论文检索

Deep Learning · Large Language Models

Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha, Dilek Hakkani-Tür, Hao Peng

Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling efforts. However, optimization practices in RL largely follow those of next-token-prediction stages (e.g., pretraining and supervised fine-tuning), despite the fundamental differences between RL and these stages emphasized by recent work. One such practice is the use of the AdamW optimizer, which is widely adopted for training large-scale transformers despite its high memory overhead. Our analysis shows that both momentum and adaptive learning rate of AdamW are less influential in RL than in SFT, leading us to hypothesize that RL benefits less from Adam’s per-parameter adaptive learning rates and momentum. Confirming our hypothesis, our experiments demonstrate that the substantially more memory-efficient SGD, which is known to perform poorly in supervised learning of large-scale transformers, matches or even outperforms AdamW in RL for LLMs. Remarkably, full fine-tuning with SGD updates fewer than 0.02% of model without any sparsity-promoting regularization, more than 1,000 times fewer than AdamW. Our analysis offers potential reasons for this update sparsity. Our findings provide fresh insights into the optimization dynamics of RL in LLMs and demonstrate that RL can be substantially more parameter-efficient than previously recognized.

Applications · Everything Else

Joohyung Yun, Doyup Lee, Wook-Shin Han

Open-domain multimodal document retrieval aims to retrieve specific components (paragraphs, tables, or images) from large and interconnected document corpora. Existing graph-based retrieval approaches typically rely on a uniform similarity metric that overlooks hop-specific semantics, and their rigid pre-defined plans hinder dynamic error correction. These limitations suggest that a retriever should adapt its reasoning to the evolving context and recover intelligently from dead ends. To address these needs, we propose Failure is Feedback (FiF), which casts subgraph retrieval as a sequential decision process and introduces two key innovations. (i) We introduce a history-aware backtracking mechanism; unlike standard backtracking that simply reverts the state, our approach piggybacks on the context of failed traversals, leveraging insights from previous failures. (ii) We implement an economically-rational agentic workflow. Unlike conventional agents with static strategies, our orchestrator employs a cost-aware traversal method to dynamically manage the trade-off between retrieval accuracy and inference costs, escalating to intensive LLM-based reasoning only when the prior failure justifies the additional computational investment. Extensive experiments show that FiF achieves state-of-the-art retrieval on the benchmarks of MultimodalQA, MMCoQA and WebQA.

Applications · Chemistry, Physics, and Earth Sciences

Zhonghao Li, Chaoyu Liu, Qian Zhang

Partial differential equations (PDEs) are fundamental for modeling complex natural and physical phenomena. In many real-world applications, however, observational data are \textbf{extremely sparse}, which severely limits the applicability of both classical numerical solvers and existing neural approaches. While neural methods have shown promising results under moderately sparse observations, their inference efficiency at high resolutions is limited, and their accuracy degrades substantially in the extremely sparse regime. In this work, we propose the \textbf{Di-BiLPS}, a unified neural framework that effectively handle \textbf{both forward and inverse} PDE problems under extremely sparse observations. Di-BiLPS combines a variational autoencoder to compress high-dimensional inputs into a compact latent space, a latent diffusion module to model uncertainty, and contrastive learning to align representations. Operating entirely in this latent space, the framework achieves efficient inference while retaining flexible input–output mapping. In addition, we introduce a \textbf{PDE-informed denoising algorithm} based on a variance-preserving diffusion process, which further improves inference efficiency. Extensive experiments on multiple PDE benchmarks demonstrate that Di-BiLPS consistently achieves \textbf{SOTA performance under extremely sparse inputs (as low as 3\%)}, while substantially reducing computational cost. Moreover, Di-BiLPS enables \textbf{zero-shot super-resolution}, as it allows predictions over continuous spatial–temporal domains.

Deep Learning · Large Language Models

WenXiang Lin, HuangJunTao, ZhangLuHan, Lilaiyi, Xiang Bao, mengyang zhang, BingWang Wang, Shaohuai Shi

Quantization is a key method for reducing the GPU memory requirement of training large language models (LLMs). Yet, current approaches are ineffective for 4-bit activations and 8-bit gradients, which would easily cause slow convergence or accuracy loss. To address this, we introduce AGoQ, incorporating two new techniques: 1) a layer-aware activation quantization algorithm that allocates appropriate bit-widths for activations of various layers based on their types and pipeline stages to achieve near 4-bit activation storage, and 2) a gradient quantization algorithm that reduces memory usage and shortens communication time by employing 8-bit gradient storage and precision-preserving 8-bit All-Reduce communication. We conduct extensive experiments using different sizes of LLMs on two GPU clusters (up to 64 GPUs), and the experimental results show that our AGoQ reduces the memory by up to 52\% and achieves up to 1.34$\times$ improvement of training speed compared to state-of-the-art training systems Megatron-LM (w/ or w/o ZeRO), COAT and DeepSpeed with 8B to 32B LLaMA models, while achieving convergence loss on pretraining and comparable accuracy on downstream tasks with LLaMA architectures.

General Machine Learning · Online Learning, Active Learning and Bandits

Shion Takeno, Shogo Iwazaki

We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP. Compared with the GP upper confidence bound (GP-UCB) with established high-probability and expected regret bounds, most analyses of GP-TS have been limited to expected regret. Moreover, whether the recent analyses of GP-UCB for the lenient regret and the improved cumulative regret upper bound can be applied to GP-TS remains unclear. To fill these gaps, this paper shows several regret bounds: (i) a regret lower bound for GP-TS, which implies that GP-TS suffers from a polynomial dependence on $1/\delta$ with probability $\delta$, (ii) an upper bound of the second moment of cumulative regret, which directly suggests an improved regret upper bound on $\delta$, (iii) expected lenient regret upper bounds, and (iv) an improved cumulative regret upper bound on the time horizon $T$. Along the way, we provide several useful lemmas, including a relaxation of the necessary condition from recent analysis to obtain improved regret upper bounds on $T$.

Hongbin Zhang, Kehai Chen, Xuefeng Bai, Youcheng Pan, Yang Xiang, Jinpeng Wang, Min zhang

Large language models (LLMs) have emerged as a standard paradigm for automated multilingual evaluation, yet exhibit systematic biases. In this paper, we identify ``translationese bias'', in which LLMs systematically favor machine-translated text over human-authored references, and this bias is particularly pronounced in low-resource languages. We attribute this bias to spurious correlations with (a) strong latent manifold isomorphism with English and (b) high predictive confidence. To mitigate these issues, we present DIBJudge, a robust fine-tuning framework that decouples robust features and bias representations by explicitly isolating spurious attributes into a dedicated bias branch and penalizing mutual dependence to enforce disentanglement. In particular, we present a vector-quantized compression that ensures the robust representation retains minimal and sufficient judgment-critical information. Extensive evaluations on multilingual reward modeling benchmarks and a specially designed translationese bias evaluation suite demonstrate that DIBJudge outperforms strong baselines and effectively mitigates translationese bias.

Yanzhe Wen, Xunkai Li, Qi Zhang, Lei Zhu, Guang Zeng, Zhihan Zhang, Rong-Hua Li, Guoren Wang

Recently, large language models (LLMs) have driven a systematic shift in the graph ML com- munity through the adoption of text-attributed graphs (TAGs). Although a variety of frameworks have been developed, most fail to properly ad- dress the challenge of data uncertainty in open- world environments. A representative source of such uncertainty is the limited availability of la- bels in large-scale datasets due to high annotation costs, where unlabeled nodes may belong to either known classes or novel, unknown classes. While node-level out-of-distribution detection and con- ventional open-world graph learning attempt to tackle this problem, two core limitations remain: ① Insufficient methods — existing approaches typically optimize semantics or topology in isola- tion for unknown-class rejection, failing to effec- tively integrate textual and structural information in TAGs; ② Incomplete pipelines — most stud- ies conduct only idealized analyses, such as as- suming a predefined number of unknown classes, which restricts practical utility for model updates and long-term deployment. To overcome these issues, we introduce the Open-world Graph Assis- tant (OGA), an LLM-based framework. OGA first performs unknown-class rejection via adaptive la- bel traceability (ALT), harmoniously combining semantic and topological cues, and then applies the graph label annotator (GLA) for unknown- class annotation, allowing unlabeled nodes to con- tribute to model training. In essence, OGA offers a new pipeline that fully automates the handling of unlabeled nodes in open-world environments, and we establish a systematic benchmark cover- ing four key aspects to validate its effectiveness and practicality through extensive experiments.

General Machine Learning · Representation Learning

Yubo Ye, Sweekar Piya, Xiajun Jiang, Linwei Wang

Learning *latent dynamics* is central to assessing current states and forecasting future trajectories for high-dimensional time series. For locally-stationary latent dynamics of the form $\mathcal{F}(\mathbf{z}_{<t}; \mathbf{c})$ with latent dynamics state $\mathbf{z}_t$ and environment variable $\mathbf{c}$, prior identifiability results largely focus on $\mathbf{z}_t$ when conditioned on pre-defined label $u$ of the dynamics environment. This leaves two limitations: reliance on pre-defined labels that hinder generalization to unseen environments, and limited understanding of the identifiability of $\mathcal{F}$ and $\mathbf{c}$ which---while offering important structural properties for the identifiabilty of $\mathbf{z}_t$---are learned jointly with $\mathbf{z}_t$. We address these challenges with Meta-iLaD, a novel latent dynamics framework to attain identifiability by meta-learning across dynamics environments. Meta-iLad replaces the conditioning of $\mathbf{c}$ on pre-defined labels with a novel condition prior, modeled as a feedforward meta-learner that rapidly extracts $\mathbf{c}$ from few-shot examples. We further establish simultaneous identifiability for $\mathbf{z}\_t$, $\mathbf{c}$ and $\mathcal{F}$, for a general formulation of $\mathcal{F}(\mathbf{z}\_{< t};\mathbf{c})$ without restricting the dimension of $\mathbf{c}$ or how it modulates $\mathcal{F}$. We provide strong empirical evidence that 1) conditioning on few-shot examples enables generalization to out-of-distribution environments, and 2) identifiability for $\mathbf{c}$ and $\mathcal{F}$ is critical for accurate forecasting beyond reconstructing observed trajectories.

Deep Learning · Robustness

Qin Yang, Xin Wei, Yanjia Li, Jiasun Feng, Mingrui Zhu, Nannan Wang, Xinbo Gao

Vision-Language Pre-trained (VLP) models are vulnerable to real-world query noise. Current cross-modal Test-Time Adaptation (TTA) methods often rely on high-confidence predictions, which induces confirmation bias and neglects the informative signals in ambiguous Low-Confidence Queries. To address this, we propose Generative Semantic Refinement and Exclusion-Guided Adaptation (ReEx), a robust retrieval framework that extends adaptation to the entire query stream. Specifically, textual structural noise is rectified by a Generative Semantic Refinement (GSR) module, which employs Confidence-Guided Dynamic Fusion to anchor LLM-based repairs and prevent semantic drift. To exploit ambiguous data, adaptation is driven by Exclusion-Guided Proxy Contrastive Learning (EPCL), which imposes negative constraints via Exclusion Sets of unlikely candidates. Experimental results on COCO-C and Flickr-C demonstrate that ReEx consistently outperforms existing TTA methods, achieving significant robustness gains with a justifiable computational trade-off.

Deep Learning · Generative Models and Autoencoders

Erkan Turan, Ari Siozopoulos, Louis Martinez, Julien Gaubil, Emery Pierson, Maks Ovsjanikov

Continuous Normalizing Flows (CNFs) enable elegant generative modeling but remain bottlenecked by their iterative nature requiring costly sampling and lacking interpretability of the intermediate states. Recent approaches accelerate sampling by straightening trajectories or distilling endpoints, yet they treat the original generative process as a black box, discarding the teacher’s intermediate dynamics. We propose a fundamentally different perspective: globally linearizing flow dynamics via Koopman theory to achieve trajectory-preserving linearization. By lifting Conditional Flow Matching (CFM) into a higher-dimensional Koopman space, we represent its evolution with a single linear operator. Crucially, unlike boundary-only distillation, our method enforces infinitesimal consistency with the teacher's vector field along *the full generative path*. We derive a practical, simulation-free training objective that ensures this global alignment and yields two key benefits. First, sampling becomes one-step and parallelizable. Second, because the linearization is faithful to the dynamics, the Koopman operator provides unique insights on the generation. We demonstrate that this structure enables novel applications unavailable in prior approaches, including discovery of semantically coherent editing directions, inversion with a teacher-aligned linear operator and class-conditional spectral signatures. Empirically, our approach achieves competitive sample quality, while enabling spectral analysis and control of the *entire trajectories* of generative flows.

Deep Learning · Large Language Models

Ting Zhou, Zhenqing Ling, Yiyang Zhao, Ying Shen, Daoyuan Chen

Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or misspecified rewards. We identify a failure mode we call directional inconsistency: within a batch, a small set of high-reward rollouts induces representation-space preference directions that sharply disagree with the batch majority, resulting in high-variance and destabilizing updates. We propose GeoAlign, a lightweight plug-in for rollout curation in iterative policy optimization. GeoAlign (i) forms within-prompt preference pairs, (ii) learns an online projector on per-rollout hidden states to concentrate reward-ordered displacement directions, and (iii) detects directionally inconsistent rollouts via their angular deviation from a batch consensus prototype and rectifies them with within-prompt stable alternatives. GeoAlign is forward-pass only and adds negligible overhead. Across dialogue alignment with a learned reward model and mathematical reasoning with binary verified rewards, GeoAlign improves final performance and reduces training oscillation, outperforming PF-PPO, PAR, PODS, and Seed-GRPO. These results suggest latent directional consensus as an effective reliability signal for online LLM RL.

Deep Learning · Large Language Models

Mingyuan Xu, Xinzi Tan, Jiawei Wu, Doudou Zhou

Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability; treating all judges equally can yield biased leaderboards and misleading uncertainty estimates—more data can make evaluation more confidently wrong under misspecified aggregation. We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters, jointly estimating latent model quality and judge reliability from pairwise comparisons without reference labels. We establish identifiability up to natural normalizations and prove consistency and asymptotic normality of the maximum likelihood estimator, enabling confidence intervals for score differences and rank comparisons. Across multiple public benchmarks and a newly collected dataset, our method improves agreement with human preferences, achieves higher data efficiency than unweighted baselines, and produces calibrated uncertainty quantification for LLM rankings.

Theory · Game Theory

Vinzenz Thoma, Georgios Piliouras, Luke Marris

Automated design of multi-agent interactions with desirable equilibrium outcomes is inherently difficult due to the computational hardness, non-uniqueness, and instability of the resulting equilibria. In this work, we propose the use of game-agnostic _differentiable equilibrium blocks_ (DEBs) as modules in a novel, differentiable framework to address a wide variety of incentive design problems from economics and computer science. We call this framework _deep incentive design_ (DID). To validate our approach, we examine three diverse, challenging incentive design tasks: contract design, machine scheduling, and inverse equilibrium problems. For each task, we train a single neural network using a unified pipeline and DEB. This architecture solves the _full distribution_ of problem instances, parameterized by a context, handling _all_ games across a wide range of scales (from two to sixteen actions per player).

Applications · Chemistry, Physics, and Earth Sciences

Philipp Höllmer, Stefano Martiniani

Continuous-time generative models for crystalline materials enable inverse materials design by learning to predict stable crystal structures, but incorporating explicit target properties into the generative process remains challenging. Policy-gradient reinforcement learning (RL) provides a principled mechanism for aligning generative models with downstream objectives but typically requires access to the score, which has prevented its application to flow-based models that learn only velocity fields. We introduce Open Materials Generation with Inference-time Reinforcement Learning (OMatG-IRL), a policy-gradient RL framework that operates directly on the learned velocity fields and eliminates the need for the explicit computation of the score. OMatG-IRL leverages stochastic perturbations of the underlying generation dynamics preserving the baseline performance of the pretrained generative model while enabling exploration and policy-gradient estimation at inference time. Using OMatG-IRL, we present the first application of RL to crystal structure prediction (CSP). Our method enables effective reinforcement of an energy-based objective while preserving diversity through composition conditioning, and it achieves performance competitive with score-based RL approaches. Finally, we show that OMatG-IRL can learn time-dependent velocity-annealing schedules, enabling accurate CSP with order-of-magnitude improvements in sampling efficiency and, correspondingly, reduction in generation time.

General Machine Learning · Causality

Alpar Turkoglu, Muralikrishnna Guruswamy Sethuraman, Faramarz Fekri

Learning causal relationships between variables from data is a fundamental research area with many applications across disciplines. Most of the existing causal discovery algorithms rely on the assumptions that (i) the underlying system is acyclic, (ii) the exogenous noise variables are Gaussian, and (iii) that the intervention targets for the data generating experiments are known. While these assumptions simplify the analysis, they are violated in real-life systems. Most existing methods that address these issues either assume the underlying model is linear or are constrained to operate in limited interventional settings. To that end, we propose SCOUT, a novel causal discovery framework to learn nonlinear causal cyclic relationships from soft interventional data with unknown targets. Our main approach maximizes the data log-likelihood to recover the graph structure, using two normalizing-flow architectures—contractive residual flows and neural spline flows. By conducting experiments on synthetic and real-world data, we show that SCOUT outperforms state-of-the-art methods in both causal graph and unknown target recovery across various interventional and noise settings.

Deep Learning · Large Language Models

Jie Wu, Haoran Ma, Shisong Tang, Yulin Xu, Xiaoyu Kang, Jiechao Gao

Generating runnable front-end code from UI screenshots is a long-standing goal in automated software engineering. Existing MLLM-based methods predominantly focused on HTML/CSS, leaving multi-framework generation for React/Vue/Angular underexplored. Naively modifying prompts leads to substantial performance gaps across multi-framework and highly framework-specific error modes. To address this, we propose \textbf{MulFCoder}, a framework-conditioned multi-agent method that explicitly encodes framework constraints to bring multi-framework differences into a decidable rule space. MulFCoder orchestrates four agents: Grounder constructs an ElementTable, ContentTable, and macro-layout regions from detected UI elements; Planner builds a DOM-like hierarchical layout tree, produces a task schedule, and derives a framework-specific file Contract; Writer generates structured file writes or patches within a restricted edit window; Judger enforces lightweight, framework-conditioned FastGate constraints to accept or reject updates and trigger bounded repairs, preventing drift and deadlocks without expensive builds. Experiments demonstrate that MulFCoder substantially improves multi-framework compilation success and reduces framework-specific errors, with particularly pronounced gains on constraint-heavy frameworks.

Social Aspects · Privacy

Xutong Mu, Yanbiao Ma, Jia Shi, Xueli Geng, Fengkai Xiang, Tao Zhang, Ke Cheng, Yulong Shen

Federated Learning (FL) faces significant challenges due to domain heterogeneity, where data from different clients exhibit substantial statistical shifts that hinder the generalization of the global model. Although existing methods attempt to mitigate this by exchanging class prototypes, they fall short by representing an entire class's complex distribution with a single point. This oversimplification disregards the rich structural information within the data, especially across diverse domains. To address this limitation, we propose a paradigm shift from point-based representation to structure-based knowledge transfer. We introduce Federated Manifold Learning (FML), a novel framework that leverages perceptual manifolds—the intrinsic geometric structures of classes in the feature space—as rich knowledge carriers. In FML, clients transmit compressed manifolds, which are adaptively fused on the server using an attention-based Manifold Mutual Learning (MML) mechanism. This process enables domain-specific structures to learn from each other, creating a unified yet flexible global convergence target. Manifold-guided local training, enforced by a manifold approximation loss and a separation loss, further aligns local models with this global structure. Extensive experiments on the Digits and Office31 benchmarks demonstrate that FML substantially outperforms state-of-the-art methods, achieving accuracy improvements of up to 6.48%.

Deep Learning · Large Language Models

Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf

Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences. However, DAAs have been observed to over-optimize their implicit reward model and decrease the likelihood of preferred responses. This results in a decrease in the total likelihood assigned to responses seen in the preference dataset, potentially resulting in undesirable behavior. To counteract this undesired side-effect of DAAs, we examine the effect of using objectives that add a regularization term to maintain the total length-normalized probabilities of the chosen and rejected responses. To better understand over-optimization, we investigate how response likelihood changes are distributed over the tokens with and without regularization. We find that a significant portion of the likelihood changes are due to a small set of outlier tokens, which explains how DAAs improve generation quality despite decreasing the likelihoods of chosen responses. We apply the proposed regularization to reference-based (DPO) and reference-free (SimPO) methods and find (1) improved trade-offs between generation quality and general benchmark capability and (2) improvements in reward modeling across datasets. For example, on Llama-3.1-8B-Instruct, we see both a >20\% relative increase in AlpacaEval2 scores and >9\% relative performance gains on general benchmarks. Additionally, we find that the added regularization term effectively mitigates the amount of displacement within preferred responses overall, and for the outlier tokens specifically, by utilizing low-likelihood tokens.

Deep Learning · Robustness

Xin Wei, Qin Yang, Hongji Zhao, Fei Gao, Mingrui Zhu, Nannan Wang, Xinbo Gao

While data augmentation is essential for robust point cloud recognition, conventional spatial mixup strategies often compromise geometric integrity by generating physically unrealistic samples. To overcome this limitation, we propose PSMix, which shifts the mixing paradigm to the spectral domain via the Spherical Harmonic Transform. Instead of simple coordinate interpolation, PSMix performs a rotation-aware hierarchical mixing on spectral coefficients. This approach explicitly preserves global structural properties while diversifying local details, achieving a balance that spatial methods struggle to maintain. Complementing this, we introduce an adversarial rotation optimization strategy to enforce invariance against challenging orientations. Extensive experiments on ModelNet-C and ScanObjectNN-C demonstrate that PSMix achieves state-of-the-art robustness, while also serving as an orthogonal plug-in that further boosts the performance of existing spatial strategies.

Deep Learning · Large Language Models

Hyungjoo Chae, Jungsoo Park, Alan Ritter

Training autonomous web agents is fundamentally limited by the environments they learn from: real-world websites are unsafe to explore, hard to reset, and rarely provide verifiable feedback. We propose VeriEnv, a framework that treats language models as environment creators, automatically cloning real-world websites into fully executable, verifiable synthetic environments. By exposing controlled internal access via a Python SDK, VeriEnv enables agents to self-generate tasks with deterministic, programmatically verifiable rewards, eliminating reliance on heuristic or LLM-based judges. This design decouples agent learning from unsafe real-world interaction while enabling scalable self-evolution through environment expansion. Through experiments on web agent benchmarks, we show that agents trained with VeriEnv generalize to unseen websites, achieve site-specific mastery through self-evolving training, and benefit from scaling the number of training environments.