NeurIPS 2025 论文列表

In this paper, we present two effective policy learning algorithms for multi-agent online coordination(MA-OC) problem. The first one, **MA-SPL**, not only can achieve the optimal $(1-\frac{c}{e})$-approximation guarantee for the MA-OC problem with submodular objectives but also can handle the unexplored $\alpha$-weakly DR-submodular and $(\gamma,\beta)$-weakly submodular scenarios, where $c$ is the curvature of the investigated submodular functions, $\alpha$ denotes the diminishing-return(DR) ratio and the tuple$(\gamma,\beta)$ represents the submodularity ratios. Subsequently, in order to reduce the reliance on the unknown parameters $\alpha,\gamma,\beta$ inherent in the **MA-SPL** algorithm, we then introduce the second online algorithm named **MA-MPL**. This **MA-MPL** algorithm is entirely *parameter-free* and simultaneously can maintain the same approximation ratio as the first **MA-SPL** algorithm. The core of our **MA-SPL** and **MA-MPL** algorithms is a novel continuous-relaxation technique term as policy-based continuous extension. Compared with the well-established multi-linear extension, a notable advantage of this new policy-based continuous extension is its ability to provide a lossless rounding scheme for any set function, thereby enabling us to tackle the challenging weakly submodular objective functions. Finally, extensive simulations are conducted to demonstrate the effectiveness of our proposed algorithms.

Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While these agents have the potential to tackle complicated tasks, their problem-solving process—agents' interaction trajectory leading to task completion—remains underexploited. These trajectories contain rich feedback that can navigate agents toward the right directions for solving problems correctly. Although prevailing approaches, such as Monte Carlo Tree Search (MCTS), can effectively balance exploration and exploitation, they ignore the interdependence among various trajectories and lack the diversity of search spaces, which leads to redundant reasoning and suboptimal outcomes. To address these challenges, we propose SE-Agent, a Self-Evolution framework that enables Agents to optimize their reasoning processes iteratively. Our approach revisits and enhances former pilot trajectories through three key operations: revision, recombination, and refinement. This evolutionary mechanism enables two critical advantages: (1) it expands the search space beyond local optima by intelligently exploring diverse solution paths guided by previous trajectories, and (2) it leverages cross-trajectory inspiration to efficiently enhance performance while mitigating the impact of suboptimal reasoning paths. Through these mechanisms, SE-Agent achieves continuous self-evolution that incrementally improves reasoning quality. We evaluate SE-Agent on SWE-bench Verified to resolve real-world GitHub issues. Experimental results across five strong LLMs show that integrating SE-Agent delivers up to 55% relative improvement, achieving state-of-the-art performance among all open-source agents on SWE-bench Verified.

Conventional video outpainting methods primarily focus on maintaining coherent textures and visual consistency across frames. However, they often fail at handling dynamic scenes due to the complex motion of objects or camera movement, leading to temporal incoherence and visible flickering artifacts across frames. This is primarily because they lack instance-aware modeling to accurately separate and track individual object motions throughout the video. In this paper, we propose a novel video outpainting framework that explicitly takes shadow-object pairs into consideration to enhance the temporal and spatial consistency of instances, even when they are temporarily invisible. Specifically, we first track the shadow-object pairs across frames and predict the instances in the scene to unveil the spatial regions of invisible instances. Then, these prediction results are fed to guide the instance-aware optical flow completion to unveil the temporal motion of invisible instances. Next, these spatiotemporal guidances of instances are used to guide the video outpainting process. Finally, a video-aware discriminator is implemented to enhance alignment among dynamic shadows and the extended semantics in the scene. Comprehensive experiments underscore the superiority of our approach, outperforming existing state-of-the-art methods in widely recognized benchmarks.

We study the problem of aligning a generative model's response with a user's preferences. Recent works have proposed several different formulations for personalized alignment; however, they either require a large amount of user preference queries or require that the preference be explicitly specified as a text input. In this paper, we propose a novel inference-time personalized alignment method, UserAlign, that elicits the user's preferences with a few queries as pairwise response comparisons. In particular, UserAlign builds on the theoretical framework of best-arm identification in logistic bandits and selects a personalized response from a fixed pool of the model's generated responses. The key idea is to consider the user's feedback consistent and noise-free, and incorporate it into the theoretical framework to identify the best response quickly. Experimental results across several tasks, involving personalized text and image generation, showcase the effectiveness of UserAlign in achieving personalized alignment.

We introduce UniGen, a unified multimodal large language model (MLLM) capable of image understanding and generation. We study the full training pipeline of UniGen from a data-centric perspective, including multi-stage pre-training, supervised fine-tuning, and direct preference optimization. More importantly, we propose a new Chain-of-Thought Verification (CoT-V) strategy for test-time scaling, which significantly boosts UniGen’s image generation quality using a simple Best-of-N test-time strategy. Specifically, CoT-V enables UniGen to act as both image generator and verifier at test time, assessing the semantic alignment between a text prompt and its generated image in a step-by-step CoT manner. Trained entirely on open-source datasets across all stages, UniGen achieves state-of-the-art performance on a range of image understanding and generation benchmarks, with a final score of 0.78 on GenEval and 85.19 on DPG-Bench. Through extensive ablation studies, our work provides actionable insights and addresses key challenges in the full life cycle of building unified MLLMs, contributing meaningful directions to future research.

Test-time adaptation (TTA) for Vision-Language Models (VLMs) aims to enhance performance on unseen test data. However, existing methods struggle to achieve robust and continuous knowledge accumulation during test time. To address this, we propose Statistics Caching test-time Adaptation (SCA), a novel cache-based approach. Unlike traditional feature-caching methods prone to forgetting, SCA continuously accumulates task-specific knowledge from all encountered test samples. By formulating the reuse of past features as a least squares problem, SCA avoids storing raw features and instead maintains compact, incrementally updated feature statistics. This design enables efficient online adaptation without the limitations of fixed-size caches, ensuring that the accumulated knowledge grows persistently over time. Furthermore, we introduce adaptive strategies that leverage the VLM's prediction uncertainty to reduce the impact of noisy pseudo-labels and dynamically balance multiple prediction sources, leading to more robust and reliable performance. Extensive experiments demonstrate that SCA achieves compelling performance while maintaining competitive computational efficiency.

Model-free optimization methods typically rely on cost samples gathered by perturbing the current solution estimate along a finite and fixed set of directions. However, at each iteration, only the current cost samples are used, while potentially informative, previously collected samples are discarded. In this work, we challenge this conventional approach by introducing a simple yet effective memory mechanism that maintains an auxiliary vector of iteratively updated cost samples. By leveraging this stored information, our method estimates descent directions through an averaging of all perturbing directions weighted by the auxiliary vector components. This results in a faster convergence without increasing the number of function queries. By interpreting the resulting algorithm as a time-varying dynamical system, we are able to establish its convergence properties in the strongly convex case. In particular, by using tools from system theory based on timescale separation, we are able to guarantee a linear convergence rate toward an arbitrarily small neighborhood of the optimal solution. Numerical simulations on regression problems demonstrate that the proposed approach significantly outperforms existing model-free optimization methods.

Adversarial optimization algorithms that explicitly search for flaws in agents' policies have been successfully applied to finding robust and diverse policies in the context of multi-agent learning. However, the success of adversarial optimization has been largely limited to zero-sum settings because its naive application in cooperative settings leads to a critical failure mode: agents are irrationally incentivized to *self-sabotage*, blocking the completion of tasks and halting further learning. To address this, we introduce *Rationality-preserving Policy Optimization (RPO)*, a formalism for adversarial optimization that avoids self-sabotage by ensuring agents remain *rational*—that is, their policies are optimal with respect to some possible partner policy. To solve RPO, we develop *Rational Policy Gradient (RPG)*, which trains agents to maximize their own reward in a modified version of the original game in which we use *opponent shaping* techniques to optimize the adversarial objective. RPG enables us to extend a variety of existing adversarial optimization algorithms that, no longer subject to the limitations of self-sabotage, can find adversarial examples, improve robustness and adaptability, and learn diverse policies. We empirically validate that our approach achieves strong performance in several popular cooperative and general-sum environments. Our project page can be found at https://rational-policy-gradient.github.io.

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational costs, heavy hyperparameter tuning process, and coarse-grained optimization. To address these challenges, we propose a novel two-stage noisy learning framework that enables instance-level optimization through a dynamically weighted loss function, avoiding hyperparameter tuning. To obtain stable and accurate information about noise modeling, we introduce a simple yet effective metric, termed $\textit{wrong event}$, which dynamically models the cleanliness and difficulty of individual samples while maintaining computational costs. Our framework first collects $\textit{wrong event}$ information and builds a strong base model. Then we perform noise-robust training on the base model, using a probabilistic model to handle the $\textit{wrong event}$ information of samples. Experiments on six synthetic and real-world LNL benchmarks demonstrate our method surpasses state-of-the-art methods in performance, achieves a nearly 75\% reduction in storage and computational time, strongly improving model scalability. Our code is available at https://github.com/iTheresaApocalypse/IDO.

We study strategic classification in binary decision-making settings where agents can modify their features in order to improve their classification outcomes. Importantly, our work considers the causal structure across different features, acknowledging that effort in one feature may affect other features. The main goal of our work is to understand when and how much agent effort is invested towards desirable features, and how this is influenced by the deployed classifier, the causal structure of the agent's features, their ability to modify them, and the information available to the agent about the classifier and the feature causal graph. We characterize conditions under which agents with full information about the causal structure and the principal's classifier align with the principal's goals of incentivizing effort mostly in ``desirable'' features, and identify cases where designing such classifiers (from the principal's side) is still tractable despite general non-convexity. Under incomplete information, we show that uncertainty leads agents to prioritize features with high expected impact and low variance, which may often be misaligned with the principal's goals. Finally, using numerical experiments based on a cardiovascular disease risk study, we illustrate how to incentivize desirable modifications even under uncertainty.

In this paper, we pioneer the idea of implicit decomposition. And based on this idea, we propose a powerful decomposition-based enhancement framework, namely DecompNet. Our method converts the time series decomposition into an implicit process, where it can give a time series model the decomposition-related knowledge during inference, even though this model does not actually decompose the input time series. Thus, our DecompNet can enable a model to inherit the performance promotion brought by time series decomposition but will not introduce any additional inference costs, successfully enhancing the model performance while enjoying better efficiency. Experimentally, our DecompNet exhibits promising enhancement capability and compelling framework generality. Especially, it can also enhance the performance of the latest and state-of-the-art models, greatly pushing the performance limit of time series forecasting. Through comprehensive comparisons, DecompNet also shows excellent performance and efficiency superiority, making the decomposition-based enhancement framework surpass the well-recognized normalization-based frameworks for the first time. Code is available at this repository: https://github.com/luodhhh/DecompNet.

We study a fundamental question of domain generalization: given a family of domains (i.e., data distributions), how many randomly sampled domains do we need to collect data from in order to learn a model that performs reasonably well on every seen and unseen domain in the family? We model this problem in the PAC framework and introduce a new combinatorial measure, which we call the domain shattering dimension. We show that this dimension characterizes the domain sample complexity. Furthermore, we establish a tight quantitative relationship between the domain shattering dimension and the classic VC dimension, demonstrating that every hypothesis class that is learnable in the standard PAC setting is also learnable in our setting.

We propose a new approach to vision-based dexterous grasp translation, which aims to transfer grasp intent across robotic hands with differing morphologies. Given a visual observation of a source hand grasping an object, our goal is to synthesize a functionally equivalent grasp for a target hand without requiring paired demonstrations or hand-specific simulations. We frame this problem as a stochastic transport between grasp distributions using the Schrödinger Bridge formalism. Our method learns to map between source and target latent grasp spaces via score and flow matching, conditioned on visual observations. To guide this translation, we introduce physics-informed cost functions that encode alignment in base pose, contact maps, wrench space, and manipulability. Experiments across diverse hand-object pairs demonstrate that our approach generates stable, physically grounded grasps with strong generalization. This work enables semantic grasp transfer for heterogeneous manipulators and bridges vision-based grasping with probabilistic generative modeling. Additional details at https://grasp2grasp.github.io/.

Representation Alignment (REPA) that aligns Diffusion Transformer (DiT) hidden-states with ViT visual encoders has proven highly effective in DiT training, demonstrating superior convergence properties, but it has not been validated on the canonical diffusion U-Net architecture that shows faster convergence compared to DiTs. However, adapting REPA to U-Net architectures presents unique challenges: (1) different block functionalities necessitate revised alignment strategies; (2) spatial-dimension inconsistencies emerge from U-Net's spatial downsampling operations; (3) space gaps between U-Net and ViT hinder the effectiveness of tokenwise alignment. To encounter these challenges, we propose U-REPA, a representation alignment paradigm that bridges U-Net hidden states and ViT features as follows: Firstly, we propose via observation that due to skip connection, the middle stage of U-Net is the best alignment option. Secondly, we propose upsampling of U-Net features after passing them through MLPs. Thirdly, we observe difficulty when performing tokenwise similarity alignment, and further introduces a manifold loss that regularizes the relative similarity between samples. Experiments indicate that the resulting U-REPA could achieve excellent generation quality and greatly accelerates the convergence speed. With CFG guidance interval, U-REPA could reach FID<1.5 in 200 epochs or 1M iterations on ImageNet 256 $\times$ 256, and needs only half the total epochs to perform better than REPA under \textit{sd-vae-ft-ema}.

We introduce EnerVerse, a generative robotics foundation model that constructs and interprets embodied spaces. EnerVerse employs a chunk-wise autoregressive video diffusion framework to predict future embodied spaces from instructions, enhanced by a sparse context memory for long-term reasoning. To model the 3D robotics world, we adopt a multi-view video representation, providing rich perspectives to address challenges like motion ambiguity and 3D grounding. Additionally, EnerVerse-D, a data engine pipeline combining generative modeling with 4D Gaussian Splatting, forms a self-reinforcing data loop to reduce the sim-to-real gap. Leveraging these innovations, EnerVerse translates 4D world representations into physical actions via a policy head (EnerVerse-A), achieving state-of-the-art performance in both simulation and real-world tasks. For efficiency, EnerVerse-A reuses features from the first denoising step and predicts action chunks, achieving about 280 ms per 8-step action chunk on a single RTX 4090. Further video demos, dataset samples could be found in our project page.

Generative models for materials, especially inorganic crystals, hold potential to transform the theoretical prediction of novel compounds and structures. Advancement in this field depends critically on robust benchmarks and minimal, information-rich datasets that enable meaningful model evaluation. This paper critically examines common datasets and reported metrics for a crystal structure prediction task—generating the most likely structures given the chemical composition of a material. We focus on three key issues: First, materials datasets should contain unique crystal structures; for example, we show that the widely-utilized carbon-24 dataset only contains $\approx 40$% unique structures. Second, materials datasets should not be split randomly if polymorphs of many different compositions are numerous—which we find to be the case for the perov-5 and MP-20 datasets. Third, benchmarks can mislead if used uncritically, e.g., reporting a match rate metric without considering the structural variety exhibited by identical building blocks. To address these oft-overlooked issues, we introduce several fixes. We provide revised versions of the carbon-24 dataset: one with duplicates removed, one deduplicated and split by number of atoms $N$, one with enantiomorphs, and two containing only identical structures but with different unit cells. We also propose new splits for datasets with polymorphs, ensuring that polymorphs are grouped within each split subset, setting a more sensible standard for benchmarking model performance. Finally, we present METRe and cRMSE, new model evaluation metrics that can correct existing issues with the match rate metric.

Transformers have achieved remarkable success across natural language processing (NLP) and computer vision (CV). However, deep transformer models often suffer from an over-smoothing issue, in which token representations converge to similar values as they pass through successive transformer blocks. In this paper, we establish an equivalence between the hidden-state dynamics induced by stacked attention layers and graph neural diffusion on a complete graph. From this perspective, over-smoothing can be interpreted as a consequence of the dissipative nature of the underlying diffusion dynamics. Motivated by this physical interpretation, we propose Wavy Transformer, which consists of a novel attention layer based on second-order wavy dynamics. We also introduce a feed-forward network and a normalization layer designed to preserve the physical state-velocity relationship under the chain rule, thereby extending the transformer architecture. We further validate our proposed techniques on various transformer models for NLP and CV tasks. The results consistently demonstrate that Wavy Transformer improves performance with minimal additional parameters and no extra hyperparameter tuning.

Process reward models (PRMs) offer fine-grained, step-level evaluations that facilitate deeper reasoning processes in large language models (LLMs), proving effective in complex tasks like mathematical reasoning. However, developing PRMs is challenging due to the high cost and limited scalability of human-annotated data. Synthetic data from Monte Carlo (MC) estimation is a promising alternative but suffers from a high noise ratio, which can cause overfitting and hinder large-scale training. In this work, we conduct a preliminary study on the noise distribution in synthetic data from MC estimation, identifying that annotation models tend to both underestimate and overestimate step correctness due to limitations in their annotation capabilities. Building on these insights, we propose {\bf S}elf-Denoising Monte {\bf C}arlo {\bf An}notation (\textsc{Scan}), an efficient data synthesis and noise-tolerant learning framework. Our key findings indicate that: (1) Even lightweight models (e.g., 1.5B parameters) can produce high-quality annotations through self-denoising strategy, enabling PRMs to achieve superior performance with only 6\% the inference cost required by vanilla MC estimation. (2) With our robust learning strategy, PRMs can effectively learn from this weak supervision, achieving a 39.2 F1 score improvement (from 19.9 to 59.1) in ProcessBench. Despite using only a compact synthetic dataset, our models surpass strong baselines, including those trained on large-scale human-annotated datasets such as PRM800K. Furthermore, performance continues to improve as we scale up the synthetic data, highlighting the potential of \textsc{Scan} for scalable, cost-efficient, and robust PRM training.

Learning robust representations from unlabeled time series is crucial, and contrastive learning offers a promising avenue. However, existing contrastive learning approaches for time series often struggle with defining meaningful similarities, tending to overlook inherent physical correlations and diverse, sequence-varying non-stationarity. This limits their representational quality and real-world adaptability. To address these limitations, we introduce AdaTS, a novel adaptive soft contrastive learning strategy. AdaTS offers a compute-efficient solution centered on dynamic instance-wise and temporal assignments to enhance time series representations, specifically by: (i) leveraging Time-Frequency Coherence for robust physics-guided similarity measurement; (ii) preserving relative instance similarities through ordinal consistency learning; and (iii) dynamically adapting to sequence-specific non-stationarity with dynamic temporal assignments. AdaTS is designed as a pluggable module to standard contrastive frameworks, achieving up to 13.7% accuracy improvements across diverse time series datasets and three state-of-the-art contrastive frameworks while enhancing robustness against label scarcity. The code will be publicly available upon acceptance.