论文检索

Applications · Computer Vision

Yuhua Luo, Junsheng Zhang, Mengyin Liu, Xincheng Lin, Ming Yan, Zhudi Chen, Chenglu Wen, Lan Xu, Siqi Shen, Cheng Wang

Human motion inherently exhibits a sophisticated temporal hierarchical architecture, spanning from global low-frequency trajectories to local high-frequency dynamics. Inspired by this intrinsic property and the success of multi-scale autoregressive modeling in vision, we propose MotionMAR, a novel framework for human motion reconstruction from sparse observations. Unlike traditional methods, MotionMAR adopts a temporal coarse-to-fine design: it first estimates the global motion envelope and progressively refines temporal details for higher precision. The framework comprises three key components. First, a Temporal Multi-scale VQ-VAE defines hierarchical levels based on temporal resolutions, effectively disentangling global semantic information from fine-grained jitter. Second, the Motion Autoregressive Network (MAN) employs a next-scale prediction strategy: it generates coarse-scale indices to lock in the global structure, followed by finer-scale indices to restore details. This process is strictly guided by a Control Module that incorporates sparse tracking priors to ensure alignment with observed signals. Finally, a Motion Refinement Network functions as a temporal stabilizer on the decoded continuous pose space, mitigating quantization artifacts and smoothing local kinematics. Experiments demonstrate that MotionMAR achieves state-of-the-art accuracy, offering a principled, temporal-hierarchy-aware paradigm for robust motion reconstruction.

Deep Learning · Graph Neural Networks

Junshu Sun, Wanxing Chang, Qingming Huang, Shuhui Wang

Graph neural networks (GNNs) tightly couple their input-output parameters to dataset-specific feature spaces and target sets, exhibiting limited transferability across different datasets. In contrast, language models (LMs) generalize flexibly via a unified input-output interface, motivating recent attempts to adapt LMs to graph tasks. However, existing methods struggle to encode whole-graph information, leading to potential information loss and suboptimal graph understanding. In this work, we propose a novel weight-level information injection paradigm for adapting LMs to graph tasks. This paradigm injects whole-graph information by generating task-specific weight updates that interact directly with hidden representations. Instantiating this paradigm following low-rank adaptation (LoRA), we introduce GaRA, a Graph-aware LoRA generation model. GaRA constructs low-rank weight updates conditioned on the original graph structures and constrains the norm of the generated updates, thus injecting whole-graph information and avoiding the optimization bias in the weight generation. Empirical studies demonstrate that GaRA consistently outperforms baselines on zero-shot graph learning tasks. Codes are provided in the supplementary material.

Bing Liu, Xinrui Shan, Boyu Zhang, Qiankun Zhang, Bin Yuan, Wang, Xianjun Deng

*Model merging* offers an appealing route to multi-task learning by composing independently fine-tuned checkpoints without centralized data or retraining. However, this convenience can come with a hidden cost. Model merging may *amplify* performance disparities across subgroups, raising fairness concerns even when average accuracy remains competitive. To explain this phenomenon, we develop a sensitivity-based theoretical analysis that upper bounds the fairness gap induced by model merging. Theoretical analysis with empirical verifications reveals that the resulting fairness gap is governed by two coupled factors, a *merging magnitude* term that measures how far the merged parameters move from the target model and *global sensitivity* terms that determine how unevenly the perturbation affects subgroup losses. Guided by these insights, we propose *FairMerging*, a two-stage merging framework that first reduces the sensitivity of the target model and then performs fairness-aware coefficient optimization with orthogonally normalized task vectors. Experiments across multiple datasets, backbones, and merging baselines demonstrate that FairMerging substantially mitigates unfairness while retaining competitive multi-task performance.

Tong Chen, Akari Asai, Luke Zettlemoyer, Hannaneh Hajishirzi, Faeze Brahman

Modern post-trained language models are increasingly capable, but remain prone to extrinsic hallucinations. We target the utility degradation issue that prior hallucination-reduction methods often struggle to avoid, and propose online RL with Binary Retrieval-Augmented Reward (Binary RAR) to reduce hallucinations while preserving general capabilities. Binary RAR assigns a reward of 1 if a response contains no factual contradictions with retrieved evidence, and 0 otherwise. We theoretically show that this method reduces the probability of error-containing responses while preserving the distribution of error-free responses. This helps preserve the model’s capabilities, whereas other methods often degrade them. We evaluate Binary RAR on multiple widely used models. On Qwen3-8B, it reduces long-form hallucination rates by 39.3\% and short-form hallucination rates by 54.4\%, outperforming supervised learning and preference optimization baselines. Our error analysis shows that continuous factuality rewards (e.g., VeriScore) can be exploited via reward hacking by producing fewer or more generic claims, whereas Binary RAR is more robust and better preserves general capabilities, including instruction following, math, and coding.

Deep Learning · Large Language Models

TIANCI TANG, Tielong Cai, Hongwei Wang, Gaoang Wang

Pre-trained perception models excel in generic image domains but degrade significantly in novel environments like indoor scenes. The conventional remedy is fine-tuning on downstream data which incurs catastrophic forgetting of prior knowledge and demands costly, scene-specific annotations. We propose a paradigm shift through Sea$^2$ ($\textbf{Se}$e, $\textbf{A}$ct, $\textbf{A}$dapt): rather than adapting the perception modules themselves, we adapt how they are deployed through an intelligent pose-control agent. Sea$^2$ keeps all perception modules frozen, requiring no downstream labels during training, and uses only scalar perceptual feedback to navigate the agent toward informative viewpoints. Specially, we transform a vision-language model (VLM) into a low-level pose controller through a two-stage training pipeline: first fine-tuning it on rule-based exploration trajectories that systematically probe indoor scenes, and then refining the policy via unsupervised reinforcement learning that constructs rewards from the perception module’s outputs and confidence. Unlike prior active perception methods that couple exploration with specific models or collect data for retraining them, Sea$^2$ directly leverages off-the-shelf perception models for various tasks without the need for retraining. We conducted experiments on three visual perception tasks, including visual grounding, segmentation and 3D box estimation, with performance improvements of 13.54\%, 15.92\% and 27.68\% respectively on dataset ReplicaCAD.

Deep Learning · Large Language Models

Yanxing Huang, Zihan Tang, Zejin Lin, Peng Li, Yang Liu

Automatic verification is a critical component in building math-solving agents and reinforcement learning, yet it often falls short in generalizability, performance, and cost-efficiency. Identifying that the primary bottleneck of verification lies in error detection capability, we propose pessimistic verification, a paradigm of agentic workflows that rejects a solution if any of multiple parallel verifiers identifies a flaw. We further introduce progressive pessimistic verification, which employs fine-grained proof decomposition to significantly enhance verification accuracy and efficiency. Our approach surpasses the performance and token efficiency of extended long chain-of-thought (long CoT) and mainstream verification workflows, crucially, our analysis reveals that existing benchmarks underestimate its effectiveness on stronger models due to inherent annotation errors. To further validate the effectiveness of our method, we applied a verification-based solving workflow on the IMO 2025 and MathArena Apex 2025 datasets, where the workflow with progressive pessimistic verification exhibits remarkable improvements in both efficiency and accuracy on highly challenging contest-level math problems with state-of-the-art models.

Deep Learning · Large Language Models

Marco Pollanen

Direct Preference Optimization (DPO) is often tuned as if increasing alignment pressure (controlled by $\beta$) yields progressively “better” behavior. We instead treat $\beta$ as a control parameter and densely sweep it for three 7B open-weight families under a fixed DPO recipe. In Mistral, capability is sharply non-monotonic: aggregated logic-probe margins become positive only in a narrow band near $\beta \approx 10^{-2}$ and revert outside it, with boundary points that are seed-sensitive. Across architectures under the same sweep, we observe qualitatively different response modes: sharp reorganization in Mistral, selective changes in Llama, and smooth trade-offs in Qwen. Critically, the DPO preference margin can anticorrelate with reasoning capability (Pearson $r=-0.91$ for Llama logic), so margin-based selection can prefer capability-impaired models. Training path also matters: exposure to high $\beta$ induces capability losses that persist even after $\beta$ is reduced (hysteresis). These findings motivate capability-resolved evaluation across the $\beta$ landscape rather than reliance on margins or aggregate benchmarks.

Deep Learning · Large Language Models

Qingzhuo Wang, Ruiyang Qin, Zhenxin Qin, Wen Shen, Zhihua Wei

Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unified approach to explore the common mechanism of various KD methods using interactions. Specifically, we decompose the output score of the LLM into the sum of numerous interactions. Each interaction represents a nonlinear relationship involving a set of input variables (e.g., words). Based on the decomposed interactions, we discover that the common mechanism underlying various KD methods is the sparsification of interactions, i.e., student models retain fewer interactions for inference while suppressing other interactions to zero effects. Furthermore, we discover that the performance variance across different KD methods arises from their capabilities in handling complex interactions. A KD method typically yields better performance if it enables the student model to achieve higher sparsity of complex interactions. Motivated by these insights, we propose a plug-and-play loss function called Complex Interaction Penalty (CIP) to explicitly enforce the sparsity of complex interactions during the distillation process. Extensive experiments demonstrate that integrating CIP consistently improves the performance of diverse KD methods on both in-domain and out-of-distribution benchmarks.

Optimization · Large Scale, Parallel and Distributed

Samuel Erickson, Mikael Johansson

In modern machine learning, parallelization of training is an important strategy for increasing scale. Asynchronous stochastic gradient descent (ASGD), which maximally utilizes available hardware, avoids having to wait for slow workers. However, with constant step sizes, the convergence of ASGD is nonetheless negatively effected by slow workers due to large delays in updates. At the same time, it has been empirically observed in asynchronous training of deep learning models that gradient clipping ``stabilizes'' training. In this work, we provide a theoretical justification for this behavior, as we show that clipping removes the dependence of the maximum delay in the oracle complexity. We employ a sub-Weibull model of gradient noise which generalize sub-Gaussian and sub-exponential disitributions to more heavy-tailed distributions, motivated by empirical observations in deep learning. We show convergence in expectation, and for the first time in asynchronous optimization, convergence with high probability.

Reinforcement Learning · Batch/Offline

Baolong Bi, Shenghua Liu, Yiwei Wang, Siqian Tong, Lingrui Mei, Yuyao Ge, Yilong Xu, Jiafeng Guo, Xueqi Cheng

Recent advances in reinforcement learning (RL) have significantly improved the complex reasoning capabilities of large language models (LLMs). Despite these successes, existing methods mainly focus on single-domain RL (e.g., mathematics) with verifiable rewards (RLVR), and their reliance on purely online RL frameworks restricts the exploration space, thereby limiting reasoning performance. In this paper, we address these limitations by leveraging rubrics to provide both fine-grained reward signals and offline guidance. We propose $\textbf{RGR-GRPO}$ (Reward and Guidance through Rubrics), a rubric-driven RL framework for multi-domain reasoning. RGR-GRPO enables LLMs to receive dense and informative rewards while exploring a larger solution space during GRPO training. Extensive experiments across 14 benchmarks spanning multiple domains demonstrate that RGR-GRPO consistently outperforms RL methods that rely solely on alternative reward schemes or offline guidance. Compared with verifiable online RL baseline, RGR-GRPO achieves average improvements of +7.0%, +5.4%, +8.4%, and +6.6% on mathematics, physics, chemistry, and general reasoning tasks, respectively. Notably, RGR-GRPO maintains stable entropy fluctuations during off-policy training and achieves superior pass@k performance, reflecting sustained exploration and effective breakthrough beyond existing performance bottlenecks.

Deep Learning · Graph Neural Networks

Erkan Turan, Gaspard Abel, Maysam Behmanesh, Emery Pierson, Maks Ovsjanikov

Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features converge to a homogeneous, non-informative state. We re-frame this problem of representational collapse from a \emph{bifurcation theory} perspective, characterizing oversmoothing as convergence to a stable ``homogeneous fixed point.'' Our central contribution is the theoretical discovery that this undesired stability can be broken by replacing standard monotone activations (e.g., ReLU) with a class of functions. Using Lyapunov-Schmidt reduction, we analytically prove that this substitution induces a bifurcation that destabilizes the homogeneous state and creates a new pair of stable, non-homogeneous \emph{patterns} that provably resist oversmoothing. Our theory predicts a precise, nontrivial scaling law for the amplitude of these emergent patterns, which we quantitatively validate in experiments. Finally, we demonstrate the practical utility of our theory by deriving a closed-form, bifurcation-aware initialization and showing its utility in real benchmark experiments.

Deep Learning · Large Language Models

Qichuan Liu, Chenfeng Zheng, Yuxuan Hu, Zerui Chen, Chentao Zhang, Qinggang Zhang, Zhihong Zhang

Retrieval-Augmented Generation (RAG) has recently been enhanced with tree or graph structures to match user intent for precise passage retrieval, which facilitates large language models (LLMs) in effectively mitigating hallucinations by leveraging external knowledge. However, we identify that existing structure-augmented RAG systems are experiencing (i) potential retrieval suspension and (ii) cumulative semantic drift, due to low-quality structures and semantic embeddings that often poorly capture textual details. Motivated by this, we propose a novel paradigm named KG-Translator, which is distinct from traditional matching-based paradigms and instead translates user queries into graph-level clues. Specifically, KG-Translator utilizes lightweight models to conduct named entity recognition (NER) and syntactic parsing on the corpus, constructing a reliable knowledge graph (ParseKG). On top of ParseKG, KG-Translator adopts constrained decoding strategies to faithfully translate clues, traces them to original passages, and employs a lightweight ranking model for precise passage retrieval. Extensive experiments on five datasets demonstrate that KG-Translator significantly outperforms baselines.

General Machine Learning · Kernel methods

Meiling Zeng, Jinhong You, Jicai Liu, Shouxia Wang

This paper introduces a nonparametric test for conditional mean independence between a manifold‑valued $Y$ and Euclidean predictors $X$. The test is built on a new measure called the Manifold Martingale Difference Divergence (MMDD), which characterizes conditional mean dependence by projecting observations onto the tangent space via the logarithmic map. We provide an empirical estimator for the MMDD, establish its asymptotic null distribution, and implement a wild bootstrap procedure for finite‑sample inference. Simulations on three representative manifolds demonstrate that the proposed test maintains correct size under the null even when the distribution of $Y$ depends on $X$, in contrast to the severe size distortion exhibited by the distance covariance (dCov) test. At the same time, it achieves competitive power across a range of alternatives. An application to real data illustrates its practical utility.

Beomsu Kim, ByungHee Cha, Jong Chul YE

With diffusion and flow matching models achieving state-of-the-art generating performance, the interest of the community now turned to reducing the inference time without sacrificing sample quality. Consistency Models (CMs), which are trained to be consistent on diffusion or probability flow ordinary differential equation (PF-ODE) trajectories, enable one or two-step flow or diffusion sampling. However, CMs typically require prolonged training with large batch sizes to obtain competitive sample quality. In this paper, we examine the training dynamics of CMs near convergence and discover that CM trajectory tangents -- CM output update directions -- are quite oscillatory, in the sense that they move parallel to the data manifold, not towards the manifold. To mitigate oscillatory trajectory tangents, we propose a new loss function, called the {\em manifold feature distance (MFD)}, which provides manifold-aligned trajectory tangents that point toward the data manifold. Consequently, our method -- dubbed {\em Align Your Trajectory Tangent (AYT)} -- can accelerate CM training by orders of magnitude and even out-perform the learned perceptual image patch similarity metric (LPIPS). Furthermore, we find that our loss enables training with extremely small batch sizes without compromising sample quality.

Theory · Optimization

Ashkan Norouzi-Fard, Silvio Lattanzi, MohammadHossein Bateni, Morteza Monemizadeh

Many machine learning problems are geometric at their core, relying on metric representations of data for tasks such as clustering, prototype selection, nearest-neighbor search, and graph-based learning. Furthermore, data is constantly evolving and it is routinely transformed through dimensionality reduction, random projections, feature embeddings, compression, or privacy-preserving mechanisms. These transformations are designed to preserve geometry approximately. As a result, they preserve objective values for many geometric optimization problems, but they fail to guarantee that algorithmic outcomes remain consistent. In this work, we study \emph{resilient data summaries} for geometric optimization. Building on the notion of \emph{$\gamma$-resilient algorithms} from Ahmadian, we introduce $\gamma$-resilient coresets. A $\gamma$-resilient $(k,\varepsilon)$-coreset is a compact, weighted summary that guarantees a $(1+\varepsilon)$ approximation to the objective and enforces stability at the level of assignments. We complement our positive result with a lower bound showing that to obtain a tight approximation for resilient clustering it is necessary to use a bi-criteria solution.

Theory · Reinforcement Learning and Planning

Haoqun Cao, Tengyang Xie

Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have proven remarkably effective, from large language models (LLMs) to vision-language-action systems (VLAs). However, applying autoregressive models to continuous control requires discretizing actions through quantization, a practice widely adopted yet poorly understood theoretically. This paper provides theoretical foundations for this practice. We analyze how quantization error propagates along the horizon and interacts with statistical sample complexity. We show that behavior cloning with quantized actions and log-loss achieves optimal sample complexity—matching existing lower bounds—and incurs only polynomial horizon dependence on quantization error, provided the dynamics are stable and the policy satisfies a probabilistic smoothness condition. We further characterize when different quantization schemes satisfy or violate these requirements, and propose a model-based augmentation that provably improves the error bound without requiring policy smoothness. Finally, we establish fundamental limits that jointly capture the effects of quantization error and statistical complexity.

Applications · Language, Speech and Dialog

Yiqun Sun, Pengfei Wei, Lawrence Hsieh

Listwise reranking is a critical yet costly component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG) over long documents. Although recent VLM-based rerankers achieve strong accuracy, they are often impractical due to long visual-token inputs and autoregressive decoding, resulting in high latency. We propose ZipRerank, a very efficient listwise multimodal reranker that directly addresses both bottlenecks: it shortens the input via query-image early interaction and eliminates multi-step generation by scoring all candidates in a single forward pass. ZipRerank is trained with a two-stage recipe: listwise pretraining on large-scale text reranking data rendered as images, followed by multimodal finetuning with VLM-teacher supervision and a soft-ranking objective to handle noisy rankings. Extensive experiments on the MMDocIR benchmark demonstrate that ZipRerank matches or surpasses state-of-the-art multimodal rerankers while reducing LLM inference latency by up to an order of magnitude, making it well-suited for latency-sensitive real-world systems. Source code is available at https://anonymous.4open.science/r/ZipRerank.

Social Aspects · Alignment

Zidi Xiong, Shan Chen, Himabindu Lakkaraju

As Large Reasoning Models (LRMs) are increasingly deployed, auditing their chain-of-thought (CoT) traces for safety becomes critical. Recent work has reported that monitorability—the degree to which CoT faithfully and informatively reflects internal computation—can appear as a "free gift" during the early stages of Reinforcement Learning with Verifiable Rewards (RLVR). We make this observation concrete through a systematic evaluation across model families and training domains. Our results show that this effect is not universal: monitorability improvements are strongly data-dependent. In particular, we demonstrate the critical role of data diversity and instruction-following data during RLVR training. We further show that monitorability is orthogonal to capability—improvements in reasoning performance do not imply increased transparency. Through mechanistic analysis, we attribute monitorability gains primarily to response distribution sharpening (entropy reduction) and increased attention to the prompt, rather than stronger causal reliance on reasoning traces. We also reveal how monitorability dynamics vary with controlled training and evaluation difficulty. Together, these findings provide a holistic view of how monitorability emerges under RLVR, clarifying when gains are likely to occur and when they are not.

Social Aspects · Fairness

Minh Phu Vuong, Jinyoung Lee, Young-Ju Lee, Chul-Ho Lee

Fair graph clustering has emerged as a critical research area for addressing algorithmic bias in machine learning. The objective is to ensure that the proportion of each protected group within a cluster is consistent with its representation in the entire dataset. However, most existing spectral solutions rely on computationally expensive eigendecompositions of the graph Laplacian, limiting their scalability. In this paper, we propose Riemannian Fair Spectral Clustering (R-FairSC), a novel method that formulates fair spectral clustering as a constrained optimization problem on a Riemannian manifold. We develop a Riemannian alternating direction method of multipliers employing a variable-splitting strategy to efficiently solve the associated subproblems. Numerical experiments on large synthetic and real-world graphs demonstrate that R-FairSC significantly improves computational efficiency over state-of-the-art methods while maintaining high clustering quality and fairness.

Social Aspects · Robustness

Yujie Huang, Wenwu He, Zhuo-Xu Cui

Chain-of-Thought (CoT) prompting enables multi-step reasoning in large language models, yet long-horizon generation remains brittle under distribution shift and context interference: irrelevant cues persist, small deviations compound into inference drift, and late-stage corrections can destabilize the trajectory. We recast autoregressive decoding as a perturbed long-horizon dynamical system and introduce an *inference-time stabilization operator* that targets *trajectory-level* reliability rather than token-level fluency. Specifically, we propose *ODE-guided language models*, which augment a base Transformer with a persistent continuous-time *thought state* whose dynamics are explicitly designed to be dissipative, enabling stable evidence accumulation with controlled forgetting. Instantiating this framework, *Thinking in Flow* (TiF) equips the model with a lightweight Neural ODE controller and injects its output through post-norm residual updates to achieve numerically stable, low-intrusion steering. A demand--supply (uncertainty--capacity) gate determines *when* intervention is warranted, while a direction gate determines *how* to steer in representation space, yielding selective, do-no-harm corrections instead of persistent bias. We establish well-posedness, dissipativity, and incremental stability of the controlled thought dynamics, implying bounded interventions over arbitrarily long contexts, and empirically demonstrate improved robustness to distractions and semantic perturbations, while matching or improving accuracy on mathematical reasoning benchmarks across both the Llama and Qwen model families; we further observe gains on non-mathematical BBH reasoning tasks when training TiF on Llama.