论文检索

Applications · Social Sciences

Keane Ong, Sabri Boughorbel, Luwei Xiao, Chanakya Ekbote, David Dai, Ao Qu, Jingyao Wu, Rui Mao, Ehsan Hoque, Erik Cambria 等

To develop socially intelligent AI, existing approaches typically model behavioral dimensions (e.g., affective, cognitive, or social attributes) in isolation. Although useful, this task-specific modeling increases training costs and limits generalization across behavioral settings. Recent reasoning RL methods facilitate training a single unified model across multiple behavioral tasks, but do not explicitly address learning across different heterogeneous behavioral data. To address this gap, we introduce Heterogeneity-Aware Relative Policy Optimization (HARPO), a RL method that balances leaning across heterogeneous tasks and samples. This is achieved by modulating advantages to ensure that no single task or sample carries disproportionate influence during policy optimization. Using HARPO, we develop and release OMNISAPIENS-7B 2.0, a foundation model for social behavior processing. Relative to existing behavioral foundation models, OMNISAPIENS-7B 2.0 achieves the strongest performance across behavioral tasks, with gains of up to +16.85% and +9.37% on multitask and held-out settings respectively, while producing more explicit and robust reasoning traces. We also validate HARPO against recent RL methods, where it achieves the most consistently strong performance across behavioral tasks.

Applications · Computer Vision

Hao Zhu, Shuo Jin, Wenbin Liao, Jiayu Xiao, Yan Zhu, Siyue Yu, Feng Dai

Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial bias in CLIP. To overcome the limitations of existing solutions, this work moves beyond the CLIP-based paradigm and harnesses the recent spatially-aware dino.txt framework to facilitate more efficient and high-quality dense prediction. While dino.txt exhibits robust spatial awareness, we find that the semantic ambiguity of text queries gives rise to severe mismatch within its dense cross-modal interactions. To address this, we introduce VIsual-guided Prompt evolution (VIP) to rectify the semantic expressiveness of text queries in dino.txt, unleashing its potential for fine-grained object perception. Towards this end, VIP integrates alias expansion with a visual-guided distillation mechanism to mine valuable semantic cues, which are robustly aggregated in a saliency-aware manner to yield a high-fidelity prediction. Extensive evaluations demonstrate that VIP: I) surpasses the top-leading methods by 1.4%~8.4\% average mIoU, II) generalizes well to diverse challenging domains, and III) requires marginal inference time and memory overhead. Our code will be released to foster future research.

Deep Learning · Theory

Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Hau-San Wong, Qingfu Zhang, Taiji Suzuki

Recent curriculum techniques in the post-training stage of LLMs have been empirically observed to outperform non-curriculum approaches in improving reasoning performance, yet a principled understanding of their effectiveness and limitations remains incomplete. To bridge this gap, we develop an abstract theoretical framework and identify sufficient conditions under which curriculum post-training yields exponential improvements in sample complexity. To substantiate this framework, we model the base model’s Chain-of-Thought generation as a state-conditioned autoregressive reasoning tree, and formalize curriculum subtasks as either depth-increasing curricula that progressively extend reasoning horizons or hint-decreasing curricula that gradually remove partial hints. Our analysis shows that, under outcome-only reward signals, reinforcement learning finetuning with both curriculum strategies achieves high accuracy with polynomial sample complexity, whereas non-curriculum counterpart encounters an exponential complexity bottleneck. We further establish analogous guarantees for test-time scaling, demonstrating that curriculum-aware querying strategies reduce both reward oracle complexity and sampling cost from exponential to polynomial order. Empirical simulations support our theoretical findings.

Probabilistic Methods · Bayesian Models and Methods

Albus Li, Matthew Wicker

Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring responsible deployment. While Bayesian methods offer a principled approach to uncertainty quantification, their computational overhead renders their use impractical for training or inference at foundation model scale. State-of-the-art models achieve parameter counts in the trillions through carefully engineered sparsity including Mixture-of-Experts (MoE) layers. In this work, we demonstrate calibrated uncertainty at scale by introducing Variational Mixture-of-Experts Routing (VMoER), a structured Bayesian approach for modelling uncertainty in MoE layers. VMoER confines Bayesian inference to the expert-selection stage which is typically done by a deterministic routing network. We instantiate VMoER using two inference strategies: amortised variational inference over routing logits and inferring a temperature parameter for stochastic expert selection. Across tested foundation models, VMoER improves routing stability under noise by 38%, reduces calibration error by 94%, and increases out-of-distribution AUROC by 12%, while incurring less than 1% additional FLOPs. These results suggest VMoER offers a scalable path toward robust and uncertainty-aware foundation models.

Applications · Chemistry, Physics, and Earth Sciences

Youngwoo Cho, Jaekak Yoo, Soyoung Yang, Dong-Joon Yi, Seung Lee, Mun Jeong, Jaegul Choo

The machine learning community has focused on computational efficiency, often leveraging lower-precision formats such as FP16, rather than the standard FP32. In contrast, little attention has been paid to higher-precision formats, such as FP64, despite their critical role in scientific domains like materials science, where even small numerical differences can lead to significant inaccuracies in physicochemical properties. This need for high precision extends to the emerging field of *machine learning for scientific tasks*, yet it has not been thoroughly investigated. According to several studies and our experiments, models trained with FP32 show insufficient accuracy compared to those trained with FP64, indicating that higher precision is also crucial in scientific machine learning, as in traditional scientific computing. This precision issue limits the potential of scientific machine learning that can replace the traditional scientific computing in practical research. Our position paper not only highlights these precision-related issues but also recommends reporting comparisons between FP32 and FP64 results, encouraging the release of FP64 models. We believe that these efforts can enable machine learning to contribute meaningfully to the natural sciences, ensuring both scientific reliability and practical applicability.

Deep Learning · Generative Models and Autoencoders

Ruchi Sandilya, Sumaira Perez, Charles Lynch, Lindsay Victoria, Benjamin Zebley, Derrick Buchanan, Mahendra Bhati, Nolan Williams, Timothy Spellman, FAITH GUNNING 等

Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control. We introduce ConDA (Contrastive Diffusion Alignment), a plug-and-play geometry layer that applies contrastive learning to pretrained diffusion latents using auxiliary variables (e.g., time, stimulation parameters, facial action units). ConDA learns a low-dimensional embedding whose directions align with underlying dynamical factors, consistent with recent contrastive learning results on structured and disentangled representations. In this embedding, simple nonlinear trajectories support smooth interpolation, extrapolation, and counterfactual editing while rendering remains in the original diffusion space. ConDA separates editing and rendering by lifting embedding trajectories back to diffusion latents with a neighborhood-preserving kNN decoder and is robust across inversion solvers. Across fluid dynamics, neural calcium imaging, therapeutic neurostimulation, facial expression dynamics, and monkey motor cortex activity, ConDA yields more interpretable and controllable latent structure than linear traversals and conditioning-based baselines, indicating that diffusion latents encode dynamics-relevant structure that can be exploited by an explicit contrastive geometry layer.

Deep Learning · Attention Mechanisms

Siran Liu, Zheng Cao, Yongchao He

Efficient long-context understanding is increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the core self-attention scales quadratically with sequence length, creating a fundamental computational bottleneck. Existing sparse attention methods alleviate this issue but face trade-offs: training-based methods are costly and cannot be directly applied as acceleration plugins for other models, while inference-time methods often compromise efficiency or cross-modal generality. To address these limitations, we present UniSparse, a unified mechanism that introduces the notion of composite tokens—compact representations that aggregate multi-granularity contextual information. Building on this abstraction, UniSparse dynamically constructs sparse attention through multi-granularity compression and block-level selection, enabling efficient and hardware-friendly execution on GPU. Across multiple modalities and tasks ranging from synthetic benchmarks to real-world applications, UniSparse consistently surpasses state-of-the-art sparse attention methods (e.g., MInference, XAttention, FlexPrefill) in both accuracy and efficiency, achieving $\ge$ 99\% of full-attention accuracy and up to 2.61$\times$ faster attention computation than FlashAttention.

Applications · Time Series

Tong Guan, SHENG PAN, Johan Barthelemy, Zhao Li, Yujun Cai, Cesare Alippi, Ming Jin, Shirui Pan

Recent time series modeling faces a sharp divide between numerical generation and semantic understanding, with research showing that generation models often rely on superficial pattern matching, while understanding-oriented models struggle with high-fidelity numerical output. Although unified multimodal models (UMMs) have bridged this gap in vision, their potential for time series remains untapped. We propose TimeOmni-VL, the first vision-centric framework that unifies time series understanding and generation through two key innovations: (1) Fidelity-preserving bidirectional mapping between time series and images (Bi-TSI), which advances Time Series-to-Image (TS2I) and Image-to-Time Series (I2TS) conversions to ensure near-lossless transformations. (2) Understanding-guided generation. We introduce TSUMM-Suite, a novel dataset consists of six understanding tasks rooted in time series analytics that are coupled with two generation tasks. With a calibrated Chain-of-Thought (CoT), TimeOmni-VL is the first to leverage time series understanding as an explicit control signal for high-fidelity generation. Experiments confirm that this unified approach significantly improves both semantic understanding and numerical precision, establishing a new frontier for multimodal time series modeling.

Deep Learning · Foundation Models

Guangyu Zhao, Kewei Lian, Haoxuan Ru, Borong Zhang, Haowei Lin, Zhancun Mu, Haobo Fu, Qiang Fu, Shaofei Cai, Zihao Wang 等

Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of discrete text prompts, we formulate post-training adaptation as a latent control problem, where the goal embedding serves as a continuous control variable to modulate the behavior of a frozen policy. We propose Preference Goal Tuning (PGT), a framework that optimizes this latent control variable to align the induced trajectory distribution with task preferences. Unlike standard fine-tuning that updates policy parameters, PGT keeps the policy frozen and updates only the latent goal using a trajectory-level preference objective. This approach essentially searches for the optimal conditioning input that maximizes the likelihood of preferred behaviors while suppressing undesirable ones. We evaluate PGT on the Minecraft SkillForge benchmark across 17 tasks. With minimal data, PGT achieves average relative improvements of 72.0\% and 81.6\% on two foundation policies, consistently outperforming expert-crafted prompts. Crucially, by decoupling task alignment (latent goal) from physical dynamics (frozen policy), PGT surpasses full fine-tuning by 13.4\% in out-of-distribution settings, demonstrating superior robustness and generalization.

Optimization · Non-Convex

Qiujing Lu, Tonmoy Monsoor, Ehsan Ebrahimzadeh, Kartik Sharma, Vwani Roychowdhury

Nonnegative matrix factorization (NMF) seeks a low-rank approximation $X \approx UV^T$ with nonnegative factors and is commonly solved using *interior* methods that enforce feasibility throughout optimization. We show that such constraint-driven approaches can impede progress in the nonconvex landscape, leading to slow convergence or convergence to suboptimal stationary points. We propose an *exterior* framework for NMF (eNMF) that separates low-rank approximation from nonnegativity enforcement. Our method initializes from the optimal unconstrained factorization and introduces a rotation procedure that maps unconstrained factors to an exterior point closest to the nonnegative orthant. This viewpoint yields an algorithmic framework in which simple iterative updates converge to KKT-satisfying stationary points on the boundary of the positive orthant. The exterior formulation also enables a geometric interpretation of NMF solutions, clarifying equivalence classes of factorizations under permutation and orthogonal transformations. An intriguing numerical result, involving 400 NMF experiments across both real and synthetic datasets, show that in 99\% of the cases, different algorithms tend to converge towards equivalent factor matrices. We benchmark eNMF against 9 state-of-the-art NMF algorithms with 9 initialization schemes across 3 real-world and 2 synthetic datasets. eNMF consistently outperforms all 81 competitors, achieving up to 30\% lower reconstruction error under equal-time settings and up to 150\% speedup under equal-error settings. The downstream experiments further demonstrate substantial performance gains in audio processing and recommendation tasks, corroborating the practical benefits of the proposed exterior optimization framework. Anonymized code is available at https://anonymous.4open.science/r/eNMF-6240/README.md

Reinforcement Learning · Everything Else

Zihao Wang, Muyao Li, Kaichen He, Haowei Lin, Xiaojian Ma, Anji Liu, Yitao Liang

Prevailing autonomous agents are often constrained by a single, predefined action space, which limits their generalization capabilities across diverse tasks and can introduce compounding errors through decoupled policy execution. To address these limitations, we introduce the Deep Hierarchical Agent (DeepHA), a unified architecture that operates across a mixture of heterogeneous action spaces, flexibly generating actions ranging from high-level semantic skills to low-level motor controls. We further propose a Chain-of-Action (CoA) reasoning framework, which enables the agent to use higher-level abstract actions as structured `thoughts' to guide the generation of more granular, subsequent actions. To manage the computational demands of this deep reasoning in long-horizon tasks, we develop a memory-efficient mechanism that dynamically compresses historical context and leverages Key-Value (KV) caching, reducing context length by approximately 75% without sacrificing performance. We conduct extensive evaluations on a new, large-scale benchmark of over 800 diverse Minecraft tasks. Results show that DHA significantly outperforms prior methods, establishing a new state-of-the-art and demonstrating superior generalization, particularly in complex, multi-step planning tasks. Our work presents a novel, unified framework for building more capable and efficient autonomous agents.

Reinforcement Learning · Multi-agent

Siyao Song, Cong Ma, Zhihao Cheng, Shiye Lei, MINGHAO LI, Ying Zeng, Huaixiao Tou, Kai Jia

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning, often leading to inefficient exploration and sparse rewards. To mitigate this issue, we propose Expert-Assisted Policy Optimization (EAPO), a novel RL framework that enhances exploration by incorporating multi-turn interactions with external experts during training. Unlike prior methods, where policies reason in isolation, EAPO incentivizes the policy to adaptively determine when and how to consult experts, yielding richer reward signals and more reliable reasoning trajectories. External assistance ultimately internalizes expert knowledge into the policy model, amplifying the model’s inherent reasoning capabilities. During evaluation, the policy model has been well-optimized to solve questions independently, producing improved reasoning paths and more accurate solutions. On AIME 2024/2025 and AIMO 2025, EAPO consistently outperforms expert-assisted, expert-distilled, and RL baselines, averaging a 5-point gain over self-exploration RL, and also generalizes to non-math benchmarks, including HumanEval, HLE, GPQA, MMLU, EvalPlus, HotpotQA, and SimpleQA.

Reinforcement Learning · Everything Else

Zihao Wang, Muyao Li, Kaichen He, Xiangyu Wang, Zhancun Mu, Minghao Liu, Anji Liu, Yitao Liang

A critical challenge in developing capable AI agents is defining their "action space''—the set of possible actions they can take. These spaces can range widely, from generating code and using language skills to operating on latent representations or raw joystick controls. Through a large-scale study in Minecraft, we discovered a major dilemma: no single action space is universally best. The most effective action space is highly task-dependent, which complicates the goal of building one generalist agent that can handle everything. To solve this, we introduce Chain-of-Action (CoA), a novel framework that unifies high-level abstracted actions and low-level control actions within a single model. With CoA, an abstract goal is not just a final command; instead, it serves as an intermediate reasoning step that guides the model to generate the precise, executable actions needed to complete the task. Furthermore, we show that an All-in-One generalist agent, trained on a diverse mix of action spaces using CoA, learns a more generalizable policy. This unified agent achieves a new state-of-the-art, outperforming strong, specialized baselines. To support the research community, we are releasing the OpenHA (Open Hierarchical Agents) suite, which includes our benchmark of over 800 tasks, curated datasets, source code, and all model checkpoints at: \url{https://anonymous.4open.science/anonymize/OpenHA-ACFE}.

Applications · Chemistry, Physics, and Earth Sciences

Jonas Elsborg, Felix Aertebjerg, Luca Anthony Thiede, Alan Aspuru-Guzik, Tejs Vegge, Arghya Bhowmik

We introduce ELECTRAFI, a fast, end-to-end differentiable model for predicting periodic charge densities in crystalline materials. ELECTRAFI constructs anisotropic Gaussians in real space and exploits their closed-form Fourier transforms to analytically evaluate plane-wave coefficients via the Poisson summation formula. This formulation delegates non-local and periodic behavior to analytic transforms, enabling reconstruction of the full periodic charge density with a single inverse FFT. By avoiding explicit real-space grid probing, periodic image summation, and spherical harmonic expansions, ELECTRAFI matches or exceeds state-of-the-art accuracy across periodic benchmarks while being up to $633\times$ faster than the strongest competing method, reconstructing crystal charge densities in a fraction of a second. When used to initialize DFT calculations, ELECTRAFI reduces total DFT compute cost by up to $\sim$20 \%, whereas slower charge density models negate savings due to high inference times. Our results show that accuracy and inference cost jointly determine end-to-end DFT speedups, and motivate our focus on efficiency.

Deep Learning · Foundation Models

Shijie Mei, Man Yao, Jiabo Tong, Bo XU, Guoqi Li

The state-transition (decay) matrix governs how fixed-size memory is updated and used, making it a core design in linear attention models. Prior work exploits rank-1 approximations to reduce the cost of constructing decay matrices, but this low-rank constraint also limits the expressive capacity. We therefore formulate decay-matrix design as an open optimization problem: maximizing expressiveness while introducing minimal additional cost. Inspired by the multi-head mechanism, we propose Head-in-Head, which introduces an additional mask matrix to structure memory partitioning and interactions within a single linear-attention head. This simple, generic, and efficient design: \romannumeral1) enables a rank-$r$ approximation of the decay matrix with only a few extra parameters and \romannumeral2) strengthens intra-head information interaction. We further develop mask normalization and a chunk-wise parallelization scheme to support efficient parallel training. Extensive experiments on synthetic benchmarks and language modeling tasks, together with visual analyses, show that Head-in-Head consistently improves baseline performance by enriching information diversity and strengthening intra-head interactions.

Social Aspects · Accountability, Transparency, and Interpretability

David Boetius, Shahaf Bassan, Guy Katz, Stefan Leue, Tobias Sutter

Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact SHAP computation to larger search spaces by introducing an algorithm that leverages recent advances in neural network verification to compute arbitrarily tight exact lower and upper bounds on SHAP values for neural networks, ultimately recovering the exact SHAP values. We demonstrate that our approach scales to orders of magnitude larger search spaces than state-of-the-art exact methods. This provides an important first step towards exact SHAP computation and establishes a principled cornerstone for evaluating statistical approximation methods on larger search spaces.

Deep Learning · Large Language Models

Hongcheng Wang, Yinuo Huang, Sukai Wang, Guanghui Ren, Hao Dong

Group Relative Policy Optimization (GRPO) trains Chain-of-Thought reasoning with verifiable rewards, but estimating thought-level advantages without value functions often suffers from high variance. Although tree-style branching is used in practice to reduce the variance, it lacks a theoretical explanation of why it works and whether it is important or even potentially necessary. We study thought-level advantage estimation in GRPO from a variance perspective under a minimal tree-style setting where multiple answers are sampled for each thought. Using the multivariate delta method, we reveal an asymmetry in how different sampling dimensions affect variance. Increasing the number of sampled thoughts ($K$) leaves a strictly positive variance floor, whereas increasing the number of answers per thought ($M$) induces a monotonic decrease in variance, asymptotically driving it to zero. This implies that accurate thought-level advantage estimation is impossible through scaling thought sampling alone, making branching a potentially necessary mechanism rather than a heuristic. Experiments further provide empirical evidence for both the effectiveness and necessity of answer-level branching, demonstrating improved optimization stability, training efficiency, and final performance not only in math but also across a broad range of vision domains and under different model architectures and sizes.

General Machine Learning · Kernel methods

Hachem Kadri, Joachim Tomasi, Yuka Hashimoto, Sandrine Anthoine

Quantum kernels are reproducing kernel functions built using quantum-mechanical principles and have emerged as a centerpiece of quantum machine learning. The initial enthusiasm for quantum kernel machines has been tempered by recent studies suggesting that quantum kernels could not offer significant computational or statistical advantages when learning from classical data. However, most of the research in this area has been devoted to scalar-valued kernels in standard classification or regression settings for which classical kernel methods are efficient and effective, leaving very little room for improvement with quantum kernels. In this position paper, we argue that progress in this field requires moving beyond scalar-valued kernels toward more expressive kernel frameworks. Scalar-valued kernels lack the degrees of freedom necessary to fully exploit intrinsically quantum resources such as entanglement and are not rich enough to deal with complex learning tasks where classical learning methods struggle. Building on recent advances in operator-valued kernel learning and C*-algebraic kernel representations, we propose a roadmap for designing quantum kernels capable of leveraging entanglement and non-commutative structures to tackle complex structured prediction problems. To support this viewpoint, we present an initial proof-of-concept illustrating how quantum entangled operator-valued kernel formulations can reveal structural dependencies that remain difficult to access for scalar-valued kernel methods. This shift in focus could open a pathway toward a new generation of quantum kernel machines and a more faithful exploration of their potential advantages.

Theory · Domain Adaptation and Transfer Learning

Steve Hanneke, Mingyue Xu

Multitask learning and related frameworks have achieved tremendous success in modern applications. In multitask learning problem, we are given a set of heterogeneous datasets collected from related source tasks and hope to enhance the performance above what we could hope to achieve by solving each of them individually. The recent work of Hanneke & Kpotufe (2022) has showed that, without access to distributional information, no algorithm based on aggregating samples alone can guarantee optimal risk as long as the sample size per task is bounded. In this paper, we focus on understanding the statistical limits of multitask learning. We go beyond the no-free-lunch theorem in Hanneke & Kpotufe (2022) by establishing a stronger impossibility result of adaptation that holds for arbitrarily large sample size per task. This improvement conveys an important message that the hardness of multitask learning cannot be overcame by having abundant data per task. We also discuss the notion of optimal adaptivity that may be of future interests.

Deep Learning · Algorithms

Moritz Thoma, Maximilian Groezinger, Maximilian Forstenhäusler, Emad Aghajanzadeh, Manoj Rohit Vemparala, Christos Anagnostopoulos, Pierpaolo Mori, Nael Fasfous, Alexander Frickenstein, Daniel Mueller-Gritschneder 等

Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of Large language models (LLMs); however, existing methods commonly encounter two recurring obstacles: (i) global rank allocation, where uncalibrated error proxies fail to account for complex error propagation, and (ii) decomposition quality, where Fisher-based estimators suffer from severe rank collapse. In this work, we address these limitations by presenting Layer-wise Error Modeling Search (LEMS) and KFAC-SVD. LEMS advances rank allocation by introducing a layer-wise error surrogate that integrates both local and global layer importance alongside a propagation bias, allowing us to determine global rank configurations efficiently as an Integer Linear Program (ILP). Simultaneously, KFAC-SVD improves decomposition quality by utilizing token-wise statistics, preventing the rank deficiency observed in prior Fisher-based SVD. We demonstrate across Mistral, Qwen3, and Llama-3 families that KFAC-SVD achieves an average perplexity improvements of 15%, while LEMS consistently outperforms existing search strategies, delivering significant zero-shot accuracy improvements of up to 4.7 p.p. that generalize to scales of 70B parameters. Code is made available in the Supplement.