论文检索

Reinforcement Learning · Planning

Michael Psenka, Michael Rabbat, Aditi Krishnapriyan, Yann LeCun, Amir Bar

World models simulate environment dynamics from raw sensory inputs like video. However, using them for planning can be challenging due to the vast and unstructured search space. We propose a robust and highly parallelizable planner that leverages the differentiability of the learned world model for efficient optimization, solving long-horizon control tasks from visual input. Our method treats states as optimization variables ("virtual states") with soft dynamics constraints, enabling parallel computation and easier optimization. To facilitate exploration and avoid local optima, we introduce stochasticity into the states. To mitigate sensitive gradients through high-dimensional vision-based world models, we modify the gradient structure to descend towards valid plans while only requiring action-input gradients. Our approach can be viewed as a stochastic version of a non-condensed or collocation-based optimal controller. We provide theoretical justification and experiments on video-based world models, where our resulting planner outperforms existing planning algorithms like the cross-entropy method (CEM) and vanilla gradient-based optimization (GD) on long-horizon experiments, both in success rate and time to convergence.

Reinforcement Learning · Online

Olivier Goudet, Quentin Suire, Adrien Goëffon, Frédéric Saubion, sylvain lamprier

We introduce an order-invariant reinforcement learning framework for black-box combinatorial optimization. Classical estimation-of-distribution algorithms (EDAs) often rely on learning explicit variable dependency graphs, which can be costly and fail to capture complex interactions efficiently. In contrast, we parameterize a multivariate autoregressive generative model trained without a fixed variable ordering. By sampling random generation orders during training - a form of information-preserving dropout - the model is encouraged to be invariant to variable order, promoting search-space diversity and shaping the model to focus on the most relevant variable dependencies, improving sample efficiency. We adapt Group Relative Policy Optimization (GRPO) to this setting, providing stable policy-gradient updates from scale-invariant advantages. Across a wide range of benchmark algorithms and problem instances of varying sizes, our method frequently achieves the best performance and consistently avoids catastrophic failures.

Applications · Computer Vision

Xu Guo, Fulong Ye, Qichao Sun, Liyang Chen, Bingchuan Li, Pengze Zhang, Jiawei Liu, Songtao Zhao, Qian HE, Xiangwang Hou

Recent advancements in foundation models have revolutionized joint audio-video generation. However, existing approaches typically treat human-centric tasks including reference-based audio-video generation (R2AV), video editing (RV2AV) and audio-driven video animation (RA2V) as isolated objectives. Furthermore, achieving precise, disentangled control over multiple character identities and voice timbres within a single framework remains an open challenge. In this paper, we propose DreamID-Omni, a unified framework for controllable human-centric audio-video generation. Specifically, we design a Symmetric Conditional Diffusion Transformer that integrates heterogeneous conditioning signals via a symmetric conditional injection scheme. To resolve the pervasive identity-timbre binding failures and speaker confusion in multi-person scenarios, we introduce a Dual-Level Disentanglement strategy: Synchronized RoPE at the signal level to ensure rigid attention-space binding, and Structured Captions at the semantic level to establish explicit attribute-subject mappings. Furthermore, we devise a Multi-Task Progressive Training scheme that leverages weakly-constrained generative priors to regularize strongly-constrained tasks, preventing overfitting and harmonizing disparate objectives. Extensive experiments demonstrate that DreamID-Omni achieves comprehensive state-of-the-art performance across video, audio, and audio-visual consistency, even outperforming leading proprietary commercial models. We will release our code to bridge the gap between academic research and commercial-grade applications.

Deep Learning · Large Language Models

Yu Wang, Yijian Liu, Liheng Ji, Han Luo, Wenjie Li, Xiaofei Zhou, Chiyun Feng, Puji Wang, Yuhan Cao, Geyuan Zhang 等

Large language models (LLMs) have demonstrated remarkable capabilities across a variety of domains. However, their applications in cryptography, which serve as a foundational pillar of cybersecurity, remain largely unexplored. To address this gap, we build \textbf{AICrypto}, a comprehensive benchmark designed to evaluate the cryptography capabilities of LLMs. The benchmark comprises 135 multiple-choice questions, 150 capture-the-flag challenges, and 30 proof problems, covering a broad range of skills from knowledge memorization to vulnerability exploitation and formal reasoning. All tasks are carefully reviewed or constructed by cryptography experts to improve correctness and rigor. For each proof problem, we provide detailed scoring rubrics and reference solutions that enable automated grading, achieving high correlation with human expert evaluations. We introduce strong human expert performance baselines for comparison across all task types. Our evaluation of 17 leading LLMs reveals that state-of-the-art models match or even surpass human experts in memorizing cryptographic concepts, exploiting common vulnerabilities, and routine proofs. However, our analysis reveals that they still lack a deep understanding of abstract mathematical concepts and struggle with tasks that require multi-step reasoning and dynamic analysis. We hope this work could provide insights for future research on LLMs in cryptographic applications. Our code and dataset are available at https://anonymous.4open.science/r/aicrypto-CE6E/.

Applications · Health / Medicine

Aryan Pedawi, Jordi Silvestre-Ryan, Bradley Worley, Darren Hsu, Kushal Shah, Elias Stehle, Jingrong Zhang, Izhar Wallach

Make-on-demand combinatorial synthesis libraries (CSLs) like Enamine REAL have significantly enabled drug discovery efforts. However, their large size presents a challenge for virtual screening, where the goal is to identify the top compounds in a library according to a computational objective (e.g., optimizing docking score) subject to computational constraints under a limited computational budget. For current library sizes---numbering in the tens of billions of compounds---and scoring functions of interest, a routine virtual screening campaign may be limited to scoring fewer than 0.1% of the available compounds, leaving potentially many high scoring compounds undiscovered. Furthermore, as constraints (and sometimes objectives) change during the course of a virtual screening campaign, existing virtual screening algorithms typically offer little room for amortization. We propose the approximate-but-exhaustive search protocol for CSLs, or APEX. APEX utilizes a neural network surrogate that exploits the structure of CSLs in the prediction of objectives and constraints to make full enumeration on a consumer GPU possible in under a minute, allowing for exact retrieval of approximate top-k sets. To demonstrate APEX's capabilities, we develop a benchmark CSL comprised of more than 10 million compounds, all of which have been annotated with their docking scores on five medically relevant targets along with physicohemical properties measured with RDKit such that, for any objective and set of constraints, the ground truth top-k compounds can be identified and compared against the retrievals from any virtual screening algorithm. We show APEX's consistently strong performance both in retrieval accuracy and runtime compared to alternative methods.

Hao-Yi Lei, Zhi-Hao Tan, Zhi-Hua Zhou

The *learnware* paradigm aims to enable users to leverage numerous existing high-performing models instead of building machine learning models from scratch. A learnware consists of a submitted model together with a *specification* derived from the developer’s training data. As the key component, a specification should characterize the capabilities of the model, enabling it to be adequately identified and reused, while preserving the developer's original data. In this paper, we present the first formal study of the risks that arise when a specification is attached to a model, as opposed to releasing the model alone. We develop a game-theoretic framework and, by combining variational inference with geometry analysis, provide quantitative estimates of the resulting risk of specification. Our analysis provides theoretical guarantees on the data protection ability for the commonly adopted RKME specification. Finally, we prove that with a properly chosen size of specification, releasing the specification alongside the model introduces almost no additional risk of exposing the raw data, while still retaining sufficient information for effective learnware identification.

Social Aspects · Safety

Jiajia Li, Xiaoyu Wen, Shuyue Hu, Qiaosheng Zhang, Zhen Wang

The growing capabilities of large language models (LLMs) have driven their widespread deployment across diverse domains, even in potentially high-risk scenarios. Despite advances in safety alignment techniques, current models remain vulnerable to emerging *persona-based jailbreak attacks*. Existing research on persona-based jailbreak has primarily focused on attack iterations, yet it lacks systemic and mechanistic constraints on the defense side. To address this challenge, we propose Persona-Invariant Alignment (PIA), an adversarial self-play framework that achieves co-evolution through Persona Lineage Evolution (PLE) on the attack side and Persona-Invariant Consistency Learning (PICL) on the defense side. Theoretically, PICL is grounded in the *structural separation hypothesis*, using a unilateral KL-divergence constraint to enable the structural decoupling of safety decisions from persona context, thereby maintaining safe behavior under persona-based jailbreak attacks. Experimental results demonstrate that PLE efficiently explores high-risk persona spaces by leveraging lineage-based credit propagation. Meanwhile, the PICL defense method significantly reduces the Attack Success Rate (ASR) while preserving the model's general capability, thereby validating the superiority and robustness of this alignment paradigm. WARNING: This paper contains potentially offensive and harmful text.

Social Aspects · Security

Yaofei Wang, Yufeng Zheng, Han Fang, Wenzhao Cao, Donghui Hu

Messages embedded in diffusion generation noise suffer from severe attenuation due to denoising and VAE decoding, creating a persistent capacity–robustness trade-off. Identifying that extraction accuracy strictly correlates with the distance between candidate hypothesis images, we propose ASIR, a training-free and provably secure steganography framework for both pixel and latent diffusion models. ASIR introduces two key innovations: (i) Antipodal Sampling, which maximizes signal separation in probability space to enhance distinguishability, and (ii) Iterative Recovery, a paradigm shift that treats extraction as a gradient-based optimization problem to reverse non-linear distortions. Extensive experiments demonstrate that ASIR achieves state-of-the-art performance, embedding up to 65,536 bits (pixel-space) and 16,384 bits (latent-space) with 99\% accuracy, while remaining statistically undetectable to deep steganalyzers.

Deep Learning · Large Language Models

Yirui Zhan, Xu, Jun Gao

In correctness-sensitive scenarios, it is crucial for Large Language Models (LLMs) to strictly follow the provided evidence. However, even with reference texts, models often suffer from hallucinations, especially when processing long contexts. Existing work attempts to reinforce the use of citations through Retrieval-Augmented Generation (RAG) or post-hoc methods, while citations remain a probabilistic output rather than a foundation for the generated content. To address this, we propose Guidance, which aims to correct outputs and naturally incorporate citations during the LLM decoding phase. Specifically, we first build a structured fact pool (Prefix-Tail pairs) from the documents. Then, during inference, Guidance predicts the model's intent using a lookahead strategy. When it detects a match with a context prefix, it automatically replaces the output with the verified fact and its citation. This approach is training-free and can be plugged into general-purpose or citation-fine-tuned LLMs. Experiments on LongBench-Cite demonstrate that Guidance improves the citation F1 score by 11.2\% over state-of-the-art baselines. The source code is available at: https://anonymous.4open.science/r/Guidance-D870/.

Social Aspects · Safety

Xiaoyu Wen, Zhida He, Han Qi, Ziyu Wan, Zhongtian Ma, Ying Wen, Tianhang Zheng, Xingcheng Xu, Chaochao Lu, Qiaosheng Zhang

Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we introduce \textbf{MAGIC}, a novel multi-turn multi-agent reinforcement learning framework that formulates LLM safety alignment as an adversarial asymmetric game. Specifically, an attacker agent learns to iteratively rewrite original queries into deceptive prompts, while a defender agent simultaneously optimizes its policy to recognize and refuse such inputs. This dynamic process triggers a \textbf{co-evolution}, where the attacker's ever-changing strategies continuously uncover long-tail vulnerabilities, driving the defender to generalize to unseen attack patterns. Remarkably, we observe that the attacker, endowed with initial reasoning ability, evolves \textbf{novel, previously unseen combinatorial strategies} through iterative RL training, underscoring our method’s substantial potential. Theoretically, we provide insights into a more robust game equilibrium and derive safety guarantees. Extensive experiments validate our framework's effectiveness, demonstrating superior defense success rates without compromising the helpfulness of the model.

Qibing Ren, Xinhao Song, Ke Fan, Lijun Li, Zhanpeng Zhou, Gongshen Liu, Junchi Yan, Lizhuang Ma, Jing Shao

The capabilities of large language models (LLMs), particularly large reasoning models (LRMs), are rapidly advancing. This raises concerns about whether LRMs can maintain their safety awareness throughout long-form reasoning. Frustratingly, we identify a prevalent safety issue across LLMs and LRMs, where LRMs can reveal dangerous thoughts, leading to harmful knowledge elicitation when confronting sensitive yet benign topics. For example, when explaining the chemical context of Lewisite, a biological weapon, LRMs analyze its synthesis in their reasoning without recognizing the associated risks. We refer to this issue as the unintended elicitation issue. Experiments on our benchmark show that it is a common issue across current LRMs due to their strong multi-step reasoning capabilities. To address this issue, we propose placing LLMs in our synthesized open-ended environments, allowing them to self-search for a safety reasoning pattern to respond responsibly and helpfully. We first design a scalable data synthesis pipeline to generate data that triggers the ``unintended elicitation'' issue. We further propose a safety-first reward model design, which prioritizes safety while also evaluating the helpfulness of responses and the faithfulness of reasoning. Experiments show that our method improves safety, reduces over-refusal, and maintains strong helpfulness, paving the way for safer deployment in high-stakes domains.

General Machine Learning · Evaluation

YongKyung Oh

State-of-the-Art (SOTA) claims pervade Artificial Intelligence (AI) and Machine Learning (ML) research. These claims rest on benchmark evaluations, where models are ranked by aggregate scores across tasks. Public leaderboards are the most visible instance, but the same structure appears in paper tables throughout the literature. However, such minimal evidence often cannot support these strong claims. We identify a widespread claim-evidence gap in AI benchmarking. Claiming SOTA implies robust superiority. It suggests that a model significantly outperforms alternatives across most tasks. However, a marginal improvement in the mean score merely indicates a top average rank rather than true superiority. Analyzing ten cross-domain benchmarks from public leaderboards, we found that in more than half of top-model comparisons, at least one commonly assumed property of superiority does not hold. These properties include meaningful effect size, consistency across tasks, or robustness to dataset removal. Instead, aggregate gains are frequently driven by outlier datasets. This fragility persists even in benchmarks with many tasks. We argue that claim language should reflect the strength of the underlying evidence. This requires no additional experiments, only honest reporting of what results actually show.

Deep Learning · Large Language Models

Valentin NOËL

Validating mathematical reasoning in large language models currently requires a trade-off between computationally expensive learned verifiers and the unreliability of output-based heuristics. We therefore propose a training-free, mechanistic alternative: spectral analysis of attention topology. By treating attention matrices as dynamic graphs over tokens, we extract four interpretable spectral diagnostics, Fiedler value, High-Frequency Energy Ratio (HFER), spectral entropy, and graph smoothness, that differentiate valid reasoning from hallucinated outputs without any learned parameters. We perform experiments across seven models from four architectural families (Llama, Qwen, Phi, Mistral) yield effect sizes up to Cohen's $d = 3.30$ ($p < 10^{-116}$), enabling $85$--$96\%$ classification accuracy with a single threshold. We discover that spectral analysis detects logical coherence rather than compiler acceptance: proofs rejected by formal verifiers due to timeouts or missing imports are correctly identified as valid, a phenomenon we term "Platonic validity". Furthermore, causal ablation studies confirm that this spectral signature reflects the functional health of induction head circuits, establishing a mechanistic basis for the method. We also identify an architectural dependency: Sliding Window Attention shifts the discriminative signal from HFER to late-layer smoothness ($d = 2.09$, $p < 10^{-48}$), demonstrating that attention mechanism design determines which spectral features capture reasoning validity. The method generalizes to informal chain-of-thought reasoning ($d = 0.78$, $p < 10^{-3}$). These findings establish spectral graph analysis as a principled framework for reasoning verification, with immediate applications to hallucination detection and real-time safety monitoring.

General Machine Learning · Evaluation

Anna Genevaux, Simon Frieder

This position paper argues that documentation is infrastructure for reproducible geometry reasoning: a benchmark for formal geometry problems to test AI systems is not usable in research unless its documented vocabulary is matched by executable, versioned behavior and minimal runnable examples. We use JGEX (as implemented by Newclid) as a case study of how documentation--implementation gaps and missing examples can silently constrain expressivity, fragment tool interoperability, and bias benchmark construction. To make our point, we introduce "A JGEX Dataset", a curated collection of $78$ Euclidean geometry problems with (i) original natural-language statements and sources, (ii) a JGEX-oriented rewrite that makes formalization steps explicit, (iii) executable JGEX code validated under a pinned solver version, and (iv) rich metadata. To make the target language auditable, we also provide a predicate-level support matrix for the $33$ documented predicates, generated from minimal test instances, and categorize predicates as supported, unsupported, or unstable due to missing accessible examples. Finally, we release validation scripts and a concise tutorial with worked walk-throughs. Our broader claim is that benchmark authors, tool maintainers, and reviewers should treat language documentation and conformance evidence as first-class artifacts—on par with datasets and evaluation code—if cross-tool, cross-version reproducibility is the goal.

Reinforcement Learning · Planning

Michael Katz, Harsha Kokel, Christian Muise, Shirin Sohrabi, Sarath Sreedharan

In over sixty years since its inception, the field of planning has made significant contributions to both the theory and practice of building planning software that can solve a never-before-seen planning problem. This was done through established practices of rigorous design and evaluation of planning systems. **It is our position that this rigor should be applied to the current trend of work on planning with large language models.** One way to do so is by correctly incorporating the insights, tools, and data from the automated planning community into the design and evaluation of LLM-based planners. The experience and expertise of the planning community could play a crucial role in accelerating the development of LLM-based planners. This position is particularly important in light of the abundance of recent works that replicate and propagate the same pitfalls that the planning community has encountered and learned from. We believe that establishing practices that avoid such known pitfalls will contribute greatly to the progress in building LLM-based planners and to planning in general.

Social Aspects · Safety

Enrico Cassano, Riccardo Renzulli, Marco Nurisso, Mirko Zaffaroni, Alan Perotti, Marco Grangetto

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse autoencoder framework that overcomes this by enforcing one-to-one concept-neuron mappings. By systematically labeling concepts during training, our method achieves feature centralization, binding each concept to a single, interpretable neuron. This enables highly targeted and efficient concept erasure. SAEmnesia reduces hyperparameter search by 96.7% and achieves a 9.2% improvement over the state-of-the-art on the UnlearnCanvas benchmark. Our method also demonstrates superior scalability in sequential unlearning, improving accuracy by 28.4% when removing nine objects, establishing a new standard for precise and controllable concept erasure. Moreover, SAEmnesia mitigates the possibility of generating unwanted content under adversarial attack and effectively removes nudity when evaluated with I2P.

Applications · Everything Else

Wenbin Xing, Quanxing Zha, Lizheng Zu, Mengran Li, Ming Li, Junchi Yan

Current research on video hallucination mitigation primarily focuses on isolated error types, leaving *compositional* hallucinations—arising from incorrect reasoning over multiple interacting spatial and temporal factors largely underexplored. We introduce **OmniVCHall**, a benchmark designed to systematically evaluate both isolated and compositional hallucinations in video multimodal large language models (VLLMs). OmniVCHall spans diverse video domains, introduces a novel camera-based hallucination type, and defines a fine-grained taxonomy, together with adversarial answer options (*e.g.*, “All are correct” and “None of the above”) to prevent shortcut reasoning. The evaluations of 39 representative VLLMs reveal that even advanced models (*e.g.*, Qwen3-VL and GPT-5) exhibit substantial performance degradation. We propose **TriCD**, a contrastive decoding framework with a triple-pathway calibration mechanism. An adaptive perturbation controller dynamically selects distracting operations to construct negative video variants, while a saliency-guided enhancement module adaptively reinforces grounded token-wise visual evidences. These components are optimized via reinforcement learning to encourage precise decision-making under compositional hallucination settings. Experimental results show that TriCD consistently improves performance across two representative backbones, achieving an average accuracy improvement of over 10\%.

Reinforcement Learning · Batch/Offline

Hojun Chung, Junseo Lee, Songhwai Oh

Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. However, it often suffers from compounding errors due to repeated model inference. While geometric horizon models (GHM) alleviate this issue through direct prediction over a discounted infinite-horizon future, they remain challenged in accurately modeling distant future states. To this end, we introduce universal horizon models (UHM), a generalization of GHM that directly predicts future states under arbitrary horizons. Leveraging this flexibility, we propose a scalable value learning method that employs a winsorized horizon distribution to stabilize training by capping excessively large horizons. Experimental results on 100 challenging OGBench tasks demonstrate that the proposed method outperforms competitive baselines, particularly on tasks with highly sub-optimal datasets and those requiring long-horizon reasoning.

Deep Learning · Generative Models and Autoencoders

Junseo Bang, Dong Ju Mun, Hoigi Seo, Seongmin Hong, Se Young Chun

Generative posterior sampling using diffusion models has emerged as a dominant paradigm for solving inverse problems in imaging, which usually consists of three main components: data consistency (DC) guidance, classifier-free guidance (CFG) and stochasticity. While prior arts have focused on how to develop each or all components, less attention has given to how to schedule them, leading to heuristically fixed or partially adjusted suboptimal schedules. In this work, we argue that the interactions among all three components in terms of scheduling are crucial for significantly improved performance in solving inverse problems in imaging. Our analysis shows that aggressive CFG early in sampling conflict with DC guidance, while stochasticity brings the trajectory back to higher-probability regions. Based on these findings, we propose Triadic Dynamics Aware Posterior Sampling (TriPS), which reformulates posterior sampling as a time-varying control problem and optimizes schedules following a triadic trend of decreasing DC and stochasticity scales alongside increasing CFG scale. TriPS achieves this through two strategies: template-based search over functional priors for reliable baseline schedules, and Group Relative Policy Optimization (GRPO)-based reinforcement learning for more flexible temporal curves. Experiments demonstrate TriPS outperforms state-of-the-art baselines in data fidelity and perceptual realism.

Probabilistic Methods · Monte Carlo and Sampling Methods

Francisco M Castro-Macías, Pablo Morales-Alvarez, Saifuddin Syed, Daniel Hernández-Lobato, Rafael Molina, Jose Miguel Hernandez-Lobato

Sampling from unnormalized multimodal distributions with limited density evaluations remains a fundamental challenge in machine learning and natural sciences. Successful approaches construct a bridge between a tractable reference and the target distribution. Parallel Tempering (PT) serves as the gold standard, while recent diffusion-based approaches offer a continuous alternative at the cost of neural training. In this work, we introduce Conditional Diffusion Sampling (CDS), a framework that combines these two paradigms. To this end, we derive Conditional Interpolants, a class of stochastic processes whose transport dynamics are governed by an exact, closed-form stochastic differential equation (SDE), requiring no neural approximation. Although these dynamics require sampling from a non-trivial initialization distribution, we show both theoretically and empirically that the cost of this initialization diminishes for sufficiently short diffusion times. CDS leverages this by a two-stage procedure: (1) PT is used to efficiently sample the initial distribution, and then (2) samples are transported via the transport SDE. This combination couples the robust global exploration of PT with efficient local transport. Experiments suggest that CDS has the potential to achieve a superior trade-off between sample quality and density evaluation cost compared to state-of-the-art samplers.