论文检索

Deep Learning · Graph Neural Networks

Jintao Li, Yong-Yi Wang, Zheng-An Wang, Heng Fan

Diffusion-based neural solvers for combinatorial optimization repeatedly re-evaluate dense edge/factor interactions, making inference expensive in wall-clock time and often memory-bound at scale. We introduce LoRe, a training-free, inference-time drop-in wrapper that enforces per-step interaction-evaluation budgeting: at each iteration, it evaluates only a fixed fraction of interactions by dynamically routing computation to high-conflict or high-uncertainty interactions, instead of using a fixed sparsification (e.g., static kNN graphs or static masks). Under fully inclusive end-to-end wall-clock accounting, LoRe substantially improves scalability on maximum independent set, pushing feasible inference beyond the baseline out-of-memory boundary by $2.5\times$ while delivering $4$--$5\times$ speedup, about 81% peak-memory reduction, and 86.9% MIS-size retention. As an auxiliary study on large-scale TSP, LoRe achieves $7.5\times$ median speedup at $n=1000$ with 97% median memory reduction and a median gap difference of $-0.22$ percentage points versus the baseline, supporting its generality across problem families.

Applications · Computer Vision

Lai Wei, Liangbo He, jun lan, Lingzhong Dong, Yutong Cai, Siyuan Li, Huijia Zhu, Weiqiang Wang, Linghe Kong, Yue Wang 等

Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent "Thinking-with-Images" methods alleviate this by iteratively zooming into regions of interest during inference, but incur high latency due to repeated tool calls and visual re-encoding. To address this, we propose Region-to-Image Distillation, which transforms zooming from an inference-time tool into a training-time primitive, thereby internalizing the benefits of agentic zooming into a single forward pass. In particular, we first zoom in to micro-cropped regions to let strong teacher models generate high-quality VQA data, and then distill this region-grounded supervision back to the full image. After training on such data, the smaller student model improves "single-glance" fine-grained perception without tool use. To rigorously evaluate this capability, we further present MicroPercept, a hybrid-annotated benchmark of 845 VQA data spanning six fine-grained perceptual dimensions, together with a dual-view protocol that quantifies the global-regional "zooming gap". Experiments show that our model achieves consistent gains across multiple fine-grained perception benchmarks, surpasses state-of-the-art agentic models while eliminating their inference latency, and improves out-of-distribution generalization.

Applications · Chemistry, Physics, and Earth Sciences

Liao Chang, Luotian Yuan, Yiping Ke, Ying Wei

Multi-step retrosynthesis planning is a fundamental challenge in organic chemistry, defined by its enormous search space. Existing methods typically formulate it as a Markov Decision Process (MDP) with a fixed choice of transition model (i.e., a single-step retrosynthesis model), and focus on improving *how to search* through better policies and value functions. However, *how the transition space itself is navigated* remains largely unexplored. This limitation is particularly urgent given our observation of pronounced *skill disparity* among single-step prediction models: different models exhibit substantially different performance across molecule states. Motivated by this observation, we introduce RetrOrchestrator, an LLM-powered agent that explicitly accounts for model skill disparity by reframing retrosynthesis planning as a Partially Observable Markov Decision Process (POMDP). By regarding each single-step prediction model as a tool, we further propose a scaffold-aware reinforcement learning algorithm to optimize navigation policy within the transition space. As a result, RetrOrchestrator jointly searches which molecule to expand and which single-step model to apply for the molecule at the current step. Empirically, RetrOrchestrator significantly outperforms static baselines on the Retro*-190 benchmark, achieving a state-of-the-art 94.21\% success rate as well as a Pareto front in both wallclock time and number of model queries.

Applications · Computer Vision

Nanjie Yao, Junlong Ren, Wenhao Shen, Hao Wang

This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distribution matching, leading to local joint reconstruction errors. We propose MotionGRPO, a novel framework leveraging reinforcement learning post-training to inject fine-grained guidance into the diffusion process. Technically, we model diffusion sampling as a Markov decision process optimized via Group Relative Policy Optimization (GRPO). To this end, we introduce a hybrid reward mechanism that combines a learned conditioned perceptual model for global visual plausibility and explicit constraints for local joint precision. Our key technical insight is that policy optimization in diffusion-based recovery suffers from vanishing gradients due to limited intra-group sample diversity. To address this, we further introduce a noise-injection strategy that explicitly increases sample variance and stabilizes learning. Extensive experiments demonstrate that MotionGRPO achieves state-of-the-art performance with superior visual fidelity.

Deep Learning · Large Language Models

Yu He, Yingxi Li, Colin White, Ellen Vitercik

Large language models (LLMs) are deployed on increasingly complex tasks that require multi-step decision-making. Understanding their algorithmic reasoning abilities is therefore crucial. However, we lack a diagnostic benchmark for evaluating this capability. We propose data structures as a principled lens: as fundamental building blocks of algorithms, they naturally probe structural reasoning—the ability to understand and manipulate relationships such as order, hierarchy, and connectivity that underpin algorithmic reasoning. We introduce DSR-Bench, spanning 20 data structures, 35 operations, and 4,140 problem instances. DSR-Bench features hierarchical task organization, fully automated generation and evaluation, and fine-grained diagnostics. Evaluating 13 state-of-the-art LLMs reveals critical limitations: the top-performing model achieves only 0.46/1 on challenging instances. Three auxiliary probes targeting more realistic usages expose further weaknesses: models perform poorly on spatial data and context-rich scenarios, and they struggle to reason over their own code.

Deep Learning · Large Language Models

Weida Liang, Yiyou Sun, Shuyuan Nan, Chuang Li, Dawn Song, Kenji Kawaguchi

Example-based guidance is widely used to improve mathematical reasoning at inference time, yet its effectiveness is highly unstable across problems and models—even when the guidance is correct and problem-relevant. We show that this instability arises from a previously underexplored gap between *strategy usage*—whether a reasoning strategy appears in successful solutions—and *strategy executability*—whether the strategy remains effective when instantiated as guidance for a target model. Through a controlled analysis of paired human-written and model-generated solutions, we identify a systematic dissociation between usage and executability: human- and model-derived strategies differ in structured, domain-dependent ways, leading to complementary strengths and consistent source-dependent reversals under guidance. Building on this diagnosis, we propose *Selective Strategy Retrieval* (SSR), a test-time framework that explicitly models executability by selectively retrieving and combining strategies using empirical, multi-route, source-aware signals. Across multiple mathematical reasoning benchmarks, SSR yields reliable and consistent improvements over direct solving, in-context learning, and single-source guidance, improving accuracy by up to $+13$ points on AIME25 and $+5$ points on Apex for compact reasoning models.

Theory · Online Learning and Bandits

Xueping Gong, Jiheng Zhang

Contextual bandits serve as a foundational framework for sequential decision-making in domains like recommendation systems, IoT device management, and conversational AI, yet classical models overlook a critical practical constraint: acquiring extra observations incurs non-trivial costs, creating an unaddressed trade-off between information gain and expenditure. To fill this gap, we study contextual bandits with paid observations, where the learner actively chooses which actions to observe (at a specified cost) in each round, with the goal of minimizing total regret that combines learning losses and cumulative observation costs. We first design a near-optimal algorithm for adversarial environments, proving it achieves a regret rate significantly higher than that of cost-free contextual bandits—even for small observation costs—thus quantifying how paid observations reshape learning complexity. We then uncover a critical phase-transition phenomenon when incorporating free observation budgets: below a threshold budget, free observations only reduce total costs without changing the underlying regret rate, while above this threshold, they drastically improve learning efficiency, lowering the regret rate to match that of cost-free settings. To leverage this phenomenon, we develop a meta-controller that adaptively switches strategies based on the available budget, ensuring near-optimal performance across both low- and high-budget regimes. Furthermore, to address practical challenges like infinite policy spaces and computational inefficiency, we propose an oracle-efficient algorithm under a function approximation framework, which leverages an online regression oracle to maintain strong performance for stochastic losses. Our results also shed light on the scenarios about switching costs, budgeted constraints, model misspecification and the trade-offs involved in knapsack problems. Finally, we conduct numerical experiments to validate our theoretical findings and demonstrate practical efficiency. Key words: Contextual bandit, paid observation, function approximation, phase transition.

Deep Learning · Large Language Models

Yash Akhauri, Mohamed Abdelfattah

Efficient LLM inference research has largely focused on reducing the cost of each decoding step (e.g., using quantization, pruning, or sparse attention), typically applying a uniform computation budget to every generated token. In practice, token difficulty varies widely, so static compression can over-compute on easy steps and under-compute on hard ones. We study **dynamic budget allocation** for autoregressive decoding: learning how much computation to spend **per token** from within a single model. Self-Optimizing Language Models (SOL) pair a frozen LLM with a lightweight policy network that reads the LLM hidden state and selects a discrete **efficiency action** at each decode step. Actions can jointly control (i) token-level attention sparsity, (ii) structured activation pruning in the MLP, and (iii) activation quantization bit-width, while leaving the base model weights unchanged. We train the policy with group-relative policy optimization on teacher-forced episodes: the token sequence is fixed, while we sample multiple compute schedules (i.e., “counterfactual” schedules that vary only the efficiency actions for the same token path) and compare their likelihoods under the same supervision. Our reward trades off language‑model quality against soft penalties that encourage episode‑average budget usage to match a requested target. Across model variants and compute regimes, SOL improves quality at matched budget over static allocation and strong random schedule search, offering a complementary axis for inference‑efficiency optimization. SOL discovers a better quality-efficiency pareto-front across all our experiments and improves MMLU accuracy by upto 7.3\% over uniform budget allocation strategies.

Deep Learning · Large Language Models

Yash Akhauri, Xingyou Song, Arissa Wongpanich, Bryan Lewandowski, Mohamed Abdelfattah

We study \textbf{code-to-metric regression}: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of programming languages. While prior methods have resorted to heavy and domain-specific feature engineering, we show that a single unified Regression Language Model (RLM) can simultaneously predict directly from text, (i) the memory footprint of code across multiple high-level languages such as Python and C++, (ii) the latency of Triton GPU kernels, and (iii) the accuracy and speed of trained neural networks represented in ONNX. In particular, a relatively small 300M parameter RLM initialized from T5Gemma, obtains $>$0.9 Spearman-rank on competitive programming submissions from APPS, and a single unified model achieves $>$0.5 average Spearman-rank across 17 separate languages from CodeNet. Furthermore, the RLM can obtain the highest average Kendall-Tau of 0.46 on five classic NAS design spaces previously dominated by graph neural networks, and simultaneously predict architecture latencies on numerous hardware platforms.

Deep Learning · Large Language Models

Junnan Ren, Yan Zhang, Qian Chen, Yunhang Shen, Ke Li, Shengchuan Zhang, Liujuan Cao, Rongrong Ji

Recent Large Reasoning Models (LRMs) have demonstrated powerful multi-step problem-solving capabilities but often suffer from inefficiency due to an ``overthinking phenomenon", where they apply complex reasoning to simple tasks, resulting in unnecessary computational cost and latency. While adaptive reasoning models that can switch between generating explicit reasoning and producing direct answers offer a potential solution, their effectiveness is compromised by a critical flaw: they are often misled by superficial linguistic complexity, mistaking verbosely phrased simple problems for complex ones. To address this, we propose a two-stage training framework to create a more robust adaptive reasoner. The first stage uses supervised fine-tuning with augmented data—presenting simple problems in both concise and redundant forms—to teach the model to ignore superficial verbosity. Subsequently, a reinforcement learning phase utilizes Generalized Reward Policy Optimization (GRPO) with a custom reward function to refine the model's adaptive policy, ensuring it selects a reasoning mode based on true task complexity rather than surface-level cues. The resulting model reduces computational overhead without sacrificing accuracy and demonstrates improved robustness to misleading linguistic cues.

Reinforcement Learning · Inverse

Raphaël Baur, Yannick Metz, Maria Gkoulta, Mennatallah El-Assady, Giorgia Ramponi, Thomas Kleine Buening

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as demonstrations, comparisons, ratings, rankings, and stops that provide qualitatively different signals. We address this challenge by formulating reward learning from multiple feedback types as Bayesian inference over a shared latent reward function, where each feedback type contributes information through an explicit likelihood. We introduce a scalable amortized variational inference approach that learns a shared reward encoder and feedback-specific likelihood decoders and is trained by optimizing a single evidence lower bound. Our approach avoids reducing feedback to a common intermediate representation and eliminates the need for manual loss balancing. Across discrete and continuous-control benchmarks, we show that jointly inferred reward posteriors outperform single-type baselines, exploit complementary information across feedback types, and yield policies that are more robust to environment perturbations. The inferred reward uncertainty further provides interpretable signals for analyzing model confidence and consistency across feedback types.

Deep Learning · Large Language Models

Avinandan Bose, Stella Li, Faeze Brahman, Pang Wei Koh, Simon Du, Yulia Tsvetkov, Maryam Fazel, Lin Xiao, Asli Celikyilmaz

Cold-start personalization requires inferring preferences from minimal interaction when no user-specific historical data is available. The space of possible preferences is vast, yet users care about only a sparse subset and rarely articulate them upfront; combined with limited interaction budgets, this makes preference elicitation challenging. Our key insight is that preferences exhibit predictable structure across populations; e.g., users who want detailed explanations often also value worked examples. We propose PEP (Preference Elicitation with Priors), a principled system decomposition framework for cold-start personalization: learning a structured world model of preference correlations offline using latent variables, then performing Bayesian inference online without retraining. Even simple belief model instantiations (e.g., linear regression) substantially outperform end-to-end RL. Across medical, mathematical, social, and commonsense reasoning, PEP achieves 80.8% alignment with ground-truth user preferences versus 68.5% for RL, requires 3-5× fewer interactions, and adapts twice as often. Our contribution is a principled decomposition of cold-start personalization that makes Bayesian preference elicitation practical at scale for LLM systems.

Deep Learning · Robustness

Mingyuan Bai, Wei Huang, Tenghui Li, Andong Wang, Chao Li, Cesar F Caiafa, Junbin Gao, Qibin Zhao

Adversarial purification uses generative models to restore clean data distributions from unseen attacks without retraining classifiers. However, unimodal diffusion-based approaches struggle to preserve semantic consistency, while recent multimodal variants rely on computationally expensive adversarial training or distillation. Both approaches often lack theoretical guarantees. In this work, we propose MultiDAP, a novel framework leveraging multimodal diffusion models for efficient adversarial purification. MultiDAP first learns continuous class-agnostic prompts from clean data to capture rich semantic priors, replacing rigid hand-crafted templates. Guided by these prompts, MultiDAP purifies adversarial inputs by minimizing a regularized DDPM loss for only a few steps (e.g., 5-20). We provide theoretical guarantees for both the likelihood improvement via prompt learning and the convergence of the purification process. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that MultiDAP matches the robustness of state-of-the-art baselines but with improved efficiency.

General Machine Learning · Everything Else

Junhua Zeng, Yuning Qiu, Binghua Li, Chao Li, Qibin Zhao, Guoxu Zhou

Over the years, the unsupervised and supervised learning research directions of tensor networks (TNs) have mainly developed in parallel. In this paper, we provide a view for their cooperative advancement through a novel mixed tensor network learning (MTNL) framework that unifies the two fields. Specifically, inspired by supervised TN learning tasks, multiple TNs are fused in a deep-network style in MTNL, enhancing the expressive power for the unsupervised TN learning tasks. We then develop a more flexible TN structure search prior with theoretical guarantees for learning multiple TN structures, aligning with trends in many supervised learning setups. More interestingly, by combining these components within a Bayesian framework, we show that MTNL induces a lightweight uncertainty quantification mechanism that is theoretically guaranteed by its connection to the dropout-based counterpart problem, making the mechanism a potential alternative for large-scale learning problems. Finally, we demonstrate the effectiveness of the MTNL framework on tensor recovery, parameter-efficient fine-tuning, and tensor regression experiments.

Xianzhen Luo, Jingyuan Zhang, Shiqi Zhou, JinYang Huang, Chuan Xiao, Qingfu Zhu, Zhiyuan Ma, YUE XING, Yang Yue, WencongZeng 等

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\% solution correctness and 96\% environment fidelity, confirming its expert-level quality. It is also evaluated on the latest realistic vulnerabilities and achieves a 66.2\% verified success. This automation enables two downstream contributions. First, we construct LiveCVEBench, a continuously updated benchmark of 190 tasks spanning 14 languages and 153 repositories that captures emerging threats including AI-tooling vulnerabilities. Second, we synthesize over 1,000 executable training environments, the first large-scale scaling of agentic tasks in code security. Fine-tuned Qwen3-32B improves from 5.3\% to 35.8\% on LiveCVEBench, surpassing Claude 4.5 Sonnet, with gains generalizing to Terminal Bench (12.5\% to 31.3\%). We open-source all code, data, and models.

General Machine Learning · Causality

Michael Lindon, Nathan Kallus

Delayed outcomes are ubiquitous in online experimentation. When such a temporal dimension is present, treatment influences not only the outcome value but also the outcome timing, which can move in opposite directions. Motivated by the desire to continuously monitor the performance of treatment arms, we develop an anytime-valid approach to inference in the delayed outcome setting. We adopt a design-based framework where both the outcome timing and value are fixed potential outcomes, and randomness is introduced by treatment assignment only. We target the sample cumulative reward as a function of time, a causal estimand that avoids modeling the unobserved future, which would require strong assumptions violated by the nonstationarity and heterogeneity of our setting. We prove that the estimation error for the Horvitz-Thompson (IPW) estimator forms a martingale with respect to a specific single-arm filtration. Conversely, the estimation error for the AIPW estimator fails to be adapted to this filtration. We prove a fundamental negative result for the treatment effect: the estimation error is not a martingale under any filtration, arising from cross-arm covariance induced by randomized assignment. We resolve this using a union bound, showing it yields tighter intervals than the standard variance upper bound when treatment induces asymmetry in outcome arrival rates.

Deep Learning · Theory

Ruizhe Shi, Minhak Song, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon Du

We present a fine-grained theoretical analysis of the performance gap between reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) under a representation gap. Our study decomposes this gap into two sources: an explicit representation gap under exact optimization and an implicit representation gap under finite samples. In the exact optimization setting, we characterize how the relative capacities of the reward and policy model classes influence the final policy qualities. We show that RLHF, DPO, or online DPO can outperform one another depending on type of model mis-specifications. Notably, online DPO can outperform both RLHF and standard DPO when the reward and policy model classes are isomorphic and both mis-specified. In the approximate optimization setting, we provide a concrete construction where the ground-truth reward is implicitly sparse and show that RLHF requires significantly fewer samples than DPO to recover an effective reward model, highlighting a statistical advantage of two-stage learning. Together, these results provide a comprehensive understanding of the performance gap between RLHF and DPO under various settings, and offer practical insights into when each method is preferred.

Deep Learning · Large Language Models

Fangru Lin, Valentin Hofmann, Xingchen Wan, Weixing Wang, Zifeng Ding, Anthony Cohn, Janet Pierrehumbert

Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language. To what extent can LLMs generalize across these representations? Here, we approach this question by studying isomorphic tasks involving procedures represented in code, graphs, and natural language (e.g., scheduling steps in planning). We find that training LLMs with popular post-training methods on graphs or code data alone does not reliably generalize to corresponding natural language tasks, while training solely on natural language can lead to inefficient performance gains. To address this gap, we propose a two-stage data curriculum that first trains on symbolic, then natural language data. The curriculum substantially improves model performance across model families and tasks. Remarkably, a 1.5B Qwen model trained by our method can closely match zero-shot GPT-4o in naturalistic planning. Finally, our analysis suggests that successful cross-representation generalization can be interpreted as a form of generative analogy, which our curriculum effectively encourages.

Wenbo Pan, Zhichao Liu, Xianlong Wang, Yu Haining, Xiaohua Jia

Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as modern LLMs increasingly rely on extended reasoning chains, existing schemes face two critical challenges: (1) efficiency bottleneck, where attributing a sequence of $|\mathbf{S}|$ tokens requires $\mathcal{O}(|\mathbf{S}|^2)$ operations, making long-context attribution prohibitively slow; and (2) faithfulness drop, where intermediate reasoning tokens absorb attribution mass, preventing importance from propagating back to the original input. To address these, we introduce **FlashTrace**, an efficient multi-token attribution method that employs span-wise aggregation to compute attribution over *multi-token targets in a single pass*, reducing complexity to $\mathcal{O}(|\mathbf{S}|)$. Moreover, we design a recursive attribution mechanism that traces importance through intermediate reasoning chains back to source inputs. Extensive experiments on long-context retrieval (RULER) and multi-step reasoning (MATH, MorehopQA) tasks demonstrate that FlashTrace achieves over 130× speedup over existing baselines while maintaining superior faithfulness. We further analyze the dynamics of recursive attribution, showing that even a single recursive hop substantially improves faithfulness by tracing importance through the reasoning chain.

Deep Learning · Large Language Models

Zhiwei Ning, Xuanang Gao, Jiaxi Cao, Gengming Zhang, Shengnan Ma, Wenwen Tong, Hanming Deng, JIE YANG, Wei Liu

Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although recent agentic approaches incorporate tool use, they often neglect critical execution feedback. Consequently, they suffer from the imagination-action-observer (IAO) bias, a misalignment between prior imagination and observer feedback that undermines reasoning stability and optimality. To bridge this gap, we introduce V-ABS, an action-observer driven beam search framework that enables deliberate reasoning through thinker-actor-observer iterations. We also propose an entropy-based adaptive weighting algorithm to mitigate the IAO bias by dynamically balancing the confidence scores between the policy priors and the observational feedback. Moreover, we construct a large-scale supervised fine-tuning (SFT) dataset comprising over 80k samples to guide the model to assign higher prior confidence to correct action paths. Extensive experiments across eight diverse benchmarks show that V-ABS achieves state-of-the-art performance, delivering an average improvement of 19.7\% on the Qwen3-VL-8B baseline and consistent gains across both open-source and proprietary models.