NeurIPS 2025 论文列表

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs) to unlock advanced visual reasoning. We introduce a two-stage paradigm built on Qwen2.5-VL-7B: a massive linguistic cold-start fine-tuning, followed by multimodal reinforcement learning (RL) spanning nearly 1,000 steps—surpassing all previous open-source efforts in scale. This pioneering work reveals three fundamental insights: 1) Behavior transfer emerges surprisingly early in cold start due to linguistic mental imagery. 2) Cold start broadly memorizes visual behaviors, while RL critically discerns and scales up effective patterns. 3) Transfer strategically favors high-utility behaviors such as visual reflection. Our resulting model, Open-Vision-Reasoner (OVR), achieves state-of-the-art performance on a suite of reasoning benchmarks, including 95.3% on MATH500, 51.8% on MathVision and 54.6% on MathVerse. We release our model, data, and training dynamics to catalyze the development of more capable, behavior-aligned multimodal reasoners.

Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation-learning tasks. However, these controllers employ a fixed inference budget at every control step, regardless of task complexity, leading to computational inefficiency for simple subtasks while potentially underperforming on challenging ones. To address these issues, we introduce Difficulty-Aware Stochastic Interpolant Policy (DA-SIP), a framework that enables robotic controllers to adaptively adjust their integration horizon in real-time based on task difficulty. Our approach employs a difficulty classifier that analyzes RGB-D observations to dynamically select the step budget, the optimal solver variant, and ODE/SDE integration at each control cycle. DA-SIP builds upon the stochastic interpolant formulation to provide a unified framework that unlocks diverse training and inference configurations for diffusion- and flow-based policies. Through comprehensive benchmarks across diverse manipulation tasks, DA-SIP achieves 2.6-4.4× reduction in total computation time while maintaining task-success rates comparable to fixed maximum-computation baselines. By implementing adaptive computation within this framework, DA-SIP transforms generative robot controllers into efficient, task-aware systems that intelligently allocate inference resources where they provide the greatest benefit.

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple queries. However, the LLMs still need to encode the entire context for each query, leading to redundant computation. In this paper, we investigate a new strategy to eliminate such inefficiency, where the KV cache of each document is precomputed independently. During inference, the KV caches of retrieved documents are concatenated, allowing the model to reuse cached representations instead of recomputing them. To mitigate the performance degradation when using KV caches computed independently for each document, KVLink introduces two key techniques: adjusting positional embeddings of the KV cache at inference to match the global position after concatenation, and using trainable special tokens to restore self-attention across independently encoded documents. Experiments across 7 datasets demonstrate that KVLink improves question answering accuracy by an average of 4% over state-of-the-art methods. Furthermore, by leveraging precomputed KV caches, our approach reduces time-to-first-token by up to 96% compared to standard LLM inference, making it a scalable and efficient solution for context reuse. Additionally, KVLink can be combined with KV cache compression to further save cache loading and storage overhead while outperforming the baselines.

As machine learning applications grow increasingly ubiquitous and complex, they face an increasing set of requirements beyond accuracy. The prevalent approach to handle this challenge is to aggregate a weighted combination of requirement violation penalties into the training objective. To be effective, this approach requires careful tuning of these hyperparameters (weights), involving trial-and-error and cross-validation, which becomes ineffective even for a moderate number of requirements. These issues are exacerbated when the requirements involve parities or equalities, as is the case in fairness and boundary value problems. An alternative technique uses constrained optimization to formulate these learning problems. Yet, existing approximation and generalization guarantees do not apply to problems involving equality constraints. In this work, we derive a generalization theory for equality-constrained statistical learning problems, showing that their solutions can be approximated using samples and rich parametrizations. Using these results, we propose a practical algorithm based on solving a sequence of *unconstrained*, *empirical* learning problems. We showcase its effectiveness and the new formulations enabled by equality constraints in fair learning, interpolating classifiers, and boundary value problems.

Pre-trained Large language models (LLMs) have shown impressive advancements in functional magnetic resonance imaging (fMRI) analysis and causal discovery. Considering the unique nature of the causal discovery field, which focuses on extracting causal graphs from observed data, research on LLMs in this field is still at an early exploratory stage. As a subfield of causal discovery, effective connectivity (EC) has received even less attention, and LLM-based approaches in EC remain unexplored. Existing LLM-based approaches for causal discovery typically rely on iterative querying to assess the causal influence between variable pairs, without any model adaptation or fine-tuning, making them ill-suited for handling the cross-modal gap and complex causal structures. To this end, we propose BrainEC-LLM, the first method to fine-tune LLMs for estimating brain EC from fMRI data. Specifically, multiscale decomposition mixing module decomposes fMRI time series data into short-term and long-term multiscale trends, then mixing them in bottom-up (fine to coarse) and top-down (coarse to fine) manner to extract multiscale temporal variations. And cross attention is applied with pre-trained word embeddings to ensure consistency between the fMRI input and pre-trained natural language. The experimental results on simulated and real resting-state fMRI datasets demonstrate that BrainEC-LLM can achieve superior performance when compared to state-of-the-art baselines.

Out-of-distribution (OOD) fine-tuning has emerged as a promising approach for anomaly segmentation. Current OOD fine-tuning strategies typically employ global-level objectives, aiming to guide segmentation models to accurately predict a large number of anomaly pixels. However, these strategies often perform poorly on small anomalies. To address this issue, we propose an instance-level OOD fine-tuning framework, dubbed LNOIB (Leaving No OOD Instance Behind). We start by theoretically analyzing why global-level objectives fail to segment small anomalies. Building on this analysis, we introduce a simple yet effective instance-level objective. Moreover, we propose a feature separation objective to explicitly constrain the representations of anomalies, which are prone to be smoothed by their in-distribution (ID) surroundings. LNOIB integrates these objectives to enhance the segmentation of small anomalies and serves as a paradigm adaptable to existing OOD fine-tuning strategies, without introducing additional inference cost. Experimental results show that integrating LNOIB into various OOD fine-tuning strategies yields significant improvements, particularly in component-level results, highlighting its strength in comprehensive anomaly segmentation.

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation (ODE) into an equivalent Stochastic Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps, enabling statistical sampling for RL exploration; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original number of inference steps, significantly improving sampling efficiency without sacrificing performance. Empirically, Flow-GRPO is effective across multiple text-to-image tasks. For compositional generation, RL-tuned SD3.5-M generates nearly perfect object counts, spatial relations, and fine-grained attributes, increasing GenEval accuracy from $63\%$ to $95\%$. In visual text rendering, accuracy improves from $59\%$ to $92\%$, greatly enhancing text generation. Flow-GRPO also achieves substantial gains in human preference alignment. Notably, very little reward hacking occurred, meaning rewards did not increase at the cost of appreciable image quality or diversity degradation.

Interpretable machine learning is essential in high-stakes domains like healthcare. Rule lists are a popular choice due to their transparency and accuracy, but learning them effectively remains a challenge. Existing methods require feature pre-discretization, constrain rule complexity or ordering, or struggle to scale. We present NeuRules, a novel end-to-end framework that overcomes these limitations. At its core, NeuRules transforms the inherently combinatorial task of rule list learning into a differentiable optimization problem, enabling gradient-based learning. It simultaneously discovers feature conditions, assembles them into conjunctive rules, and determines their order—without pre-processing or manual constraints. A key contribution here is a gradient shaping technique that steers learning toward sparse rules with strong predictive performance. To produce ordered lists, we introduce a differentiable relaxation that, through simulated annealing, converges to a strict rule list. Extensive experiments show that NeuRules consistently outperforms combinatorial and neural baselines on binary as well as multi-class classification tasks across a wide range of datasets.

In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DUSt3R, that are originally designed for static 3D scene reconstruction. Although these methods provide an elegant and powerful solution in static settings, they struggle in the presence of dynamic motions that disrupt alignment based solely on camera poses. To overcome this, we propose D$^2$USt3R that directly regresses Static-Dynamic Aligned Pointmaps (SDAP) that simultaneiously capture both static and dynamic 3D scene geometry. By explicitly incorporating both spatial and temporal aspects, our approach successfully encapsulates 3D dense correspondence to the proposed pointmaps, enhancing downstream tasks. Extensive experimental evaluations demonstrate that our proposed approach consistently achieves superior 3D reconstruction performance across various datasets featuring complex motions.

We introduce MusclePose as an end-to-end learnable physics-infused 3D human pose estimator that incorporates muscle-dynamics modeling to infer human dynamics from monocular video. Current physics pose estimators aim to predict physically plausible poses by enforcing the underlying dynamics equations that govern motion. Since this is an underconstrained problem without force-annotated data, methods often estimate kinetics with external physics optimizers that may not be compatible with existing learning frameworks, or are too slow for real-time inference. While more recent methods use a regression-based approach to overcome these issues, the estimated kinetics can be seen as auxiliary predictions, and may not be physically plausible. To this end, we build on existing regression-based approaches, and aim to improve the biofidelity of kinetic inference with a multihypothesis approach --- by inferring joint torques via Lagrange’s equations and via muscle dynamics modeling with muscle torque generators. Furthermore, MusclePose predicts detailed human anthropometrics based on values from biomechanics studies, in contrast to existing physics pose estimators that construct their human models with shape primitives. We show that MusclePose is competitive with existing 3D pose estimators in positional accuracy, while also able to infer plausible human kinetics and muscle signals consistent with values from biomechanics studies, without requiring an external physics engine.

We propose a general framework for conditional sampling in PDE-based inverse problems, targeting the recovery of whole solutions from extremely sparse or noisy measurements. This is accomplished by a function-space diffusion model and plug-and-play guidance for conditioning. Our method first trains an unconditional discretization-agnostic denoising model using neural operator architectures. At inference, we refine the samples to satisfy sparse observation data via a gradient-based guidance mechanism. Through rigorous mathematical analysis, we extend Tweedie's formula to infinite-dimensional Hilbert spaces, providing the theoretical foundation for our posterior sampling approach. Our method (FunDPS) accurately captures posterior distribution in function spaces under minimal supervision and severe data scarcity. Across five PDE tasks with only 3\% observation, our method achieves an average 32\% accuracy improvement over state-of-the-art fixed-resolution diffusion baselines while reducing sampling steps by 4x. Furthermore, multi-resolution fine-tuning ensures strong cross-resolution generalizability and speedup. To the best of our knowledge, this is the first diffusion-based framework to operate independently of discretization, offering a practical and flexible solution for forward and inverse problems in the context of PDEs. Code is available at https://github.com/neuraloperator/FunDPS.

Brain-computer interfaces (BCIs) promise to enable vital functions, such as speech and prosthetic control, for individuals with neuromotor impairments. Central to their success are neural decoders, models that map neural activity to intended behavior. Current learning-based decoding approaches fall into two classes: simple, causal models that lack generalization, or complex, non-causal models that generalize and scale offline but struggle in real-time settings. Both face a common challenge, their reliance on power-hungry artificial neural network backbones, which makes integration into real-world, resource-limited systems difficult. Spiking neural networks (SNNs) offer a promising alternative. Because they operate causally (i.e. only on present and past inputs) these models are suitable for real-time use, and their low energy demands make them ideal for battery-constrained environments. To this end, we introduce **Spikachu: a scalable, causal, and energy-efficient neural decoding framework based on SNNs**. Our approach processes binned spikes directly by projecting them into a shared latent space, where spiking modules, adapted to the timing of the input, extract relevant features; these latent representations are then integrated and decoded to generate behavioral predictions. We evaluate our approach on 113 recording sessions from 6 non-human primates, totaling 43 hours of recordings. Our method outperforms causal baselines when trained on single sessions using between 2.26× and 418.81× less energy. Furthermore, we demonstrate that scaling up training to multiple sessions and subjects improves performance and enables few-shot transfer to unseen sessions, subjects, and tasks. Overall, Spikachu introduces a scalable, online-compatible neural decoding framework based on SNNs, whose performance is competitive relative to state-of-the-art models while consuming orders of magnitude less energy.

Latent Diffusion-based Text-to-Image (T2I) is a free image editing tool that typically reverses an image into noise, reconstructs it using its original text prompt, and then generates an edited version under a new target prompt. To preserve unaltered image content, features from the reconstruction are directly injected to replace selected features in the generation. However, this direct replacement often leads to feature incompatibility, compromising editing fidelity and limiting creative flexibility, particularly for non-rigid edits (\emph{e.g.}, structural or pose changes). In this paper, we aim to address these limitations by proposing \textbf{FSI-Edit}, a novel framework using frequency- and stochasticity-based feature injection for flexible image editing. First, FSI-Edit enhances feature consistency by injecting \emph{high-frequency} components of reconstruction features into generation features, mitigating incompatibility while preserving the editing ability for major structures encoded in low-frequency information. Second, it introduces controlled \emph{noise} into the replaced reconstruction features, expanding the generative space to enable diverse non-rigid edits beyond the original image’s constraints. Experiments on non-rigid edits, \emph{e.g.}, addition, deletion, and pose manipulation, demonstrate that FSI-Edit outperforms existing baselines in target alignment, semantic fidelity and visual quality. Our work highlights the critical roles of frequency-aware design and stochasticity in overcoming rigidity in diffusion-based editing.

Transformers have the representational capacity to simulate Massively Parallel Computation (MPC) algorithms, but they suffer from quadratic time complexity, which severely limits their scalability. We introduce an efficient attention mechanism called Approximate Nearest Neighbor Attention (ANNA) with sub-quadratic time complexity. We prove that ANNA-transformers (1) retain the expressive power previously established for standard attention in terms of matching the capabilities of MPC algorithms, and (2) can solve key reasoning tasks such as Match2 and $k$-hop with near-optimal depth. Using the MPC framework, we further prove that constant-depth ANNA-transformers can simulate constant-depth low-rank transformers, thereby providing a unified way to reason about a broad class of efficient attention approximations.

Mathematical modeling is a cornerstone of scientific discovery and engineering practice, enabling the translation of real-world problems into formal systems across domains such as physics, biology, and economics. Unlike mathematical reasoning, which assumes a predefined formulation, modeling requires open-ended problem analysis, abstraction, and principled formalization. While Large Language Models (LLMs) have shown strong reasoning capabilities, they fall short in rigorous model construction, limiting their utility in real-world problem-solving. To this end, we formalize the task of LLM-powered real-world mathematical modeling, where agents must analyze problems, construct domain-appropriate formulations, and generate complete end-to-end solutions.We introduce MM-Bench, a curated benchmark of 111 problems from the Mathematical Contest in Modeling (MCM/ICM), spanning the years 2000 to 2025 and across ten diverse domains such as physics, biology, and economics. To tackle this task, we propose MM-Agent, an expert-inspired framework that decomposes mathematical modeling into four stages: open-ended problem analysis, structured model formulation, computational problem solving, and report generation.Experiments on MM-Bench show that MM-Agent significantly outperforms baseline agents, achieving an 11.88\% improvement over human expert solutions while requiring only 15 minutes and \$0.88 per task using GPT-4o. Furthermore, under official MCM/ICM protocols, MM-Agent assisted two undergraduate teams in winning the Finalist Award (\textbf{top 2.0\% among 27,456 teams}) in MCM/ICM 2025, demonstrating its practical effectiveness as a modeling copilot.

Reinforcement learning (RL) has achieved significant success across a wide range of domains, however, most existing methods are formulated in discrete time. In this work, we introduce a novel RL method for continuous-time control, where stochastic differential equations govern state-action dynamics. Departing from traditional value function-based approaches, our key contribution is the characterization of continuous-time Q-functions via a martingale condition and the linking of diffusion policy scores to the action gradient of a learned continuous Q-function by the dynamic programming principle. This insight motivates Continuous Q-Score Matching (CQSM), a score-based policy improvement algorithm. Notably, our method addresses a long-standing challenge in continuous-time RL: preserving the action-evaluation capability of Q-functions without relying on time discretization. We further provide theoretical closed-form solutions for linear-quadratic (LQ) control problems within our framework. Numerical results in simulated environments demonstrate the effectiveness of our proposed method and compare it to popular baselines.

Neural networks are often described as black boxes, reflecting the significant challenge of understanding their internal workings and interactions. We propose a different perspective that challenges the prevailing view: rather than being inscrutable, neural networks exhibit patterns in their raw population activity that mirror regularities in the training data. We refer to this as the \textit{Reflection Hypothesis} and provide evidence for this phenomenon in both simple recurrent neural networks (RNNs) and complex large language models (LLMs). Building on this insight, we propose to leverage cognitively-inspired methods of \textit{chunking} to segment high-dimensional neural population dynamics into interpretable units that reflect underlying concepts. We propose three methods to extract these emerging entities, complementing each other based on label availability and neural data dimensionality. Discrete sequence chunking (DSC) creates a dictionary of entities in a lower-dimensional neural space; population averaging (PA) extracts recurring entities that correspond to known labels; and unsupervised chunk discovery (UCD) can be used when labels are absent. We demonstrate the effectiveness of these methods in extracting entities across varying model sizes, ranging from inducing compositionality in RNNs to uncovering recurring neural population states in large language models with diverse architectures, and illustrate their advantage to other interpretability methods. Throughout, we observe a robust correspondence between the extracted entities and concrete or abstract concepts in the sequence. Artificially inducing the extracted entities in neural populations effectively alters the network's generation of associated concepts. Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data to reveal the hidden computations of complex learning systems, gradually transforming them from black boxes into systems we can begin to understand. Implementation and code are publicly available at _https://github.com/swu32/Chunk-Interpretability_

Frontier vision-language models (VLMs) have made remarkable improvements in video understanding tasks. However, real-world videos typically exist as continuously evolving data streams (e.g., dynamic scenes captured by wearable glasses), necessitating models to continually adapt to shifting data distributions and novel scenarios. Considering the prohibitive computational costs of fine-tuning models on new tasks, usually, a small subset of parameters is updated while the bulk of the model remains frozen. This poses new challenges to existing continual learning frameworks in the context of large multimodal foundation models, i.e., catastrophic forgetting and update conflict. While the foundation models struggle with parameter-efficient continual learning, the hippocampus in the human brain has evolved highly efficient mechanisms for memory formation and consolidation. Inspired by the rapid **Bi**nding and pattern **se**paration mechanisms in the hippocampus, in this work, we propose **Bisecle** for video-language **c**ontinual **le**arning, where a multi-directional supervision module is used to capture more cross-modal relationships and a contrastive prompt learning scheme is designed to isolate task-specific knowledge to facilitate efficient memory storage. Binding and separation processes further strengthen the ability of VLMs to retain complex experiences, enabling robust and efficient continual learning in video understanding tasks. We perform a thorough evaluation of the proposed Bisecle, demonstrating its ability to mitigate forgetting and enhance cross-task generalization on several VideoQA benchmarks.

Properly evaluating the ability of Video-Language Models (VLMs) to understand long videos remains a challenge. We propose a long-context video understanding benchmark, Causal2Needles, that assesses two crucial abilities insufficiently addressed by existing benchmarks: (1) extracting information from two separate locations (two needles) in a long video and understanding them jointly, and (2) modeling the world in terms of cause and effect in human behaviors. Causal2Needles evaluates these abilities using noncausal one-needle, causal one-needle, and causal two-needle questions. The most complex question type, causal two-needle questions, require extracting information from both the cause and effect events from a long video and the associated narration text. To prevent textual bias, we introduce two complementary question formats: locating the video clip containing the answer, and verbal description of a visual detail from that video clip. Our experiments reveal that models excelling on existing benchmarks struggle with causal 2-needle questions, and the model performance is negatively correlated with the distance between the two needles. These findings highlight critical limitations in current VLMs.