论文检索

Deep Learning · Everything Else

Yu Zhou, Xingyu Wu, Jibin Wu, Liang Feng, KC Tan

Model merging is a technique that combines multiple large pretrained models into a single model, enhancing performance and broadening task adaptability without original data or additional training. However, most existing model merging methods focus primarily on exploring the parameter space, merging models with identical architectures. Despite its potential, merging in the architecture space remains in its early stages due to the vast search space and challenges related to layer compatibility. This paper designs a hierarchical model merging framework named HM3, formulating a bilevel multi-objective model merging problem across both parameter and architecture spaces. At the parameter level, HM3 integrates existing merging methods to quickly identify optimal parameters. Based on these, an actor-critic strategy with efficient policy discretization is employed at the architecture level to explore inference paths with Markov property in the layer-granularity search space for reconstructing these optimal models. By training reusable policy and value networks, HM3 learns Pareto optimal models to provide customized solutions for various tasks. Experimental results on language and vision tasks demonstrate that HM3 outperforms methods focusing solely on the parameter or architecture space.

Deep Learning · Everything Else

Jiaqi Chen, Bang Zhang, Ruotian Ma, Peisong Wang, Xiaodan Liang, Zhaopeng Tu, Xiaolong Li, Kwan-Yee K. Wong

Evaluating the step-by-step reliability of large language model (LLM) reasoning, such as Chain-of-Thought, remains challenging due to the difficulty and cost of obtaining high-quality step-level supervision. In this paper, we introduce Self-Play Critic (SPC), a novel approach where a critic model evolves its ability to assess reasoning steps through adversarial self-play games, eliminating the need for manual step-level annotation. SPC involves fine-tuning two copies of a base model to play two roles, namely a "sneaky generator" that deliberately produces erroneous steps designed to be difficult to detect, and a "critic" that analyzes the correctness of reasoning steps. These two models engage in an adversarial game in which the generator aims to fool the critic, while the critic model seeks to identify the generator's errors. Using reinforcement learning based on the game outcomes, the models iteratively improve; the winner of each confrontation receives a positive reward and the loser receives a negative reward, driving continuous self-evolution. Experiments on three reasoning process benchmarks (ProcessBench, PRM800K, DeltaBench) demonstrate that our SPC progressively enhances its error detection capabilities (e.g., accuracy increases from 70.8% to 77.7% on ProcessBench) and surpasses strong baselines, including distilled R1 model. Furthermore, SPC can guide the test-time search of diverse LLMs and significantly improve their mathematical reasoning performance on MATH500 and AIME2024, surpassing those guided by state-of-the-art process reward models.

Computer Vision · Image and Video Generation

Jinlai Liu, Jian Han, Bin Yan, Hui Wu, Fengda Zhu, Xing Wang, Yi Jiang, BINGYUE PENG, Zehuan Yuan

We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete approach jointly captures spatial and temporal dependencies within a single architecture. This unified design naturally supports a variety of generation tasks such as text-to-image, text-to-video, image-to-video, and long-duration video synthesis via straightforward temporal autoregression. Through extensive experiments, InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10$\times$ faster than leading diffusion-based methods. To our knowledge, InfinityStar is the first discrete autoregressive video generator capable of producing industrial-level 720p videos. We release all code and models to foster further research in efficient, high-quality video generation.

General Machine Learning · Representation Learning

Shenzhi Yang, Junbo Zhao, Sharon Li, Shouqing Yang, Dingyu Yang, Xiaofang Zhang, Haobo Wang

Out-of-distribution (OOD) node detection in graphs is a critical yet challenging task. Most existing approaches rely heavily on fine-grained labeled data to obtain a pre-trained supervised classifier, inherently assuming the existence of a well-defined pretext classification task. However, when such a task is ill-defined or absent, their applicability becomes severely limited. To overcome this limitation, there is an urgent need to propose a more scalable OOD detection method that is independent of both pretext tasks and label supervision. We harness a new phenomenon called **Feature Resonance**, focusing on the feature space rather than the label space. We observe that, ideally, during the optimization of known ID samples, unknown ID samples undergo more significant representation changes than OOD samples, even when the model is trained to align arbitrary targets. The rationale behind it is that even without gold labels, the local manifold may still exhibit smooth resonance. Based on this, we further develop a novel graph OOD framework, dubbed **R**esonance-based **S**eparation and **L**earning (**RSL**), which comprises two core modules: (i)-a more practical micro-level proxy of feature resonance that measures the movement of feature vectors in one training step. (ii)-integrate with a synthetic OOD node strategy to train an effective OOD classifier. Theoretically, we derive an error bound showing the superior separability of OOD nodes during the resonance period. Extensive experiments on a total of thirteen real-world graph datasets empirically demonstrate that RSL achieves state-of-the-art performance.

Reinforcement Learning · Everything Else

Tyron Lardy, Christina Katsimerou, Wouter Koolen

In real-world decision-making problems, one needs to pick among multiple policies the one that performs best while respecting economic constraints. This motivates the problem of constrained best-arm identification for bandit problems where every arm is a joint distribution of reward and cost. We investigate the general case where reward and cost are dependent. The goal is to accurately identify the arm with the highest mean reward among all arms whose mean cost is below a given threshold. We prove information-theoretic lower bounds on the sample complexity for three models: Gaussian with fixed covariance, Gaussian with unknown covariance, and non-parametric distributions of rectangular support. We propose a combination of a sampling and a stopping rule that correctly identifies the constrained best arm and matches the optimal sample complexities for each of the three models. Simulations demonstrate the performance of our algorithms.

Deep Learning · Generative Models and Autoencoders

Jaesik Yoon, Hyeonseo Cho, Yoshua Bengio, Sungjin Ahn

Diffusion models have recently emerged as a powerful approach for trajectory planning. However, their inherently non-sequential nature limits their effectiveness in long-horizon reasoning tasks at test time. The recently proposed Monte Carlo Tree Diffusion (MCTD) offers a promising solution by combining diffusion with tree-based search, achieving state-of-the-art performance on complex planning problems. Despite its strengths, our analysis shows that MCTD incurs substantial computational overhead due to the sequential nature of tree search and the cost of iterative denoising. To address this, we propose Fast-MCTD, a more efficient variant that preserves the strengths of MCTD while significantly improving its speed and scalability. Fast-MCTD integrates two techniques: Parallel MCTD, which enables parallel rollouts via delayed tree updates and redundancy-aware selection; and Sparse MCTD, which reduces rollout length through trajectory coarsening. Experiments show that Fast-MCTD achieves up to 100× speedup over standard MCTD while maintaining or improving planning performance. Remarkably, it even outperforms Diffuser in inference speed on some tasks, despite Diffuser requiring no search and yielding weaker solutions. These results position Fast-MCTD as a practical and scalable solution for diffusion-based inference-time reasoning.

Applications · Neuroscience, Cognitive Science

Anuja Negi, SUBBAREDDY OOTA, Anwar Nunez-Elizalde, Manish Gupta, Fatma Deniz

Recent studies have demonstrated that fine-tuning language models with brain data can improve their semantic understanding, although these findings have so far been limited to English. Interestingly, similar to the shared multilingual embedding space of pretrained multilingual language models, human studies provide strong evidence for a shared semantic system in bilingual individuals. Here, we investigate whether fine-tuning language models with bilingual brain data changes model representations in a way that improves them across multiple languages. To test this, we fine-tune monolingual and multilingual language models using brain activity recorded while bilingual participants read stories in English and Chinese. We then evaluate how well these representations generalize to the bilingual participants’ first language, their second language, and several other languages that the participants are not fluent in. We assess the fine-tuned language models on brain encoding performance and downstream NLP tasks. Our results show that bilingual brain-informed fine-tuned language models outperform their vanilla (pretrained) counterparts in both brain encoding performance and most downstream NLP tasks across multiple languages. These findings suggest that brain-informed fine-tuning improves multilingual understanding in language models, offering a bridge between cognitive neuroscience and NLP research. We make our code publicly available.

Deep Learning · Algorithms

Rongchao Zhang, Yu Huang, Yongzhi Cao, Hanpin Wang

Molecular synthetic space projecting is a critical technique in de novo molecular design, which aims to rectify molecules without synthesizability guarantee by converting them into synthetic postfix notations. However, the vast synthesizable chemical space and the discrete data modalities involved pose significant challenges to postfix notation conversion benchmarking. In this paper, we exploit conditional probability transitions in discrete state space and introduce MoleBridge, a deep generative model built on the Markov bridge approach for designing postfix notations of molecular synthesis pathways. MoleBridge consists of two iterative optimizations: i) Autoregressive extending of notation tokens from molecular graphs, and ii) generation of discrete reaction postfix notations through Markov bridge, where noisy token blocks are progressively denoised over multi-step iterations. For the challenging second iteration, which demands sensitivity to incorrect generative probability paths within intricate chemical spaces, we employ a thinking and denoising separation approach to denoise. Empirically, we find that MoleBridge is capable of accurately predicting synthesis pathways while exhibiting excellent performance in a variety of application scenarios.

Applications · Chemistry and Drug Discovery

Matthieu Kirchmeyer, Pedro O. Pinheiro, Emma Willett, Karolis Martinkus, Joseph Kleinhenz, Emily Makowski, Andrew Watkins, Vladimir Gligorijevic, Richard Bonneau, Saeed Saremi

Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBind, a framework based on computer vision to generate target-conditioned, all-atom molecules across atomic systems. FuncBind uses neural fields to represent molecules as continuous atomic densities and employs score-based generative models with modern architectures adapted from the computer vision literature. This modality-agnostic representation allows a single unified model to be trained on diverse atomic systems, from small to large molecules, and handle variable atom/residue counts, including non-canonical amino acids. FuncBind achieves competitive in silico performance in generating small molecules, macrocyclic peptides, and antibody complementarity-determining region loops, conditioned on target structures. FuncBind also generated in vitro novel antibody binders via de novo redesign of the complementarity-determining region H3 loop of two chosen co-crystal structures. As a final contribution, we introduce a new dataset and benchmark for structure-conditioned macrocyclic peptide generation.

Social Aspects · Fairness, Equity, Justice and Safety

Jun Jiang, Zijin Yang, Weiming Zhang, Nenghai Yu, Kejiang Chen

Generative steganography has emerged as an active research area, yet its practical system is constrained by the inherent secret payload limitation caused by low entropy in generating stego texts. This payload limitation necessitates the use of lengthy stego texts or frequent transmissions, which increases the risk of suspicion by adversaries. Previous studies have mainly focused on payload enhancement through optimized entropy utilization while overlooking the crucial role of secret message processing. To address this gap, we propose StegoZip, a framework that leverages large language models to optimize secret message processing. StegoZip consists of two core components: semantic redundancy pruning and index-based compression coding. The former dynamically prunes the secret message to extract a low-semantic representation, whereas the latter further compresses it into compact binary codes. When integrated with state-of-the-art steganographic methods under lossless decoding, StegoZip achieves 2.5$\times$ the payload of the baselines while maintaining comparable processing time in practice. This enhanced payload significantly improves covertness by mitigating the risks associated with frequent transmissions while maintaining provable content security.

Social Aspects · Everything Else

Chunlong Xie, Kangjie Chen, Shangwei Guo, Shudong Zhang, Tianwei Zhang, Tao Xiang

Modern Text-to-Image (T2I) models deploy multi-layered defenses to block Not-Safe-For-Work (NSFW) content generation. These defenses typically include sequential layers such as prompt filters, concept erasers and image filters. While existing adversarial attacks have demonstrated vulnerabilities in isolated defense layers, they prove largely ineffective against multi-layered defenses deployed in real-world T2I systems. In this paper, we demonstrate that exploiting overlapping vulnerabilities across these distinct defense layers enables adversaries to systematically bypass the entire safeguard of T2I systems. We propose Transstratal Adversarial Attack (TAA, a novel black-box framework to compromise T2I models with multi-layered protection. It generates transstratal adversarial prompts to evade all defense layers simultaneously. This is accomplished through transstratal adversarial candidate generation using LLMs to fulfill implicit and subjective adversarial requirements against different defense layers, combined with adversarial genetic optimization for efficient black-box search to maximize the bypass rates and generated image harmfulness. Evaluated across 14 T2I models (e.g., Stable Diffusion, DALL·E, and Midjourney) and 17 safety modules, our attack achieves an average attack success rate of 85.6\%, surpassing state-of-the-art methods by 73.5\%. Our findings challenge the isolated design of safety mechanisms and establish the first benchmark for holistic robustness evaluation in multi-layered safeguarded T2I models. The code can be found in https://github.com/Bluedask/TAA-T2I.

Reinforcement Learning · Deep RL

Likun Wang, Xiangteng Zhang, Yinuo Wang, Guojian Zhan, Wenxuan Wang, Haoyu Gao, Jingliang Duan, Shengbo Li

Exploration is crucial in Reinforcement Learning (RL) as it enables the agent to understand the environment for better decision-making. Existing exploration methods fall into two paradigms: active exploration, which injects stochasticity into the policy but struggles in high-dimensional environments, and passive exploration, which manages the replay buffer to prioritize under-explored regions but lacks sample diversity. To address the limitation in passive exploration, we propose Modelic Generative Exploration (MoGE), which augments exploration through the generation of under-explored critical states and synthesis of dynamics-consistent experiences. MoGE consists of two components: (1) a diffusion generator for critical states under the guidance of entropy and TD error, and (2) a one-step imagination world model for constructing critical transitions for agent learning. Our method is simple to implement and seamlessly integrates with mainstream off-policy RL algorithms without structural modifications. Experiments on OpenAI Gym and DeepMind Control Suite demonstrate that MoGE, as an exploration augmentation, significantly enhances efficiency and performance in complex tasks.

Deep Learning · Attention Mechanisms

Jang-Hyun Kim, Jinuk Kim, Sangwoo Kwon, Jae W. Lee, Sangdoo Yun, Hyun Oh Song

Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory overhead and increased attention latency. This paper introduces \textit{KVzip}, a query-agnostic KV cache eviction method enabling effective reuse of compressed KV caches across diverse queries. KVzip quantifies the importance of a KV pair using the underlying LLM to reconstruct original contexts from cached KV pairs, subsequently evicting pairs with lower importance. Extensive empirical evaluations demonstrate that KVzip reduces KV cache size by $3$-$4\times$ and FlashAttention decoding latency by approximately $2\times$, with negligible performance loss in question-answering, retrieval, reasoning, and code comprehension tasks. Evaluations include various models such as LLaMA3.1, Qwen2.5, and Gemma3, with context lengths reaching up to 170K tokens. KVzip significantly outperforms existing query-aware KV eviction methods, which suffer from performance degradation even at a 90\% cache budget ratio under multi-query scenarios.

Applications · Language, Speech and Dialog

Songhao Wu, Ang Lv, xiao feng, Yufei zhang, Xun Zhang, Guojun Yin, Wei Lin, Rui Yan

The increasing demand for long-context generation has made the KV cache in large language models a bottleneck in memory consumption. Quantizing the cache to lower bit widths is an effective way to reduce memory costs; however, previous methods struggle with key cache quantization due to outliers, resulting in suboptimal performance. We propose a novel quantization approach PolarQuant, which provides a new perspective for key cache quantization and efficiently addresses the outlier dilemma. We observe that the distribution of the key states reveals well-structured patterns under polar transformation. Outliers generally appear in only one of the two dimensions, which are rotated together by a specific angle when rotary position embeddings are applied. When represented as two-dimensional vectors, these dimensions exhibit well-organized patterns, with radii and angles smoothly distributed in polar space. This alleviates the channel-wise outliers, making them well-suited for key cache quantization. PolarQuant divides key vectors into groups of two-dimensional sub-vectors, encoding them as the quantized radius and the polar angle, rather than quantizing original key vectors directly. PolarQuant achieves the superior efficiency in KV cache quantization and accelerates the decoding process by turning the query-key inner product into a table lookup, all while maintaining the downstream performance of full-precision models. Our code is available at https://github.com/ericshwu/PolarQuant.

Deep Learning · Theory

Wei Huang, Andi Han, Yujin Song, Yilan Chen, Denny Wu, Difan Zou, Taiji Suzuki

The capacity of deep learning models is often large enough to both learn the underlying statistical signal and overfit to noise in the training set. This noise memorization can be harmful especially for data with a low signal-to-noise ratio (SNR), leading to poor generalization. Inspired by prior observations that label noise provides implicit regularization that improves generalization, in this work, we investigate whether introducing label noise to the gradient updates can enhance the test performance of neural network (NN) in the low SNR regime. Specifically, we consider training a two-layer NN with a simple label noise gradient descent (GD) algorithm, in an idealized signal-noise data setting. We prove that adding label noise during training suppresses noise memorization, preventing it from dominating the learning process; consequently, label noise GD enjoys rapid signal growth while the overfitting remains controlled, thereby achieving good generalization despite the low SNR. In contrast, we also show that NN trained with standard GD tends to overfit to noise in the same low SNR setting and establish a non-vanishing lower bound on its test error, thus demonstrating the benefit of introducing label noise in gradient-based training.

Reinforcement Learning · Everything Else

Xiaolin Sun, Feidi Liu, Zhengming Ding, Zizhan Zheng

Reinforcement learning (RL) systems, while achieving remarkable success across various domains, are vulnerable to adversarial attacks. This is especially a concern in vision-based environments where minor manipulations of high-dimensional image inputs can easily mislead the agent's behavior. To this end, various defenses have been proposed recently, with state-of-the-art approaches achieving robust performance even under large state perturbations. However, after closer investigation, we found that the effectiveness of the current defenses is due to a fundamental weakness of the existing $l_p$ norm-constrained attacks, which can barely alter the semantics of image input even under a relatively large perturbation budget. In this work, we propose SHIFT, a novel policy-agnostic diffusion-based state perturbation attack to go beyond this limitation. Our attack is able to generate perturbed states that are semantically different from the true states while remaining realistic and history-aligned to avoid detection. Evaluations show that our attack effectively breaks existing defenses, including the most sophisticated ones, significantly outperforming existing attacks while being more perceptually stealthy. The results highlight the vulnerability of RL agents to semantics-aware adversarial perturbations, indicating the importance of developing more robust policies.

Reinforcement Learning · Multi-agent

Shuze Chen, Tianyi Peng

Value decomposition has long been a fundamental technique in multi-agent reinforcement learning and dynamic programming. Specifically, the value function of a global state $(s_1,s_2,\ldots,s_N)$ is often approximated as the sum of local functions: $V(s_1,s_2,\ldots,s_N)\approx\sum_{i=1}^N V_i(s_i)$. This approach has found various applications in modern RL systems. However, the theoretical justification for why this decomposition works so effectively remains underexplored. In this paper, we uncover the underlying mathematical structure that enables value decomposition. We demonstrate that a Markov decision process (MDP) permits value decomposition *if and only if* its transition matrix is not "entangled"—a concept analogous to quantum entanglement in quantum physics. Drawing inspiration from how physicists measure quantum entanglement, we introduce how to measure the "Markov entanglement" and show that this measure can be used to bound the decomposition error in general multi-agent MDPs. Using the concept of Markov entanglement, we proved that a widely-used class of policies, the index policy, is weakly-entangled and enjoys a sublinear $\mathcal O(\sqrt{N})$ scale of decomposition error for $N$-agent systems. Finally, we show Markov entanglement can be efficiently estimated, guiding practitioners on the feasibility of value decomposition.

Deep Learning · Generative Models and Autoencoders

Anindya Sarkar, Binglin Ji, Yevgeniy Vorobeychik

In many scientific and engineering fields, where acquiring high-quality data is expensive—such as medical imaging, environmental monitoring, and remote sensing—strategic sampling of unobserved regions based on prior observations is crucial for maximizing discovery rates within a constrained budget. The rise of powerful generative models, such as diffusion models, has enabled active target discovery in partially observable environments by leveraging learned priors—probabilistic representations that capture underlying structure from data. With guidance from sequentially gathered task-specific observations, these models can progressively refine exploration and efficiently direct queries toward promising regions. However, in domains where learning a strong prior is infeasible due to extremely limited data or high sampling cost (such as rare species discovery, diagnostics for emerging diseases, etc.), these methods struggle to generalize. To overcome this limitation, we propose a novel approach that enables effective active target discovery even in settings with uninformative priors, ensuring robust exploration and adaptability in complex real-world scenarios. Our framework is theoretically principled and draws inspiration from neuroscience to guide its design. Unlike black-box policies, our approach is inherently interpretable, providing clear insights into decision-making. Furthermore, it guarantees a strong, monotonic improvement in prior estimates with each new observation, leading to increasingly accurate sampling and reinforcing both reliability and adaptability in dynamic settings. Through comprehensive experiments and ablation studies across various domains, including species distribution modeling and remote sensing, we demonstrate that our method substantially outperforms baseline approaches.

Deep Learning · Everything Else

Kelvin Kan, Xingjian Li, Benjamin Zhang, Tuhin Sahai, Stanley Osher, Markos Katsoulakis

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing Transformer models while providing desirable theoretical guarantees, including generalization and robustness. Our framework is designed to be plug-and-play, enabling seamless integration with established Transformer models and requiring only slight changes to the implementation. We conduct seven extensive experiments on tasks motivated by text generation, sentiment analysis, image classification, and point cloud classification. Experimental results show that the framework improves the test performance of the baselines, while being more parameter-efficient. On character-level text generation with nanoGPT, our framework achieves a 46\% reduction in final test loss while using 42\% fewer parameters. On GPT-2, our framework achieves a 9.3\% reduction in final test loss, demonstrating scalability to larger models. To the best of our knowledge, this is the first work that applies optimal control theory to both the training and architecture of Transformers. It offers a new foundation for systematic, theory-driven improvements and moves beyond costly trial-and-error approaches.

Theory · Domain Adaptation and Transfer Learning

Yang Qiu, Yixiong Zou, Jun Wang, Wei Liu, Xiangyu Fu, Ruixuan Li

Out-of-distribution generalization under distributional shifts remains a critical challenge for graph neural networks. Existing methods generally adopt the Invariant Risk Minimization (IRM) framework, requiring costly environment annotations or heuristically generated synthetic splits. To circumvent these limitations, in this work, we aim to develop an IRM-free method for capturing causal subgraphs. We first identify that causal subgraphs exhibit substantially smaller distributional variations than non-causal components across diverse environments, which we formalize as the Invariant Distribution Criterion and theoretically prove in this paper. Building on this criterion, we systematically uncover the quantitative relationship between distributional shift and representation norm for identifying the causal subgraph, and investigate its underlying mechanisms in depth. Finally, we propose an IRM-free method by introducing a norm-guided invariant distribution objective for causal subgraph discovery and prediction. Extensive experiments on two widely used benchmarks demonstrate that our method consistently outperforms state-of-the-art methods in graph generalization. Code is available at https://github.com/anders1123/IDG.