论文检索

General Machine Learning · Causality

Hugh Dance, Peter Orbanz, Arthur Gretton

Reliable uncertainty quantification for causal effects is crucial in various applications, but remains difficult in nonparametric models, particularly for continuous treatments. We introduce IMPspec, a Gaussian process (GP) framework for modeling uncertainty over interventional causal functions under continuous treatments, which can be represented using reproducing Kernel Hilbert Spaces (RKHSs). By using principled function class expansions and a spectral representation of RKHS features, IMPspec yields tractable training and inference, a spectral algorithm to calibrate posterior credible intervals, and avoids the underfitting and variance collapse pathologies of earlier GP-on-RKHS methods. Across synthetic benchmarks and an application in healthcare, IMPspec delivers state-of-the-art performance in causal uncertainty quantification and downstream causal Bayesian optimization tasks.

Deep Learning · Everything Else

Haojie Duanmu, Jifeng Ding, Size Zheng, Xuegui Zheng, Jiangfei Duan, Xingcheng ZHANG, Li-Wen Chang, Xin Liu, Dahua Lin

The rapid scaling of large language models (LLMs) has made distributed inference indispensable, yet end-to-end latency is increasingly dominated by communication, forming a critical bandwidth wall that fundamentally limits the practical gains of existing quantization techniques. Existing approaches typically treat communication and computation in isolation, failing to exploit their coupled nature and introducing limited system-level acceleration and accuracy degradation. To address this, we propose CoCoQuant, a co-designed framework that jointly optimizes communication and computation as a unified end-to-end design space. CoCoQuant introduces a precision-aligned graph-rewriting that enables zero-overhead fusion between low-precision communication and computation. CoCoQuant formulates a hardware-aware mixed-precision allocation problem that integrates roofline-based cost modeling with relative sensitivity calibration, solved via global integer linear programming. Extensive experiments on LLMs of varing scales demonstrate that CoCoQuant achieves Pareto-optimal accuracy-latency trade-offs, delivering up to 2.92 end-to-end speedup with a negligible increase in perplexity (0.22).

Deep Learning · Other Representation Learning

Aoran Zhang, Yu-Bin Yang, Yonghong Yu

Recently, the integration of large language models (LLMs) with generative recommendation (GR) has demonstrated promising potential. However, most existing GR methods adopt residual quantization to implicitly model hierarchical relationships across codebook layers in Euclidean space, which distorts the intrinsic tree-like hierarchy and leads to low codebook utilization. To address these issues, we propose a Hyperbolic RQ-VAE enhanced Generative Recommendation, namely HG-Rec. Specifically, HG-Rec enhances the residual quantization mechanism by embedding the latent discrete representations into hyperbolic space to explicitly model hierarchical relationships across codebook layers. Motivated by the exponential volume growth of hyperbolic space, we further design a differential-length codebook strategy, i.e. the codebook size follows a pyramidal structure, which aligns with the tree-like structure and effectively compresses the codebook size. Hence, benefiting from the alignment of hyperbolic geometry and codebook hierarchy, HG-Rec achieves lower collision rates, more uniform codebook usage, and less training time compared to existing methods. Extensive experiments across multiple benchmark datasets demonstrate that HG-Rec consistently achieves state-of-the-art performance. The code is available in the Supplementary Material.

Reinforcement Learning · Batch/Offline

Harry Amad, Mihaela van der Schaar

A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. However, the typical design process of machine learning-based DTs does not optimise for this objective. We prove that, when model capacity is limited, typical DT training paradigms, which minimise one-step transition errors, can produce suboptimal models for ranking sets of policies. We further show that this holds empirically, even with expressive model classes. To address this, we introduce DT$^2$, a decision-targeted DT training paradigm. DT$^2$ uses off-policy evaluation methods to estimate values of candidate policies on offline data, and encourages the DT to generate rollouts that preserve pairwise policy rankings derived from these proxy ground-truths with an architecture-agnostic loss function. We empirically demonstrate the efficacy of our method across a range of settings and architectures, showing that DT$^2$ consistently improves policy ranking and reduces decision regret relative to conventional DT training, both for policies used during training and for unseen policies, while maintaining a good level of raw simulation fidelity.

Applications · Everything Else

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.

Theory · Game Theory

Christopher Liaw, Wennan Zhu

The rise of auto-bidding in online advertising has created new challenges for ensuring advertiser incentive compatibility, particularly when advertisers delegate bidding to agents with high-level constraints. One challenge is the multiplicity of equilibria with reported constraints. Alimohammadi et al. proposed a notion of Auto-bidding Incentive Compatibility (AIC) which serves to highlight that standard auctions may not incentivize truthful reporting of these constraints. However, their definition of AIC is very stringent as it requires that the worst-case outcome of an advertiser's truthful report is at least as good as the best-case outcome of any of the advertiser's possible deviations. In this paper, we introduce two refined and relaxed concepts: Risk-Averse Auto-bidding Incentive Compatibility (RAIC) and Optimistic Auto-bidding Incentive Compatibility (OAIC). RAIC (OAIC) stipulates that truthful reporting is preferred if its least (most) favorable equilibrium outcome is no worse than the least (most) favorable equilibrium outcome from any misreport. We demonstrate that SPA satisfies both RAIC and OAIC. These findings clarify SPA's incentive properties under auto-bidding, specifically regarding advertiser perspectives on equilibrium selection.

Simon Mahns, Randall Balestriero, Mahmoud Assran

We investigate whether Joint-Embedding Predictive Architectures (JEPA) can learn useful representations of U.S. equity markets. We jointly train a permutation-invariant tokenizer that maps each trading day's unordered per-asset features to a fixed set of learned factor tokens, together with a temporal JEPA using masked prediction to obtain a compact daily market-state embedding. Our evaluations show that these embeddings are strongly associated with second-moment market structure (realized volatility, correlation concentration, effective factor dimensionality) and weakly associated with market direction. The embedding helps predict gradual recovery dynamics but not sudden stress onsets. Without any text supervision, latent regimes show statistically significant alignment with news-topic shifts.

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.