NeurIPS 2025 论文列表

We study the problem of computing an optimal large language model (LLM) policy for the constrained alignment problem, where the goal is to maximize a primary reward objective while satisfying constraints on secondary utilities. Despite the popularity of Lagrangian-based LLM policy search in constrained alignment, iterative primal-dual methods often fail to converge, and non-iterative dual-based methods do not achieve optimality in the LLM parameter space. To address these challenges, we employ Lagrangian duality to develop an iterative dual-based alignment method that alternates between updating the LLM policy via Lagrangian maximization and updating the dual variable via dual descent. In theory, we characterize the primal-dual gap between the primal value in the distribution space and the dual value in the LLM parameter space. We further quantify the optimality gap of the learned LLM policies at near-optimal dual variables with respect to both the objective and the constraint functions. These results prove that dual-based alignment methods can find an optimal constrained LLM policy, up to an LLM parametrization gap. We demonstrate the effectiveness and merits of our approach through extensive experiments conducted on the PKU-SafeRLHF and Anthropic HH-RLHF datasets.

In real-world information-seeking scenarios, users have dynamic and diverse needs, requiring RAG systems to demonstrate adaptable resilience. To comprehensively evaluate the resilience of current RAG methods, we introduce HawkBench, a human-labeled, multi-domain benchmark designed to rigorously assess RAG performance across categorized task types. By stratifying tasks based on information-seeking behaviors, HawkBench provides a systematic evaluation of how well RAG systems adapt to diverse user needs. Unlike existing benchmarks, which focus primarily on specific task types (mostly factoid queries) and rely on varying knowledge bases, HawkBench offers: (1) systematic task stratification to cover a broad range of query types, including both factoid and rationale queries, (2) integration of multi-domain corpora across all task types to mitigate corpus bias, and (3) rigorous annotation for high-quality evaluation. HawkBench includes 1,600 high-quality test samples, evenly distributed across domains and task types. Using this benchmark, we evaluate representative RAG methods, analyzing their performance in terms of answer quality and response latency. Our findings highlight the need for dynamic task strategies that integrate decision-making, query interpretation, and global knowledge understanding to improve RAG generalizability. We believe HawkBench serves as a pivotal benchmark for advancing the resilience of RAG methods and their ability to achieve general-purpose information seeking.

Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest. Existing benchmarks have highlighted the impressive performance of LMMs in text recognition; however, their abilities in certain challenging tasks, such as text localization, handwritten content extraction, and logical reasoning, remain underexplored. To bridge this gap, we introduce OCRBench v2, a large-scale bilingual text-centric benchmark with currently the most comprehensive set of tasks ($4\times$ more tasks than the previous multi-scene benchmark OCRBench), the widest coverage of scenarios ($31$ diverse scenarios), and thorough evaluation metrics, with $10,000$ human-verified question-answering pairs and a high proportion of difficult samples. Moreover, we construct a private test set with $1,500$ manually annotated images. The consistent evaluation trends observed across both public and private test sets validate the OCRBench v2's reliability. After carefully benchmarking state-of-the-art LMMs, we find that most LMMs score below $50$ ($100$ in total) and suffer from five-type limitations, including less frequently encountered text recognition, fine-grained perception, layout perception, complex element parsing, and logical reasoning. The benchmark and evaluation scripts are available at https://github.com/Yuliang-Liu/MultimodalOCR.

High-dimensional data often exhibit hierarchical structures in both modes: samples and features. Yet, most existing approaches for hierarchical representation learning consider only one mode at a time. In this work, we propose an unsupervised method for jointly learning hierarchical representations of samples and features via Tree-Wasserstein Distance (TWD). Our method alternates between the two data modes. It first constructs a tree for one mode, then computes a TWD for the other mode based on that tree, and finally uses the resulting TWD to build the second mode’s tree. By repeatedly alternating through these steps, the method gradually refines both trees and the corresponding TWDs, capturing meaningful hierarchical representations of the data. We provide a theoretical analysis showing that our method converges. We show that our method can be integrated into hyperbolic graph convolutional networks as a pre-processing technique, improving performance in link prediction and node classification tasks. In addition, our method outperforms baselines in sparse approximation and unsupervised Wasserstein distance learning tasks on word-document and single-cell RNA-sequencing datasets.

Spiking neural networks (SNNs) are emerging as a promising alternative to traditional artificial neural networks (ANNs), offering biological plausibility and energy efficiency. Despite these merits, SNNs are frequently hampered by limited capacity and insufficient representation power, yet remain underexplored in remote sensing image (RSI) super-resolution (SR) tasks. In this paper, we first observe that spiking signals exhibit drastic intensity variations across diverse textures, highlighting an active learning state of the neurons. This observation motivates us to apply SNNs for efficient SR of RSIs. Inspired by the success of attention mechanisms in representing salient information, we devise the spiking attention block (SAB), a concise yet effective component that optimizes membrane potentials through inferred attention weights, which, in turn, regulates spiking activity for superior feature representation. Our key contributions include: 1) we bridge the independent modulation between temporal and channel dimensions, facilitating joint feature correlation learning, and 2) we access the global self-similar patterns in large-scale remote sensing imagery to infer spatial attention weights, incorporating effective priors for realistic and faithful reconstruction. Building upon SAB, we proposed SpikeSR, which achieves state-of-the-art performance across various remote sensing benchmarks such as AID, DOTA, and DIOR, while maintaining high computational efficiency. Code of SpikeSR will be available at https://github.com/XY-boy/SpikeSR.

Recent advances in large language models (LLMs) have enabled the automatic generation of executable code for task planning and control in embodied agents such as robots, demonstrating the potential of LLM-based embodied intelligence. However, these LLM-based code-as-policies approaches often suffer from limited environmental grounding, particularly in dynamic or partially observable settings, leading to suboptimal task success rates due to incorrect or incomplete code generation. In this work, we propose a neuro-symbolic embodied task planning framework that incorporates explicit symbolic verification and interactive validation processes during code generation. In the validation phase, the framework generates exploratory code that actively interacts with the environment to acquire missing observations while preserving task-relevant states. This integrated process enhances the grounding of generated code, resulting in improved task reliability and success rates in complex environments. We evaluate our framework on RLBench and in real-world settings across dynamic, partially observable scenarios. Experimental results demonstrate that our framework improves task success rates by 46.2\% over Code as Policies baselines and attains over 86.8\% executability of task-relevant actions, thereby enhancing the reliability of task planning in dynamic environments.

Neural Network (NN) verification methods provide local robustness guarantees for a NN in the dense perturbation space of an input. In this paper we introduce H$^2$V, a method for the validation of local robustness of NNs against geometric perturbations. H$^2$V uniquely employs a Hilbert space-filling construction to recast multi-dimensional problems into single-dimensional ones and Hölder optimisation, iteratively refining the estimation of the Hölder constant for constructing the lower bound. In common with methods, Hölder optimisation might theoretically converge to a local minimum, thereby resulting in a robustness result being incorrect. However, we here identify conditions for H$^2$V to be provably sound, and show experimentally that even outside the soundness conditions, the risk of incorrect results can be minimised by introducing appropriate heuristics in the global optimisation procedure. Indeed, we found no incorrect results validated by H$^2$V on a large set of benchmarks from SoundnessBench and VNN-COMP. To assess the scalability of the approach, we report the results obtained on large NNs ranging from Resnet34 to Resnet152 and vision transformers. These point to SoA scalability of the approach when validating the local robustness of large NNs against geometric perturbations on the ImageNet dataset. Beyond image tasks, we show that the method's scalability enables for the first time the robustness validation of large-scale 3D-NNs in video classification tasks against geometric perturbations for long-sequence input frames on Kinetics/UCF101 datasets.

Brain-Computer Interfaces (BCIs) offer a direct communication pathway between the human brain and external devices, holding significant promise for individuals with severe neurological impairments. However, their widespread adoption is hindered by critical limitations, such as low information transfer rates and extensive user-specific calibration. To overcome these challenges, recent research has explored the integration of Large Language Models (LLMs), extending the focus from simple command decoding to understanding complex cognitive states. Despite these advancements, deploying agentic AI faces technical hurdles and ethical concerns. Due to the lack of comprehensive discussion on this emerging direction, this position paper argues that the field is poised for a paradigm extension from BCI to Brain-Agent Collaboration (BAC). We emphasize reframing agents as active and collaborative partners for intelligent assistance rather than passive brain signal data processors, demanding a focus on ethical data handling, model reliability, and a robust human-agent collaboration framework to ensure these systems are safe, trustworthy, and effective.

Endowing robots with tool design abilities is critical for enabling them to solve complex manipulation tasks that would otherwise be intractable. While recent generative frameworks can automatically synthesize task settings—such as 3D scenes and reward functions—they have not yet addressed the challenge of tool-use scenarios. Simply retrieving human-designed tools might not be ideal since many tools (e.g., a rolling pin) are difficult for robotic manipulators to handle. Furthermore, existing tool design approaches either rely on predefined templates with limited parameter tuning or apply generic 3D generation methods that are not optimized for tool creation. To address these limitations, we propose **RobotSmith**, an automated pipeline that leverages the implicit physical knowledge embedded in vision-language models (VLMs) alongside the more accurate physics provided by physics simulations to design and use tools for robotic manipulation. Our system (1) iteratively proposes tool designs using collaborative VLM agents, (2) generates low-level robot trajectories for tool use, and (3) jointly optimizes tool geometry and usage for task performance. We evaluate our approach across a wide range of manipulation tasks involving rigid, deformable, and fluid objects. Experiments show that our method consistently outperforms strong baselines in both task success rate and overall performance. Notably, our approach achieves a 50.0\% average success rate, significantly surpassing other baselines such as 3D generation (21.4\%) and tool retrieval (11.1\%). Finally, we deploy our system in real-world settings, demonstrating that the generated tools and their usage plans transfer effectively to physical execution, validating the practicality and generalization capabilities of our approach.

Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare, where accurate expressions of uncertainty are essential for reliability and trust. However, current LLMs are often observed to generate incorrect answers with high confidence—a phenomenon known as "overconfidence". Recent efforts have focused on calibrating LLMs' verbalized confidence: i.e., their expressions of confidence in text form, such as "I am 80% confident that...". Existing approaches either rely on prompt engineering or fine-tuning with heuristically generated uncertainty estimates, both of which have limited effectiveness and generalizability. Motivated by the notion of proper scoring rules for calibration in classical machine learning models, we introduce ConfTuner, a simple and efficient fine-tuning method that introduces minimal overhead and does not require ground-truth confidence scores or proxy confidence estimates. ConfTuner relies on a new loss function, tokenized Brier score, which we theoretically prove to be a proper scoring rule, intuitively meaning that it "correctly incentivizes the model to report its true probability of being correct". ConfTuner improves calibration across diverse reasoning tasks and generalizes to black-box models such as GPT-4o. Our results further show that better-calibrated confidence enables downstream gains in self-correction and model cascade, advancing the development of trustworthy LLM systems. The code is available at https://github.com/liushiliushi/ConfTuner.

Large recommender models have extended LLMs as powerful recommenders via encoding or item generation, and recent breakthroughs in LLM reasoning synchronously motivate the exploration of reasoning in recommendation. In this work, we propose R$^2$ec, a unified large recommender model with intrinsic reasoning capability. R$^2$ec introduces a dual-head architecture that supports both reasoning chain generation and efficient item prediction in a single model, significantly reducing inference latency. To overcome the lack of annotated reasoning data, we design RecPO, a reinforcement learning framework that optimizes reasoning and recommendation jointly with a novel fused reward mechanism. Extensive experiments on three datasets demonstrate that R$^2$ec outperforms traditional, LLM-based, and reasoning-augmented recommender baselines, while further analyses validate its competitive efficiency among conventional LLM-based recommender baselines and strong adaptability to diverse recommendation scenarios. Code and checkpoints available at https://github.com/YRYangang/RRec.

Multi-agent reinforcement learning (MARL) has long been seen as inseparable from Markov games (Littman 1994). Yet, the most remarkable achievements of practical MARL have arguably been in extensive-form games (EFGs)---spanning games like Poker, Stratego, and Hanabi. At the same time, little is known about provable equilibrium convergence for MARL algorithms applied to EFGs as they stumble upon the inherent nonconvexity of the optimization landscape and the failure of the value-iteration subroutine in EFGs. To this goal, we utilize contemporary advances in nonconvex optimization theory to prove that regularized alternating policy gradient with (i) *direct policy parametrization*, (ii) *softmax policy parametrization*, and (iii) *softmax policy parametrization with natural policy gradient* updates converge to an approximate Nash equilibrium (NE) in the *last-iterate* in imperfect-information perfect-recall zero-sum EFGs. Namely, we observe that since the individual utilities are concave with respect to the sequence-form strategy, they satisfy gradient dominance w.r.t. the behavioral strategy---or, \textit{policy}, in reinforcement learning terms. We exploit this structure to further prove that the regularized utility satisfies the much stronger proximal Polyak- Łojasiewicz condition. In turn, we show that the different flavors of alternating policy gradient methods converge to an $\epsilon$-approximate NE with a number of iterations and trajectory samples that are polynomial in $1/\epsilon$ and the natural parameters of the game. Our work is a preliminary---yet principled---attempt in bridging the conceptual gap between the theory of Markov and imperfect-information EFGs while it aspires to stimulate a deeper dialogue between them.

In this paper, we leverage stochastic projection and lossy compression to establish new conditional mutual information (CMI) bounds on the generalization error of statistical learning algorithms. It is shown that these bounds are generally tighter than the existing ones. In particular, we prove that for certain problem instances for which existing MI and CMI bounds were recently shown in Attias et al. [2024] and Livni [2023] to become vacuous or fail to describe the right generalization behavior, our bounds yield suitable generalization guarantees of the order of $\mathcal{O}(1/\sqrt{n})$, where $n$ is the size of the training dataset. Furthermore, we use our bounds to investigate the problem of data "memorization" raised in those works, and which asserts that there are learning problem instances for which any learning algorithm that has good prediction there exist distributions under which the algorithm must "memorize'' a big fraction of the training dataset. We show that for every learning algorithm, there exists an auxiliary algorithm that does not memorize and which yields comparable generalization error for any data distribution. In part, this shows that memorization is not necessary for good generalization.

Improving robustness of the Segment Anything Model (SAM) to input degradations is critical for its deployment in high-stakes applications such as autonomous driving and robotics. Our approach to this challenge prioritizes three key aspects: first, parameter efficiency to maintain the inherent generalization capability of SAM; second, fine-grained and input-aware robustification to precisely address the input corruption; and third, adherence to standard training protocols for ease of training. To this end, we propose gated-rank adaptation (GaRA). GaRA introduces lightweight adapters into intermediate layers of the frozen SAM, where each adapter dynamically adjusts the effective rank of its weight matrix based on the input by selectively activating (rank-1) components of the matrix using a learned gating module. This adjustment enables fine-grained and input-aware robustification without compromising the generalization capability of SAM. Our model, GaRA-SAM, significantly outperforms prior work on all robust segmentation benchmarks. In particular, it surpasses the previous best IoU score by up to 21.3%p on ACDC, a challenging real corrupted image dataset.

Models such as Word2Vec and GloVe construct word embeddings based on the co-occurrence probability $P(i,j)$ of words $i$ and $j$ in text corpora. The resulting vectors $W_i$ not only group semantically similar words but also exhibit a striking linear analogy structure---for example, $W_{\text{king}} - W_{\text{man}} + W_{\text{woman}} \approx W_{\text{queen}}$---whose theoretical origin remains unclear. Previous observations indicate that this analogy structure: (i) already emerges in the top eigenvectors of the matrix $M(i,j) = P(i,j)/P(i)P(j)$, (ii) strengthens and then saturates as more eigenvectors of $M (i, j)$, which controls the dimension of the embeddings, are included, (iii) is enhanced when using $\log M(i,j)$ rather than $M(i,j)$, and (iv) persists even when all word pairs involved in a specific analogy relation (e.g., king--queen, man--woman) are removed from the corpus. To explain these phenomena, we introduce a theoretical generative model in which words are defined by binary semantic attributes, and co-occurrence probabilities are derived from attribute-based interactions. This model analytically reproduces the emergence of linear analogy structure and naturally accounts for properties (i)--(iv). It can be viewed as giving fine-grained resolution into the role of each additional embedding dimension. It is robust to various forms of noise and agrees well with co-occurrence statistics measured on Wikipedia and the analogy benchmark introduced by Mikolov et al.

This study presents AutoOpt-11k, a unique image dataset of over 11,000 handwritten and printed mathematical optimization models corresponding to single-objective, multi-objective, multi-level, and stochastic optimization problems exhibiting various types of complexities such as non-linearity, non-convexity, non-differentiability, discontinuity, and high-dimensionality. The labels consist of the LaTeX representation for all the images and modeling language representation for a subset of images. The dataset is created by 25 experts following ethical data creation guidelines and verified in two-phases to avoid errors. Further, we develop AutoOpt framework, a machine learning based automated approach for solving optimization problems, where the user just needs to provide an image of the formulation and AutoOpt solves it efficiently without any further human intervention. AutoOpt framework consists of three Modules: (i) M1 (Image_to_Text)- a deep learning model performs the Mathematical Expression Recognition (MER) task to generate the LaTeX code corresponding to the optimization formulation in image; (ii) M2 (Text_to_Text)- a small-scale fine-tuned LLM generates the PYOMO script (optimization modeling language) from LaTeX code; (iii) M3 (Optimization)- a Bilevel Optimization based Decomposition (BOBD) method solves the optimization formulation described in the PYOMO script. We use AutoOpt-11k dataset for training and testing of deep learning models employed in AutoOpt. The deep learning model for MER task (M1) outperforms ChatGPT, Gemini and Nougat on BLEU score metric. BOBD method (M3), which is a hybrid approach, yields better results on complex test problems compared to common approaches, like interior-point algorithm and genetic algorithm.

We introduce PurpCode, the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities. PurpCode trains a reasoning model in two stages: (i) Rule Learning, which explicitly teaches the model to reference cybersafety rules to generate vulnerability-free code and to avoid facilitating malicious cyberactivities; and (ii) Reinforcement Learning, which optimizes model safety and preserves model utility through diverse, multi-objective reward mechanisms. To empower the training pipelines with comprehensive cybersafety data, we conduct internal red-teaming to synthesize comprehensive and high-coverage prompts based on real-world tasks for inducing unsafe cyberactivities in the model. Based on PurpCode, we develop a reasoning-based coding model, namely PurpCode-32B, which demonstrates state-of-the-art cybersafety, outperforming various frontier models. Moreover, our alignment method decreases the model overrefusal rates in both general and cybersafety-specific scenarios, while preserving model utility in both code generation and common security knowledge.

Recent works have highlighted the optimization difficulties encountered by gradient descent in training the first and last layer of transformer-based language models, which are overcome by optimizers such as Adam. The problem appears linked to the heavy-tailed distribution of words in text data, where the frequency of the $k$th most frequent word $\pi_k$ is proportional to $1/k$, following Zipf's law. To better understand the impact of the data distribution on training performance, we study a linear bigram model for next-token prediction when the tokens follow a power-law $\pi_k \propto 1/k^\alpha$ parameterized by the exponent $\alpha$. We derive optimization scaling laws for deterministic gradient descent and sign descent as a proxy for Adam as a function of the power $\alpha \geq 0$. This setting differs from existing theoretical investigations in scaling laws which assume that the eigenvalues of the data decay as a power with power $\alpha > 1$. This assumption effectively makes the problem "finite dimensional" as most of the loss comes from a few of the largest eigencomponents. In comparison, we show that the problem is more difficult when the data have heavier tails. The case $\alpha = 1$ as found in text is ``worst-case'' for gradient descent, in that the number of iterations required to reach a small relative error scales almost linearly with dimension. While the performance of sign descent also depends on the dimension, for Zipf-distributed data the number of iterations scales only with the square-root of the dimension, leading to a large improvement over gradient descent for large vocabularies.

State-of-the-art text-to-image models like Infinity generate photorealistic images at an unprecedented speed. These models operate in a bitwise autoregressive manner over a discrete set of tokens that is practically infinite in size. However, their impressive generative power comes with a growing risk: as their outputs increasingly populate the Internet, they are likely to be scraped and reused as training data, potentially by the very same models. This phenomenon has been shown to lead to model collapse, where repeated training on generated content, especially from the models' own previous versions, causes a gradual degradation in performance. A promising mitigation strategy is watermarking, which embeds human-imperceptible yet detectable signals into generated images, enabling the identification of generated content. In this work, we introduce BitMark, a robust bitwise watermarking framework. Our method embeds a watermark directly at the bit level of the token stream during the image generation process. Our bitwise watermark subtly influences the bits to preserve visual fidelity and generation speed while remaining robust against a spectrum of removal techniques. Furthermore, it exhibits high radioactivity, i.e., when watermarked generated images are used to train another image generative model, this second model's outputs will also carry the watermark. The radioactive traces remain detectable even when only fine-tuning diffusion or image autoregressive models on images watermarked with our BitMark. Overall, our approach provides a principled step toward preventing model collapse in image generative models by enabling reliable detection of generated outputs.