NeurIPS 2025 论文列表

We propose a new algorithm for fine-tuning large language models using reinforcement learning. Tapered Off-Policy REINFORCE (TOPR) uses an asymmetric, tapered variant of importance sampling to speed up learning while maintaining stable learning dynamics, even without the use of KL regularization. TOPR can be applied in a fully offline fashion, allows the handling of positive and negative examples in a unified framework, and benefits from the implementational simplicity that is typical of Monte Carlo algorithms. We demonstrate the effectiveness of our approach with a series of experiments on the GSM8K and MATH reasoning benchmarks, finding performance gains for training both a model for solution generation and as a generative verifier. We show that properly leveraging positive and negative examples alike in the off-policy regime simultaneously increases test-time accuracy and training data efficiency, all the while avoiding the ``wasted inference'' that comes with discarding negative examples. We find that this advantage persists over multiple iterations of training and can be amplified by dataset curation techniques, enabling us to match 70B-parameter model performance with 8B language models. As a corollary to this work, we find that REINFORCE's baseline parameter plays an important and unexpected role in defining dataset composition in the presence of negative examples, and is consequently critical in driving off-policy performance.

3D shape completion methods typically assume scans are pre-aligned to a canonical frame. This leaks pose and scale cues that networks may exploit to memorize absolute positions rather than inferring intrinsic geometry. When such alignment is absent in real data, performance collapses. We argue that robust generalization demands architectural equivariance to the similarity group, SIM(3), so the model remains agnostic to pose and scale. Following this principle, we introduce the first SIM(3)-equivariant shape completion network, whose modular layers successively canonicalize features, reason over similarity-invariant geometry, and restore the original frame. Under a de-biased evaluation protocol that removes the hidden cues, our model outperforms both equivariant and augmentation baselines on the PCN benchmark. It also sets new cross-domain records on real driving and indoor scans, lowering minimal matching distance on KITTI by 17\% and Chamfer distance $\ell1$ on OmniObject3D by 14\%. Perhaps surprisingly, ours under the stricter protocol still outperforms competitors under their biased settings. These results establish full SIM(3) equivariance as an effective route to truly generalizable shape completion.

Modern LLMs can now produce highly readable abstractive summaries, to the point that traditional automated metrics for evaluating summary quality, such as ROUGE, have saturated. However, LLMs still sometimes introduce inaccuracies into summaries, i.e., information inconsistent with or unsupported by the corresponding source. Measuring the occurrence of these often subtle factual inconsistencies automatically has proved challenging. This in turn has motivated development of metrics intended to measure the factual consistency of generated summaries against sources. But are these approaches measuring what they purport to? Or are they mostly exploiting artifacts? In this work, we stress test a range of automatic factuality metrics—including specialized model-based approaches and LLM-based prompting methods—to probe what they actually capture. Using a shallow classifier to separate “easy” examples for factual evaluation—where surface features suffice—from “hard” cases requiring deeper reasoning, we find that all metrics show substantial performance drops on the latter. Furthermore, some metrics are more sensitive to benign, fact-preserving edits than to factual corrections. Building on this observation, we demonstrate that most automatic factuality metrics can be gamed—that is, their scores can be artificially inflated by appending innocuous, content-free sentences to summaries. Among the metrics tested, the LLM prompt-based ChatGPT-DA approach is the most robust and reliable; however, it exhibits a notable caveat: it likely relies more on parametric knowledge than on the provided source when making judgments. Taken together, our findings call into question the reliability of current factuality metrics and prompt a broader reflection on what these metrics are truly measuring. We conclude with concrete recommendations for improving both benchmark design and metric robustness, particularly in light of their vulnerability to superficial manipulations.

Chip placement is a critical step in the Electronic Design Automation (EDA) workflow, which aims to arrange chip modules on the canvas to optimize the performance, power, and area (PPA) metrics of final designs. Recent advances show great potential of AI-based algorithms in chip placement. However, due to the lengthy EDA workflow, evaluations of these algorithms often focus on intermediate surrogate metrics, which are computationally efficient but often misalign with the final end-to-end performance (i.e., the final design PPA). To address this challenge, we propose to build ChiPBench, a comprehensive benchmark specifically designed to evaluate the effectiveness of AI-based algorithms in final design PPA metrics. Specifically, we generate a diverse evaluation dataset from $20$ circuits across various domains, such as CPUs, GPUs, and NPUs. We then evaluate six state-of-the-art AI-based chip placement algorithms on the dataset and conduct a thorough analysis of their placement behavior. Extensive experiments show that AI-based chip placement algorithms produce unsatisfactory final PPA results, highlighting the significant influence of often-overlooked factors like regularity and dataflow. We believe ChiPBench will effectively bridge the gap between academia and industry.

Enhancing the network architecture of the YOLO framework has been crucial for a long time. Still, it has focused on CNN-based improvements despite the proven superiority of attention mechanisms in modeling capabilities. This is because attention-based models cannot match the speed of CNN-based models. This paper proposes an attention-centric YOLO framework, namely YOLOv12, that matches the speed of previous CNN-based ones while harnessing the performance benefits of attention mechanisms. YOLOv12 surpasses popular real-time object detectors in accuracy with competitive speed. For example, YOLOv12-N achieves 40.5% mAP with an inference latency of 1.62 ms on a T4 GPU, outperforming advanced YOLOv10-N / YOLO11-N by 2.0%/1.1% mAP with a comparable speed. This advantage extends to other model scales. YOLOv12 also surpasses end-to-end real-time detectors that improve DETR, such as RT-DETRv2 / RT-DETRv3: YOLOv12-X beats RT-DETRv2-R101 / RT-DETRv3-R101 while running faster with fewer computations and parameters. See more comparisons in Figure 1. Source code is available at https://github.com/sunsmarterjie/yolov12.

Recent large language models (LLMs) with long-chain-of-thought reasoning—such as DeepSeek-R1—have achieved impressive results on Olympiad-level mathematics benchmarks. However, they often rely on a narrow set of strategies and struggle with problems that require a novel way of thinking. To systematically investigate these limitations, we introduce OMEGA—Out-of-distribution Math Problems Evaluation with 3 Generalization Axes—a controlled yet diverse bench- mark designed to evaluate three axes of out-of-distribution generalization, inspired by Boden’s typology of creativity: (1) Exploratory—applying known problem- solving skills to more complex instances within the same problem domain; (2) Com- positional—combining distinct reasoning skills, previously learned in isolation, to solve novel problems that require integrating these skills in new and coherent ways; and (3) Transformative—adopting novel, often unconventional strategies by moving beyond familiar approaches to solve problems more effectively. OMEGA consists of programmatically generated training–test pairs derived from templated problem generators across geometry, number theory, algebra, combinatorics, logic, and puzzles, with solutions verified using symbolic, numerical, or graphical methods. We evaluate frontier (or top-tier) LLMs and observe sharp performance degradation as problem complexity increases. Moreover, we fine-tune the Qwen-series models across all generalization settings and observe notable improvements in exploratory generalization, while compositional generalization remains limited, and transformative reasoning shows little to no improvement. By isolating and quantifying these fine-grained failures, OMEGA lays the groundwork for advancing LLMs toward genuine mathematical creativity beyond mechanical proficiency. Our code and dataset are available at https://github.com/sunblaze-ucb/omega.

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a resource exhaustion method that hijacks an LRM's generative control flow by training a malicious adversarial embedding to induce perpetual reasoning loops. Specifically, the optimized embedding encourages transitional tokens (e.g., “Wait”, “But”) after reasoning steps, preventing the model from concluding its answer. A key challenge we identify is the continuous-to-discrete projection gap: naïve projections of adversarial embeddings to token sequences nullify the attack. To overcome this, we introduce a backdoor implantation strategy, enabling reliable activation through specific trigger tokens. Our method achieves a 100\% attack success rate across four advanced LRMs (Phi-RM, Nemotron-Nano, R1-Qwen, R1-Llama) and three math reasoning benchmarks, forcing models to generate up to their maximum token limits. The attack is also stealthy (in terms of causing negligible utility loss on benign user inputs) and remains robust against existing strategies trying to mitigate the overthinking issue. Our findings expose a critical and underexplored security vulnerability in LRMs from the perspective of reasoning (in)efficiency.

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models fail to robustly verify their own outputs. We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this. RISE explicitly and simultaneously trains an LLM to improve both its problem-solving and self-verification abilities within a single, integrated RL process. The core mechanism involves leveraging verifiable rewards from an outcome verifier to provide on-the-fly feedback for both solution generation and self-verification tasks. In each iteration, the model generates solutions, then critiques its own on-policy generated solutions, with both trajectories contributing to the policy update. Extensive experiments on diverse mathematical reasoning benchmarks show that RISE consistently improves model's problem-solving accuracy while concurrently fostering strong self-verification skills. Our analyses highlight the advantages of online verification and the benefits of increased verification compute. Additionally, RISE models exhibit more frequent and accurate self-verification behaviors during reasoning. These advantages reinforce RISE as a flexible and effective path towards developing more robust and self-aware reasoners.

Large language models (LLMs) have achieved remarkable achievements across diverse applications; however, they remain plagued by spurious correlations and the generation of hallucinated content. Despite extensive efforts to enhance the resilience of LLMs, existing approaches either rely on indiscriminate fine-tuning of all parameters, resulting in parameter inefficiency and lack of specificity, or depend on post-processing techniques that offer limited adaptability and flexibility. This study introduces a novel Causality-driven Robust Optimization (CdRO) approach that selectively updates model components sensitive to causal reasoning, enhancing model causality while preserving valuable pretrained knowledge to mitigate overfitting. Our method begins by identifying the parameter components within LLMs that capture causal relationships, achieved through comparing the training dynamics of parameter matrices associated with the original samples, as well as augmented counterfactual and paraphrased variants. These comparisons are then fed into a lightweight logistic regression model, optimized in real time to dynamically identify and adapt the causal components within LLMs. The identified parameters are subsequently optimized using an enhanced policy optimization algorithm, where the reward function is designed to jointly promote both model generalization and robustness. Extensive experiments across various tasks using twelve different LLMs demonstrate the superior performance of our framework, underscoring its significant effectiveness in reducing the model’s dependence on spurious associations and mitigating hallucinations.

Neural operators or emulators for PDEs trained on data from numerical solvers are conventionally assumed to be limited by their training data's fidelity. We challenge this assumption by identifying "emulator superiority," where neural networks trained purely on low-fidelity solver data can achieve higher accuracy than those solvers when evaluated against a higher-fidelity reference. Our theoretical analysis reveals how the interplay between emulator inductive biases, training objectives, and numerical error characteristics enables superior performance during multi-step rollouts. We empirically validate this finding across different PDEs using standard neural architectures, demonstrating that emulators can implicitly learn dynamics that are more regularized or exhibit more favorable error accumulation properties than their training data, potentially surpassing training data limitations and mitigating numerical artifacts. This work prompts a re-evaluation of emulator benchmarking, suggesting neural emulators might achieve greater physical fidelity than their training source within specific operational regimes. Project Page: https://tum-pbs.github.io/emulator-superiority

Generating high-fidelity, differentially private (DP) synthetic images offers a promising route to share and analyze sensitive visual data without compromising individual privacy. However, existing DP image synthesis methods struggle to produce high-resolution outputs that faithfully capture the structure of the original data. In this paper, we introduce a novel method, referred to as Synthesis via Private Textual Intermediaries (SPTI), that can generate high-resolution DP images with easy adoptions. The key idea is to shift the challenge of DP image synthesis from the image domain to the text domain by leveraging state-of-the-art DP text generation methods. SPTI first summarizes each private image into a concise textual description using image-to-text models, then applies a modified Private Evolution algorithm to generate DP text, and finally reconstructs images using text-to-image models. Notably, SPTI requires no model training, only inferences with off-the-shelf models. Given a private dataset, SPTI produces synthetic images of substantially higher quality than prior DP approaches. On the LSUN Bedroom dataset, SPTI attains an FID $=$ 26.71 under $\epsilon=1.0$, improving over Private Evolution’s FID of 40.36. Similarly, on MM-CelebA-HQ, SPTI achieves an FID $=$ 33.27 at $\epsilon=1.0$, compared to 57.01 from DP fine-tuning baselines. Overall, our results demonstrate that Synthesis via Private Textual Intermediaries provides a resource-efficient and proprietary-model-compatible framework for generating high-resolution DP synthetic images, greatly expanding access to private visual datasets. Our code release: https://github.com/MarkGodrick/SPTI

Sequence models such as transformers require inputs to be represented as one-dimensional sequences. In vision, this typically involves flattening images using a fixed row-major (raster-scan) order. While full self-attention is permutation-equivariant, modern long-sequence transformers increasingly rely on architectural approximations that break this invariance and introduce sensitivity to patch ordering. We show that patch order significantly affects model performance in such settings, with simple alternatives like column-major or Hilbert curves yielding notable accuracy shifts. Motivated by this, we propose _REOrder_, a two-stage framework for discovering task-optimal patch orderings. First, we derive an information-theoretic prior by evaluating the compressibility of various patch sequences. Then, we learn a policy over permutations by optimizing a Plackett-Luce policy using REINFORCE. This approach enables efficient learning in a combinatorial permutation space. _REOrder_ improves top-1 accuracy over row-major ordering on ImageNet-1K by up to 3.01% and Functional Map of the World by 13.35%.

World models have recently gained prominence for action-conditioned visual prediction in complex environments. However, relying on only a few recent observations causes them to lose long-term context. Consequently, within a few steps, the generated scenes drift from what was previously observed, undermining temporal coherence. This limitation, common in state-of-the-art world models, which are diffusion-based, stems from the lack of a lasting environment state. To address this problem, we introduce StateSpaceDiffuser, where a diffusion model is enabled to perform long-context tasks by integrating features from a state-space model, representing the entire interaction history. This design restores long-term memory while preserving the high-fidelity synthesis of diffusion models. To rigorously measure temporal consistency, we develop an evaluation protocol that probes a model’s ability to reinstantiate seen content in extended rollouts. Comprehensive experiments show that StateSpaceDiffuser significantly outperforms a strong diffusion-only baseline, maintaining a coherent visual context for an order of magnitude more steps. It delivers consistent views in both a 2D maze navigation and a complex 3D environment. These results establish that bringing state-space representations into diffusion models is highly effective in demonstrating both visual details and long-term memory. Project page: https://insait-institute.github.io/StateSpaceDiffuser/

Adapting large-scale foundation models in multi-task scenarios often suffers from task conflict and oblivion. To mitigate such issues, we propose a novel "model MoE-ization" strategy that leads to a conflict- and oblivion-resistant multi-task adaptation method. Given a weight matrix of a pre-trained model, our method applies SVD to it and introduces a learnable router to adjust its singular values based on tasks and samples. Accordingly, the weight matrix becomes a Mixture of Orthogonal Rank-one Experts (MoORE), in which each expert corresponds to the outer product of a left singular vector and the corresponding right one. We can improve the model capacity by imposing a learnable orthogonal transform on the right singular vectors. Unlike low-rank adaptation (LoRA) and its MoE-driven variants, MoORE guarantees the experts' orthogonality and maintains the column space of the original weight matrix. These two properties make the adapted model resistant to the conflicts among the new tasks and the oblivion of its original tasks, respectively. Experiments on various datasets demonstrate that MoORE outperforms existing multi-task adaptation methods consistently, showing its superiority in terms of conflict- and oblivion-resistance. The code is available at https://github.com/DaShenZi721/MoORE.

Autonomy is a hallmark of animal intelligence, enabling adaptive and intelligent behavior in complex environments without relying on external reward or task structure. Existing reinforcement learning approaches to exploration in reward-free environments, including a class of methods known as *model-based intrinsic motivation*, exhibit inconsistent exploration patterns and do not converge to an exploratory policy, thus failing to capture robust autonomous behaviors observed in animals. Moreover, systems neuroscience has largely overlooked the neural basis of autonomy, focusing instead on experimental paradigms where animals are motivated by external reward rather than engaging in ethological, naturalistic and task-independent behavior. To bridge these gaps, we introduce a novel model-based intrinsic drive explicitly designed after the principles of autonomous exploration in animals. Our method (3M-Progress) achieves animal-like exploration by tracking divergence between an online world model and a fixed prior learned from an ecological niche. To the best of our knowledge, we introduce the first autonomous embodied agent that predicts brain data entirely from self-supervised optimization of an intrinsic goal—without any behavioral or neural training data—demonstrating that 3M-Progress agents capture the explainable variance in behavioral patterns and whole-brain neural-glial dynamics recorded from autonomously behaving larval zebrafish, thereby providing the first goal-driven, population-level model of neural-glial computation. Our findings establish a computational framework connecting model-based intrinsic motivation to naturalistic behavior, providing a foundation for building artificial agents with animal-like autonomy.

3D molecule generation is crucial for drug discovery and material science, requiring models to process complex multi-modalities, including atom types, chemical bonds, and 3D coordinates. A key challenge is integrating these modalities of different shapes while maintaining SE(3) equivariance for 3D coordinates. To achieve this, existing approaches typically maintain separate latent spaces for invariant and equivariant modalities, reducing efficiency in both training and sampling. In this work, we propose **U**nified Variational **A**uto-**E**ncoder for **3D** Molecular Latent Diffusion Modeling (**UAE-3D**), a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space, while maintaining near-zero reconstruction error. This unified latent space eliminates the complexities of handling multi-modality and equivariance when performing latent diffusion modeling. We demonstrate this by employing the Diffusion Transformer--a general-purpose diffusion model without any molecular inductive bias--for latent generation. Extensive experiments on GEOM-Drugs and QM9 datasets demonstrate that our method significantly establishes new benchmarks in both *de novo* and conditional 3D molecule generation, achieving leading efficiency and quality. On GEOM-Drugs, it reduces FCD by 72.6% over the previous best result, while achieving over 70% relative average improvements in geometric fidelity. Our code is released at [https://github.com/lyc0930/UAE-3D/](https://github.com/lyc0930/UAE-3D/).

Recently, Multimodal Large Language Models (MLLMs) have made rapid progress, particularly in enhancing their reasoning capabilities. However, existing reasoning benchmarks still primarily assess language-based reasoning, often treating visual input as replaceable context. To address this gap, we introduce BLINK-Twice, a vision-centric reasoning benchmark grounded in challenging perceptual tasks. Instead of relying on external knowledge, our tasks require models to reason from visual content alone, shifting the focus from language-based to image-grounded reasoning. Compared to prior perception benchmarks, it moves beyond shallow perception ("see") and requires fine-grained observation and analytical reasoning ("observe"). BLINK-Twice integrates three core components: seven types of visual challenges for testing visual reasoning, natural adversarial image pairs that enforce reliance on visual content, and annotated reasoning chains for fine-grained evaluation of the reasoning process rather than final answers alone. We evaluate 20 leading MLLMs, including 12 foundation models and 8 reasoning-enhanced models. BLINK-Twice poses a significant challenge to current models. While existing reasoning strategies in the language space—such as chain-of-thought or self-criticism can improve performance, they often result in unstable and redundant reasoning. We observe that repeated image observation improves performance across models, and active visual interaction, as demonstrated by models like o3, highlights the need for a new paradigm for vision reasoning. The dataset is publicly available at https://github.com/PicoTrex/BLINK-Twice.

Follow-the-Regularized-Leader (FTRL) policies have achieved Best-of-Both-Worlds (BOBW) results in various settings through hybrid regularizers, whereas analogous results for Follow-the-Perturbed-Leader (FTPL) remain limited due to inherent analytical challenges. To advance the analytical foundations of FTPL, we revisit classical FTRL-FTPL duality for unbounded perturbations and establish BOBW results for FTPL under a broad family of asymmetric unbounded Fréchet-type perturbations, including hybrid perturbations combining Gumbel-type and Fréchet-type tails. These results not only extend the BOBW results of FTPL but also offer new insights into designing alternative FTPL policies competitive with hybrid regularization approaches. Motivated by earlier observations in two-armed bandits, we further investigate the connection between the $1/2$-Tsallis entropy and a Fréchet-type perturbation. Our numerical observations suggest that it corresponds to a symmetric Fréchet-type perturbation, and based on this, we establish the first BOBW guarantee for symmetric unbounded perturbations in the two-armed setting. In contrast, in general multi-armed bandits, we find an instance in which symmetric Fréchet-type perturbations violate the standard condition for BOBW analysis, which is a problem not observed with asymmetric or nonnegative Fréchet-type perturbations. Although this example does not rule out alternative analyses achieving BOBW results, it suggests the limitations of directly applying the relationship observed in two-armed cases to the general case and thus emphasizes the need for further investigation to fully understand the behavior of FTPL in broader settings.

Real-world objects frequently undergo state transformations. From an apple being cut into pieces to a butterfly emerging from its cocoon, tracking through these changes is important for understanding real-world objects and dynamics. However, existing methods often lose track of the target object after transformation, due to significant changes in object appearance. To address this limitation, we introduce the task of Track Any State: tracking objects through transformations while detecting and describing state changes, accompanied by a new benchmark dataset, VOST-TAS. To tackle this problem, we present TubeletGraph, a zero-shot system that recovers missing objects after transformation and maps out how object states are evolving over time. TubeletGraph first identifies potentially overlooked tracks, and determines whether they should be integrated based on semantic and proximity priors. Then, it reasons about the added tracks and generates a state graph describing each observed transformation. TubeletGraph achieves state-of-the-art tracking performance under transformations, while demonstrating deeper understanding of object transformations and promising capabilities in temporal grounding and semantic reasoning for complex object transformations. Code, additional results, and the benchmark dataset are available at https://tubelet-graph.github.io.