasoning-driven prompt rewriting. To this end, we introduce VLMGuard-R1, a proactive framework that refines user inputs through a reasoning-guided rewriter, dynamically interpreting text-image interactions to deliver refined prompts that bolster safety across diverse VLM architectures without altering their core parameters. To achieve this, we devise a three-stage reasoning pipeline to synthesize a dataset that trains the rewriter to infer subtle threats, enabling tailored, actionable responses over generic refusals. Extensive experiments across three benchmarks with five VLMs reveal that VLMGuard-R1 outperforms four baselines. In particular, VLMGuard-R1 achieves a remarkable 43.59\% increase in average safety across five models on the SIUO benchmark.
Authors: Siwei Huang, Chenhao Yang, Chuan Hu
Abstract: Drivers' perception of risk determines their acceptance, trust, and use of the Automated Driving Systems (ADSs). However, perceived risk is subjective and difficult to evaluate using existing methods. To address this issue, a driver's subjective perceived risk (DSPR) model is proposed, regarding perceived risk as a dynamically triggered mechanism with anisotropy and attenuation. 20 participants are recruited for a driver-in-the-loop experiment to report their real-time subjective risk ratings (SRRs) when experiencing various automatic driving scenarios. A convolutional neural network and bidirectional long short-term memory network with temporal pattern attention (CNN-Bi-LSTM-TPA) is embedded into a semi-supervised learning strategy to predict SRRs, aiming to reduce data noise caused by subjective randomness of participants. The results illustrate that DSPR achieves the highest prediction accuracy of 87.91% in predicting SRRs, compared to three state-of-the-art risk models. The semi-supervised strategy improves accuracy by 20.12%. Besides, CNN-Bi-LSTM-TPA network presents the highest accuracy among four different LSTM structures. This study offers an effective method for assessing driver's perceived risk, providing support for the safety enhancement of ADS and driver's trust improvement.
Authors: Pengtao Dang, Tingbo Guo, Sha Cao, Chi Zhang
Abstract: A physics-informed neural network (PINN) models the dynamics of a system by integrating the governing physical laws into the architecture of a neural network. By enforcing physical laws as constraints, PINN overcomes challenges with data scarsity and potentially high dimensionality. Existing PINN frameworks rely on fully observed time-course data, the acquisition of which could be prohibitive for many systems. In this study, we developed a new PINN learning paradigm, namely Constrained Learning, that enables the approximation of first-order derivatives or motions using non-time course or partially observed data. Computational principles and a general mathematical formulation of Constrained Learning were developed. We further introduced MPOCtrL (Message Passing Optimization-based Constrained Learning) an optimization approach tailored for the Constrained Learning framework that strives to balance the fitting of physical models and observed data. Its code is available at github link: https://github.com/ptdang1001/MPOCtrL Experiments on synthetic and real-world data demonstrated that MPOCtrL can effectively detect the nonlinear dependency between observed data and the underlying physical properties of the system. In particular, on the task of metabolic flux analysis, MPOCtrL outperforms all existing data-driven flux estimators.
Authors: Hyunji Jung, Hanseul Cho, Chulhee Yun
Abstract: We study continual learning on multiple linear classification tasks by sequentially running gradient descent (GD) for a fixed budget of iterations per task. When all tasks are jointly linearly separable and are presented in a cyclic/random order, we show the directional convergence of the trained linear classifier to the joint (offline) max-margin solution. This is surprising because GD training on a single task is implicitly biased towards the individual max-margin solution for the task, and the direction of the joint max-margin solution can be largely different from these individual solutions. Additionally, when tasks are given in a cyclic order, we present a non-asymptotic analysis on cycle-averaged forgetting, revealing that (1) alignment between tasks is indeed closely tied to catastrophic forgetting and backward knowledge transfer and (2) the amount of forgetting vanishes to zero as the cycle repeats. Lastly, we analyze the case where the tasks are no longer jointly separable and show that the model trained in a cyclic order converges to the unique minimum of the joint loss function.
Authors: Long Zeng, Jianxiang Yu, Jiapeng Zhu, Qingsong Zhong, Xiang Li
Abstract: Graph self-supervised learning has gained significant attention recently. However, many existing approaches heavily depend on perturbations, and inappropriate perturbations may corrupt the graph's inherent information. The Vector Quantized Variational Autoencoder (VQ-VAE) is a powerful autoencoder extensively used in fields such as computer vision; however, its application to graph data remains underexplored. In this paper, we provide an empirical analysis of vector quantization in the context of graph autoencoders, demonstrating its significant enhancement of the model's capacity to capture graph topology. Furthermore, we identify two key challenges associated with vector quantization when applying in graph data: codebook underutilization and codebook space sparsity. For the first challenge, we propose an annealing-based encoding strategy that promotes broad code utilization in the early stages of training, gradually shifting focus toward the most effective codes as training progresses. For the second challenge, we introduce a hierarchical two-layer codebook that captures relationships between embeddings through clustering. The second layer codebook links similar codes, encouraging the model to learn closer embeddings for nodes with similar features and structural topology in the graph. Our proposed model outperforms 16 representative baseline methods in self-supervised link prediction and node classification tasks across multiple datasets.
Authors: Yihang Lu, Yangyang Xu, Qitao Qing, Xianwei Meng
Abstract: Recent deep learning models for Long-term Time Series Forecasting (LTSF) often emphasize complex, handcrafted designs, while simpler architectures like linear models or MLPs have often outperformed these intricate solutions. In this paper, we revisit and organize the core ideas behind several key techniques, such as redundancy reduction and multi-scale modeling, which are frequently employed in advanced LTSF models. Our goal is to streamline these ideas for more efficient deep learning utilization. To this end, we introduce TimeCapsule, a model built around the principle of high-dimensional information compression that unifies these techniques in a generalized yet simplified framework. Specifically, we model time series as a 3D tensor, incorporating temporal, variate, and level dimensions, and leverage mode production to capture multi-mode dependencies while achieving dimensionality compression. We propose an internal forecast within the compressed representation domain, supported by the Joint-Embedding Predictive Architecture (JEPA), to monitor the learning of predictive representations. Extensive experiments on challenging benchmarks demonstrate the versatility of our method, showing that TimeCapsule can achieve state-of-the-art performance.
Authors: Yifan Cao, Zhilong Mi, Ziqiao Yin, Binghui Guo, Jin Dong
Abstract: As artificial intelligence methods are increasingly applied to complex task scenarios, high dimensional multi-label learning has emerged as a prominent research focus. At present, the curse of dimensionality remains one of the major bottlenecks in high-dimensional multi-label learning, which can be effectively addressed through multi-label feature selection methods. However, existing multi-label feature selection methods mostly focus on identifying global features shared across all labels, which overlooks personalized characteristics and specific requirements of individual labels. This global-only perspective may limit the ability to capture label-specific discriminative information, thereby affecting overall performance. In this paper, we propose a novel method called GPMFS (Global Foundation and Personalized Optimization for Multi-Label Feature Selection). GPMFS firstly identifies global features by exploiting label correlations, then adaptively supplements each label with a personalized subset of discriminative features using a threshold-controlled strategy. Experiments on multiple real-world datasets demonstrate that GPMFS achieves superior performance while maintaining strong interpretability and robustness. Furthermore, GPMFS provides insights into the label-specific strength across different multi-label datasets, thereby demonstrating the necessity and potential applicability of personalized feature selection approaches.
Authors: Yuan Zhou, Xinli Shi, Xuelong Li, Jiachen Zhong, Guanghui Wen, Jinde Cao
Abstract: Decentralized Federated Learning (DFL) eliminates the reliance on the server-client architecture inherent in traditional federated learning, attracting significant research interest in recent years. Simultaneously, the objective functions in machine learning tasks are often nonconvex and frequently incorporate additional, potentially nonsmooth regularization terms to satisfy practical requirements, thereby forming nonconvex composite optimization problems. Employing DFL methods to solve such general optimization problems leads to the formulation of Decentralized Nonconvex Composite Federated Learning (DNCFL), a topic that remains largely underexplored. In this paper, we propose a novel DNCFL algorithm, termed \bf{DEPOSITUM}. Built upon proximal stochastic gradient tracking, DEPOSITUM mitigates the impact of data heterogeneity by enabling clients to approximate the global gradient. The introduction of momentums in the proximal gradient descent step, replacing tracking variables, reduces the variance introduced by stochastic gradients. Additionally, DEPOSITUM supports local updates of client variables, significantly reducing communication costs. Theoretical analysis demonstrates that DEPOSITUM achieves an expected $\epsilon$-stationary point with an iteration complexity of $\mathcal{O}(1/\epsilon^2)$. The proximal gradient, consensus errors, and gradient estimation errors decrease at a sublinear rate of $\mathcal{O}(1/T)$. With appropriate parameter selection, the algorithm achieves network-independent linear speedup without requiring mega-batch sampling. Finally, we apply DEPOSITUM to the training of neural networks on real-world datasets, systematically examining the influence of various hyperparameters on its performance. Comparisons with other federated composite optimization algorithms validate the effectiveness of the proposed method.
Authors: Hao Xu, Xiangru Jian, Xinjian Zhao, Wei Pang, Chao Zhang, Suyuchen Wang, Qixin Zhang, Joao Monteiro, Qiuzhuang Sun, Tianshu Yu
Abstract: In this paper, we presented GraphOmni, a comprehensive benchmark framework for systematically evaluating the graph reasoning capabilities of LLMs. By analyzing critical dimensions, including graph types, serialization formats, and prompt schemes, we provided extensive insights into the strengths and limitations of current LLMs. Our empirical findings emphasize that no single serialization or prompting strategy consistently outperforms others. Motivated by these insights, we propose a reinforcement learning-based approach that dynamically selects the best serialization-prompt pairings, resulting in significant accuracy improvements. GraphOmni's modular and extensible design establishes a robust foundation for future research, facilitating advancements toward general-purpose graph reasoning models.
Authors: Advait Gadhikar, Tom Jacobs, Chao Zhou, Rebekka Burkholz
Abstract: The performance gap between training sparse neural networks from scratch (PaI) and dense-to-sparse training presents a major roadblock for efficient deep learning. According to the Lottery Ticket Hypothesis, PaI hinges on finding a problem specific parameter initialization. As we show, to this end, determining correct parameter signs is sufficient. Yet, they remain elusive to PaI. To address this issue, we propose Sign-In, which employs a dynamic reparameterization that provably induces sign flips. Such sign flips are complementary to the ones that dense-to-sparse training can accomplish, rendering Sign-In as an orthogonal method. While our experiments and theory suggest performance improvements of PaI, they also carve out the main open challenge to close the gap between PaI and dense-to-sparse training.
Authors: Nitin Gupta, Indu Bala, Bapi Dutta, Luis Mart\'inez, Anupam Yadav
Abstract: Swarm intelligence effectively optimizes complex systems across fields like engineering and healthcare, yet algorithm solutions often suffer from low reliability due to unclear configurations and hyperparameters. This study analyzes Particle Swarm Optimization (PSO), focusing on how different communication topologies Ring, Star, and Von Neumann affect convergence and search behaviors. Using an adapted IOHxplainer , an explainable benchmarking tool, we investigate how these topologies influence information flow, diversity, and convergence speed, clarifying the balance between exploration and exploitation. Through visualization and statistical analysis, the research enhances interpretability of PSO's decisions and provides practical guidelines for choosing suitable topologies for specific optimization tasks. Ultimately, this contributes to making swarm based optimization more transparent, robust, and trustworthy.
Authors: Georgios Papadopoulos, Shaltiel Eloul, Yash Satsangi, Jamie Heredge, Niraj Kumar, Chun-Fu Chen, Marco Pistoia
Abstract: The loss landscape of Variational Quantum Neural Networks (VQNNs) is characterized by local minima that grow exponentially with increasing qubits. Because of this, it is more challenging to recover information from model gradients during training compared to classical Neural Networks (NNs). In this paper we present a numerical scheme that successfully reconstructs input training, real-world, practical data from trainable VQNNs' gradients. Our scheme is based on gradient inversion that works by combining gradients estimation with the finite difference method and adaptive low-pass filtering. The scheme is further optimized with Kalman filter to obtain efficient convergence. Our experiments show that our algorithm can invert even batch-trained data, given the VQNN model is sufficiently over-parameterized.
Authors: Vishrut Ramraj, Nithin Nagaraj, Harikrishnan N B
Abstract: In this paper, we explore the application of Permutation Decision Trees (PDT) and strategic trailing for predicting stock market movements and executing profitable trades in the Indian stock market. We focus on high-frequency data using 5-minute candlesticks for the top 50 stocks listed in the NIFTY 50 index. We implement a trading strategy that aims to buy stocks at lower prices and sell them at higher prices, capitalizing on short-term market fluctuations. Due to regulatory constraints in India, short selling is not considered in our strategy. The model incorporates various technical indicators and employs hyperparameters such as the trailing stop-loss value and support thresholds to manage risk effectively. Our results indicate that the proposed trading bot has the potential to outperform the market average and yield returns higher than the risk-free rate offered by 10-year Indian government bonds. We trained and tested data on a 60 day dataset provided by Yahoo Finance. Specifically, 12 days for testing and 48 days for training. Our bot based on permutation decision tree achieved a profit of 1.3468 % over a 12-day testing period, where as a bot based on LSTM gave a return of 0.1238 % over a 12-day testing period and a bot based on RNN gave a return of 0.3096 % over a 12-day testing period. All of the bots outperform the buy-and-hold strategy, which resulted in a loss of 2.2508 %.
Authors: Bal\'azs P. Halmos, Bal\'azs Haj\'os, Vince \'A. Moln\'ar, Marcell T. Kurbucz, Antal Jakov\'ac
Abstract: We introduce ALT, an open-source Python package created for efficient and accurate time series classification (TSC). The package implements the adaptive law-based transformation (ALT) algorithm, which transforms raw time series data into a linearly separable feature space using variable-length shifted time windows. This adaptive approach enhances its predecessor, the linear law-based transformation (LLT), by effectively capturing patterns of varying temporal scales. The software is implemented for scalability, interpretability, and ease of use, achieving state-of-the-art performance with minimal computational overhead. Extensive benchmarking on real-world datasets demonstrates the utility of ALT for diverse TSC tasks in physics and related domains.
Authors: Phung Lai, Xiaopeng Jiang, Hai Phan, Cristian Borcea, Khang Tran, An Chen, Vijaya Datta Mayyuri, Ruoming Jin
Abstract: Federated Learning (FL) allows collaborative training among multiple devices without data sharing, thus enabling privacy-sensitive applications on mobile or Internet of Things (IoT) devices, such as mobile health and asset tracking. However, designing an FL system with good model utility that works with low computation/communication overhead on heterogeneous, resource-constrained mobile/IoT devices is challenging. To address this problem, this paper proposes FedX, a novel adaptive model decomposition and quantization FL system for IoT. To balance utility with resource constraints on IoT devices, FedX decomposes a global FL model into different sub-networks with adaptive numbers of quantized bits for different devices. The key idea is that a device with fewer resources receives a smaller sub-network for lower overhead but utilizes a larger number of quantized bits for higher model utility, and vice versa. The quantization operations in FedX are done at the server to reduce the computational load on devices. FedX iteratively minimizes the losses in the devices' local data and in the server's public data using quantized sub-networks under a regularization term, and thus it maximizes the benefits of combining FL with model quantization through knowledge sharing among the server and devices in a cost-effective training process. Extensive experiments show that FedX significantly improves quantization times by up to 8.43X, on-device computation time by 1.5X, and total end-to-end training time by 1.36X, compared with baseline FL systems. We guarantee the global model convergence theoretically and validate local model convergence empirically, highlighting FedX's optimization efficiency.
Authors: Khaled SH. Raslan, Almohammady S. Alsharkawy, K. R. Raslan
Abstract: Classifying imbalanced datasets remains a significant challenge in machine learning, particularly with big data where instances are unevenly distributed among classes, leading to class imbalance issues that impact classifier performance. While Synthetic Minority Over-sampling Technique (SMOTE) addresses this challenge by generating new instances for the under-represented minority class, it faces obstacles in the form of noise and outliers during the creation of new samples. In this paper, a proposed approach, iHHO-SMOTe, which addresses the limitations of SMOTE by first cleansing the data from noise points. This process involves employing feature selection using a random forest to identify the most valuable features, followed by applying the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to detect outliers based on the selected features. The identified outliers from the minority classes are then removed, creating a refined dataset for subsequent oversampling using the hybrid approach called iHHO-SMOTe. The comprehensive experiments across diverse datasets demonstrate the exceptional performance of the proposed model, with an AUC score exceeding 0.99, a high G-means score of 0.99 highlighting its robustness, and an outstanding F1-score consistently exceeding 0.967. These findings collectively establish Cleansed iHHO-SMOTe as a formidable contender in addressing imbalanced datasets, focusing on noise reduction and outlier handling for improved classification models.
Authors: Phung Lai, Guanxiong Liu, Hai Phan, Issa Khalil, Abdallah Khreishah, Xintao Wu
Abstract: Federated learning (FL) enables collaborative model training using decentralized private data from multiple clients. While FL has shown robustness against poisoning attacks with basic defenses, our research reveals new vulnerabilities stemming from non-independent and identically distributed (non-IID) data among clients. These vulnerabilities pose a substantial risk of model poisoning in real-world FL scenarios. To demonstrate such vulnerabilities, we develop a novel collaborative backdoor poisoning attack called CollaPois. In this attack, we distribute a single pre-trained model infected with a Trojan to a group of compromised clients. These clients then work together to produce malicious gradients, causing the FL model to consistently converge towards a low-loss region centered around the Trojan-infected model. Consequently, the impact of the Trojan is amplified, especially when the benign clients have diverse local data distributions and scattered local gradients. CollaPois stands out by achieving its goals while involving only a limited number of compromised clients, setting it apart from existing attacks. Also, CollaPois effectively avoids noticeable shifts or degradation in the FL model's performance on legitimate data samples, allowing it to operate stealthily and evade detection by advanced robust FL algorithms. Thorough theoretical analysis and experiments conducted on various benchmark datasets demonstrate the superiority of CollaPois compared to state-of-the-art backdoor attacks. Notably, CollaPois bypasses existing backdoor defenses, especially in scenarios where clients possess diverse data distributions. Moreover, the results show that CollaPois remains effective even when involving a small number of compromised clients. Notably, clients whose local data is closely aligned with compromised clients experience higher risks of backdoor infections.
Authors: Lukas Rauch, Ilyass Moummad, Ren\'e Heinrich, Alexis Joly, Bernhard Sick, Christoph Scholz
Abstract: Masked Autoencoders (MAEs) pretrained on AudioSet fail to capture the fine-grained acoustic characteristics of specialized domains such as bioacoustic monitoring. Bird sound classification is critical for assessing environmental health, yet general-purpose models inadequately address its unique acoustic challenges. To address this, we introduce Bird-MAE, a domain-specialized MAE pretrained on the large-scale BirdSet dataset. We explore adjustments to pretraining, fine-tuning and utilizing frozen representations. Bird-MAE achieves state-of-the-art results across all BirdSet downstream tasks, substantially improving multi-label classification performance compared to the general-purpose Audio-MAE baseline. Additionally, we propose prototypical probing, a parameter-efficient method for leveraging MAEs' frozen representations. Bird-MAE's prototypical probes outperform linear probing by up to 37\% in MAP and narrow the gap to fine-tuning to approximately 3\% on average on BirdSet.
Authors: Tom Jacobs, Chao Zhou, Rebekka Burkholz
Abstract: Implicit bias plays an important role in explaining how overparameterized models generalize well. Explicit regularization like weight decay is often employed in addition to prevent overfitting. While both concepts have been studied separately, in practice, they often act in tandem. Understanding their interplay is key to controlling the shape and strength of implicit bias, as it can be modified by explicit regularization. To this end, we incorporate explicit regularization into the mirror flow framework and analyze its lasting effects on the geometry of the training dynamics, covering three distinct effects: positional bias, type of bias, and range shrinking. Our analytical approach encompasses a broad class of problems, including sparse coding, matrix sensing, single-layer attention, and LoRA, for which we demonstrate the utility of our insights. To exploit the lasting effect of regularization and highlight the potential benefit of dynamic weight decay schedules, we propose to switch off weight decay during training, which can improve generalization, as we demonstrate in experiments.
Authors: Nischal Mainali, Lucas Teixeira
Abstract: Transformer models exhibit remarkable in-context learning (ICL), adapting to novel tasks from examples within their context, yet the underlying mechanisms remain largely mysterious. Here, we provide an exact analytical characterization of ICL emergence by deriving the closed-form stochastic gradient descent (SGD) dynamics for a simplified linear transformer performing regression tasks. Our analysis reveals key properties: (1) a natural separation of timescales directly governed by the input data's covariance structure, leading to staged learning; (2) an exact description of how ICL develops, including fixed points corresponding to learned algorithms and conservation laws constraining the dynamics; and (3) surprisingly nonlinear learning behavior despite the model's linearity. We hypothesize this phenomenology extends to non-linear models. To test this, we introduce theory-inspired macroscopic measures (spectral rank dynamics, subspace stability) and use them to provide mechanistic explanations for (1) the sudden emergence of ICL in attention-only networks and (2) delayed generalization (grokking) in modular arithmetic models. Our work offers an exact dynamical model for ICL and theoretically grounded tools for analyzing complex transformer training.
Authors: Julien Pallage, Antoine Lesage-Landry
Abstract: We propose a new unsupervised anomaly detection method based on the sliced-Wasserstein distance for training data selection in machine learning approaches. Our filtering technique is interesting for decision-making pipelines deploying machine learning models in critical sectors, e.g., power systems, as it offers a conservative data selection and an optimal transport interpretation. To ensure the scalability of our method, we provide two efficient approximations. The first approximation processes reduced-cardinality representations of the datasets concurrently. The second makes use of a computationally light Euclidian distance approximation. Additionally, we open the first dataset showcasing localized critical peak rebate demand response in a northern climate. We present the filtering patterns of our method on synthetic datasets and numerically benchmark our method for training data selection. Finally, we employ our method as part of a first forecasting benchmark for our open-source dataset.
Authors: Daniel Homm, Patrick Carqueville, Christian Eichhorn, Thomas Weikert, Thomas Menard, David A. Plecher, Chris Awai Easthope
Abstract: This study explores the potential of using wrist-worn inertial sensors to automate the labeling of ARAT (Action Research Arm Test) items. While the ARAT is commonly used to assess upper limb motor function, its limitations include subjectivity and time consumption of clinical staff. By using IMU (Inertial Measurement Unit) sensors and MiniROCKET as a time series classification technique, this investigation aims to classify ARAT items based on sensor recordings. We test common preprocessing strategies to efficiently leverage included information in the data. Afterward, we use the best preprocessing to improve the classification. The dataset includes recordings of 45 participants performing various ARAT items. Results show that MiniROCKET offers a fast and reliable approach for classifying ARAT domains, although challenges remain in distinguishing between individual resembling items. Future work may involve improving classification through more advanced machine-learning models and data enhancements.
Authors: Zhenao Song
Abstract: Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs). However, their performance heavily relies on the strategy used to select training points. Conventional adaptive sampling methods, such as residual-based refinement, often require multi-round sampling and repeated retraining of PINNs, leading to computational inefficiency due to redundant points and costly gradient computations-particularly in high-dimensional or high-order derivative scenarios. To address these limitations, we propose RL-PINNs, a reinforcement learning(RL)-driven adaptive sampling framework that enables efficient training with only a single round of sampling. Our approach formulates adaptive sampling as a Markov decision process, where an RL agent dynamically selects optimal training points by maximizing a long-term utility metric. Critically, we replace gradient-dependent residual metrics with a computationally efficient function variation as the reward signal, eliminating the overhead of derivative calculations. Furthermore, we employ a delayed reward mechanism to prioritize long-term training stability over short-term gains. Extensive experiments across diverse PDE benchmarks, including low-regular, nonlinear, high-dimensional, and high-order problems, demonstrate that RL-PINNs significantly outperforms existing residual-driven adaptive methods in accuracy. Notably, RL-PINNs achieve this with negligible sampling overhead, making them scalable to high-dimensional and high-order problems.
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: Yaoyao Ding, Bohan Hou, Xiao Zhang, Allan Lin, Tianqi Chen, Cody Yu Hao, Yida Wang, Gennady Pekhimenko
Abstract: Serving Large Language Models (LLMs) is critical for AI-powered applications but demands substantial computational resources, particularly in memory bandwidth and computational throughput. Low-precision computation has emerged as a key technique to improve efficiency while reducing resource consumption. Existing approaches for generating low-precision kernels are limited to weight bit widths that are powers of two and suffer from suboptimal performance due to high-level GPU programming abstractions. These abstractions restrict critical optimizations, such as fine-grained register management and optimized memory access patterns, which are essential for efficient low-precision computations. In this paper, we introduce a virtual machine (VM) designed for General-Purpose GPU (GPGPU) computing, enabling support for low-precision data types with arbitrary bit widths while maintaining GPU programmability. The proposed VM features a thread-block-level programming model, a hierarchical memory space, a novel algebraic layout system, and extensive support for diverse low-precision data types. VM programs are compiled into highly efficient GPU programs with automatic vectorization and instruction selection. Extensive experiments demonstrate that our VM efficiently supports a full spectrum of low-precision data types, and outperforms state-of-the-art low-precision kernels on their supported types. Compared to existing compilers like Triton and Ladder, as well as hand-optimized kernels such as QuantLLM and Marlin, our VM achieves performance improvements of 1.75x, 2.61x, 1.29x and 1.03x, respectively.
Authors: Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
Abstract: Learning-to-Defer (L2D) enables decision-making systems to improve reliability by selectively deferring uncertain predictions to more competent agents. However, most existing approaches focus exclusively on single-agent deferral, which is often inadequate in high-stakes scenarios that require collective expertise. We propose Top-$k$ Learning-to-Defer, a generalization of the classical two-stage L2D framework that allocates each query to the $k$ most confident agents instead of a single one. To further enhance flexibility and cost-efficiency, we introduce Top-$k(x)$ Learning-to-Defer, an adaptive extension that learns the optimal number of agents to consult for each query, based on input complexity, agent competency distributions, and consultation costs. For both settings, we derive a novel surrogate loss and prove that it is Bayes-consistent and $(\mathcal{R}, \mathcal{G})$-consistent, ensuring convergence to the Bayes-optimal allocation. Notably, we show that the well-established model cascades paradigm arises as a restricted instance of our Top-$k$ and Top-$k(x)$ formulations. Extensive experiments across diverse benchmarks demonstrate the effectiveness of our framework on both classification and regression tasks.
Authors: Yu Wang, Fu-Chieh Chang, Pei-Yuan Wu
Abstract: Chain-of-Thought (CoT) prompting has emerged as a powerful technique to improve in-context learning (ICL) in large language models (LLMs) by breaking complex reasoning into intermediate steps. However, the ability of CoT to generalize under distribution shift remains poorly understood. In this work, we extend a latent-variable framework for CoT prompting and study its behavior on two prototypical out-of-distribution (OOD) scenarios: (i) the latent variables for CoT steps are permuted into novel combinations, and (ii) the latent variables uniformly scaled by a factor. Our experiments demonstrate that CoT inference generalizes effectively to OOD samples whose latent variables closely resemble those seen during training, but its performance degrades as this similarity decreases. These findings provide foundational insights into the strengths and limitations of CoT prompting under OOD conditions and suggest directions for developing more resilient reasoning strategies in future LLMs.
Authors: Yangxin Fan, Haolai Che, Yinghui Wu
Abstract: Graph Neural Networks (GNNs) have demonstrated promising performance in graph analysis. Nevertheless, the inference process of GNNs remains costly, hindering their applications for large graphs. This paper proposes inference-friendly graph compression (IFGC), a graph compression scheme to accelerate GNNs inference. Given a graph $G$ and a GNN $M$, an IFGC computes a small compressed graph $G_c$, to best preserve the inference results of $M$ over $G$, such that the result can be directly inferred by accessing $G_c$ with no or little decompression cost. (1) We characterize IFGC with a class of inference equivalence relation. The relation captures the node pairs in $G$ that are not distinguishable for GNN inference. (2) We introduce three practical specifications of IFGC for representative GNNs: structural preserving compression (SPGC), which computes $G_c$ that can be directly processed by GNN inference without decompression; ($\alpha$, $r$)-compression, that allows for a configurable trade-off between compression ratio and inference quality, and anchored compression that preserves inference results for specific nodes of interest. For each scheme, we introduce compression and inference algorithms with guarantees of efficiency and quality of the inferred results. We conduct extensive experiments on diverse sets of large-scale graphs, which verifies the effectiveness and efficiency of our graph compression approaches.
Authors: Ruizhe Chen, Dongyu Xue, Xiangxin Zhou, Zaixiang Zheng, Xiangxiang Zeng, Quanquan Gu
Abstract: Proteins typically exist in complexes, interacting with other proteins or biomolecules to perform their specific biological roles. Research on single-chain protein modeling has been extensively and deeply explored, with advancements seen in models like the series of ESM and AlphaFold. Despite these developments, the study and modeling of multi-chain proteins remain largely uncharted, though they are vital for understanding biological functions. Recognizing the importance of these interactions, we introduce APM (All-Atom Protein Generative Model), a model specifically designed for modeling multi-chain proteins. By integrating atom-level information and leveraging data on multi-chain proteins, APM is capable of precisely modeling inter-chain interactions and designing protein complexes with binding capabilities from scratch. It also performs folding and inverse-folding tasks for multi-chain proteins. Moreover, APM demonstrates versatility in downstream applications: it achieves enhanced performance through supervised fine-tuning (SFT) while also supporting zero-shot sampling in certain tasks, achieving state-of-the-art results. Code will be released at https://github.com/bytedance/apm.
Authors: Patrik Reizinger, Randall Balestriero, David Klindt, Wieland Brendel
Abstract: Self-Supervised Learning (SSL) powers many current AI systems. As research interest and investment grow, the SSL design space continues to expand. The Platonic view of SSL, following the Platonic Representation Hypothesis (PRH), suggests that despite different methods and engineering approaches, all representations converge to the same Platonic ideal. However, this phenomenon lacks precise theoretical explanation. By synthesizing evidence from Identifiability Theory (IT), we show that the PRH can emerge in SSL. However, current IT cannot explain SSL's empirical success. To bridge the gap between theory and practice, we propose expanding IT into what we term Singular Identifiability Theory (SITh), a broader theoretical framework encompassing the entire SSL pipeline. SITh would allow deeper insights into the implicit data assumptions in SSL and advance the field towards learning more interpretable and generalizable representations. We highlight three critical directions for future research: 1) training dynamics and convergence properties of SSL; 2) the impact of finite samples, batch size, and data diversity; and 3) the role of inductive biases in architecture, augmentations, initialization schemes, and optimizers.
Authors: Kumar Manas, Christian Schlauch, Adrian Paschke, Christian Wirth, Nadja Klein
Abstract: Deep learning-based trajectory prediction models have demonstrated promising capabilities in capturing complex interactions. However, their out-of-distribution generalization remains a significant challenge, particularly due to unbalanced data and a lack of enough data and diversity to ensure robustness and calibration. To address this, we propose SHIFT (Spectral Heteroscedastic Informed Forecasting for Trajectories), a novel framework that uniquely combines well-calibrated uncertainty modeling with informative priors derived through automated rule extraction. SHIFT reformulates trajectory prediction as a classification task and employs heteroscedastic spectral-normalized Gaussian processes to effectively disentangle epistemic and aleatoric uncertainties. We learn informative priors from training labels, which are automatically generated from natural language driving rules, such as stop rules and drivability constraints, using a retrieval-augmented generation framework powered by a large language model. Extensive evaluations over the nuScenes dataset, including challenging low-data and cross-location scenarios, demonstrate that SHIFT outperforms state-of-the-art methods, achieving substantial gains in uncertainty calibration and displacement metrics. In particular, our model excels in complex scenarios, such as intersections, where uncertainty is inherently higher. Project page: https://kumarmanas.github.io/SHIFT/.
Authors: Grigorios G Chrysos, Yongtao Wu, Razvan Pascanu, Philip Torr, Volkan Cevher
Abstract: While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard product. Despite its widespread implementation across various applications, the Hadamard product has not been systematically analyzed as a core architectural primitive. We present the first comprehensive taxonomy of its applications in deep learning, identifying four principal domains: higher-order correlation, multimodal data fusion, dynamic representation modulation, and efficient pairwise operations. The Hadamard product's ability to model nonlinear interactions with linear computational complexity makes it particularly valuable for resource-constrained deployments and edge computing scenarios. We demonstrate its natural applicability in multimodal fusion tasks, such as visual question answering, and its effectiveness in representation masking for applications including image inpainting and pruning. This systematic review not only consolidates existing knowledge about the Hadamard product's role in deep learning architectures but also establishes a foundation for future architectural innovations. Our analysis reveals the Hadamard product as a versatile primitive that offers compelling trade-offs between computational efficiency and representational power, positioning it as a crucial component in the deep learning toolkit.
Authors: Jason Zev Ludmir, Sophia Rebello, Jacob Ruiz, Tirthak Patel
Abstract: Detecting mission-critical anomalous events and data is a crucial challenge across various industries, including finance, healthcare, and energy. Quantum computing has recently emerged as a powerful tool for tackling several machine learning tasks, but training quantum machine learning models remains challenging, particularly due to the difficulty of gradient calculation. The challenge is even greater for anomaly detection, where unsupervised learning methods are essential to ensure practical applicability. To address these issues, we propose Quorum, the first quantum anomaly detection framework designed for unsupervised learning that operates without requiring any training.
Authors: Niamh Mimnagh, Andrew Parnell, Conor McAloon, Jaden Carlson, Maria Guelbenzu, Jonas Brock, Damien Barrett, Guy McGrath, Jamie Tratalos, Rafael Moral
Abstract: Bovine Viral Diarrhoea (BVD) has been the focus of a successful eradication programme in Ireland, with the herd-level prevalence declining from 11.3% in 2013 to just 0.2% in 2023. As the country moves toward BVD freedom, the development of predictive models for targeted surveillance becomes increasingly important to mitigate the risk of disease re-emergence. In this study, we evaluate the performance of a range of machine learning algorithms, including binary classification and anomaly detection techniques, for predicting BVD-positive herds using highly imbalanced herd-level data. We conduct an extensive simulation study to assess model performance across varying sample sizes and class imbalance ratios, incorporating resampling, class weighting, and appropriate evaluation metrics (sensitivity, positive predictive value, F1-score and AUC values). Random forests and XGBoost models consistently outperformed other methods, with the random forest model achieving the highest sensitivity and AUC across scenarios, including real-world prediction of 2023 herd status, correctly identifying 219 of 250 positive herds while halving the number of herds that require compared to a blanket-testing strategy.
Authors: Kristen Goebel, Paola Pesantez-Cabrera, Markus Keller, Alan Fern
Abstract: Cold temperatures can cause significant frost damage to fruit crops depending on their resilience, or cold hardiness, which changes throughout the dormancy season. This has led to the development of predictive cold-hardiness models, which help farmers decide when to deploy expensive frost-mitigation measures. Unfortunately, cold-hardiness data for model training is only available for some fruit cultivars due to the need for specialized equipment and expertise. Rather, farmers often do have years of phenological data (e.g. date of budbreak) that they regularly collect for their crops. In this work, we introduce a new transfer-learning framework, Transfer via Auxiliary Labels (TAL), that allows farmers to leverage the phenological data to produce more accurate cold-hardiness predictions, even when no cold-hardiness data is available for their specific crop. The framework assumes a set of source tasks (cultivars) where each has associated primary labels (cold hardiness) and auxiliary labels (phenology). However, the target task (new cultivar) is assumed to only have the auxiliary labels. The goal of TAL is to predict primary labels for the target task via transfer from the source tasks. Surprisingly, despite the vast literature on transfer learning, to our knowledge, the TAL formulation has not been previously addressed. Thus, we propose several new TAL approaches based on model selection and averaging that can leverage recent deep multi-task models for cold-hardiness prediction. Our results on real-world cold-hardiness and phenological data for multiple grape cultivars demonstrate that TAL can leverage the phenological data to improve cold-hardiness predictions in the absence of cold-hardiness data.
Authors: Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iv\'an Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov
Abstract: How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of meaningful and lasting evaluation standards, we propose MIB, a benchmark with two tracks spanning four tasks and five models. MIB favors methods that precisely and concisely recover relevant causal pathways or specific causal variables in neural language models. The circuit localization track compares methods that locate the model components - and connections between them - most important for performing a task (e.g., attribution patching or information flow routes). The causal variable localization track compares methods that featurize a hidden vector, e.g., sparse autoencoders (SAEs) or distributed alignment search (DAS), and locate model features for a causal variable relevant to the task. Using MIB, we find that attribution and mask optimization methods perform best on circuit localization. For causal variable localization, we find that the supervised DAS method performs best, while SAE features are not better than neurons, i.e., standard dimensions of hidden vectors. These findings illustrate that MIB enables meaningful comparisons of methods, and increases our confidence that there has been real progress in the field.
Authors: Ali Behrouz, Meisam Razaviyayn, Peilin Zhong, Vahab Mirrokni
Abstract: Designing efficient and effective architectural backbones has been in the core of research efforts to enhance the capability of foundation models. Inspired by the human cognitive phenomenon of attentional bias-the natural tendency to prioritize certain events or stimuli-we reconceptualize neural architectures, including Transformers, Titans, and modern linear recurrent neural networks as associative memory modules that learn a mapping of keys and values using an internal objective, referred to as attentional bias. Surprisingly, we observed that most existing sequence models leverage either (1) dot-product similarity, or (2) L2 regression objectives as their attentional bias. Going beyond these objectives, we present a set of alternative attentional bias configurations along with their effective approximations to stabilize their training procedure. We then reinterpret forgetting mechanisms in modern deep learning architectures as a form of retention regularization, providing a novel set of forget gates for sequence models. Building upon these insights, we present Miras, a general framework to design deep learning architectures based on four choices of: (i) associative memory architecture, (ii) attentional bias objective, (iii) retention gate, and (iv) memory learning algorithm. We present three novel sequence models-Moneta, Yaad, and Memora-that go beyond the power of existing linear RNNs while maintaining a fast parallelizable training process. Our experiments show different design choices in Miras yield models with varying strengths. For example, certain instances of Miras achieve exceptional performance in special tasks such as language modeling, commonsense reasoning, and recall intensive tasks, even outperforming Transformers and other modern linear recurrent models.
Authors: Evan Casey, Tianyu Zhang, Shu Ishida, John Roger Thompson, Amir Khasahmadi, Joseph George Lambourne, Pradeep Kumar Jayaraman, Karl D. D. Willis
Abstract: We adapt alignment techniques from reasoning LLMs to the task of generating engineering sketch constraints found in computer-aided design (CAD) models. Engineering sketches consist of geometric primitives (e.g. points, lines) connected by constraints (e.g. perpendicular, tangent) that define the relationships between them. For a design to be easily editable, the constraints must effectively capture design intent, ensuring the geometry updates predictably when parameters change. Although current approaches can generate CAD designs, an open challenge remains to align model outputs with design intent, we label this problem `design alignment'. A critical first step towards aligning generative CAD models is to generate constraints which fully-constrain all geometric primitives, without over-constraining or distorting sketch geometry. Using alignment techniques to train an existing constraint generation model with feedback from a constraint solver, we are able to fully-constrain 93% of sketches compared to 34% when using a na\"ive supervised fine-tuning (SFT) baseline and only 8.9% without alignment. Our approach can be applied to any existing constraint generation model and sets the stage for further research bridging alignment strategies between the language and design domains.
Authors: Xin Gao, Qizhi Pei, Zinan Tang, Yu Li, Honglin Lin, Jiang Wu, Conghui He, Lijun Wu
Abstract: While data synthesis and distillation are promising strategies to enhance small language models, current approaches heavily rely on Large Language Models (LLMs), which suffer from high computational costs, environmental inefficiency, and potential biases inherited from monolithic architectures. In contrast, smaller LLMs are more accessible and sustainable, but their individual capabilities often fall short in generating high-quality, diverse, and reliable data. Inspired by collaborative human processes (e.g., peer review), we propose a multiple small LLMs involved framework, GRA, that aggregates specialized roles across small LLMs to iterative refinement and quality control typically achieved by a single large LLM. In this collaborative framework, multiple small LLMs assume distinct roles-Generator, Reviewer, and Adjudicator-to simulate a peer-review-inspired data synthesis pipeline. The Generator proposes initial data samples, the Reviewer critiques their quality and diversity, and the Adjudicator resolves conflicts to finalize the output. By decomposing the synthesis process into specialized sub-tasks, collaborative small LLMs can achieve data-level parity with large LLM-based distillation. Through experiments across multiple benchmarks, we demonstrate that GRA-produced data matches or exceeds the quality of single large LLM outputs, e.g., Qwen-2.5-72B-Instruct. Our results challenge the necessity of monolithic large models for high-quality data synthesis, advocating instead for strategic coordination of smaller agents. Our datasets, models, and code are publicly available at https://github.com/GX-XinGao/GRA.
Authors: Shahriar Noroozizadeh, Jeremy C. Weiss
Abstract: Clinical case reports and discharge summaries may be the most complete and accurate summarization of patient encounters, yet they are finalized, i.e., timestamped after the encounter. Complementary data structured streams become available sooner but suffer from incompleteness. To train models and algorithms on more complete and temporally fine-grained data, we construct a pipeline to phenotype, extract, and annotate time-localized findings within case reports using large language models. We apply our pipeline to generate an open-access textual time series corpus for Sepsis-3 comprising 2,139 case reports from the Pubmed-Open Access (PMOA) Subset. To validate our system, we apply it on PMOA and timeline annotations from I2B2/MIMIC-IV and compare the results to physician-expert annotations. We show high recovery rates of clinical findings (event match rates: O1-preview--0.755, Llama 3.3 70B Instruct--0.753) and strong temporal ordering (concordance: O1-preview--0.932, Llama 3.3 70B Instruct--0.932). Our work characterizes the ability of LLMs to time-localize clinical findings in text, illustrating the limitations of LLM use for temporal reconstruction and providing several potential avenues of improvement via multimodal integration.
Authors: David Anderson, Michaela Anderson, Margret Bjarnadottir, Stephen Mahar, Shriyan Reyya
Abstract: There is a long history of building predictive models in healthcare using tabular data from electronic medical records. However, these models fail to extract the information found in unstructured clinical notes, which document diagnosis, treatment, progress, medications, and care plans. In this study, we investigate how answers generated by GPT-4o-mini (ChatGPT) to simple clinical questions about patients, when given access to the patient's discharge summary, can support patient-level mortality prediction. Using data from 14,011 first-time admissions to the Coronary Care or Cardiovascular Intensive Care Units in the MIMIC-IV Note dataset, we implement a transparent framework that uses GPT responses as input features in logistic regression models. Our findings demonstrate that GPT-based models alone can outperform models trained on standard tabular data, and that combining both sources of information yields even greater predictive power, increasing AUC by an average of 5.1 percentage points and increasing positive predictive value by 29.9 percent for the highest-risk decile. These results highlight the value of integrating large language models (LLMs) into clinical prediction tasks and underscore the broader potential for using LLMs in any domain where unstructured text data remains an underutilized resource.
Authors: Shuo Shuo Liu, Shikun Wang, Yuxuan Chen, Anil K. Rustgi, Ming Yuan, Jianhua Hu
Abstract: Background: Spatial transcriptomics have emerged as a powerful tool in biomedical research because of its ability to capture both the spatial contexts and abundance of the complete RNA transcript profile in organs of interest. However, limitations of the technology such as the relatively low resolution and comparatively insufficient sequencing depth make it difficult to reliably extract real biological signals from these data. To alleviate this challenge, we propose a novel transfer learning framework, referred to as TransST, to adaptively leverage the cell-labeled information from external sources in inferring cell-level heterogeneity of a target spatial transcriptomics data. Results: Applications in several real studies as well as a number of simulation settings show that our approach significantly improves existing techniques. For example, in the breast cancer study, TransST successfully identifies five biologically meaningful cell clusters, including the two subgroups of cancer in situ and invasive cancer; in addition, only TransST is able to separate the adipose tissues from the connective issues among all the studied methods. Conclusions: In summary, the proposed method TransST is both effective and robust in identifying cell subclusters and detecting corresponding driving biomarkers in spatial transcriptomics data.
Authors: Konstantin Grotov, Sergey Titov
Abstract: In this work, we present a benchmark that consists of Jupyter notebooks development trajectories and allows measuring how large language models (LLMs) can leverage runtime information for predicting code output and code generation. We demonstrate that the current generation of LLMs performs poorly on these tasks and argue that there exists a significantly understudied domain in the development of code-based models, which involves incorporating the runtime context.
Authors: Babak Ghassemi, Cassio Fraga-Dantas, Raffaele Gaetano, Dino Ienco, Omid Ghorbanzadeh, Emma Izquierdo-Verdiguier, Francesco Vuolo
Abstract: Land use and land cover mapping from Earth Observation (EO) data is a critical tool for sustainable land and resource management. While advanced machine learning and deep learning algorithms excel at analyzing EO imagery data, they often overlook crucial geospatial metadata information that could enhance scalability and accuracy across regional, continental, and global scales. To address this limitation, we propose BRIDGE-LC (Bi-level Representation Integration for Disentangled GEospatial Land Cover), a novel deep learning framework that integrates multi-scale geospatial information into the land cover classification process. By simultaneously leveraging fine-grained (latitude/longitude) and coarse-grained (biogeographical region) spatial information, our lightweight multi-layer perceptron architecture learns from both during training but only requires fine-grained information for inference, allowing it to disentangle region-specific from region-agnostic land cover features while maintaining computational efficiency. To assess the quality of our framework, we use an open-access in-situ dataset and adopt several competing classification approaches commonly considered for large-scale land cover mapping. We evaluated all approaches through two scenarios: an extrapolation scenario in which training data encompasses samples from all biogeographical regions, and a leave-one-region-out scenario where one region is excluded from training. We also explore the spatial representation learned by our model, highlighting a connection between its internal manifold and the geographical information used during training. Our results demonstrate that integrating geospatial information improves land cover mapping performance, with the most substantial gains achieved by jointly leveraging both fine- and coarse-grained spatial information.
Authors: Namu Kroupa, G\'abor Cs\'anyi, Will Handley
Abstract: In high dimensions, reflective Hamiltonian Monte Carlo with inexact reflections exhibits slow mixing when the particle ensemble is initialised from a Dirac delta distribution and the uniform distribution is targeted. By quantifying the instantaneous non-uniformity of the distribution with the Sinkhorn divergence, we elucidate the principal mechanisms underlying the mixing problems. In spheres and cubes, we show that the collective motion transitions between fluid-like and discretisation-dominated behaviour, with the critical step size scaling as a power law in the dimension. In both regimes, the particles can spontaneously unmix, leading to resonances in the particle density and the aforementioned problems. Additionally, low-dimensional toy models of the dynamics are constructed which reproduce the dominant features of the high-dimensional problem. Finally, the dynamics is contrasted with the exact Hamiltonian particle flow and tuning practices are discussed.
Authors: Nayoung Lee, Minsoo Shin, Asel Sagingalieva, Ayush Joshi Tripathi, Karan Pinto, Alexey Melnikov
Abstract: Accurate prediction and stabilization of blast furnace temperatures are crucial for optimizing the efficiency and productivity of steel production. Traditional methods often struggle with the complex and non-linear nature of the temperature fluctuations within blast furnaces. This paper proposes a novel approach that combines hybrid quantum machine learning with pulverized coal injection control to address these challenges. By integrating classical machine learning techniques with quantum computing algorithms, we aim to enhance predictive accuracy and achieve more stable temperature control. For this we utilized a unique prediction-based optimization method. Our method leverages quantum-enhanced feature space exploration and the robustness of classical regression models to forecast temperature variations and optimize pulverized coal injection values. Our results demonstrate a significant improvement in prediction accuracy over 25 percent and our solution improved temperature stability to +-7.6 degrees of target range from the earlier variance of +-50 degrees, highlighting the potential of hybrid quantum machine learning models in industrial steel production applications.
Authors: Aleix Alcacer, Irene Epifanio, Sebastian Mair, Morten M{\o}rup
Abstract: Archetypal analysis (AA) was originally proposed in 1994 by Adele Cutler and Leo Breiman as a computational procedure to extract the distinct aspects called archetypes in observations with each observational record approximated as a mixture (i.e., convex combination) of these archetypes. AA thereby provides straightforward, interpretable, and explainable representations for feature extraction and dimensionality reduction, facilitating the understanding of the structure of high-dimensional data with wide applications throughout the sciences. However, AA also faces challenges, particularly as the associated optimization problem is non-convex. This survey provides researchers and data mining practitioners an overview of methodologies and opportunities that AA has to offer surveying the many applications of AA across disparate fields of science, as well as best practices for modeling data using AA and limitations. The survey concludes by explaining important future research directions concerning AA.
Authors: Benjamin Krummenacher, Jonas Frey, Turcan Tuna, Olga Vysotska, Marco Hutter
Abstract: Mobile robots on construction sites require accurate pose estimation to perform autonomous surveying and inspection missions. Localization in construction sites is a particularly challenging problem due to the presence of repetitive features such as flat plastered walls and perceptual aliasing due to apartments with similar layouts inter and intra floors. In this paper, we focus on the global re-positioning of a robot with respect to an accurate scanned mesh of the building solely using LiDAR data. In our approach, a neural network is trained on synthetic LiDAR point clouds generated by simulating a LiDAR in an accurate real-life large-scale mesh. We train a diffusion model with a PointNet++ backbone, which allows us to model multiple position candidates from a single LiDAR point cloud. The resulting model can successfully predict the global position of LiDAR in confined and complex sites despite the adverse effects of perceptual aliasing. The learned distribution of potential global positions can provide multi-modal position distribution. We evaluate our approach across five real-world datasets and show the place recognition accuracy of 77% +/-2m on average while outperforming baselines at a factor of 2 in mean error.
Authors: Nikhil Kandpal, Colin Raffel
Abstract: Training a state-of-the-art Large Language Model (LLM) is an increasingly expensive endeavor due to growing computational, hardware, energy, and engineering demands. Yet, an often-overlooked (and seldom paid) expense is the human labor behind these models' training data. Every LLM is built on an unfathomable amount of human effort: trillions of carefully written words sourced from books, academic papers, codebases, social media, and more. This position paper aims to assign a monetary value to this labor and argues that the most expensive part of producing an LLM should be the compensation provided to training data producers for their work. To support this position, we study 64 LLMs released between 2016 and 2024, estimating what it would cost to pay people to produce their training datasets from scratch. Even under highly conservative estimates of wage rates, the costs of these models' training datasets are 10-1000 times larger than the costs to train the models themselves, representing a significant financial liability for LLM providers. In the face of the massive gap between the value of training data and the lack of compensation for its creation, we highlight and discuss research directions that could enable fairer practices in the future.
Authors: Asutay Ozmen, Jo\~ao P. Hespanha, Katie Byl
Abstract: Accurately modeling friction in robotics remains a core challenge, as robotics simulators like Mujoco and PyBullet use simplified friction models or heuristics to balance computational efficiency with accuracy, where these simplifications and approximations can lead to substantial differences between simulated and physical performance. In this paper, we present a physics-informed friction estimation framework that enables the integration of well-established friction models with learnable components-requiring only minimal, generic measurement data. Our approach enforces physical consistency yet retains the flexibility to adapt to real-world complexities. We demonstrate, on an underactuated and nonlinear system, that the learned friction models, trained solely on small and noisy datasets, accurately simulate dynamic friction properties and reduce the sim-to-real gap. Crucially, we show that our approach enables the learned models to be transferable to systems they are not trained on. This ability to generalize across multiple systems streamlines friction modeling for complex, underactuated tasks, offering a scalable and interpretable path toward bridging the sim-to-real gap in robotics and control.
Authors: Jiawei Zhang, Yu Zhang, Wei Xu, Yifei Zhang, Weiran Jiang, Qi Jiao, Yao Ren, Ziyou Song
Abstract: Data-driven methods have shown potential in electric-vehicle battery management tasks such as capacity estimation, but their deployment is bottlenecked by poor performance in data-limited scenarios. Sharing battery data among algorithm developers can enable accurate and generalizable data-driven models. However, an effective battery management framework that simultaneously ensures data privacy and fault tolerance is still lacking. This paper proposes a swarm battery management system that unites a decentralized swarm learning (SL) framework and credibility weight-based model merging mechanism to enhance battery capacity estimation in data-limited scenarios while ensuring data privacy and security. The effectiveness of the SL framework is validated on a dataset comprising 66 commercial LiNiCoAlO2 cells cycled under various operating conditions. Specifically, the capacity estimation performance is validated in four cases, including data-balanced, volume-biased, feature-biased, and quality-biased scenarios. Our results show that SL can enhance the estimation accuracy in all data-limited cases and achieve a similar level of accuracy with central learning where large amounts of data are available.
Authors: Keshav Srinivasan, Dietmar Plenz, Michelle Girvan
Abstract: Reservoir computers (RCs) provide a computationally efficient alternative to deep learning while also offering a framework for incorporating brain-inspired computational principles. By using an internal neural network with random, fixed connections$-$the 'reservoir'$-$and training only the output weights, RCs simplify the training process but remain sensitive to the choice of hyperparameters that govern activation functions and network architecture. Moreover, typical RC implementations overlook a critical aspect of neuronal dynamics: the balance between excitatory and inhibitory (E-I) signals, which is essential for robust brain function. We show that RCs characteristically perform best in balanced or slightly over-inhibited regimes, outperforming excitation-dominated ones. To reduce the need for precise hyperparameter tuning, we introduce a self-adapting mechanism that locally adjusts E/I balance to achieve target neuronal firing rates, improving performance by up to 130% in tasks like memory capacity and time series prediction compared with globally tuned RCs. Incorporating brain-inspired heterogeneity in target neuronal firing rates further reduces the need for fine-tuning hyperparameters and enables RCs to excel across linear and non-linear tasks. These results support a shift from static optimization to dynamic adaptation in reservoir design, demonstrating how brain-inspired mechanisms improve RC performance and robustness while deepening our understanding of neural computation.
Authors: Shravan Chaudhari, Trilokya Akula, Yoon Kim, Tom Blake
Abstract: In this paper, we advance the study of AI-augmented reasoning in the context of Human-Computer Interaction (HCI), psychology and cognitive science, focusing on the critical task of visual perception. Specifically, we investigate the applicability of Multimodal Large Language Models (MLLMs) in this domain. To this end, we leverage established principles and explanations from psychology and cognitive science related to complexity in human visual perception. We use them as guiding principles for the MLLMs to compare and interprete visual content. Our study aims to benchmark MLLMs across various explainability principles relevant to visual perception. Unlike recent approaches that primarily employ advanced deep learning models to predict complexity metrics from visual content, our work does not seek to develop a mere new predictive model. Instead, we propose a novel annotation-free analytical framework to assess utility of MLLMs as cognitive assistants for HCI tasks, using visual perception as a case study. The primary goal is to pave the way for principled study in quantifying and evaluating the interpretability of MLLMs for applications in improving human reasoning capability and uncovering biases in existing perception datasets annotated by humans.
Authors: Dmitry Yarotsky
Abstract: We consider SGD-type optimization on infinite-dimensional quadratic problems with power law spectral conditions. It is well-known that on such problems deterministic GD has loss convergence rates $L_t=O(t^{-\zeta})$, which can be improved to $L_t=O(t^{-2\zeta})$ by using Heavy Ball with a non-stationary Jacobi-based schedule (and the latter rate is optimal among fixed schedules). However, in the mini-batch Stochastic GD setting, the sampling noise causes the Jacobi HB to diverge; accordingly no $O(t^{-2\zeta})$ algorithm is known. In this paper we show that rates up to $O(t^{-2\zeta})$ can be achieved by a generalized stationary SGD with infinite memory. We start by identifying generalized (S)GD algorithms with contours in the complex plane. We then show that contours that have a corner with external angle $\theta\pi$ accelerate the plain GD rate $O(t^{-\zeta})$ to $O(t^{-\theta\zeta})$. For deterministic GD, increasing $\theta$ allows to achieve rates arbitrarily close to $O(t^{-2\zeta})$. However, in Stochastic GD, increasing $\theta$ also amplifies the sampling noise, so in general $\theta$ needs to be optimized by balancing the acceleration and noise effects. We prove that the optimal rate is given by $\theta_{\max}=\min(2,\nu,\tfrac{2}{\zeta+1/\nu})$, where $\nu,\zeta$ are the exponents appearing in the capacity and source spectral conditions. Furthermore, using fast rational approximations of the power functions, we show that ideal corner algorithms can be efficiently approximated by finite-memory algorithms, and demonstrate their practical efficiency on a synthetic problem and MNIST.
Authors: Aochong Oliver Li, Tanya Goyal
Abstract: Large language models (LLMs) encode vast amounts of pre-trained knowledge in their parameters, but updating them as real-world information evolves remains a challenge. Existing methodologies and benchmarks primarily target entity substitutions, failing to capture the full breadth of complex real-world dynamics. In this paper, we introduce Knowledge Update Playground (KUP), an automatic pipeline for simulating realistic knowledge updates reflected in an evidence corpora. KUP's evaluation framework includes direct and indirect probes to both test memorization of updated facts and reasoning over them, for any update learning methods. Next, we present a lightweight method called memory conditioned training (MCT), which conditions tokens in the update corpus on self-generated "memory" tokens during training. Our strategy encourages LLMs to surface and reason over newly memorized knowledge at inference. Our results on two strong LLMs show that (1) KUP benchmark is highly challenging, with the best CPT models achieving $<2\%$ in indirect probing setting (reasoning) and (2) MCT training significantly outperforms prior continued pre-training (CPT) baselines, improving direct probing (memorization) results by up to $25.4\%$.
Authors: Carlos Misael Madrid Padilla, Shitao Fan, Lizhen Lin
Abstract: We propose a robust and scalable framework for variational Bayes (VB) that effectively handles outliers and contamination of arbitrary nature in large datasets. Our approach divides the dataset into disjoint subsets, computes the posterior for each subset, and applies VB approximation independently to these posteriors. The resulting variational posteriors with respect to the subsets are then aggregated using the geometric median of probability measures, computed with respect to the Wasserstein distance. This novel aggregation method yields the Variational Median Posterior (VM-Posterior) distribution. We rigorously demonstrate that the VM-Posterior preserves contraction properties akin to those of the true posterior, while accounting for approximation errors or the variational gap inherent in VB methods. We also provide provable robustness guarantee of the VM-Posterior. Furthermore, we establish a variational Bernstein-von Mises theorem for both multivariate Gaussian distributions with general covariance structures and the mean-field variational family. To facilitate practical implementation, we adapt existing algorithms for computing the VM-Posterior and evaluate its performance through extensive numerical experiments. The results highlight its robustness and scalability, making it a reliable tool for Bayesian inference in the presence of complex, contaminated datasets.
Authors: Iris Ma, Ian Domingo, Alberto Krone-Martins, Pierre Baldi, Cristina V. Lopes
Abstract: To what extent can entire books be extracted from LLMs? Using the Llama 3 70B family of models, and the "prefix-prompting" extraction technique, we were able to auto-regressively reconstruct, with a very high level of similarity, one entire book (Alice's Adventures in Wonderland) from just the first 500 tokens. We were also able to obtain high extraction rates on several other books, piece-wise. However, these successes do not extend uniformly to all books. We show that extraction rates of books correlate with book popularity and thus, likely duplication in the training data. We also confirm the undoing of mitigations in the instruction-tuned Llama 3.1, following recent work (Nasr et al., 2025). We further find that this undoing comes from changes to only a tiny fraction of weights concentrated primarily in the lower transformer blocks. Our results provide evidence of the limits of current regurgitation mitigation strategies and introduce a framework for studying how fine-tuning affects the retrieval of verbatim memorization in aligned LLMs.
Authors: Alejandra Perez, Han Zhang, Yu-Chun Ku, Lalithkumar Seenivasan, Roger Soberanis, Jose L. Porras, Richard Day, Jeff Jopling, Peter Najjar, Mathias Unberath
Abstract: Purpose: The operating room (OR) is a complex environment where optimizing workflows is critical to reduce costs and improve patient outcomes. The use of computer vision approaches for the automatic recognition of perioperative events enables identification of bottlenecks for OR optimization. However, privacy concerns limit the use of computer vision for automated event detection from OR videos, which makes privacy-preserving approaches needed for OR workflow analysis. Methods: We propose a two-stage pipeline for privacy-preserving OR video analysis and event detection. In the first stage, 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. In the second stage, we employ the SafeOR model, a fused two-stream approach that processes segmentation masks and depth maps for OR event detection. We evaluate this method on an internal dataset of 38 simulated surgical trials with five event classes. Results: Our results indicate that this DT-based approach to the OR event detection model achieves performance on par and sometimes even better than raw RGB video-based models on detecting OR events. Conclusion: DTs enable privacy-preserving OR workflow analysis, facilitating the sharing of de-identified data across institutions and they can potentially enhance model generalizability by mitigating domain-specific appearance differences.
Authors: Haris Riaz, Sourav Bhabesh, Vinayak Arannil, Miguel Ballesteros, Graham Horwood
Abstract: Recent smaller language models such Phi-3.5 and Phi-4 rely on synthetic data generated using larger Language models. Questions remain about leveraging synthetic data for other use cases, such as adapting LLMs to specific domains. A key limitation of synthetic data is low diversity, which negatively impacts its downstream applicability for improving other models. To address this, we propose MetaSynth, a method for generating synthetic data that enhances diversity through meta-prompting, where a language model orchestrates multiple "expert" LLM agents to collaboratively generate data. Using only 25 million tokens of synthetic data generated with MetaSynth, we successfully adapt a well-trained LLM (Mistral-7B-v0.3) to two specialized domains-Finance and Biomedicine-without compromising the capabilities of the resulting model in general tasks. In addition, we evaluate the diversity of our synthetic data using seven automated metrics, and find that it approaches the diversity of LLM pre-training corpora. Continually pre-training Mistral-7B-v0.3 with MetaSynth notably outperforms the base LLM, showing improvements of up to 4.08% in Finance and 13.75% in Biomedicine. The same model shows degraded performance when trained on data generated using a template prompt, even when the template includes prior generations and varying In-Context exemplars of real data. Our findings suggest that a few million tokens of diverse synthetic data without mixing any real data, is sufficient for effective domain adaptation when using MetaSynth.
Authors: Yuning Zhou, Henry Badgery, Matthew Read, James Bailey, Catherine Davey
Abstract: Labeling has always been expensive in the medical context, which has hindered related deep learning application. Our work introduces active learning in surgical video frame selection to construct a high-quality, affordable Laparoscopic Cholecystectomy dataset for semantic segmentation. Active learning allows the Deep Neural Networks (DNNs) learning pipeline to include the dataset construction workflow, which means DNNs trained by existing dataset will identify the most informative data from the newly collected data. At the same time, DNNs' performance and generalization ability improve over time when the newly selected and annotated data are included in the training data. We assessed different data informativeness measurements and found the deep features distances select the most informative data in this task. Our experiments show that with half of the data selected by active learning, the DNNs achieve almost the same performance with 0.4349 mean Intersection over Union (mIoU) compared to the same DNNs trained on the full dataset (0.4374 mIoU) on the critical anatomies and surgical instruments.
Authors: Timothy Proctor, Anh Tran, Xingxin Liu, Aditya Dhumuntarao, Stefan Seritan, Alaina Green, Norbert M Linke
Abstract: Benchmarks that concisely summarize the performance of many-qubit quantum computers are essential for measuring progress towards the goal of useful quantum computation. In this work, we present a benchmarking framework that is based on quantifying how a quantum computer's performance on quantum circuits varies as a function of features of those circuits, such as circuit depth, width, two-qubit gate density, problem input size, or algorithmic depth. Our featuremetric benchmarking framework generalizes volumetric benchmarking -- a widely-used methodology that quantifies performance versus circuit width and depth -- and we show that it enables richer and more faithful models of quantum computer performance. We demonstrate featuremetric benchmarking with example benchmarks run on IBM Q and IonQ systems of up to 27 qubits, and we show how to produce performance summaries from the data using Gaussian process regression. Our data analysis methods are also of interest in the special case of volumetric benchmarking, as they enable the creation of intuitive two-dimensional capability regions using data from few circuits.
Authors: Liyi Zhang, Veniamin Veselovsky, R. Thomas McCoy, Thomas L. Griffiths
Abstract: Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their responses. In this work, we show that, in at least some cases, LLMs actually compute the information needed to perform these tasks correctly, and we identify some interventions that can allow them to access this information to improve their performance. First, we show that simply prompting the language model to not rely on its prior knowledge leads to dramatic improvements in prior-dominated tasks. We then use mechanistic interpretability techniques to localize the prior within the LLM and manipulate the extent to which that prior influences its responses. Specifically, we show that it is possible to identify layers of the underlying neural network that correlate with the prior probability of a response and that lightweight finetuning of these layers with basic prompts on prior-dominated tasks achieves high performance on held-out answers. These results suggest that the information required to produce a correct response is contained within the representations of the problems formed by the models. Furthermore, we show that this finetuning is significantly more effective for prior-dominated tasks, and that the error after finetuning is no longer correlated with the prior. Our results suggest that it may be possible to define effective methods for manipulating the extent to which LLMs rely upon their priors in solving problems, potentially increasing their performance in settings where LLMs hallucinate for reasons related to the prior probability of token sequences.
Authors: Jun Fan, Zheng-Chu Guo, Lei Shi
Abstract: Spectral algorithms leverage spectral regularization techniques to analyze and process data, providing a flexible framework for addressing supervised learning problems. To deepen our understanding of their performance in real-world scenarios where the distributions of training and test data may differ, we conduct a rigorous investigation into the convergence behavior of spectral algorithms under distribution shifts, specifically within the framework of reproducing kernel Hilbert spaces. Our study focuses on the case of covariate shift. In this scenario, the marginal distributions of the input data differ between the training and test datasets, while the conditional distribution of the output given the input remains unchanged. Under this setting, we analyze the generalization error of spectral algorithms and show that they achieve minimax optimality when the density ratios between the training and test distributions are uniformly bounded. However, we also identify a critical limitation: when the density ratios are unbounded, the spectral algorithms may become suboptimal. To address this limitation, we propose a weighted spectral algorithm that incorporates density ratio information into the learning process. Our theoretical analysis shows that this weighted approach achieves optimal capacity-independent convergence rates. Furthermore, by introducing a weight clipping technique, we demonstrate that the convergence rates of the weighted spectral algorithm can approach the optimal capacity-dependent convergence rates arbitrarily closely. This improvement resolves the suboptimality issue in unbounded density ratio scenarios and advances the state-of-the-art by refining existing theoretical results.
Authors: Belinda Trotta, Robert Johnson, Catherine de Burgh-Day, Debra Hudson, Esteban Abellan, James Canvin, Andrew Kelly, Daniel Mentiplay, Benjamin Owen, Jennifer Whelan
Abstract: Artificial Intelligence (AI) weather models are now reaching operational-grade performance for some variables, but like traditional Numerical Weather Prediction (NWP) models, they exhibit systematic biases and reliability issues. We test the application of the Bureau of Meteorology's existing statistical post-processing system, IMPROVER, to ECMWF's deterministic Artificial Intelligence Forecasting System (AIFS), and compare results against post-processed outputs from the ECMWF HRES and ENS models. Without any modification to configuration or processing workflows, post-processing yields comparable accuracy improvements for AIFS as for traditional NWP forecasts, in both expected value and probabilistic outputs. We show that blending AIFS with NWP models improves overall forecast skill, even when AIFS alone is not the most accurate component. These findings show that statistical post-processing methods developed for NWP are directly applicable to AI models, enabling national meteorological centres to incorporate AI forecasts into existing workflows in a low-risk, incremental fashion.
Authors: Cristina Anton, Roy Shivam Ram Shreshtth
Abstract: We propose a clustering method, funWeightClustSkew, based on mixtures of functional linear regression models and three skewed multivariate distributions: the variance-gamma distribution, the skew-t distribution, and the normal-inverse Gaussian distribution. Our approach follows the framework of the functional high dimensional data clustering (funHDDC) method, and we extend to functional data the cluster weighted models based on skewed distributions used for finite dimensional multivariate data. We consider several parsimonious models, and to estimate the parameters we construct an expectation maximization (EM) algorithm. We illustrate the performance of funWeightClustSkew for simulated data and for the Air Quality dataset.
Authors: Tempei Kabayama, Motomasa Komuro, Yasuo Kuniyoshi, Kazuyuki Aihara, Kohei Nakajima
Abstract: Reservoir computing can embed attractors into random neural networks (RNNs), generating a ``mirror'' of a target attractor because of its inherent symmetrical constraints. In these RNNs, we report that an attractor-merging crisis accompanied by intermittency emerges simply by adjusting the global parameter. We further reveal its underlying mechanism through a detailed analysis of the phase-space structure and demonstrate that this bifurcation scenario is intrinsic to a general class of RNNs, independent of training data.
Authors: Robert de Mello Koch, Animik Ghosh
Abstract: We propose that learning in deep neural networks proceeds in two phases: a rapid curve fitting phase followed by a slower compression or coarse graining phase. This view is supported by the shared temporal structure of three phenomena: grokking, double descent and the information bottleneck, all of which exhibit a delayed onset of generalization well after training error reaches zero. We empirically show that the associated timescales align in two rather different settings. Mutual information between hidden layers and input data emerges as a natural progress measure, complementing circuit-based metrics such as local complexity and the linear mapping number. We argue that the second phase is not actively optimized by standard training algorithms and may be unnecessarily prolonged. Drawing on an analogy with the renormalization group, we suggest that this compression phase reflects a principled form of forgetting, critical for generalization.
Authors: Kunal Jha, Wilka Carvalho, Yancheng Liang, Simon S. Du, Max Kleiman-Weiner, Natasha Jaques
Abstract: Zero-shot coordination (ZSC), the ability to adapt to a new partner in a cooperative task, is a critical component of human-compatible AI. While prior work has focused on training agents to cooperate on a single task, these specialized models do not generalize to new tasks, even if they are highly similar. Here, we study how reinforcement learning on a distribution of environments with a single partner enables learning general cooperative skills that support ZSC with many new partners on many new problems. We introduce two Jax-based, procedural generators that create billions of solvable coordination challenges. We develop a new paradigm called Cross-Environment Cooperation (CEC), and show that it outperforms competitive baselines quantitatively and qualitatively when collaborating with real people. Our findings suggest that learning to collaborate across many unique scenarios encourages agents to develop general norms, which prove effective for collaboration with different partners. Together, our results suggest a new route toward designing generalist cooperative agents capable of interacting with humans without requiring human data.
Authors: Shin'ya Yamaguchi, Dewei Feng, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa
Abstract: Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performance on downstream tasks, the multi-modal feature spaces still suffer from a modality gap, which is a gap between image and text feature clusters and limits downstream task performance. Although existing works attempt to address the modality gap by modifying pre-training or fine-tuning, they struggle with heavy training costs with large datasets or degradations of zero-shot performance. This paper presents CLIP-Refine, a post-pre-training method for CLIP models at a phase between pre-training and fine-tuning. CLIP-Refine aims to align the feature space with 1 epoch training on small image-text datasets without zero-shot performance degradations. To this end, we introduce two techniques: random feature alignment (RaFA) and hybrid contrastive-distillation (HyCD). RaFA aligns the image and text features to follow a shared prior distribution by minimizing the distance to random reference vectors sampled from the prior. HyCD updates the model with hybrid soft labels generated by combining ground-truth image-text pair labels and outputs from the pre-trained CLIP model. This contributes to achieving both maintaining the past knowledge and learning new knowledge to align features. Our extensive experiments with multiple classification and retrieval tasks show that CLIP-Refine succeeds in mitigating the modality gap and improving the zero-shot performance.
Authors: Kyriakos Stylianopoulos, George C. Alexandropoulos
Abstract: In this paper, we demonstrate that an eXtremely Large (XL) Multiple-Input Multiple-Output (MIMO) wireless system with appropriate analog combining components exhibits the properties of a universal function approximator, similar to a feedforward neural network. By treating the XL MIMO channel coefficients as the random nodes of a hidden layer, and the receiver's analog combiner as a trainable output layer, we cast the end-to-end system to the Extreme Learning Machine (ELM) framework, leading to a novel formulation for Over-The-Air (OTA) edge inference without requiring traditional digital processing nor pre-processing at the transmitter. Through theoretical analysis and numerical evaluation, we showcase that XL-MIMO-ELM enables near-instantaneous training and efficient classification, suggesting the paradigm shift of beyond massive MIMO systems as neural networks alongside their profound communications role. Compared to deep learning approaches and conventional ELMs, the proposed framework achieves on par performance with orders of magnitude lower complexity, making it highly attractive for ultra low power wireless devices.
Authors: Leyang Li, Shilin Lu, Yan Ren, Adams Wai-Kin Kong
Abstract: Ensuring the ethical deployment of text-to-image models requires effective techniques to prevent the generation of harmful or inappropriate content. While concept erasure methods offer a promising solution, existing finetuning-based approaches suffer from notable limitations. Anchor-free methods risk disrupting sampling trajectories, leading to visual artifacts, while anchor-based methods rely on the heuristic selection of anchor concepts. To overcome these shortcomings, we introduce a finetuning framework, dubbed ANT, which Automatically guides deNoising Trajectories to avoid unwanted concepts. ANT is built on a key insight: reversing the condition direction of classifier-free guidance during mid-to-late denoising stages enables precise content modification without sacrificing early-stage structural integrity. This inspires a trajectory-aware objective that preserves the integrity of the early-stage score function field, which steers samples toward the natural image manifold, without relying on heuristic anchor concept selection. For single-concept erasure, we propose an augmentation-enhanced weight saliency map to precisely identify the critical parameters that most significantly contribute to the unwanted concept, enabling more thorough and efficient erasure. For multi-concept erasure, our objective function offers a versatile plug-and-play solution that significantly boosts performance. Extensive experiments demonstrate that ANT achieves state-of-the-art results in both single and multi-concept erasure, delivering high-quality, safe outputs without compromising the generative fidelity. Code is available at https://github.com/lileyang1210/ANT
Authors: Elior Benarous, Yilun Du, Heng Yang
Abstract: We present a novel approach to training specialized instruction-based image-editing diffusion models, addressing key challenges in structural preservation with input images and semantic alignment with user prompts. We introduce an online reinforcement learning framework that aligns the diffusion model with human preferences without relying on extensive human annotations or curating a large dataset. Our method significantly improves the realism and alignment with instructions in two ways. First, the proposed models achieve precise and structurally coherent modifications in complex scenes while maintaining high fidelity in instruction-irrelevant areas. Second, they capture fine nuances in the desired edit by leveraging a visual prompt, enabling detailed control over visual edits without lengthy textual prompts. This approach simplifies users' efforts to achieve highly specific edits, requiring only 5 reference images depicting a certain concept for training. Experimental results demonstrate that our models can perform intricate edits in complex scenes, after just 10 training steps. Finally, we showcase the versatility of our method by applying it to robotics, where enhancing the visual realism of simulated environments through targeted sim-to-real image edits improves their utility as proxies for real-world settings.
Authors: Yifeng Cheng, Juan Du
Abstract: Large pretrained vision foundation models have shown significant potential in various vision tasks. However, for industrial anomaly detection, the scarcity of real defect samples poses a critical challenge in leveraging these models. While 2D anomaly generation has significantly advanced with established generative models, the adoption of 3D sensors in industrial manufacturing has made leveraging 3D data for surface quality inspection an emerging trend. In contrast to 2D techniques, 3D anomaly generation remains largely unexplored, limiting the potential of 3D data in industrial quality inspection. To address this gap, we propose a novel yet simple 3D anomaly generation method, 3D-PNAS, based on Perlin noise and surface parameterization. Our method generates realistic 3D surface anomalies by projecting the point cloud onto a 2D plane, sampling multi-scale noise values from a Perlin noise field, and perturbing the point cloud along its normal direction. Through comprehensive visualization experiments, we demonstrate how key parameters - including noise scale, perturbation strength, and octaves, provide fine-grained control over the generated anomalies, enabling the creation of diverse defect patterns from pronounced deformations to subtle surface variations. Additionally, our cross-category experiments show that the method produces consistent yet geometrically plausible anomalies across different object types, adapting to their specific surface characteristics. We also provide a comprehensive codebase and visualization toolkit to facilitate future research.
Authors: C. Revelas, O. Boldea, B. J. M. Werker
Abstract: We study the effectiveness of randomizing split-directions in random forests. Prior literature has shown that, on the one hand, randomization can reduce variance through decorrelation, and, on the other hand, randomization regularizes and works in low signal-to-noise ratio (SNR) environments. First, we bring together and revisit decorrelation and regularization by presenting a systematic analysis of out-of-sample mean-squared error (MSE) for different SNR scenarios based on commonly-used data-generating processes. We find that variance reduction tends to increase with the SNR and forests outperform bagging when the SNR is low because, in low SNR cases, variance dominates bias for both methods. Second, we show that the effectiveness of randomization is a question that goes beyond the SNR. We present a simulation study with fixed and moderate SNR, in which we examine the effectiveness of randomization for other data characteristics. In particular, we find that (i) randomization can increase bias in the presence of fat tails in the distribution of covariates; (ii) in the presence of irrelevant covariates randomization is ineffective because bias dominates variance; and (iii) when covariates are mutually correlated randomization tends to be effective because variance dominates bias. Beyond randomization, we find that, for both bagging and random forests, bias can be significantly reduced in the presence of correlated covariates. This last finding goes beyond the prevailing view that averaging mostly works by variance reduction. Given that in practice covariates are often correlated, our findings on correlated covariates could open the way for a better understanding of why random forests work well in many applications.
Authors: Morenikeji Neri, Nicholas Pischke, Thomas Powell
Abstract: We prove a novel and general result on the asymptotic behavior of stochastic processes which conform to a certain relaxed supermartingale condition. Our result provides quantitative information in the form of an explicit and effective construction of a rate of convergence for this process, both in mean and almost surely, that is moreover highly uniform in the sense that it only depends on very few data of the surrounding objects involved in the iteration. We then apply this result to derive new quantitative versions of well-known concepts and theorems from stochastic approximation, in particular providing effective rates for a variant of the Robbins-Siegmund theorem, Dvoretzky's convergence theorem, as well as the convergence of stochastic quasi-Fej\'er monotone sequences, the latter of which formulated in a novel and highly general metric context. We utilize the classic and widely studied Robbins-Monro procedure as a template to evaluate our quantitative results and their applicability in greater detail. We conclude by illustrating the breadth of potential further applications with a brief discussion on a variety of other well-known iterative procedures from stochastic approximation, covering a range of different applied scenarios to which our methods can be immediately applied. Throughout, we isolate and discuss special cases of our results which even allow for the construction of fast, and in particular linear, rates.
Authors: Robin Hesse, Jonas Fischer, Simone Schaub-Meyer, Stefan Roth
Abstract: Mechanistic interpretability is concerned with analyzing individual components in a (convolutional) neural network (CNN) and how they form larger circuits representing decision mechanisms. These investigations are challenging since CNNs frequently learn polysemantic channels that encode distinct concepts, making them hard to interpret. To address this, we propose an algorithm to disentangle a specific kind of polysemantic channel into multiple channels, each responding to a single concept. Our approach restructures weights in a CNN, utilizing that different concepts within the same channel exhibit distinct activation patterns in the previous layer. By disentangling these polysemantic features, we enhance the interpretability of CNNs, ultimately improving explanatory techniques such as feature visualizations.
Authors: Nearchos Potamitis, Akhil Arora
Abstract: Recent advancements in large language models (LLMs) have catalyzed the development of general-purpose autonomous agents, demonstrating remarkable performance in complex reasoning tasks across various domains. This surge has spurred the evolution of a plethora of prompt-based reasoning frameworks. A recent focus has been on iterative reasoning strategies that refine outputs through self-evaluation and verbalized feedback. However, these strategies require additional computational complexity to enable models to recognize and correct their mistakes, leading to a significant increase in their cost. In this work, we introduce the concept of ``retrials without feedback'', an embarrassingly simple yet powerful mechanism for enhancing reasoning frameworks by allowing LLMs to retry problem-solving attempts upon identifying incorrect answers. Unlike conventional iterative refinement methods, our method does not require explicit self-reflection or verbalized feedback, simplifying the refinement process. Our findings indicate that simpler retrial-based approaches often outperform more sophisticated reasoning frameworks, suggesting that the benefits of complex methods may not always justify their computational costs. By challenging the prevailing assumption that more intricate reasoning strategies inherently lead to better performance, our work offers new insights into how simpler, more efficient approaches can achieve optimal results. So, are retrials all you need?
Authors: Yanmei Wang, Xiyao Liu, Fupeng Chu, Zhi Han
Abstract: Domain generalization aims at training on source domains to uncover a domain-invariant feature space, allowing the model to perform robust generalization ability on unknown target domains. However, due to domain gaps, it is hard to find reliable common image feature space, and the reason for that is the lack of suitable basic units for images. Different from image in vision space, language has comprehensive expression elements that can effectively convey semantics. Inspired by the semantic completeness of language and intuitiveness of image, we propose VLCA, which combine language space and vision space, and connect the multiple image domains by using semantic space as the bridge domain. Specifically, in language space, by taking advantage of the completeness of language basic units, we tend to capture the semantic representation of the relations between categories through word vector distance. Then, in vision space, by taking advantage of the intuitiveness of image features, the common pattern of sample features with the same class is explored through low-rank approximation. In the end, the language representation is aligned with the vision representation through the multimodal space of text and image. Experiments demonstrate the effectiveness of the proposed method.
Authors: Theshani Nuradha, Mark M. Wilde
Abstract: Quantum channel discrimination has been studied from an information-theoretic perspective, wherein one is interested in the optimal decay rate of error probabilities as a function of the number of unknown channel accesses. In this paper, we study the query complexity of quantum channel discrimination, wherein the goal is to determine the minimum number of channel uses needed to reach a desired error probability. To this end, we show that the query complexity of binary channel discrimination depends logarithmically on the inverse error probability and inversely on the negative logarithm of the (geometric and Holevo) channel fidelity. As a special case of these findings, we precisely characterize the query complexity of discriminating between two classical channels. We also provide lower and upper bounds on the query complexity of binary asymmetric channel discrimination and multiple quantum channel discrimination. For the former, the query complexity depends on the geometric R\'enyi and Petz R\'enyi channel divergences, while for the latter, it depends on the negative logarithm of (geometric and Uhlmann) channel fidelity. For multiple channel discrimination, the upper bound scales as the logarithm of the number of channels.
Authors: Farhan Khodaee, Rohola Zandie, Yufan Xia, Elazer R. Edelman
Abstract: We propose a new theory for aging based on dynamical systems and provide a data-driven computational method to quantify the changes at the cellular level. We use ergodic theory to decompose the dynamics of changes during aging and show that aging is fundamentally a dissipative process within biological systems, akin to dynamical systems where dissipation occurs due to non-conservative forces. To quantify the dissipation dynamics, we employ a transformer-based machine learning algorithm to analyze gene expression data, incorporating age as a token to assess how age-related dissipation is reflected in the embedding space. By evaluating the dynamics of gene and age embeddings, we provide a cellular aging map (CAM) and identify patterns indicative of divergence in gene embedding space, nonlinear transitions, and entropy variations during aging for various tissues and cell types. Our results provide a novel perspective on aging as a dissipative process and introduce a computational framework that enables measuring age-related changes with molecular resolution.
Authors: Linkang Du, Zheng Zhu, Min Chen, Zhou Su, Shouling Ji, Peng Cheng, Jiming Chen, Zhikun Zhang
Abstract: Text-to-image models based on diffusion processes, such as DALL-E, Stable Diffusion, and Midjourney, are capable of transforming texts into detailed images and have widespread applications in art and design. As such, amateur users can easily imitate professional-level paintings by collecting an artist's work and fine-tuning the model, leading to concerns about artworks' copyright infringement. To tackle these issues, previous studies either add visually imperceptible perturbation to the artwork to change its underlying styles (perturbation-based methods) or embed post-training detectable watermarks in the artwork (watermark-based methods). However, when the artwork or the model has been published online, i.e., modification to the original artwork or model retraining is not feasible, these strategies might not be viable. To this end, we propose a novel method for data-use auditing in the text-to-image generation model. The general idea of ArtistAuditor is to identify if a suspicious model has been finetuned using the artworks of specific artists by analyzing the features related to the style. Concretely, ArtistAuditor employs a style extractor to obtain the multi-granularity style representations and treats artworks as samplings of an artist's style. Then, ArtistAuditor queries a trained discriminator to gain the auditing decisions. The experimental results on six combinations of models and datasets show that ArtistAuditor can achieve high AUC values (> 0.937). By studying ArtistAuditor's transferability and core modules, we provide valuable insights into the practical implementation. Finally, we demonstrate the effectiveness of ArtistAuditor in real-world cases by an online platform Scenario. ArtistAuditor is open-sourced at https://github.com/Jozenn/ArtistAuditor.
Authors: Margalit Glasgow, Denny Wu, Joan Bruna
Abstract: We study the approximation gap between the dynamics of a polynomial-width neural network and its infinite-width counterpart, both trained using projected gradient descent in the mean-field scaling regime. We demonstrate how to tightly bound this approximation gap through a differential equation governed by the mean-field dynamics. A key factor influencing the growth of this ODE is the local Hessian of each particle, defined as the derivative of the particle's velocity in the mean-field dynamics with respect to its position. We apply our results to the canonical feature learning problem of estimating a well-specified single-index model; we permit the information exponent to be arbitrarily large, leading to convergence times that grow polynomially in the ambient dimension $d$. We show that, due to a certain ``self-concordance'' property in these problems -- where the local Hessian of a particle is bounded by a constant times the particle's velocity -- polynomially many neurons are sufficient to closely approximate the mean-field dynamics throughout training.
Authors: Haojian Huang, Haodong Chen, Shengqiong Wu, Meng Luo, Jinlan Fu, Xinya Du, Hanwang Zhang, Hao Fei
Abstract: Large Video Models (LVMs) built upon Large Language Models (LLMs) have shown promise in video understanding but often suffer from misalignment with human intuition and video hallucination issues. To address these challenges, we introduce VistaDPO, a novel framework for Video Hierarchical Spatial-Temporal Direct Preference Optimization. VistaDPO enhances text-video preference alignment across three hierarchical levels: i) Instance Level, aligning overall video content with responses; ii) Temporal Level, aligning video temporal semantics with event descriptions; and iii) Perceptive Level, aligning spatial objects with language tokens. Given the lack of datasets for fine-grained video-language preference alignment, we construct VistaDPO-7k, a dataset of 7.2K QA pairs annotated with chosen and rejected responses, along with spatial-temporal grounding information such as timestamps, keyframes, and bounding boxes. Extensive experiments on benchmarks such as Video Hallucination, Video QA, and Captioning performance tasks demonstrate that VistaDPO significantly improves the performance of existing LVMs, effectively mitigating video-language misalignment and hallucination. The code and data are available at https://github.com/HaroldChen19/VistaDPO.
Authors: Varun Rao, Youran Sun, Mahendra Kumar, Tejas Mutneja, Agastya Mukherjee, Haizhao Yang
Abstract: This paper investigates the application of large language models (LLMs) to financial tasks. We fine-tuned foundation models using the Open FinLLM Leaderboard as a benchmark. Building on Qwen2.5 and Deepseek-R1, we employed techniques including supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning (RL) to enhance their financial capabilities. The fine-tuned models demonstrated substantial performance gains across a wide range of financial tasks. Moreover, we measured the data scaling law in the financial domain. Our work demonstrates the potential of large language models (LLMs) in financial applications.
Authors: Jialuo Li, Wenhao Chai, Xingyu Fu, Haiyang Xu, Saining Xie
Abstract: We present a novel approach to integrating scientific knowledge into generative models, enhancing their realism and consistency in image synthesis. First, we introduce Science-T2I, an expert-annotated adversarial dataset comprising adversarial 20k image pairs with 9k prompts, covering wide distinct scientific knowledge categories. Leveraging Science-T2I, we present SciScore, an end-to-end reward model that refines the assessment of generated images based on scientific knowledge, which is achieved by augmenting both the scientific comprehension and visual capabilities of pre-trained CLIP model. Additionally, based on SciScore, we propose a two-stage training framework, comprising a supervised fine-tuning phase and a masked online fine-tuning phase, to incorporate scientific knowledge into existing generative models. Through comprehensive experiments, we demonstrate the effectiveness of our framework in establishing new standards for evaluating the scientific realism of generated content. Specifically, SciScore attains performance comparable to human-level, demonstrating a 5% improvement similar to evaluations conducted by experienced human evaluators. Furthermore, by applying our proposed fine-tuning method to FLUX, we achieve a performance enhancement exceeding 50% on SciScore.
Authors: Anamika Lochab, Ruqi Zhang
Abstract: Reward models (RMs) are essential for aligning Large Language Models (LLMs) with human preferences. However, they often struggle with capturing complex human preferences and generalizing to unseen data. To address these challenges, we introduce Energy-Based Reward Model (EBRM), a lightweight post-hoc refinement framework that enhances RM robustness and generalization. EBRM models the reward distribution explicitly, capturing uncertainty in human preferences and mitigating the impact of noisy or misaligned annotations. It achieves this through conflict-aware data filtering, label-noise-aware contrastive training, and hybrid initialization. Notably, EBRM enhances RMs without retraining, making it computationally efficient and adaptable across different models and tasks. Empirical evaluations on RM benchmarks demonstrate significant improvements in both robustness and generalization, achieving up to a 5.97% improvement in safety-critical alignment tasks compared to standard RMs. Furthermore, reinforcement learning experiments confirm that our refined rewards enhance alignment quality, effectively delaying reward hacking. These results demonstrate our approach as a scalable and effective enhancement for existing RMs and alignment pipelines. The code is available at EBRM.
Authors: Jo\~ao Loula, Benjamin LeBrun, Li Du, Ben Lipkin, Clemente Pasti, Gabriel Grand, Tianyu Liu, Yahya Emara, Marjorie Freedman, Jason Eisner, Ryan Cotterel, Vikash Mansinghka, Alexander K. Lew, Tim Vieira, Timothy J. O'Donnell
Abstract: A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as probabilistic conditioning, but exact generation from the resulting distribution -- which can differ substantially from the LM's base distribution -- is generally intractable. In this work, we develop an architecture for controlled LM generation based on sequential Monte Carlo (SMC). Our SMC framework allows us to flexibly incorporate domain- and problem-specific constraints at inference time, and efficiently reallocate computational resources in light of new information during the course of generation. By comparing to a number of alternatives and ablations on four challenging domains -- Python code generation for data science, text-to-SQL, goal inference, and molecule synthesis -- we demonstrate that, with little overhead, our approach allows small open-source language models to outperform models over 8x larger, as well as closed-source, fine-tuned ones. In support of the probabilistic perspective, we show that these performance improvements are driven by better approximation to the posterior distribution. Our system builds on the framework of Lew et al. (2023) and integrates with its language model probabilistic programming language, giving users a simple, programmable way to apply SMC to a broad variety of controlled generation problems.
Authors: Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi, Triantafyllos Afouras, Tushar Nagarajan, Muhammad Maaz, Yale Song, Tengyu Ma, Shuming Hu, Suyog Jain, Miguel Martin, Huiyu Wang, Hanoona Rasheed, Peize Sun, Po-Yao Huang, Daniel Bolya, Nikhila Ravi, Shashank Jain, Tammy Stark, Shane Moon, Babak Damavandi, Vivian Lee, Andrew Westbury, Salman Khan, Philipp Kr\"ahenb\"uhl, Piotr Doll\'ar, Lorenzo Torresani, Kristen Grauman, Christoph Feichtenhofer
Abstract: Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM-VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about "what", "where", "when", and "how" of a video. We make our work fully reproducible by providing data, training recipes, code & models.
Authors: Siddharth Joshi, Yu Yang, Yihao Xue, Wenhan Yang, Baharan Mirzasoleiman
Abstract: Deep neural networks often exploit *spurious* features that are present in the majority of examples within a class during training. This leads to *poor worst-group test accuracy*, i.e., poor accuracy for minority groups that lack these spurious features. Despite the growing body of recent efforts to address spurious correlations (SC), several challenging settings remain unexplored.In this work, we propose studying methods to mitigate SC in settings with: 1) spurious features that are learned more slowly, 2) a larger number of classes, and 3) a larger number of groups. We introduce two new datasets, Animals and SUN, to facilitate this study and conduct a systematic benchmarking of 8 state-of-the-art (SOTA) methods across a total of 5 vision datasets, training over 5,000 models. Through this, we highlight how existing group inference methods struggle in the presence of spurious features that are learned later in training. Additionally, we demonstrate how all existing methods struggle in settings with more groups and/or classes. Finally, we show the importance of careful model selection (hyperparameter tuning) in extracting optimal performance, especially in the more challenging settings we introduced, and propose more cost-efficient strategies for model selection. Overall, through extensive and systematic experiments, this work uncovers a suite of new challenges and opportunities for improving worst-group generalization in the presence of spurious features. Our datasets, methods and scripts available at https://github.com/BigML-CS-UCLA/SpuCo.
Authors: Christopher P. Ley, Felipe Tobar
Abstract: We introduce the asynchronous graph generator (AGG), a novel graph attention network for imputation and prediction of multi-channel time series. Free from recurrent components or assumptions about temporal/spatial regularity, AGG encodes measurements, timestamps and channel-specific features directly in the nodes via learnable embeddings. Through an attention mechanism, these embeddings allow for discovering expressive relationships among the variables of interest in the form of a homogeneous graph. Once trained, AGG performs imputation by \emph{conditional attention generation}, i.e., by creating a new node conditioned on given timestamps and channel specification. The proposed AGG is compared to related methods in the literature and its performance is analysed from a data augmentation perspective. Our experiments reveal that AGG achieved state-of-the-art results in time series imputation, classification and prediction for the benchmark datasets \emph{Beijing Air Quality}, \emph{PhysioNet ICU 2012} and \emph{UCI localisation}, outperforming other recent attention-based networks.
Authors: Lukas Tatzel, Jonathan Wenger, Frank Schneider, Philipp Hennig
Abstract: Non-conjugate Gaussian processes (NCGPs) define a flexible probabilistic framework to model categorical, ordinal and continuous data, and are widely used in practice. However, exact inference in NCGPs is prohibitively expensive for large datasets, thus requiring approximations in practice. The approximation error adversely impacts the reliability of the model and is not accounted for in the uncertainty of the prediction. We introduce a family of iterative methods that explicitly model this error. They are uniquely suited to parallel modern computing hardware, efficiently recycle computations, and compress information to reduce both the time and memory requirements for NCGPs. As we demonstrate on large-scale classification problems, our method significantly accelerates posterior inference compared to competitive baselines by trading off reduced computation for increased uncertainty.
Authors: Saujas Vaduguru, Daniel Fried, Yewen Pu
Abstract: Programming-by-example is the task of synthesizing a program that is consistent with a set of user-provided input-output examples. As examples are often an under-specification of one's intent, a good synthesizer must choose the intended program from the many that are consistent with the given set of examples. Prior work frames program synthesis as a cooperative game between a listener (that synthesizes programs) and a speaker (a user choosing examples), and shows that models of computational pragmatic inference are effective in choosing the user intended programs. However, these models require counterfactual reasoning over a large set of programs and examples, which is infeasible in realistic program spaces. In this paper, we propose PraX, a novel way to amortize this search with neural networks. We sample pairs of programs and examples via self-play between listener and speaker models, and use pragmatic inference to choose informative training examples from this sample. We then use the informative dataset to train models to improve the synthesizer's ability to disambiguate user-provided examples without human supervision. We validate PraX on the challenging task of synthesizing regular expressions from example strings, and find that our method (1) outperforms models trained without choosing pragmatic examples by 23% (a 51% relative increase) (2) matches the performance of supervised learning on a dataset of pragmatic examples provided by humans, despite using no human data in training.
Authors: Tatyana Benko, Martin Buck, Ilya Amburg, Stephen J. Young, Sinan G. Aksoy
Abstract: In data science, hypergraphs are natural models for data exhibiting multi-way relations, whereas graphs only capture pairwise. Nonetheless, many proposed hypergraph neural networks effectively reduce hypergraphs to undirected graphs via symmetrized matrix representations, potentially losing important information. We propose an alternative approach to hypergraph neural networks in which the hypergraph is represented as a non-reversible Markov chain. We use this Markov chain to construct a complex Hermitian Laplacian matrix - the magnetic Laplacian - which serves as the input to our proposed hypergraph neural network. We study HyperMagNet for the task of node classification, and demonstrate its effectiveness over graph-reduction based hypergraph neural networks.
Authors: Kafeng Wang, Jianfei Chen, He Li, Zhenpeng Mi, Jun Zhu
Abstract: Diffusion models represent a powerful family of generative models widely used for image and video generation. However, the time-consuming deployment, long inference time, and requirements on large memory hinder their applications on resource constrained devices. In this paper, we propose a method based on the improved Straight-Through Estimator to improve the deployment efficiency of diffusion models. Specifically, we add sparse masks to the Convolution and Linear layers in a pre-trained diffusion model, then transfer learn the sparse model during the fine-tuning stage and turn on the sparse masks during inference. Experimental results on a Transformer and UNet-based diffusion models demonstrate that our method reduces MACs by 50% while maintaining FID. Sparse models are accelerated by approximately 1.2x on the GPU. Under other MACs conditions, the FID is also lower than 1 compared to other methods.
Authors: Elahe Khatibi, Mahyar Abbasian, Zhongqi Yang, Iman Azimi, Amir M. Rahmani
Abstract: To perform effective causal inference in high-dimensional datasets, initiating the process with causal discovery is imperative, wherein a causal graph is generated based on observational data. However, obtaining a complete and accurate causal graph poses a formidable challenge, recognized as an NP- hard problem. Recently, the advent of Large Language Models (LLMs) has ushered in a new era, indicating their emergent capabilities and widespread applicability in facilitating causal reasoning across diverse domains, such as medicine, finance, and science. The expansive knowledge base of LLMs holds the potential to elevate the field of causal reasoning by offering interpretability, making inferences, generalizability, and uncovering novel causal structures. In this paper, we introduce a new framework, named Autonomous LLM-Augmented Causal Discovery Framework (ALCM), to synergize data-driven causal discovery algorithms and LLMs, automating the generation of a more resilient, accurate, and explicable causal graph. The ALCM consists of three integral components: causal structure learning, causal wrapper, and LLM-driven causal refiner. These components autonomously collaborate within a dynamic environment to address causal discovery questions and deliver plausible causal graphs. We evaluate the ALCM framework by implementing two demonstrations on seven well-known datasets. Experimental results demonstrate that ALCM outperforms existing LLM methods and conventional data-driven causal reasoning mechanisms. This study not only shows the effectiveness of the ALCM but also underscores new research directions in leveraging the causal reasoning capabilities of LLMs.
Authors: Tayab Uddin Wara, Ababil Hossain Fahad, Adri Shankar Das, Md. Mehedi Hasan Shawon
Abstract: Sleep is vital for people's physical and mental health, and sound sleep can help them focus on daily activities. Therefore, a sleep study that includes sleep patterns and sleep disorders is crucial to enhancing our knowledge about individuals' health status. This study aims to provide a comprehensive, systematic review of the recent literature to analyze the different approaches and their outcomes in sleep studies, which includes works on "sleep stages classification" and "sleep disorder detection" using AI. In this review, 183 articles were initially selected from different journals, among which 80 records were enlisted for explicit review, ranging from 2016 to 2023. Brain waves were the most commonly employed body parameters for sleep staging and disorder studies (almost 29% of the research used brain activity signals exclusively, and 77% combined with the other signals). The convolutional neural network (CNN), the most widely used of the 34 distinct artificial intelligence models, comprised 27%. The other models included the long short-term memory (LSTM), support vector machine (SVM), random forest (RF), and recurrent neural network (RNN), which consisted of 11%, 6%, 6%, and 5% sequentially. For performance metrics, accuracy was widely used for a maximum of 83.75% of the cases, the F1 score of 45%, Kappa of 36.25%, Sensitivity of 31.25%, and Specificity of 30% of cases, along with the other metrics. This article would help physicians and researchers get the gist of AI's contribution to sleep studies and the feasibility of their intended work.
Authors: Ye Yuan, Youyuan Zhang, Can Chen, Haolun Wu, Zixuan Li, Jianmo Li, James J. Clark, Xue Liu
Abstract: Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular engineering. A common approach involves training a surrogate model using existing designs and their corresponding scores, and then generating new designs through gradient-based updates with respect to the surrogate model. This method suffers from the out-of-distribution issue, where the surrogate model may erroneously predict high scores for unseen designs. To address this challenge, we introduce a novel method, Design Editing for Offline Model-based Optimization (DEMO), which leverages a diffusion prior to calibrate overly optimized designs. DEMO first generates pseudo design candidates by performing gradient ascent with respect to a surrogate model. While these pseudo design candidates contain information beyond the offline dataset, they might be invalid or have erroneously high predicted scores. Therefore, to address this challenge while utilizing the information provided by pseudo design candidates, we propose an editing process to refine these pseudo design candidates. We introduce noise to the pseudo design candidates and subsequently denoise them with a diffusion prior trained on the offline dataset, ensuring they align with the distribution of valid designs. Empirical evaluations on seven offline MBO tasks show that, with properly tuned hyperparameters, DEMOs score is competitive with the best previously reported scores in the literature.
Authors: Yi Li, Fei Song, Changwen Zheng, Jiangmeng Li, Fuchun Sun, Hui Xiong
Abstract: Multi-modal methods establish comprehensive superiority over uni-modal methods. However, the imbalanced contributions of different modalities to task-dependent predictions constantly degrade the discriminative performance of canonical multi-modal methods. Based on the contribution to task-dependent predictions, modalities can be identified as predominant and auxiliary modalities. Benchmark methods raise a tractable solution: augmenting the auxiliary modality with a minor contribution during training. However, our empirical explorations challenge the fundamental idea behind such behavior, and we further conclude that benchmark approaches suffer from certain defects: insufficient theoretical interpretability and limited exploration capability of discriminative knowledge. To this end, we revisit multi-modal representation learning from a causal perspective and build the Structural Causal Model. Following the empirical explorations, we determine to capture the true causality between the discriminative knowledge of predominant modality and predictive label while considering the auxiliary modality. Thus, we introduce the $\beta$-generalization front-door criterion. Furthermore, we propose a novel network for sufficiently exploring multi-modal discriminative knowledge. Rigorous theoretical analyses and various empirical evaluations are provided to support the effectiveness of the innate mechanism behind our proposed method.
Authors: Liyuan Wang, Jingyi Xie, Xingxing Zhang, Hang Su, Jun Zhu
Abstract: The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving tasks, a promising direction involves keeping the pre-trained backbone frozen while employing parameter-efficient tuning (PET) techniques to instruct representation learning. Despite the popularity of Prompt-based PET for CL, its empirical design often leads to sub-optimal performance in our evaluation of different PTMs and target tasks. To this end, we propose a unified framework for CL with PTMs and PET that provides both theoretical and empirical advancements. We first perform an in-depth theoretical analysis of the CL objective in a pre-training context, decomposing it into hierarchical components namely within-task prediction, task-identity inference and task-adaptive prediction. We then present Hierarchical Decomposition PET (HiDe-PET), an innovative approach that explicitly optimizes the decomposed objective through incorporating task-specific and task-shared knowledge via mainstream PET techniques along with efficient recovery of pre-trained representations. Leveraging this framework, we delve into the distinct impacts of implementation strategy, PET technique and PET architecture, as well as adaptive knowledge accumulation amidst pronounced distribution changes. Finally, across various CL scenarios, our approach demonstrates remarkably superior performance over a broad spectrum of recent strong baselines.
Authors: Martin Lindstr\"om, Borja Rodr\'iguez-G\'alvez, Ragnar Thobaben, Mikael Skoglund
Abstract: Hyperspherical Prototypical Learning (HPL) is a supervised approach to representation learning that designs class prototypes on the unit hypersphere. The prototypes bias the representations to class separation in a scale invariant and known geometry. Previous approaches to HPL have either of the following shortcomings: (i) they follow an unprincipled optimisation procedure; or (ii) they are theoretically sound, but are constrained to only one possible latent dimension. In this paper, we address both shortcomings. To address (i), we present a principled optimisation procedure whose solution we show is optimal. To address (ii), we construct well-separated prototypes in a wide range of dimensions using linear block codes. Additionally, we give a full characterisation of the optimal prototype placement in terms of achievable and converse bounds, showing that our proposed methods are near-optimal.
Authors: Adarsh Prasad Behera, Paulius Daubaris, I\~naki Bravo, Jos\'e Gallego, Roberto Morabito, Joerg Widmer, Jaya Prakash Varma Champati
Abstract: On-device inference holds great potential for increased energy efficiency, responsiveness, and privacy in edge ML systems. However, due to less capable ML models that can be embedded in resource-limited devices, use cases are limited to simple inference tasks such as visual keyword spotting, gesture recognition, and predictive analytics. In this context, the Hierarchical Inference (HI) system has emerged as a promising solution that augments the capabilities of the local ML by offloading selected samples to an edge server or cloud for remote ML inference. Existing works demonstrate through simulation that HI improves accuracy. However, they do not account for the latency and energy consumption on the device, nor do they consider three key heterogeneous dimensions that characterize ML systems: hardware, network connectivity, and models. In contrast, this paper systematically compares the performance of HI with on-device inference based on measurements of accuracy, latency, and energy for running embedded ML models on five devices with different capabilities and three image classification datasets. For a given accuracy requirement, the HI systems we designed achieved up to 73% lower latency and up to 77% lower device energy consumption than an on-device inference system. The key to building an efficient HI system is the availability of small-size, reasonably accurate on-device models whose outputs can be effectively differentiated for samples that require remote inference. Despite the performance gains, HI requires on-device inference for all samples, which adds a fixed overhead to its latency and energy consumption. Therefore, we design a hybrid system, Early Exit with HI (EE-HI), and demonstrate that compared to HI, EE-HI reduces the latency by up to 59.7% and lowers the device's energy consumption by up to 60.4%.
Authors: Junxian Li, Di Zhang, Xunzhi Wang, Zeying Hao, Jingdi Lei, Qian Tan, Cai Zhou, Wei Liu, Yaotian Yang, Xinrui Xiong, Weiyun Wang, Zhe Chen, Wenhai Wang, Wei Li, Shufei Zhang, Mao Su, Wanli Ouyang, Yuqiang Li, Dongzhan Zhou
Abstract: Large Language Models (LLMs) have achieved remarkable success and have been applied across various scientific fields, including chemistry. However, many chemical tasks require the processing of visual information, which cannot be successfully handled by existing chemical LLMs. This brings a growing need for models capable of integrating multimodal information in the chemical domain. In this paper, we introduce \textbf{ChemVLM}, an open-source chemical multimodal large language model specifically designed for chemical applications. ChemVLM is trained on a carefully curated bilingual multimodal dataset that enhances its ability to understand both textual and visual chemical information, including molecular structures, reactions, and chemistry examination questions. We develop three datasets for comprehensive evaluation, tailored to Chemical Optical Character Recognition (OCR), Multimodal Chemical Reasoning (MMCR), and Multimodal Molecule Understanding tasks. We benchmark ChemVLM against a range of open-source and proprietary multimodal large language models on various tasks. Experimental results demonstrate that ChemVLM achieves competitive performance across all evaluated tasks. Our model can be found at https://huggingface.co/AI4Chem/ChemVLM-26B.
Authors: Jielong Yang, Rui Ding, Feng Ji, Hongbin Wang, Linbo Xie
Abstract: The performance of graph neural networks (GNNs) is susceptible to discrepancies between training and testing sample distributions. Prior studies have attempted to mitigating the impact of distribution shift by reconstructing node features during the testing phase without modifying the model parameters. However, these approaches lack theoretical analysis of the proximity between predictions and ground truth at test time. In this paper, we propose a novel node feature reconstruction method grounded in Lyapunov stability theory. Specifically, we model the GNN as a control system during the testing phase, considering node features as control variables. A neural controller that adheres to the Lyapunov stability criterion is then employed to reconstruct these node features, ensuring that the predictions progressively approach the ground truth at test time. We validate the effectiveness of our approach through extensive experiments across multiple datasets, demonstrating significant performance improvements.
Authors: Moritz Willig, Tim Nelson Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting
Abstract: Most work on causality in machine learning assumes that causal relationships are driven by a constant underlying process. However, the flexibility of agents' actions or tipping points in the environmental process can change the qualitative dynamics of the system. As a result, new causal relationships may emerge, while existing ones change or disappear, resulting in an altered causal graph. To analyze these qualitative changes on the causal graph, we propose the concept of meta-causal states, which groups classical causal models into clusters based on equivalent qualitative behavior and consolidates specific mechanism parameterizations. We demonstrate how meta-causal states can be inferred from observed agent behavior, and discuss potential methods for disentangling these states from unlabeled data. Finally, we direct our analysis towards the application of a dynamical system, showing that meta-causal states can also emerge from inherent system dynamics, and thus constitute more than a context-dependent framework in which mechanisms emerge only as a result of external factors.
Authors: Hanseul Cho, Jaeyoung Cha, Srinadh Bhojanapalli, Chulhee Yun
Abstract: Transformers often struggle with length generalization, meaning they fail to generalize to sequences longer than those encountered during training. While arithmetic tasks are commonly used to study length generalization, certain tasks are considered notoriously difficult, e.g., multi-operand addition (requiring generalization over both the number of operands and their lengths) and multiplication (requiring generalization over both operand lengths). In this work, we achieve approximately 2-3x length generalization on both tasks, which is the first such achievement in arithmetic Transformers. We design task-specific scratchpads enabling the model to focus on a fixed number of tokens per each next-token prediction step, and apply multi-level versions of \Position Coupling (Cho et al., 2024; McLeish et al., 2024) to let Transformers know the right position to attend to. On the theory side, we prove that a 1-layer Transformer using our method can solve multi-operand addition, up to operand length and operand count that are exponential in embedding dimension.
Authors: Amaury Wei, Olga Fink
Abstract: Rigid body interactions are fundamental to numerous scientific disciplines, but remain challenging to simulate due to their abrupt nonlinear nature and sensitivity to complex, often unknown environmental factors. These challenges call for adaptable learning-based methods capable of capturing complex interactions beyond explicit physical models and simulations. While graph neural networks can handle simple scenarios, they struggle with complex scenes and long-term predictions. We introduce a novel framework for modeling rigid body dynamics and learning collision interactions, addressing key limitations of existing graph-based methods. Our approach extends the traditional representation of meshes by incorporating higher-order topology complexes, offering a physically consistent representation. Additionally, we propose a physics-informed message-passing neural architecture, embedding physical laws directly in the model. Our method demonstrates superior accuracy, even during long rollouts, and exhibits strong generalization to unseen scenarios. Importantly, this work addresses the challenge of multi-entity dynamic interactions, with applications spanning diverse scientific and engineering domains.
Authors: Peiyan Hu, Rui Wang, Xiang Zheng, Tao Zhang, Haodong Feng, Ruiqi Feng, Long Wei, Yue Wang, Zhi-Ming Ma, Tailin Wu
Abstract: Simulating and controlling physical systems described by partial differential equations (PDEs) are crucial tasks across science and engineering. Recently, diffusion generative models have emerged as a competitive class of methods for these tasks due to their ability to capture long-term dependencies and model high-dimensional states. However, diffusion models typically struggle with handling system states with abrupt changes and generalizing to higher resolutions. In this work, we propose Wavelet Diffusion Neural Operator (WDNO), a novel PDE simulation and control framework that enhances the handling of these complexities. WDNO comprises two key innovations. Firstly, WDNO performs diffusion-based generative modeling in the wavelet domain for the entire trajectory to handle abrupt changes and long-term dependencies effectively. Secondly, to address the issue of poor generalization across different resolutions, which is one of the fundamental tasks in modeling physical systems, we introduce multi-resolution training. We validate WDNO on five physical systems, including 1D advection equation, three challenging physical systems with abrupt changes (1D Burgers' equation, 1D compressible Navier-Stokes equation and 2D incompressible fluid), and a real-world dataset ERA5, which demonstrates superior performance on both simulation and control tasks over state-of-the-art methods, with significant improvements in long-term and detail prediction accuracy. Remarkably, in the challenging context of the 2D high-dimensional and indirect control task aimed at reducing smoke leakage, WDNO reduces the leakage by 33.2% compared to the second-best baseline. The code can be found at https://github.com/AI4Science-WestlakeU/wdno.git.
Authors: Kai Yuan, Jiahao Zhang, Yidi Wang, Xiaobing Pei
Abstract: Adversarial attacks on Graph Neural Networks aim to perturb the performance of the learner by carefully modifying the graph topology and node attributes. Existing methods achieve attack stealthiness by constraining the modification budget and differences in graph properties. However, these methods typically disrupt task-relevant primary semantics directly, which results in low defensibility and detectability of the attack. In this paper, we propose an Adversarial Attack on High-level Semantics for Graph Neural Networks (AHSG), which is a graph structure attack model that ensures the retention of primary semantics. By combining latent representations with shared primary semantics, our model retains detectable attributes and relational patterns of the original graph while leveraging more subtle changes to carry out the attack. Then we use the Projected Gradient Descent algorithm to map the latent representations with attack effects to the adversarial graph. Through experiments on robust graph deep learning models equipped with defense strategies, we demonstrate that AHSG outperforms other state-of-the-art methods in attack effectiveness. Additionally, using Contextual Stochastic Block Models to detect the attacked graph further validates that our method preserves the primary semantics of the graph.
Authors: Haorong Han, Jidong Yuan, Chixuan Wei, Zhongyang Yu
Abstract: Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup for consistency regularization may degrade SSL performance by compromising the purity of artificial labels. Moreover, most pseudo-labeling based methods utilize thresholding strategy to exclude low-confidence data, aiming to mitigate confirmation bias; however, this approach limits the utility of unlabeled samples. To address these challenges, we propose RegMixMatch, a novel framework that optimizes the use of Mixup with both high- and low-confidence samples in SSL. First, we introduce semi-supervised RegMixup, which effectively addresses reduced artificial labels purity by using both mixed samples and clean samples for training. Second, we develop a class-aware Mixup technique that integrates information from the top-2 predicted classes into low-confidence samples and their artificial labels, reducing the confirmation bias associated with these samples and enhancing their effective utilization. Experimental results demonstrate that RegMixMatch achieves state-of-the-art performance across various SSL benchmarks.
Authors: Anthony Zhou, Amir Barati Farimani
Abstract: Neural surrogates for partial differential equations (PDEs) have become popular due to their potential to quickly simulate physics. With a few exceptions, neural surrogates generally treat the forward evolution of time-dependent PDEs as a black box by directly predicting the next state. While this is a natural and easy framework for applying neural surrogates, it can be an over-simplified and rigid framework for predicting physics. In this work, we evaluate an alternate framework in which neural solvers predict the temporal derivative and an ODE integrator forwards the solution in time, which has little overhead and is broadly applicable across model architectures and PDEs. We find that by simply changing the training target and introducing numerical integration during inference, neural surrogates can gain accuracy and stability in finely-discretized regimes. Predicting temporal derivatives also allows models to not be constrained to a specific temporal discretization, allowing for flexible time-stepping during inference or training on higher-resolution PDE data. Lastly, we investigate why this framework can be beneficial and in what situations does it work well.
Authors: Sascha Saralajew, Ashish Rana, Thomas Villmann, Ammar Shaker
Abstract: Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called deep Prototype-Based Networks (PBNs), also known as prototypical parts models. In this work, we analyze these models with respect to different properties, including interpretability. In particular, we focus on the Classification-by-Components (CBC) approach, which uses a probabilistic model to ensure interpretability and can be used as a shallow or deep architecture. We show that this model has several shortcomings, like creating contradicting explanations. Based on these findings, we propose an extension of CBC that solves these issues. Moreover, we prove that this extension has robustness guarantees and derive a loss that optimizes robustness. Additionally, our analysis shows that most (deep) PBNs are related to (deep) RBF classifiers, which implies that our robustness guarantees generalize to shallow RBF classifiers. The empirical evaluation demonstrates that our deep PBN yields state-of-the-art classification accuracy on different benchmarks while resolving the interpretability shortcomings of other approaches. Further, our shallow PBN variant outperforms other shallow PBNs while being inherently interpretable and exhibiting provable robustness guarantees.
Authors: Fabian Fumagalli, Maximilian Muschalik, Eyke H\"ullermeier, Barbara Hammer, Julia Herbinger
Abstract: Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these methods still remain mostly unknown, which limits their applicability for practitioners. In this work, we introduce a unified framework for local and global feature-based explanations using two well-established concepts: functional ANOVA (fANOVA) from statistics, and the notion of value and interaction from cooperative game theory. We introduce three fANOVA decompositions that determine the influence of feature distributions, and use game-theoretic measures, such as the Shapley value and interactions, to specify the influence of higher-order interactions. Our framework combines these two dimensions to uncover similarities and differences between a wide range of explanation techniques for features and groups of features. We then empirically showcase the usefulness of our framework on synthetic and real-world datasets.
Authors: Chen Li, Yoshihiro Yamanishi
Abstract: De novo generation of hit-like molecules is a challenging task in the drug discovery process. Most methods in previous studies learn the semantics and syntax of molecular structures by analyzing molecular graphs or simplified molecular input line entry system (SMILES) strings; however, they do not take into account the drug responses of the biological systems consisting of genes and proteins. In this study we propose a hybrid neural network, HNN2Mol, which utilizes gene expression profiles to generate molecular structures with desirable phenotypes for arbitrary target proteins. In the algorithm, a variational autoencoder is employed as a feature extractor to learn the latent feature distribution of the gene expression profiles. Then, a long short-term memory is leveraged as the chemical generator to produce syntactically valid SMILES strings that satisfy the feature conditions of the gene expression profile extracted by the feature extractor. Experimental results and case studies demonstrate that the proposed HNN2Mol model can produce new molecules with potential bioactivities and drug-like properties.
Authors: Yinkai Wang, Xiaohui Chen, Liping Liu, Soha Hassoun
Abstract: The annotation (assigning structural chemical identities) of MS/MS spectra remains a significant challenge due to the enormous molecular diversity in biological samples and the limited scope of reference databases. Currently, the vast majority of spectral measurements remain in the "dark chemical space" without structural annotations. To improve annotation, we propose MADGEN (Mass-spec Attends to De Novo Molecular GENeration), a scaffold-based method for de novo molecular structure generation guided by mass spectrometry data. MADGEN operates in two stages: scaffold retrieval and spectra-conditioned molecular generation starting with the scaffold. In the first stage, given an MS/MS spectrum, we formulate scaffold retrieval as a ranking problem and employ contrastive learning to align mass spectra with candidate molecular scaffolds. In the second stage, starting from the retrieved scaffold, we employ the MS/MS spectrum to guide an attention-based generative model to generate the final molecule. Our approach constrains the molecular generation search space, reducing its complexity and improving generation accuracy. We evaluate MADGEN on three datasets (NIST23, CANOPUS, and MassSpecGym) and evaluate MADGEN's performance with a predictive scaffold retriever and with an oracle retriever. We demonstrate the effectiveness of using attention to integrate spectral information throughout the generation process to achieve strong results with the oracle retriever.
Authors: Sunwoo Kim, Minkyu Kim, Dongmin Park
Abstract: Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate guidance approaches fail to optimize target rewards effectively. Addressing these limitations, we propose a training-free, test-time method based on Sequential Monte Carlo (SMC) to sample from the reward-aligned target distribution. Our approach, tailored for diffusion sampling and incorporating tempering techniques, achieves comparable or superior target rewards to fine-tuning methods while preserving diversity and cross-reward generalization. We demonstrate its effectiveness in single-reward optimization, multi-objective scenarios, and online black-box optimization. This work offers a robust solution for aligning diffusion models with diverse downstream objectives without compromising their general capabilities. Code is available at https://github.com/krafton-ai/DAS.
Authors: Yu Wu, Yansong Li, Zeyu Dong, Nitya Sathyavageeswaran, Anand D. Sarwate
Abstract: Deploying complex machine learning models on resource-constrained devices is challenging due to limited computational power, memory, and model retrainability. To address these limitations, a hybrid system can be established by augmenting the local model with a server-side model, where samples are selectively deferred by a rejector and then sent to the server for processing. The hybrid system enables efficient use of computational resources while minimizing the overhead associated with server usage. The recently proposed Learning to Help (L2H) model trains a server model given a fixed local (client) model, differing from the Learning to Defer (L2D) framework, which trains the client for a fixed (expert) server. In both L2D and L2H, the training includes learning a rejector at the client to determine when to query the server. In this work, we extend the L2H model from binary to multi-class classification problems and demonstrate its applicability in a number of different scenarios of practical interest in which access to the server may be limited by cost, availability, or policy. We derive a stage-switching surrogate loss function that is differentiable, convex, and consistent with the Bayes rule corresponding to the 0-1 loss for the L2H model. Experiments show that our proposed methods offer an efficient and practical solution for multi-class classification in resource-constrained environments.
Authors: Elham Kiyani, Khemraj Shukla, Jorge F. Urb\'an, J\'er\^ome Darbon, George Em Karniadakis
Abstract: Physics-Informed Neural Networks (PINNs) have revolutionized the computation of PDE solutions by integrating partial differential equations (PDEs) into the neural network's training process as soft constraints, becoming an important component of the scientific machine learning (SciML) ecosystem. More recently, physics-informed Kolmogorv-Arnold networks (PIKANs) have also shown to be effective and comparable in accuracy with PINNs. In their current implementation, both PINNs and PIKANs are mainly optimized using first-order methods like Adam, as well as quasi-Newton methods such as BFGS and its low-memory variant, L-BFGS. However, these optimizers often struggle with highly non-linear and non-convex loss landscapes, leading to challenges such as slow convergence, local minima entrapment, and (non)degenerate saddle points. In this study, we investigate the performance of Self-Scaled BFGS (SSBFGS), Self-Scaled Broyden (SSBroyden) methods and other advanced quasi-Newton schemes, including BFGS and L-BFGS with different line search strategies approaches. These methods dynamically rescale updates based on historical gradient information, thus enhancing training efficiency and accuracy. We systematically compare these optimizers -- using both PINNs and PIKANs -- on key challenging linear, stiff, multi-scale and non-linear PDEs, including the Burgers, Allen-Cahn, Kuramoto-Sivashinsky, and Ginzburg-Landau equations. Our findings provide state-of-the-art results with orders-of-magnitude accuracy improvements without the use of adaptive weights or any other enhancements typically employed in PINNs. More broadly, our results reveal insights into the effectiveness of second-order optimization strategies in significantly improving the convergence and accurate generalization of PINNs and PIKANs.
Authors: Jixiu Zhai, Tianchi Lu, Haitian Zhong, Ziyang Xu, Yuhuan Liu, Shengrui Xu, Jingwan Wang, Dan Huang
Abstract: Advances in peptide identification are revolutionizing our ability to decipher protein functions and accelerate therapeutic discovery. We present PDeepPP, a deep learning framework that integrates pretrained protein language models with parallel transformer-CNN architectures, achieving state-of-the-art performance in peptide characterization tasks. The model's hybrid architecture demonstrates unique capabilities in capturing both local sequence motifs and global structural features, as evidenced by 29% improved cluster separation in UMAP visualizations compared to conventional approaches. Evaluated across 33 biological recognition tasks - including post-translational modification site prediction and bioactive peptide identification - PDeepPP outperformed existing methods in 25 tasks with average AUC improvements of 4.2%. Notably, it achieved 0.9726 accuracy with PR AUC 0.9977 in antimicrobial peptide detection while reducing false negatives by 37.5% in antimalarial recognition scenarios. This framework enables accurate large-scale peptide analysis, achieving 218* acceleration over sequence-alignment-based methods while maintaining 99.5% specificity in critical glycosylation site detection.PDeepPP establishes a new paradigm for computational peptide analysis through its synergistic architecture design, enabling rapid yet precise functional annotation that bridges molecular pattern recognition with translational biomedical applications.We have made our implementation, including code, data, and pretrained models, publicly available via GitHub (https://github.com/fondress/PDeepPP) and Hugging Face (https://huggingface.co/fondress/PDeppPP).
URLs: https://github.com/fondress/PDeepPP), https://huggingface.co/fondress/PDeppPP).
Authors: Davor Vukadin, Marin \v{S}ili\'c, Goran Dela\v{c}
Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like tabular data learning, where simpler models are often preferred due to interpretability and efficiency. In this paper, we introduce a novel yet straightforward method for incorporating LLM-generated global task feature attributions into the training process of smaller networks. Specifically, we propose an attribution-matching regularization term that aligns the training dynamics of the smaller model with the insights provided by the LLM. By doing so, our approach yields superior performance in few-shot learning scenarios. Notably, our method requires only black-box API access to the LLM, making it easy to integrate into existing training pipelines with minimal computational overhead. Furthermore, we demonstrate how this method can be used to address common issues in real-world datasets, such as skewness and bias. By integrating high-level knowledge from LLMs, our approach improves generalization, even when training data is limited or imbalanced. We validate its effectiveness through extensive experiments across multiple tasks, demonstrating improved learning efficiency and model robustness.
Authors: Blaine Quackenbush, Paul J. Atzberger
Abstract: We introduce methods for obtaining pretrained Geometric Neural Operators (GNPs) that can serve as basal foundation models for use in obtaining geometric features. These can be used within data processing pipelines for machine learning tasks and numerical methods. We show how our GNPs can be trained to learn robust latent representations for the differential geometry of point-clouds to provide estimates of metric, curvature, and other shape-related features. We demonstrate how our pre-trained GNPs can be used (i) to estimate the geometric properties of surfaces of arbitrary shape and topologies with robustness in the presence of noise, (ii) to approximate solutions of geometric partial differential equations (PDEs) on manifolds, and (iii) to solve equations for shape deformations such as curvature driven flows. We release codes and weights for using GNPs in the package geo_neural_op. This allows for incorporating our pre-trained GNPs as components for reuse within existing and new data processing pipelines. The GNPs also can be used as part of numerical solvers involving geometry or as part of methods for performing inference and other geometric tasks.
Authors: Yu Qiao, Phuong-Nam Tran, Ji Su Yoon, Loc X. Nguyen, Eui-Nam Huh, Dusit Niyato, Choong Seon Hong
Abstract: Reinforcement learning (RL)-based large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, have gained significant attention for their exceptional capabilities in natural language processing and multimodal data understanding. Meanwhile, the rapid expansion of information services has driven the growing need for intelligence, efficient, and adaptable wireless networks. Wireless networks require the empowerment of RL-based LLMs while these models also benefit from wireless networks to broaden their application scenarios. Specifically, RL-based LLMs can enhance wireless communication systems through intelligent resource allocation, adaptive network optimization, and real-time decision-making. Conversely, wireless networks provide a vital infrastructure for the efficient training, deployment, and distributed inference of RL-based LLMs, especially in decentralized and edge computing environments. This mutual empowerment highlights the need for a deeper exploration of the interplay between these two domains. We first review recent advancements in wireless communications, highlighting the associated challenges and potential solutions. We then discuss the progress of RL-based LLMs, focusing on key technologies for LLM training, challenges, and potential solutions. Subsequently, we explore the mutual empowerment between these two fields, highlighting key motivations, open challenges, and potential solutions. Finally, we provide insights into future directions, applications, and their societal impact to further explore this intersection, paving the way for next-generation intelligent communication systems. Overall, this survey provides a comprehensive overview of the relationship between RL-based LLMs and wireless networks, offering a vision where these domains empower each other to drive innovations.
Authors: Entao Yang, Xiaotian Zhang, Yue Shang, Ge Zhang
Abstract: One of the central challenges in modern machine learning is understanding how neural networks generalize knowledge learned from training data to unseen test data. While numerous empirical techniques have been proposed to improve generalization, a theoretical understanding of the mechanism of generalization remains elusive. Here we introduce the concept of Boltzmann entropy into neural networks by re-conceptualizing such networks as hypothetical molecular systems where weights and biases are atomic coordinates, and the loss function is the potential energy. By employing molecular simulation algorithms, we compute entropy landscapes as functions of both training loss and test accuracy (or test loss), on networks with up to 1 million parameters, across four distinct machine learning tasks: arithmetic question, real-world tabular data, image recognition, and language modeling. Our results reveal the existence of high-entropy advantage, wherein high-entropy network states generally outperform those reached via conventional training techniques like stochastic gradient descent. This entropy advantage provides a thermodynamic explanation for neural network generalizability: the generalizable states occupy a larger part of the parameter space than its non-generalizable analog at low train loss. Furthermore, we find this advantage more pronounced in narrower neural networks, indicating a need for different training optimizers tailored to different sizes of networks.
Authors: Alireza Aghabagherloo, Aydin Abadi, Sumanta Sarkar, Vishnu Asutosh Dasu, Bart Preneel
Abstract: The accuracy and robustness of machine learning models against adversarial attacks are significantly influenced by factors such as training data quality, model architecture, the training process, and the deployment environment. In recent years, duplicated data in training sets, especially in language models, has attracted considerable attention. It has been shown that deduplication enhances both training performance and model accuracy in language models. While the importance of data quality in training image classifier Deep Neural Networks (DNNs) is widely recognized, the impact of duplicated images in the training set on model generalization and performance has received little attention. In this paper, we address this gap and provide a comprehensive study on the effect of duplicates in image classification. Our analysis indicates that the presence of duplicated images in the training set not only negatively affects the efficiency of model training but also may result in lower accuracy of the image classifier. This negative impact of duplication on accuracy is particularly evident when duplicated data is non-uniform across classes or when duplication, whether uniform or non-uniform, occurs in the training set of an adversarially trained model. Even when duplicated samples are selected in a uniform way, increasing the amount of duplication does not lead to a significant improvement in accuracy.
Authors: Jay Lee, Hanqi Su
Abstract: Recent advancements in industrial artificial intelligence (AI) are reshaping the industry by driving smarter manufacturing, predictive maintenance, and intelligent decision-making. However, existing approaches often focus primarily on algorithms and models while overlooking the importance of systematically integrating domain knowledge, data, and models to develop more comprehensive and effective AI solutions. Therefore, the effective development and deployment of industrial AI require a more comprehensive and systematic approach. To address this gap, this paper reviews previous research, rethinks the role of industrial AI, and proposes a unified industrial AI foundation framework comprising three core modules: the knowledge module, data module, and model module. These modules help to extend and enhance the industrial AI methodology platform, supporting various industrial applications. In addition, a case study on rotating machinery diagnosis is presented to demonstrate the effectiveness of the proposed framework, and several future directions are highlighted for the development of the industrial AI foundation framework.
Authors: Xiangxiang Chu, Hailang Huang, Xiao Zhang, Fei Wei, Yong Wang
Abstract: Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and propose a minimalist RL approach termed Group Policy Gradient (GPG). Unlike conventional methods, GPG directly optimize the original RL objective, thus obviating the need for surrogate loss functions. By eliminating the critic and reference models, avoiding KL divergence constraints, and addressing the advantage and gradient estimation bias, our approach significantly simplifies the training process compared to Group Relative Policy Optimization (GRPO). Our approach achieves superior performance without relying on auxiliary techniques or adjustments. As illustrated in Figure 1, extensive experiments demonstrate that our method not only reduces computational costs but also consistently outperforms GRPO across various unimodal and multimodal tasks. Our code is available at https://github.com/AMAP-ML/GPG.
Authors: Shahryar Zehtabi, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher G. Brinton
Abstract: Much of the federated learning (FL) literature focuses on settings where local dataset statistics remain the same between training and testing time. Recent advances in domain generalization (DG) aim to use data from source (training) domains to train a model that generalizes well to data from unseen target (testing) domains. In this paper, we are motivated by two major gaps in existing work on FL and DG: (1) the lack of formal mathematical analysis of DG objectives and training processes; and (2) DG research in FL being limited to the conventional star-topology architecture. Addressing the second gap, we develop $\textit{Decentralized Federated Domain Generalization with Style Sharing}$ ($\texttt{StyleDDG}$), a fully decentralized DG algorithm designed to allow devices in a peer-to-peer network to achieve DG based on sharing style information inferred from their datasets. Additionally, we fill the first gap by providing the first systematic approach to mathematically analyzing style-based DG training optimization. We cast existing centralized DG algorithms within our framework, and employ their formalisms to model $\texttt{StyleDDG}$. Based on this, we obtain analytical conditions under which a sub-linear convergence rate of $\texttt{StyleDDG}$ can be obtained. Through experiments on two popular DG datasets, we demonstrate that $\texttt{StyleDDG}$ can obtain significant improvements in accuracy across target domains with minimal added communication overhead compared to decentralized gradient methods that do not employ style sharing.
Authors: Abdo Abouelrous, Laurens Bliek, Adriana F. Gabor, Yaoxin Wu, Yingqian Zhang
Abstract: Column Generation (CG) is a popular method dedicated to enhancing computational efficiency in large scale Combinatorial Optimization (CO) problems. It reduces the number of decision variables in a problem by solving a pricing problem. For many CO problems, the pricing problem is an Elementary Shortest Path Problem with Resource Constraints (ESPPRC). Large ESPPRC instances are difficult to solve to near-optimality. Consequently, we use a Graph neural Network (GNN) to reduces the size of the ESPPRC such that it becomes computationally tractable with standard solving techniques. Our GNN is trained by Unsupervised Learning and outputs a distribution for the arcs to be retained in the reduced PP. The reduced PP is solved by a local search that finds columns with large reduced costs and speeds up convergence. We apply our method on a set of Capacitated Vehicle Routing Problems with Time Windows and show significant improvements in convergence compared to simple reduction techniques from the literature. For a fixed computational budget, we improve the objective values by over 9\% for larger instances. We also analyze the performance of our CG algorithm and test the generalization of our method to different classes of instances than the training data.
Authors: Yemin Yu, Neil Tenenholtz, Lester Mackey, Ying Wei, David Alvarez-Melis, Ava P. Amini, Alex X. Lu
Abstract: Recent advances in self-supervised deep learning have improved our ability to quantify cellular morphological changes in high-throughput microscopy screens, a process known as morphological profiling. However, most current methods only learn from images, despite many screens being inherently multimodal, as they involve both a chemical or genetic perturbation as well as an image-based readout. We hypothesized that incorporating chemical compound structure during self-supervised pre-training could improve learned representations of images in high-throughput microscopy screens. We introduce a representation learning framework, MICON (Molecular-Image Contrastive Learning), that models chemical compounds as treatments that induce counterfactual transformations of cell phenotypes. MICON significantly outperforms classical hand-crafted features such as CellProfiler and existing deep-learning-based representation learning methods in challenging evaluation settings where models must identify reproducible effects of drugs across independent replicates and data-generating centers. We demonstrate that incorporating chemical compound information into the learning process provides consistent improvements in our evaluation setting and that modeling compounds specifically as treatments in a causal framework outperforms approaches that directly align images and compounds in a single representation space. Our findings point to a new direction for representation learning in morphological profiling, suggesting that methods should explicitly account for the multimodal nature of microscopy screening data.
Authors: Timur Carstensen, Neeratyoy Mallik, Frank Hutter, Martin Rapp
Abstract: As model sizes grow, finding efficient and cost-effective hyperparameter optimization (HPO) methods becomes increasingly crucial for deep learning pipelines. While multi-fidelity HPO (MF-HPO) trades off computational resources required for DL training with lower fidelity estimations, existing fidelity sources often fail under lower compute and memory constraints. We propose a novel fidelity source: the number of layers that are trained or frozen during training. For deep networks, this approach offers significant compute and memory savings while preserving rank correlations between hyperparameters at low fidelities compared to full model training. We demonstrate this in our empirical evaluation across ResNets and Transformers and additionally analyze the utility of frozen layers as a fidelity in using GPU resources as a fidelity in HPO, and for a combined MF-HPO with other fidelity sources. This contribution opens new applications for MF-HPO with hardware resources as a fidelity and creates opportunities for improved algorithms navigating joint fidelity spaces.
Authors: Ayan Chatterjee, Barbara Ikica, Babak Ravandi, John Palowitch
Abstract: Link prediction on graphs has applications spanning from recommender systems to drug discovery. Temporal link prediction (TLP) refers to predicting future links in a temporally evolving graph and adds additional complexity related to the dynamic nature of graphs. State-of-the-art TLP models incorporate memory modules alongside graph neural networks to learn both the temporal mechanisms of incoming nodes and the evolving graph topology. However, memory modules only store information about nodes seen at train time, and hence such models cannot be directly transferred to entirely new graphs at test time and deployment. In this work, we study a new transfer learning task for temporal link prediction, and develop transfer-effective methods for memory-laden models. Specifically, motivated by work showing the informativeness of structural signals for the TLP task, we augment a structural mapping module to the existing TLP model architectures, which learns a mapping from graph structural (topological) features to memory embeddings. Our work paves the way for a memory-free foundation model for TLP.
Authors: Wonjun Yi, Yong-Hwa Park
Abstract: This work introduces a multi-output classification (MOC) framework designed for domain adaptation in fault diagnosis, particularly under partially labeled (PL) target domain scenarios and compound fault conditions in rotating machinery. Unlike traditional multi-class classification (MCC) methods that treat each fault combination as a distinct class, the proposed approach independently estimates the severity of each fault type, improving both interpretability and diagnostic accuracy. The model incorporates multi-kernel maximum mean discrepancy (MK-MMD) and entropy minimization (EM) losses to facilitate feature transfer from the source to the target domain. In addition, frequency layer normalization (FLN) is applied to preserve structural properties in the frequency domain, which are strongly influenced by system dynamics and are often stationary with respect to changes in rpm. Evaluations across six domain adaptation cases with PL data demonstrate that MOC outperforms baseline models in macro F1 score. Moreover, MOC consistently achieves better classification performance for individual fault types, and FLN shows superior adaptability compared to other normalization techniques.
Authors: Alejandro Carderera, Sebastian Pokutta
Abstract: Constrained second-order convex optimization algorithms are the method of choice when a high accuracy solution to a problem is needed, due to their local quadratic convergence. These algorithms require the solution of a constrained quadratic subproblem at every iteration. We present the \emph{Second-Order Conditional Gradient Sliding} (SOCGS) algorithm, which uses a projection-free algorithm to solve the constrained quadratic subproblems inexactly. When the feasible region is a polytope the algorithm converges quadratically in primal gap after a finite number of linearly convergent iterations. Once in the quadratic regime the SOCGS algorithm requires $\mathcal{O}(\log(\log 1/\varepsilon))$ first-order and Hessian oracle calls and $\mathcal{O}(\log (1/\varepsilon) \log(\log1/\varepsilon))$ linear minimization oracle calls to achieve an $\varepsilon$-optimal solution. This algorithm is useful when the feasible region can only be accessed efficiently through a linear optimization oracle, and computing first-order information of the function, although possible, is costly.
Authors: Qiming Bao, Alex Yuxuan Peng, Tim Hartill, Neset Tan, Zhenyun Deng, Michael Witbrock, Jiamou Liu
Abstract: Combining deep learning with symbolic logic reasoning aims to capitalize on the success of both fields and is drawing increasing attention. Inspired by DeepLogic, an end-to-end model trained to perform inference on logic programs, we introduce IMA-GloVe-GA, an iterative neural inference network for multi-step reasoning expressed in natural language. In our model, reasoning is performed using an iterative memory neural network based on RNN with a gated attention mechanism. We evaluate IMA-GloVe-GA on three datasets: PARARULES, CONCEPTRULES V1 and CONCEPTRULES V2. Experimental results show DeepLogic with gated attention can achieve higher test accuracy than DeepLogic and other RNN baseline models. Our model achieves better out-of-distribution generalisation than RoBERTa-Large when the rules have been shuffled. Furthermore, to address the issue of unbalanced distribution of reasoning depths in the current multi-step reasoning datasets, we develop PARARULE-Plus, a large dataset with more examples that require deeper reasoning steps. Experimental results show that the addition of PARARULE-Plus can increase the model's performance on examples requiring deeper reasoning depths. The source code and data are available at https://github.com/Strong-AI-Lab/Multi-Step-Deductive-Reasoning-Over-Natural-Language.
URLs: https://github.com/Strong-AI-Lab/Multi-Step-Deductive-Reasoning-Over-Natural-Language.
Authors: Ye Tian, Yuqi Gu, Yang Feng
Abstract: Representation multi-task learning (MTL) has achieved tremendous success in practice. However, the theoretical understanding of these methods is still lacking. Most existing theoretical works focus on cases where all tasks share the same representation, and claim that MTL almost always improves performance. Nevertheless, as the number of tasks grows, assuming all tasks share the same representation is unrealistic. Furthermore, empirical findings often indicate that a shared representation does not necessarily improve single-task learning performance. In this paper, we aim to understand how to learn from tasks with \textit{similar but not exactly the same} linear representations, while dealing with outlier tasks. Assuming a known intrinsic dimension, we propose a penalized empirical risk minimization method and a spectral method that are \textit{adaptive} to the similarity structure and \textit{robust} to outlier tasks. Both algorithms outperform single-task learning when representations across tasks are sufficiently similar and the proportion of outlier tasks is small. Moreover, they always perform at least as well as single-task learning, even when the representations are dissimilar. We provide information-theoretic lower bounds to demonstrate that both methods are nearly \textit{minimax} optimal in a large regime, with the spectral method being optimal in the absence of outlier tasks. Additionally, we introduce a thresholding algorithm to adapt to an unknown intrinsic dimension. We conduct extensive numerical experiments to validate our theoretical findings.
Authors: Shan Ali, Chaima Boufaied, Domenico Bianculli, Paula Branco, Lionel Briand
Abstract: Growth in system complexity increases the need for automated log analysis techniques, such as Log-based Anomaly Detection (LAD). While deep learning (DL) methods have been widely used for LAD, traditional machine learning (ML) techniques can also perform well depending on the context and dataset. Semi-supervised techniques deserve the same attention as they offer practical advantages over fully supervised methods. Current evaluations mainly focus on detection accuracy, but this alone is insufficient to determine the suitability of a technique for a given LAD task. Other aspects to consider include training and prediction times as well as the sensitivity to hyperparameter tuning, which in practice matters to engineers. This paper presents a comprehensive empirical study evaluating a wide range of supervised and semi-supervised, traditional and deep ML techniques across four criteria: detection accuracy, time performance, and sensitivity to hyperparameter tuning in both detection accuracy and time performance. The experimental results show that supervised traditional and deep ML techniques fare similarly in terms of their detection accuracy and prediction time on most of the benchmark datasets considered in our study. Moreover, overall, sensitivity analysis to hyperparameter tuning with respect to detection accuracy shows that supervised traditional ML techniques are less sensitive than deep learning techniques. Further, semi-supervised techniques yield significantly worse detection accuracy than supervised techniques.
Authors: Henrik von Kleist, Alireza Zamanian, Ilya Shpitser, Narges Ahmidi
Abstract: Machine learning methods often assume that input features are available at no cost. However, in domains like healthcare, where acquiring features could be expensive or harmful, it is necessary to balance a feature's acquisition cost against its predictive value. The task of training an AI agent to decide which features to acquire is called active feature acquisition (AFA). By deploying an AFA agent, we effectively alter the acquisition strategy and trigger a distribution shift. To safely deploy AFA agents under this distribution shift, we present the problem of active feature acquisition performance evaluation (AFAPE). We examine AFAPE under i) a no direct effect (NDE) assumption, stating that acquisitions do not affect the underlying feature values; and ii) a no unobserved confounding (NUC) assumption, stating that retrospective feature acquisition decisions were only based on observed features. We show that one can apply missing data methods under the NDE assumption and offline reinforcement learning under the NUC assumption. When NUC and NDE hold, we propose a novel semi-offline reinforcement learning framework. This framework requires a weaker positivity assumption and introduces three new estimators: A direct method (DM), an inverse probability weighting (IPW), and a double reinforcement learning (DRL) estimator.
Authors: Antonio \'Alvarez-L\'opez, Rafael Orive-Illera, Enrique Zuazua
Abstract: We address binary classification using neural ordinary differential equations from the perspective of simultaneous control of $N$ data points. We consider a single-neuron architecture with parameters fixed as piecewise constant functions of time. In this setting, the model complexity can be quantified by the number of control switches. Previous work has shown that classification can be achieved using a point-by-point strategy that requires $O(N)$ switches. We propose a new control method that classifies any arbitrary dataset by sequentially steering clusters of $d$ points, thereby reducing the complexity to $O(N/d)$ switches. The optimality of this result, particularly in high dimensions, is supported by some numerical experiments. Our complexity bound is sufficient but often conservative because same-class points tend to appear in larger clusters, simplifying classification. This motivates studying the probability distribution of the number of switches required. We introduce a simple control method that imposes a collinearity constraint on the parameters, and analyze a worst-case scenario where both classes have the same size and all points are i.i.d. Our results highlight the benefits of high-dimensional spaces, showing that classification using constant controls becomes more probable as $d$ increases.
Authors: Salvatore Contino, Paolo Sortino, Maria Rita Gulotta, Ugo Perricone, Roberto Pirrone
Abstract: Background: Virtual Screening (VS) has become an essential tool in drug discovery, enabling the rapid and cost-effective identification of potential bioactive molecules. Among recent advancements, Graph Neural Networks (GNNs) have gained prominence for their ability to model complex molecular structures using graph-based representations. However, the integration of explainable methods to elucidate the specific contributions of molecular substructures to biological activity remains a significant challenge. This limitation hampers both the interpretability of predictive models and the rational design of novel therapeutics.\\ Results: We trained 20 GNN models on a dataset of small molecules with the goal of predicting their activity on 20 distinct protein targets from the Kinase family. These classifiers achieved state-of-the-art performance in virtual screening tasks, demonstrating high accuracy and robustness on different targets. Building upon these models, we implemented the Hierarchical Grad-CAM graph Explainer (HGE) framework, enabling an in-depth analysis of the molecular moieties driving protein-ligand binding stabilization. HGE exploits Grad-CAM explanations at the atom, ring, and whole-molecule levels, leveraging the message-passing mechanism to highlight the most relevant chemical moieties. Validation against experimental data from the literature confirmed the ability of the explainer to recognize a molecular pattern of drugs and correctly annotate them to the known target. Conclusion: Our approach may represent a valid support to shorten both the screening and the hit discovery process. Detailed knowledge of the molecular substructures that play a role in the binding process can help the computational chemist to gain insights into the structure optimization, as well as in drug repurposing tasks.
Authors: Huy Pham, Hoang Ta, Hoa T. Vu
Abstract: In this work, we present data stream algorithms to compute optimal splits for decision tree learning. In particular, given a data stream of observations \(x_i\) and their corresponding labels \(y_i\), without the i.i.d. assumption, the objective is to identify the optimal split \(j\) that partitions the data into two sets, minimizing the mean squared error (for regression) or the misclassification rate and Gini impurity (for classification). We propose several efficient streaming algorithms that require sublinear space and use a small number of passes to solve these problems. These algorithms can also be extended to the MapReduce model. Our results, while not directly comparable, complements the seminal work of Domingos-Hulten (KDD 2000) and Hulten-Spencer-Domingos (KDD 2001).
Authors: Tobias Meggendorfer, Maximilian Weininger, Patrick Wienh\"oft
Abstract: Markov decision processes (MDPs) are a fundamental model for decision making under uncertainty. They exhibit non-deterministic choice as well as probabilistic uncertainty. Traditionally, verification algorithms assume exact knowledge of the probabilities that govern the behaviour of an MDP. As this assumption is often unrealistic in practice, statistical model checking (SMC) was developed in the past two decades. It allows to analyse MDPs with unknown transition probabilities and provide probably approximately correct (PAC) guarantees on the result. Model-based SMC algorithms sample the MDP and build a model of it by estimating all transition probabilities, essentially for every transition answering the question: ``What are the odds?'' However, so far the statistical methods employed by the state of the art SMC algorithms are quite naive. Our contribution are several fundamental improvements to those methods: On the one hand, we survey statistics literature for better concentration inequalities; on the other hand, we propose specialised approaches that exploit our knowledge of the MDP. Our improvements are generally applicable to many kinds of problem statements because they are largely independent of the setting. Moreover, our experimental evaluation shows that they lead to significant gains, reducing the number of samples that the SMC algorithm has to collect by up to two orders of magnitude.
Authors: Hwiyeol Jo, Taiwoo Park, Hyunwoo Lee, Nayoung Choi, Changbong Kim, Ohjoon Kwon, Donghyeon Jeon, Eui-Hyeon Lee, Kyoungho Shin, Sun Suk Lim, Kyungmi Kim, Jihye Lee, Sun Kim
Abstract: Although there has been a growing interest among industries in integrating generative LLMs into their services, limited experience and scarcity of resources act as a barrier in launching and servicing large-scale LLM-based services. In this paper, we share our experiences in developing and operating generative AI models within a national-scale search engine, with a specific focus on the sensitiveness of user queries. We propose a taxonomy for sensitive search queries, outline our approaches, and present a comprehensive analysis report on sensitive queries from actual users. We believe that our experiences in launching generative AI search systems can contribute to reducing the barrier in building generative LLM-based services.
Authors: Davide Bianchi, Florian Bossmann, Wenlong Wang, Mingming Liu
Abstract: We introduce a data-adaptive inversion method that integrates classical or deep learning-based approaches with iterative graph Laplacian regularization, specifically targeting acoustic impedance inversion - a critical task in seismic exploration. Our method initiates from an impedance estimate derived using either traditional inversion techniques or neural network-based methods. This initial estimate guides the construction of a graph Laplacian operator, effectively capturing structural characteristics of the impedance profile. Utilizing a Tikhonov-inspired variational framework with this graph-informed prior, our approach iteratively updates and refines the impedance estimate while continuously recalibrating the graph Laplacian. This iterative refinement shows rapid convergence, increased accuracy, and enhanced robustness to noise compared to initial reconstructions alone. Extensive validation performed on synthetic and real seismic datasets across varying noise levels confirms the effectiveness of our method. Performance evaluations include four initial inversion methods: two classical techniques and two neural networks - previously established in the literature.
Authors: Nearchos Potamitis, Lars Klein, Roland Aydin, Robert West, Caglar Gulcehre, Akhil Arora
Abstract: While numerous frameworks have been developed to enhance the reasoning abilities of large language models (LLMs), there is a scarcity of methods that effectively balance the trade-off between cost and quality. In this paper, we introduce Fleet of Agents (FoA), a novel and intuitive yet principled framework utilizing LLMs as agents to navigate through dynamic tree searches, employing a genetic-type particle filtering approach. FoA spawns a multitude of agents, each exploring the search space autonomously, followed by a selection phase where resampling based on a heuristic value function optimizes the balance between exploration and exploitation. This mechanism enables dynamic branching, adapting the exploration strategy based on discovered solutions. We conduct extensive experiments on three benchmark tasks, ``Game of 24'', ``Mini-Crosswords'', and ``WebShop'', utilizing four different LLMs, ``GPT-3.5'', ``GPT-4'', ``LLaMA3.2-11B'', and ``LLaMA3.2-90B''. On average across all tasks and LLMs, FoA obtains a quality improvement of ~5% while requiring only ~40% of the cost of previous SOTA methods. Notably, our analyses reveal that (1) FoA achieves the best cost-quality trade-off among all benchmarked methods and (2) FoA + LLaMA3.2-11B surpasses the Llama3.2-90B model. FoA is publicly available at https://github.com/au-clan/FoA.
Authors: Ernesto Araya, Mihai Cucuringu, Hemant Tyagi
Abstract: Given an undirected measurement graph $\mathcal{H} = ([n], \mathcal{E})$, the classical angular synchronization problem consists of recovering unknown angles $\theta_1^*,\dots,\theta_n^*$ from a collection of noisy pairwise measurements of the form $(\theta_i^* - \theta_j^*) \mod 2\pi$, for all $\{i,j\} \in \mathcal{E}$. This problem arises in a variety of applications, including computer vision, time synchronization of distributed networks, and ranking from pairwise comparisons. In this paper, we consider a dynamic version of this problem where the angles, and also the measurement graphs evolve over $T$ time points. Assuming a smoothness condition on the evolution of the latent angles, we derive three algorithms for joint estimation of the angles over all time points. Moreover, for one of the algorithms, we establish non-asymptotic recovery guarantees for the mean-squared error (MSE) under different statistical models. In particular, we show that the MSE converges to zero as $T$ increases under milder conditions than in the static setting. This includes the setting where the measurement graphs are highly sparse and disconnected, and also when the measurement noise is large and can potentially increase with $T$. We complement our theoretical results with experiments on synthetic data.
Authors: Yunxuan Ma, Yide Bian, Hao Xu, Weitao Yang, Jingshu Zhao, Zhijian Duan, Feng Wang, Xiaotie Deng
Abstract: Market equilibrium is one of the most fundamental solution concepts in economics and social optimization analysis. Existing works on market equilibrium computation primarily focus on settings with relatively few buyers. Motivated by this, our paper investigates the computation of market equilibrium in scenarios with a large-scale buyer population, where buyers and goods are represented by their contexts. Building on this realistic and generalized contextual market model, we introduce MarketFCNet, a deep learning-based method for approximating market equilibrium. We start by parameterizing the allocation of each good to each buyer using a neural network, which depends solely on the context of the buyer and the good. Next, we propose an efficient method to unbiasedly estimate the loss function of the training algorithm, enabling us to optimize the network parameters through gradient. To evaluate the approximated solution, we propose a metric called Nash Gap, which quantifies the deviation of the given allocation and price pair from the market equilibrium. Experimental results indicate that MarketFCNet delivers competitive performance and significantly lower running times compared to existing methods as the market scale expands, demonstrating the potential of deep learning-based methods to accelerate the approximation of large-scale contextual market equilibrium.
Authors: Hao Liu, Junze Tony Ye, Jose Blanchet, Nian Si
Abstract: We introduce ScoreFusion, a theoretically grounded method for fusing multiple pre-trained diffusion models that are assumed to generate from auxiliary populations. ScoreFusion is particularly useful for enhancing the generative modeling of a target population with limited observed data. Our starting point considers the family of KL barycenters of the auxiliary populations, which is proven to be an optimal parametric class in the KL sense, but difficult to learn. Nevertheless, by recasting the learning problem as score matching in denoising diffusion, we obtain a tractable way of computing the optimal KL barycenter weights. We prove a dimension-free sample complexity bound in total variation distance, provided that the auxiliary models are well-fitted for their own task and the auxiliary tasks combined capture the target well. The sample efficiency of ScoreFusion is demonstrated by learning handwritten digits. We also provide a simple adaptation of a Stable Diffusion denoising pipeline that enables sampling from the KL barycenter of two auxiliary checkpoints; on a portrait generation task, our method produces faces that enhance population heterogeneity relative to the auxiliary distributions.
Authors: Musfiqur Rahman, SayedHassan Khatoonabadi, Ahmad Abdellatif, Haya Samaana, Emad Shihab
Abstract: Nowadays, software systems tend to include Artificial Intelligence (AI) components. Changes in the operational environment have been known to negatively impact the stability of AI-enabled software systems by causing unintended changes in behavior. However, how an environment configuration impacts the behavior of such systems has yet to be explored. Understanding and quantifying the degree of instability caused by different environment settings can help practitioners decide the best environment configuration for the most stable AI systems. To achieve this goal, we performed experiments with eight different combinations of three key environment variables (operating system, Python version, and CPU architecture) on $30$ open-source AI-enabled systems using the Travis CI platform. We determine the existence and the degree of instability introduced by each configuration using three metrics: the output of an AI component of the system (model performance), the time required to build and run the system (processing time), and the cost associated with building and running the system (expense). Our results indicate that changes in environment configurations lead to instability across all three metrics; however, it is observed more frequently with respect to processing time and expense rather than model performance. For example, between Linux and MacOS, instability is observed in 23\%, 96.67\%, and 100\% of the studied projects in model performance, processing time, and expense, respectively. Our findings underscore the importance of identifying the optimal combination of configuration settings to mitigate drops in model performance and reduce the processing time and expense before deploying an AI-enabled system.
Authors: Jiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Felix Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, Zirui Wang, Ruoming Pang
Abstract: Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges, which calls for comprehensive evaluation of tool-use capabilities. While previous works focused on either evaluating over stateless web services (RESTful API), based on a single turn user prompt, or an off-policy dialog trajectory, ToolSandbox includes stateful tool execution, implicit state dependencies between tools, a built-in user simulator supporting on-policy conversational evaluation and a dynamic evaluation strategy for intermediate and final milestones over an arbitrary trajectory. We show that open source and proprietary models have a significant performance gap, and complex tasks like State Dependency, Canonicalization and Insufficient Information defined in ToolSandbox are challenging even the most capable SOTA LLMs, providing brand-new insights into tool-use LLM capabilities. ToolSandbox evaluation framework is released at https://github.com/apple/ToolSandbox
Authors: Sayak Saha Roy, Shirin Nilizadeh
Abstract: In this paper, we introduce PhishLang, the first fully client-side anti-phishing framework built on a lightweight ensemble framework that utilizes advanced language models to analyze the contextual features of a website's source code and URL. Unlike traditional heuristic or machine learning approaches that rely on static features and struggle to adapt to evolving threats, or deep learning models that are computationally intensive, our approach utilizes MobileBERT, a fast and memory-efficient variant of the BERT architecture, to capture nuanced features indicative of phishing attacks. To further enhance detection accuracy, PhishLang employs a multi-modal ensemble approach, combining both the URL and Source detection models. This architecture ensures robustness by allowing one model to compensate for scenarios where the other may fail, or if both models provide ambiguous inferences. As a result, PhishLang excels at detecting both regular and evasive phishing threats, including zero-day attacks, outperforming popular anti-phishing tools, while operating without relying on external blocklists and safeguarding user privacy by ensuring that browser history remains entirely local and unshared. We release PhishLang as a Chromium browser extension and also open-source the framework to aid the research community.
Authors: Neil Ashton, Charles Mockett, Marian Fuchs, Louis Fliessbach, Hendrik Hetmann, Thilo Knacke, Norbert Schonwald, Vangelis Skaperdas, Grigoris Fotiadis, Astrid Walle, Burkhard Hupertz, Danielle Maddix
Abstract: Machine Learning (ML) has the potential to revolutionise the field of automotive aerodynamics, enabling split-second flow predictions early in the design process. However, the lack of open-source training data for realistic road cars, using high-fidelity CFD methods, represents a barrier to their development. To address this, a high-fidelity open-source (CC-BY-SA) public dataset for automotive aerodynamics has been generated, based on 500 parametrically morphed variants of the widely-used DrivAer notchback generic vehicle. Mesh generation and scale-resolving CFD was executed using consistent and validated automatic workflows representative of the industrial state-of-the-art. Geometries and rich aerodynamic data are published in open-source formats. To our knowledge, this is the first large, public-domain dataset for complex automotive configurations generated using high-fidelity CFD.
Authors: Jiliang Li, Yifan Zhang, Yu Huang, Kevin Leach
Abstract: Recent growth and proliferation of malware have tested practitioners ability to promptly classify new samples according to malware families. In contrast to labor-intensive reverse engineering efforts, machine learning approaches have demonstrated increased speed and accuracy. However, most existing deep-learning malware family classifiers must be calibrated using a large number of samples that are painstakingly manually analyzed before training. Furthermore, as novel malware samples arise that are beyond the scope of the training set, additional reverse engineering effort must be employed to update the training set. The sheer volume of new samples found in the wild creates substantial pressure on practitioners ability to reverse engineer enough malware to adequately train modern classifiers. In this paper, we present MalMixer, a malware family classifier using semi-supervised learning that achieves high accuracy with sparse training data. We present a domain-knowledge-aware data augmentation technique for malware feature representations, enhancing few-shot performance of semi-supervised malware family classification. We show that MalMixer achieves state-of-the-art performance in few-shot malware family classification settings. Our research confirms the feasibility and effectiveness of lightweight, domain-knowledge-aware data augmentation methods for malware features and shows the capabilities of similar semi-supervised classifiers in addressing malware classification issues.
Authors: Kin Man Lee, Sean Ye, Qingyu Xiao, Zixuan Wu, Zulfiqar Zaidi, David B. D'Ambrosio, Pannag R. Sanketi, Matthew Gombolay
Abstract: Advances in robot learning have enabled robots to generate skills for a variety of tasks. Yet, robot learning is typically sample inefficient, struggles to learn from data sources exhibiting varied behaviors, and does not naturally incorporate constraints. These properties are critical for fast, agile tasks such as playing table tennis. Modern techniques for learning from demonstration improve sample efficiency and scale to diverse data, but are rarely evaluated on agile tasks. In the case of reinforcement learning, achieving good performance requires training on high-fidelity simulators. To overcome these limitations, we develop a novel diffusion modeling approach that is offline, constraint-guided, and expressive of diverse agile behaviors. The key to our approach is a kinematic constraint gradient guidance (KCGG) technique that computes gradients through both the forward kinematics of the robot arm and the diffusion model to direct the sampling process. KCGG minimizes the cost of violating constraints while simultaneously keeping the sampled trajectory in-distribution of the training data. We demonstrate the effectiveness of our approach for time-critical robotic tasks by evaluating KCGG in two challenging domains: simulated air hockey and real table tennis. In simulated air hockey, we achieved a 25.4% increase in block rate, while in table tennis, we saw a 17.3% increase in success rate compared to imitation learning baselines.
Authors: Diego Martinez-Taboada, Aaditya Ramdas
Abstract: We present a sequential version of the kernelized Stein discrepancy goodness-of-fit test, which allows for conducting goodness-of-fit tests for unnormalized densities that are continuously monitored and adaptively stopped. That is, the sample size need not be fixed prior to data collection; the practitioner can choose whether to stop the test or continue to gather evidence at any time while controlling the false discovery rate. In stark contrast to related literature, we do not impose uniform boundedness on the Stein kernel. Instead, we exploit the potential boundedness of the Stein kernel at arbitrary point evaluations to define test martingales, that give way to the subsequent novel sequential tests. We prove the validity of the test, as well as an asymptotic lower bound for the logarithmic growth of the wealth process under the alternative. We further illustrate the empirical performance of the test with a variety of distributions, including restricted Boltzmann machines.
Authors: Giuseppe Alessio D'Inverno, Saeid Moradizadeh, Sajad Salavatidezfouli, Pasquale Claudio Africa, Gianluigi Rozza
Abstract: The complexity of the cardiovascular system needs to be accurately reproduced in order to promptly acknowledge health conditions; to this aim, advanced multifidelity and multiphysics numerical models are crucial. On one side, Full Order Models (FOMs) deliver accurate hemodynamic assessments, but their high computational demands hinder their real-time clinical application. In contrast, Reduced Order Models (ROMs) provide more efficient yet accurate solutions, essential for personalized healthcare and timely clinical decision-making. In this work, we explore the application of computational fluid dynamics (CFD) in cardiovascular medicine by integrating FOMs with ROMs for predicting the risk of aortic aneurysm growth and rupture. Wall Shear Stress (WSS) and the Oscillatory Shear Index (OSI), sampled at different growth stages of the thoracic aortic aneurysm, are predicted by means of Graph Neural Networks (GNNs). GNNs exploit the natural graph structure of the mesh obtained by the Finite Volume (FV) discretization, taking into account the spatial local information, regardless of the dimension of the input graph. Our experimental validation framework yields promising results, confirming our method as a valid alternative that overcomes the curse of dimensionality.
Authors: Zachary Novack, Ge Zhu, Jonah Casebeer, Julian McAuley, Taylor Berg-Kirkpatrick, Nicholas J. Bryan
Abstract: Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge. Sound examples can be found at https://presto-music.github.io/web/.
Authors: Xiangru Zhu, Penglei Sun, Yaoxian Song, Yanghua Xiao, Zhixu Li, Chengyu Wang, Jun Huang, Bei Yang, Xiaoxiao Xu
Abstract: Accurate interpretation and visualization of human instructions are crucial for text-to-image (T2I) synthesis. However, current models struggle to capture semantic variations from word order changes, and existing evaluations, relying on indirect metrics like text-image similarity, fail to reliably assess these challenges. This often obscures poor performance on complex or uncommon linguistic patterns by the focus on frequent word combinations. To address these deficiencies, we propose a novel metric called SemVarEffect and a benchmark named SemVarBench, designed to evaluate the causality between semantic variations in inputs and outputs in T2I synthesis. Semantic variations are achieved through two types of linguistic permutations, while avoiding easily predictable literal variations. Experiments reveal that the CogView-3-Plus and Ideogram 2 performed the best, achieving a score of 0.2/1. Semantic variations in object relations are less understood than attributes, scoring 0.07/1 compared to 0.17-0.19/1. We found that cross-modal alignment in UNet or Transformers plays a crucial role in handling semantic variations, a factor previously overlooked by a focus on textual encoders. Our work establishes an effective evaluation framework that advances the T2I synthesis community's exploration of human instruction understanding. Our benchmark and code are available at https://github.com/zhuxiangru/SemVarBench .
Authors: Zihao Zeng, Bokai Lin, Tianqi Hou, Hao Zhang, Zhijie Deng
Abstract: The KV-Cache technique has become the standard for the inference of large language models (LLMs). Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM inference system. This paper enables a novel dynamic KV-Cache eviction policy by injecting a lightweight module called Attention-Gate to the model. It accepts the global context as input and yields eviction flags for each token. The self-attention modules in the model proceed according to the flags and cache only a subset of the KV states for next token prediction. The Attention-Gates can yield various flags for different heads and layers and be easily tuned on top of a pre-trained LLM via continual pre-training or supervised fine-tuning. The computational and memory overhead introduced by Attention-Gates can be minimal. We empirically evaluate the proposed approach across multiple scenarios, showing that effective eviction of redundant tokens can not only improve efficiency but also enhance performance.
Authors: Declan Campbell, Sunayana Rane, Tyler Giallanza, Nicol\`o De Sabbata, Kia Ghods, Amogh Joshi, Alexander Ku, Steven M. Frankland, Thomas L. Griffiths, Jonathan D. Cohen, Taylor W. Webb
Abstract: Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models are able to describe and generate a diverse array of complex, naturalistic images, yet they exhibit surprising failures on basic multi-object reasoning tasks -- such as counting, localization, and simple forms of visual analogy -- that humans perform with near perfect accuracy. To better understand this puzzling pattern of successes and failures, we turn to theoretical accounts of the binding problem in cognitive science and neuroscience, a fundamental problem that arises when a shared set of representational resources must be used to represent distinct entities (e.g., to represent multiple objects in an image), necessitating the use of serial processing to avoid interference. We find that many of the puzzling failures of state-of-the-art VLMs can be explained as arising due to the binding problem, and that these failure modes are strikingly similar to the limitations exhibited by rapid, feedforward processing in the human brain.
Authors: Yan Zhang, Ming Li, Chun Li, Zhaoxia Liu, Ye Zhang, Fei Richard Yu
Abstract: Evidence-based deep learning represents a burgeoning paradigm for uncertainty estimation, offering reliable predictions with negligible extra computational overheads. Existing methods usually adopt Kullback-Leibler divergence to estimate the uncertainty of network predictions, ignoring domain gaps among various modalities. To tackle this issue, this paper introduces a novel algorithm based on H\"older Divergence (HD) to enhance the reliability of multi-view learning by addressing inherent uncertainty challenges from incomplete or noisy data. Generally, our method extracts the representations of multiple modalities through parallel network branches, and then employs HD to estimate the prediction uncertainties. Through the Dempster-Shafer theory, integration of uncertainty from different modalities, thereby generating a comprehensive result that considers all available representations. Mathematically, HD proves to better measure the ``distance'' between real data distribution and predictive distribution of the model and improve the performances of multi-class recognition tasks. Specifically, our method surpass the existing state-of-the-art counterparts on all evaluating benchmarks. We further conduct extensive experiments on different backbones to verify our superior robustness. It is demonstrated that our method successfully pushes the corresponding performance boundaries. Finally, we perform experiments on more challenging scenarios, \textit{i.e.}, learning with incomplete or noisy data, revealing that our method exhibits a high tolerance to such corrupted data.
Authors: Neel P. Bhatt, Yunhao Yang, Rohan Siva, Daniel Milan, Ufuk Topcu, Zhangyang Wang
Abstract: Multimodal foundation models offer a promising framework for robotic perception and planning by processing sensory inputs to generate actionable plans. However, addressing uncertainty in both perception (sensory interpretation) and decision-making (plan generation) remains a critical challenge for ensuring task reliability. We present a comprehensive framework to disentangle, quantify, and mitigate these two forms of uncertainty. We first introduce a framework for uncertainty disentanglement, isolating perception uncertainty arising from limitations in visual understanding and decision uncertainty relating to the robustness of generated plans. To quantify each type of uncertainty, we propose methods tailored to the unique properties of perception and decision-making: we use conformal prediction to calibrate perception uncertainty and introduce Formal-Methods-Driven Prediction (FMDP) to quantify decision uncertainty, leveraging formal verification techniques for theoretical guarantees. Building on this quantification, we implement two targeted intervention mechanisms: an active sensing process that dynamically re-observes high-uncertainty scenes to enhance visual input quality and an automated refinement procedure that fine-tunes the model on high-certainty data, improving its capability to meet task specifications. Empirical validation in real-world and simulated robotic tasks demonstrates that our uncertainty disentanglement framework reduces variability by up to 40% and enhances task success rates by 5% compared to baselines. These improvements are attributed to the combined effect of both interventions and highlight the importance of uncertainty disentanglement, which facilitates targeted interventions that enhance the robustness and reliability of autonomous systems. Fine-tuned models, code, and datasets are available at https://uncertainty-in-planning.github.io/.
Authors: Fabio Pavirani, Jonas Van Gompel, Seyed Soroush Karimi Madahi, Bert Claessens, Chris Develder
Abstract: The growing reliance on renewable energy sources, particularly solar and wind, has introduced challenges due to their uncontrollable production. This complicates maintaining the electrical grid balance, prompting some transmission system operators in Western Europe to implement imbalance tariffs that penalize unsustainable power deviations. These tariffs create an implicit demand response framework to mitigate grid instability. Yet, several challenges limit active participation. In Belgium, for example, imbalance prices are only calculated at the end of each 15-minute settlement period, creating high risk due to price uncertainty. This risk is further amplified by the inherent volatility of imbalance prices, discouraging participation. Although transmission system operators provide minute-based price predictions, the system imbalance volatility makes accurate price predictions challenging to obtain and requires sophisticated techniques. Moreover, publishing price estimates can prompt participants to adjust their schedules, potentially affecting the system balance and the final price, adding further complexity. To address these challenges, we propose a Monte Carlo Tree Search method that publishes accurate imbalance prices while accounting for potential response actions. Our approach models the system dynamics using a neural network forecaster and a cluster of virtual batteries controlled by reinforcement learning agents. Compared to Belgium's current publication method, our technique improves price accuracy by 20.4% under ideal conditions and by 12.8% in more realistic scenarios. This research addresses an unexplored, yet crucial problem, positioning this paper as a pioneering work in analyzing the potential of more advanced imbalance price publishing techniques.
Authors: Taha Abdullah, Arjun Ashok, Brandon Zarate, Shubhada Martha, Billy Ouattara, Norman Matloff, Aditya Mittal
Abstract: The growing power of data science can play a crucial role in addressing social discrimination, necessitating nuanced understanding and effective mitigation strategies for biases. "Data Science Looks At Discrimination" (DSLD) is an R and Python package designed to provide users with a comprehensive toolkit of statistical and graphical methods for assessing possible discrimination related to protected groups such as race, gender, and age. The package addresses critical issues by identifying and mitigating confounders and reducing bias against protected groups in prediction algorithms. In educational settings, DSLD offers instructors powerful tools to teach statistical principles through motivating real world examples of discrimination analysis. The inclusion of an 80 page Quarto book further supports users from statistics educators to legal professionals in effectively applying these analytical tools to real world scenarios.
Authors: Alex Finkelstein, Nikita Vladimirov, Moritz Zaiss, Or Perlman
Abstract: Biophysical model fitting plays a key role in obtaining quantitative parameters from physiological signals and images. However, the model complexity for molecular magnetic resonance imaging (MRI) often translates into excessive computation time, which makes clinical use impractical. Here, we present a generic computational approach for solving the parameter extraction inverse problem posed by ordinary differential equation (ODE) modeling coupled with experimental measurement of the system dynamics. This is achieved by formulating a numerical ODE solver to function as a step-wise analytical one, thereby making it compatible with automatic differentiation-based optimization. This enables efficient gradient-based model fitting, and provides a new approach to parameter quantification based on self-supervised learning from a single data observation. The neural-network-based train-by-fit pipeline was used to quantify semisolid magnetization transfer (MT) and chemical exchange saturation transfer (CEST) amide proton exchange parameters in the human brain, in an in-vivo molecular MRI study (n = 4). The entire pipeline of the first whole brain quantification was completed in 18.3 $\pm$ 8.3 minutes. Reusing the single-subject-trained network for inference in new subjects took 1.0 $\pm$ 0.2 s, to provide results in agreement with literature values and scan-specific fit results.
Authors: Kawshik Manikantan, Makarand Tapaswi, Vineet Gandhi, Shubham Toshniwal
Abstract: Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding. To address this, we introduce IdentifyMe, a new benchmark for mention resolution presented in a multiple-choice question (MCQ) format, commonly used for evaluating LLMs. IdentifyMe features long narratives and employs heuristics to exclude easily identifiable mentions, creating a more challenging task. The benchmark also consists of a curated mixture of different mention types and corresponding entities, allowing for a fine-grained analysis of model performance. We evaluate both closed- and open source LLMs on IdentifyMe and observe a significant performance gap (20-30%) between the state-of-the-art sub-10B open models vs. closed ones. We observe that pronominal mentions, which have limited surface information, are typically much harder for models to resolve than nominal mentions. Additionally, we find that LLMs often confuse entities when their mentions overlap in nested structures. The highest-scoring model, GPT-4o, achieves 81.9% accuracy, highlighting the strong referential capabilities of state-of-the-art LLMs while also indicating room for further improvement.
Authors: Zhenkai Wu, Xiaowen Ma, Rongrong Lian, Kai Zheng, Wei Zhang
Abstract: In complex scenes and varied conditions, effectively integrating spatial-temporal context is crucial for accurately identifying changes. However, current RS-CD methods lack a balanced consideration of performance and efficiency. CNNs lack global context, Transformers are computationally expensive, and Mambas face CUDA dependence and local correlation loss. In this paper, we propose CDXLSTM, with a core component that is a powerful XLSTM-based feature enhancement layer, integrating the advantages of linear computational complexity, global context perception, and strong interpret-ability. Specifically, we introduce a scale-specific Feature Enhancer layer, incorporating a Cross-Temporal Global Perceptron customized for semantic-accurate deep features, and a Cross-Temporal Spatial Refiner customized for detail-rich shallow features. Additionally, we propose a Cross-Scale Interactive Fusion module to progressively interact global change representations with spatial responses. Extensive experimental results demonstrate that CDXLSTM achieves state-of-the-art performance across three benchmark datasets, offering a compelling balance between efficiency and accuracy. Code is available at https://github.com/xwmaxwma/rschange.
Authors: Sylvain Sardy, Maxime van Cutsem, Xiaoyu Ma
Abstract: At the time of environmental concerns about artificial intelligence, in particular its need for greedy storage and computation, sparsity inducing neural networks offer a promising path towards frugality and solution for less waste. Sparse learners compress the inputs (features) by selecting only the ones needed for good generalization. A human scientist can then give an intelligent interpretation to the few selected features. If genes are the inputs and cancer type is the output, then the selected genes give the cancerologist clues on what genes have an effect on certain cancers. LASSO-type regularization leads to good input selection for linear associations, but few attempts have been made for nonlinear associations modeled as an artificial neural network. A stringent but efficient way of testing whether a feature selection method works is to check if a phase transition occurs in the probability of retrieving the relevant features, as observed and mathematically studied for linear models. Our method achieves just so for artificial neural networks, and, on real data, it has the best compromise between number of selected features and generalization performance. Our method is flexible, applying to complex models ranging from shallow to deep artificial neural networks and supporting various cost functions and sparsity-promoting penalties. It does not rely on cross-validation or on a validation set to select its single regularization parameter making it user-friendly. Our approach can be seen as a form of compressed sensing for complex models, allowing to distill high-dimensional data into a compact, interpretable subset of meaningful features, just the opposite of a black box. A python package is available at https://github.com/VcMaxouuu/AnnHarderLasso containing all the simulations and ready-to-use models.
Authors: Abhishek Gupta, Amruta Parulekar, Sameep Chattopadhyay, Preethi Jyothi
Abstract: Spontaneous or conversational multilingual speech presents many challenges for state-of-the-art automatic speech recognition (ASR) systems. In this work, we present a new technique AMPS that augments a multilingual multimodal ASR system with paraphrase-based supervision for improved conversational ASR in multiple languages, including Hindi, Marathi, Malayalam, Kannada, and Nyanja. We use paraphrases of the reference transcriptions as additional supervision while training the multimodal ASR model and selectively invoke this paraphrase objective for utterances with poor ASR performance. Using AMPS with a state-of-the-art multimodal model SeamlessM4T, we obtain significant relative reductions in word error rates (WERs) of up to 5%. We present detailed analyses of our system using both objective and human evaluation metrics.
Authors: Michael Yeung, Toya Teramoto, Songtao Wu, Tatsuo Fujiwara, Kenji Suzuki, Tamaki Kojima
Abstract: The use of large-scale, web-scraped datasets to train face recognition models has raised significant privacy and bias concerns. Synthetic methods mitigate these concerns and provide scalable and controllable face generation to enable fair and accurate face recognition. However, existing synthetic datasets display limited intraclass and interclass diversity and do not match the face recognition performance obtained using real datasets. Here, we propose VariFace, a two-stage diffusion-based pipeline to create fair and diverse synthetic face datasets to train face recognition models. Specifically, we introduce three methods: Face Recognition Consistency to refine demographic labels, Face Vendi Score Guidance to improve interclass diversity, and Divergence Score Conditioning to balance the identity preservation-intraclass diversity trade-off. When constrained to the same dataset size, VariFace considerably outperforms previous synthetic datasets (0.9200 $\rightarrow$ 0.9405) and achieves comparable performance to face recognition models trained with real data (Real Gap = -0.0065). In an unconstrained setting, VariFace not only consistently achieves better performance compared to previous synthetic methods across dataset sizes but also, for the first time, outperforms the real dataset (CASIA-WebFace) across six evaluation datasets. This sets a new state-of-the-art performance with an average face verification accuracy of 0.9567 (Real Gap = +0.0097) across LFW, CFP-FP, CPLFW, AgeDB, and CALFW datasets and 0.9366 (Real Gap = +0.0380) on the RFW dataset.
Authors: Dong Chen, Alice Dethise, Istemi Ekin Akkus, Ivica Rimac, Klaus Satzke, Antti Koskela, Marco Canini, Wei Wang, Ruichuan Chen
Abstract: A collaboration between dataset owners and model owners is needed to facilitate effective machine learning (ML) training. During this collaboration, however, dataset owners and model owners want to protect the confidentiality of their respective assets (i.e., datasets, models and training code), with the dataset owners also caring about the privacy of individual users whose data is in their datasets. Existing solutions either provide limited confidentiality for models and training code, or suffer from privacy issues due to collusion. We present Citadel++, a collaborative ML training system designed to simultaneously protect the confidentiality of datasets, models and training code as well as the privacy of individual users. Citadel++ enhances differential privacy mechanisms to safeguard the privacy of individual user data while maintaining model utility. By employing Virtual Machine-level Trusted Execution Environments (TEEs) as well as the improved sandboxing and integrity mechanisms through OS-level techniques, Citadel++ effectively preserves the confidentiality of datasets, models and training code, and enforces our privacy mechanisms even when the models and training code have been maliciously designed. Our experiments show that Citadel++ provides model utility and performance while adhering to the confidentiality and privacy requirements of dataset owners and model owners, outperforming the state-of-the-art privacy-preserving training systems by up to 543x on CPU and 113x on GPU TEEs.
Authors: Rishabh Kabra, Drew A. Hudson, Sjoerd van Steenkiste, Joao Carreira, Niloy J. Mitra
Abstract: We introduce a hierarchical probabilistic approach to go from a 2D image to multiview 3D: a diffusion "prior" predicts the unseen 3D geometry, which then conditions a diffusion "decoder" to generate novel views of the subject. We use a pointmap-based geometric representation to coordinate the generation of multiple target views simultaneously. We construct a predictable distribution of geometric features per target view to enable learnability across examples, and generalization to arbitrary inputs images. Our modular, geometry-driven approach to novel-view synthesis (called "unPIC") beats competing baselines such as CAT3D, EscherNet, Free3D, and One-2-3-45 on held-out objects from ObjaverseXL, as well as unseen real-world objects from Google Scanned Objects, Amazon Berkeley Objects, and the Digital Twin Catalog.
Authors: Zhenpeng Huang, Xinhao Li, Jiaqi Li, Jing Wang, Xiangyu Zeng, Cheng Liang, Tao Wu, Xi Chen, Liang Li, Limin Wang
Abstract: Multimodal Large Language Models (MLLMs) have significantly progressed in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique challenges due to the need for real-time processing of continuous online video streams. To this end, this paper presents systematic efforts from three perspectives: evaluation benchmark, model architecture, and training strategy. First, we introduce OVBench, a comprehensive question-answering benchmark designed to evaluate models' ability to perceive, memorize, and reason within online video contexts. It features 6 core task types across three temporal contexts-past, current, and future-forming 16 subtasks from diverse datasets. Second, we propose a new Pyramid Memory Bank (PMB) that effectively retains key spatiotemporal information in video streams. Third, we proposed an offline-to-online learning paradigm, designing an interleaved dialogue format for online video data and constructing an instruction-tuning dataset tailored for online video training. This framework led to the development of VideoChat-Online, a robust and efficient model for online video understanding. Despite the lower computational cost and higher efficiency, VideoChat-Online outperforms existing state-of-the-art offline and online models across popular offline video benchmarks and OVBench, demonstrating the effectiveness of our model architecture and training strategy. % Our approach surpasses existing state-of-the-art offline models Qwen2-VL 7B and online models Flash-VStream, by 4.19% and 23.7% on OVBench, respectively.
Authors: Lillian Tsai, Eugene Bagdasarian
Abstract: Judging an action's safety requires knowledge of the context in which the action takes place. To human agents who act in various contexts, this may seem obvious: performing an action such as email deletion may or may not be appropriate depending on the email's content, the goal (e.g., to erase sensitive emails or to clean up trash), and the type of email address (e.g., work or personal). Unlike people, computational systems have often had only limited agency in limited contexts. Thus, manually crafted policies and user confirmation (e.g., smartphone app permissions or network access control lists), while imperfect, have sufficed to restrict harmful actions. However, with the upcoming deployment of generalist agents that support a multitude of tasks (e.g., an automated personal assistant), we argue that we must rethink security designs to adapt to the scale of contexts and capabilities of these systems. As a first step, this paper explores contextual security in the domain of agents and proposes contextual agent security (Conseca), a framework to generate just-in-time, contextual, and human-verifiable security policies.
Authors: Daniel Levy, Siba Smarak Panigrahi, S\'ekou-Oumar Kaba, Qiang Zhu, Kin Long Kelvin Lee, Mikhail Galkin, Santiago Miret, Siamak Ravanbakhsh
Abstract: Generating novel crystalline materials has the potential to lead to advancements in fields such as electronics, energy storage, and catalysis. The defining characteristic of crystals is their symmetry, which plays a central role in determining their physical properties. However, existing crystal generation methods either fail to generate materials that display the symmetries of real-world crystals, or simply replicate the symmetry information from examples in a database. To address this limitation, we propose SymmCD, a novel diffusion-based generative model that explicitly incorporates crystallographic symmetry into the generative process. We decompose crystals into two components and learn their joint distribution through diffusion: 1) the asymmetric unit, the smallest subset of the crystal which can generate the whole crystal through symmetry transformations, and; 2) the symmetry transformations needed to be applied to each atom in the asymmetric unit. We also use a novel and interpretable representation for these transformations, enabling generalization across different crystallographic symmetry groups. We showcase the competitive performance of SymmCD on a subset of the Materials Project, obtaining diverse and valid crystals with realistic symmetries and predicted properties.
Authors: Zohar Ringel, Noa Rubin, Edo Mor, Moritz Helias, Inbar Seroussi
Abstract: Deep learning algorithms have made incredible strides in the past decade, yet due to their complexity, the science of deep learning remains in its early stages. Being an experimentally driven field, it is natural to seek a theory of deep learning within the physics paradigm. As deep learning is largely about learning functions and distributions over functions, statistical field theory, a rich and versatile toolbox for tackling complex distributions over functions (fields) is an obvious choice of formalism. Research efforts carried out in the past few years have demonstrated the ability of field theory to provide useful insights on generalization, implicit bias, and feature learning effects. Here we provide a pedagogical review of this emerging line of research.
Authors: Dana Rubin, Allan dos Santos Costa, Manvitha Ponnapati, Joseph Jacobson
Abstract: Ribonucleic acid (RNA) plays fundamental roles in biological systems, from carrying genetic information to performing enzymatic function. Understanding and designing RNA can enable novel therapeutic application and biotechnological innovation. To enhance RNA design, in this paper we introduce RiboGen, the first deep learning model to simultaneously generate RNA sequence and all-atom 3D structure. RiboGen leverages the standard Flow Matching with Discrete Flow Matching in a multimodal data representation. RiboGen is based on Euclidean Equivariant neural networks for efficiently processing and learning three-dimensional geometry. Our experiments show that RiboGen can efficiently generate chemically plausible and self-consistent RNA samples, suggesting that co-generation of sequence and structure is a competitive approach for modeling RNA.
Authors: Jay Lee, Hanqi Su, Dai-Yan Ji, Takanobu Minami
Abstract: Over the past ten years, the application of artificial intelligence (AI) and machine learning (ML) in engineering domains has gained significant popularity, showcasing their potential in data-driven contexts. However, the complexity and diversity of engineering problems often require the development of domain-specific AI approaches, which are frequently hindered by a lack of systematic methodologies, scalability, and robustness during the development process. To address this gap, this paper introduces the "ABCDE" as the key elements of Engineering AI and proposes a unified, systematic engineering AI ecosystem framework, including eight essential layers, along with attributes, goals, and applications, to guide the development and deployment of AI solutions for specific engineering needs. Additionally, key challenges are examined, and eight future research directions are highlighted. By providing a comprehensive perspective, this paper aims to advance the strategic implementation of AI, fostering the development of next-generation engineering AI solutions.
Authors: Chuning Zhu, Raymond Yu, Siyuan Feng, Benjamin Burchfiel, Paarth Shah, Abhishek Gupta
Abstract: Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations. Meanwhile, large amounts of video data depicting a wide range of environments and diverse behaviors are readily available. This data provides a rich source of information about real-world dynamics and agent-environment interactions. Leveraging this data directly for imitation learning, however, has proven difficult due to the lack of action annotation required for most contemporary methods. In this work, we present Unified World Models (UWM), a framework that allows for leveraging both video and action data for policy learning. Specifically, a UWM integrates an action diffusion process and a video diffusion process within a unified transformer architecture, where independent diffusion timesteps govern each modality. By simply controlling each diffusion timestep, UWM can flexibly represent a policy, a forward dynamics, an inverse dynamics, and a video generator. Through simulated and real-world experiments, we show that: (1) UWM enables effective pretraining on large-scale multitask robot datasets with both dynamics and action predictions, resulting in more generalizable and robust policies than imitation learning, (2) UWM naturally facilitates learning from action-free video data through independent control of modality-specific diffusion timesteps, further improving the performance of finetuned policies. Our results suggest that UWM offers a promising step toward harnessing large, heterogeneous datasets for scalable robot learning, and provides a simple unification between the often disparate paradigms of imitation learning and world modeling. Videos and code are available at https://weirdlabuw.github.io/uwm/.
Authors: Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, Pengfei Liu
Abstract: Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on either manually engineered prompts (prompt engineering-based) with brittle performance or reinforcement learning within controlled Retrieval-Augmented Generation (RAG) environments (RAG-based) that fail to capture the complexities of real-world interaction. In this paper, we introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents through scaling reinforcement learning (RL) in real-world environments with authentic web search interactions. Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web. We implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures and overcoming significant technical challenges. Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines and up to 7.2 points over RAG-based RL agents. Our qualitative analysis reveals emergent cognitive behaviors from end-to-end RL training, including the ability to formulate plans, cross-validate information from multiple sources, engage in self-reflection to redirect research, and maintain honesty when unable to find definitive answers. Our results highlight that end-to-end training in real-world web environments is not merely an implementation detail but a fundamental requirement for developing robust research capabilities aligned with real-world applications. We release DeepResearcher at https://github.com/GAIR-NLP/DeepResearcher.
Authors: Saibal De, Oliver Knitter, Rohan Kodati, Paramsothy Jayakumar, James Stokes, Shravan Veerapaneni
Abstract: Variational quantum algorithms (VQAs) are promising hybrid quantum-classical methods designed to leverage the computational advantages of quantum computing while mitigating the limitations of current noisy intermediate-scale quantum (NISQ) hardware. Although VQAs have been demonstrated as proofs of concept, their practical utility in solving real-world problems -- and whether quantum-inspired classical algorithms can match their performance -- remains an open question. We present a novel application of the variational quantum linear solver (VQLS) and its classical neural quantum states-based counterpart, the variational neural linear solver (VNLS), as key components within a minimum map Newton solver for a complementarity-based rigid body contact model. We demonstrate using the VNLS that our solver accurately simulates the dynamics of rigid spherical bodies during collision events. These results suggest that quantum and quantum-inspired linear algebra algorithms can serve as viable alternatives to standard linear algebra solvers for modeling certain physical systems.
Authors: Minjie Deng, Yan Wei, Hao Zhai, An Wu, Yuncan Ouyang, Qianyao Peng
Abstract: In image fusion tasks, the absence of real fused images as priors presents a fundamental challenge. Most deep learning-based fusion methods rely on large-scale paired datasets to extract global weighting features from raw images, thereby generating fused outputs that approximate real fused images. In contrast to previous studies, this paper explores few-shot training of neural networks under the condition of having prior knowledge. We propose a novel fusion framework named GBFF, and a Granular Ball Significant Extraction algorithm specifically designed for the few-shot prior setting. All pixel pairs involved in the fusion process are initially modeled as a Coarse-Grained Granular Ball. At the local level, Fine-Grained Granular Balls are used to slide through the brightness space to extract Non-Salient Pixel Pairs, and perform splitting operations to obtain Salient Pixel Pairs. Pixel-wise weights are then computed to generate a pseudo-supervised image. At the global level, pixel pairs with significant contributions to the fusion process are categorized into the Positive Region, while those whose contributions cannot be accurately determined are assigned to the Boundary Region. The Granular Ball performs modality-aware adaptation based on the proportion of the positive region, thereby adjusting the neural network's loss function and enabling it to complement the information of the boundary region. Extensive experiments demonstrate the effectiveness of both the proposed algorithm and the underlying theory. Compared with state-of-the-art (SOTA) methods, our approach shows strong competitiveness in terms of both fusion time and image expressiveness. Our code is publicly available at:
Authors: Hongwei Yao, Haoran Shi, Yidou Chen, Yixin Jiang, Cong Wang, Zhan Qin
Abstract: Retrieval-Augmented Generation (RAG) has significantly enhanced the factual accuracy and domain adaptability of Large Language Models (LLMs). This advancement has enabled their widespread deployment across sensitive domains such as healthcare, finance, and enterprise applications. RAG mitigates hallucinations by integrating external knowledge, yet introduces privacy risk and security risk, notably data breaching risk and data poisoning risk. While recent studies have explored prompt injection and poisoning attacks, there remains a significant gap in comprehensive research on controlling inbound and outbound query flows to mitigate these threats. In this paper, we propose an AI firewall, ControlNET, designed to safeguard RAG-based LLM systems from these vulnerabilities. ControlNET controls query flows by leveraging activation shift phenomena to detect adversarial queries and mitigate their impact through semantic divergence. We conduct comprehensive experiments on four different benchmark datasets including Msmarco, HotpotQA, FinQA, and MedicalSys using state-of-the-art open source LLMs (Llama3, Vicuna, and Mistral). Our results demonstrate that ControlNET achieves over 0.909 AUROC in detecting and mitigating security threats while preserving system harmlessness. Overall, ControlNET offers an effective, robust, harmless defense mechanism, marking a significant advancement toward the secure deployment of RAG-based LLM systems.
Authors: Zhixuan Pan, Shaowen Wang, Jian Li
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet principled explanations for their underlying mechanisms and several phenomena, such as scaling laws, hallucinations, and related behaviors, remain elusive. In this work, we revisit the classical relationship between compression and prediction, grounded in Kolmogorov complexity and Shannon information theory, to provide deeper insights into LLM behaviors. By leveraging the Kolmogorov Structure Function and interpreting LLM compression as a two-part coding process, we offer a detailed view of how LLMs acquire and store information across increasing model and data scales -- from pervasive syntactic patterns to progressively rarer knowledge elements. Motivated by this theoretical perspective and natural assumptions inspired by Heap's and Zipf's laws, we introduce a simplified yet representative hierarchical data-generation framework called the Syntax-Knowledge model. Under the Bayesian setting, we show that prediction and compression within this model naturally lead to diverse learning and scaling behaviors of LLMs. In particular, our theoretical analysis offers intuitive and principled explanations for both data and model scaling laws, the dynamics of knowledge acquisition during training and fine-tuning, factual knowledge hallucinations in LLMs. The experimental results validate our theoretical predictions.
Authors: Sina Elahimanesh, Mohammadali Mohammadkhani, Shohreh Kasaei
Abstract: In contemporary society, widespread social media usage is evident in people's daily lives. Nevertheless, disparities in emotional expressions between the real world and online platforms can manifest. We comprehensively analyzed Persian community on X to explore this phenomenon. An innovative pipeline was designed to measure the similarity between emotions in the real world compared to social media. Accordingly, recent tweets and images of participants were gathered and analyzed using Transformers-based text and image sentiment analysis modules. Each participant's friends also provided insights into the their real-world emotions. A distance criterion was used to compare real-world feelings with virtual experiences. Our study encompassed N=105 participants, 393 friends who contributed their perspectives, over 8,300 collected tweets, and 2,000 media images. Results indicated a 28.67% similarity between images and real-world emotions, while tweets exhibited a 75.88% alignment with real-world feelings. Additionally, the statistical significance confirmed that the observed disparities in sentiment proportions.