论文

面向第 11 届 ABAW 挑战赛的多任务学习系统，在标准确定性架构基础上扩展条件 Rectified Flow 头，建模真实场景下面部行为固有的模糊性，借助蒙特卡洛采样实现不确定性感知的一对多预测。A multi-task learning system for the 11th ABAW challenge that extends a standard deterministic architecture with a conditional rectified-flow head to model the inherent ambiguity of in-the-wild facial behavior, enabling uncertainty-aware one-to-many predictions through Monte Carlo sampling.

压缩可减少推理 token 并保持大部分选择题准确率，同时提示影响接近基线——在一个前沿条件下，降低推理成本移除的证据比单纯缩短轨迹所预期的更多。Compression reduces reasoning tokens and preserves most multiple choice accuracy, while hint influence remains near baseline, in a frontier where reducing reasoning costs removes more evidence than shorter traces alone would predict.

研究表明模型具备相关子群体知识，但难以稳定传递到聚合估计中，这一差距使统计自一致性成为评估 LLM 的尚未饱和、无需参考的准则。It is suggested that models possess relevant subpopulation knowledge but do not reliably propagate it into aggregate estimates, and this gap establishes statistical self-consistency as an unsaturated, reference-free criterion for evaluating LLMs.

本文对 OPD 的作用、病态与调控进行系统研究，厘清 OPD 作为探索催化剂的角色，并证实调控良好的信号质量（而非单纯的教师模型规模）才是 OPD 中成功探索的主导因素。A systematic study examining the role, pathologies, and regulations of OPD, clarifying the role of OPD as an exploration catalyst and confirming that well-regulated signal quality, rather than mere teacher scale, governs successful exploration in OPD.

结果表明稳定的循环深度需要计入参数访问次数（而非仅名义层数）的残差缩放规则；DeepLoop 在不存在物理块被重复访问时表现为中性，一旦启用循环深度则改善验证损失与下游准确率。The results show that stable recurrent depth requires residual scaling rules that account for parameter visits, not only nominal layer count, and DeepLoop is neutral when no physical block is revisited and improves validation loss and downstream accuracy once recurrent depth is activated.

本文提出 UniVR，这是首个从纯视觉演示中同时学习复杂推理、细粒度物理动力学和长期规划的研究，并配套首个在纯视觉协议下评估这些异质能力的综合评测套件。UniVR, the first investigation into simultaneously learning complex reasoning, fine-grained physical dynamics, and long-term planning from pure visual demonstrations, is introduced, the first comprehensive suite to assess these heterogeneous capabilities under a purely visual protocol.

提出一个多 Agent 框架，通过结合监督微调、直接偏好优化和检索增强生成 (RAG) 来调和事实基础与意识形态对齐，产生稳定的胜者和排名，且以宣言为锚的谱系能可靠预测现实世界中的实现，而幻觉内容则不能。A multi-agent framework that reconciles factual grounding with ideological alignment by combining Supervised Fine-Tuning, Direct Preference Optimization, and Retrieval-Augmented Generation is presented, which yields a stable winner and ranking, and manifesto-anchored lineage reliably predicts real-world materialization whereas hallucinated content does not.

提出 GRASP，一个用于训练智能体在多步推理过程中自适应协调互补检索工具的强化学习（RL）框架，并指出学会协调检索信号与上下文粒度对智能体的正确推理至关重要。GRASP is introduced, a reinforcement learning (RL) framework for training agents to adaptively coordinate complementary retrieval tools during multi-step reasoning, and it is suggested that learning to coordinate retrieval signals and context granularity is critical for agent's correct reasoning.

本文提出 HDR (Hierarchical Denoising for Visual Reasoning)，一个将层级潜变量集成到因果视频生成中以进行多步推理的统一框架，并引入一个含分布外情况的层级化多步视频推理基准。This work proposes HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning and introduces a level-stratified multi-step video reasoning benchmark with out-of-distribution cases.

提出 Hy-Embodied-RxBrain，一个具备语言-视觉联合推理与想象的具身认知基础模型，并将其扩展到连续机器人动作生成，在无需大规模动作数据预训练的情况下展现出可观的真实机器人性能。Hy-Embodied-RxBrain, an embodied cognition foundation model with joint language-visual reasoning and imagination, is introduced and extended to continuous robot action generation, where it shows promising real-robot performance without large-scale action-data pretraining.

提出 Chat2Scenic，是首个以领域特定语言 (DSL) 生成场景脚本的迭代式检索增强框架，并构建了一个涵盖 NHTSA、联合国车辆法规及其他来源共 123 个场景的开源场景生成基准。Chat2Scenic is presented, the first iterative retrieval-augmented framework to generate scenario scripts in Domain Specific Language (DSL) and proposes an open benchmark for scenario generation comprising 123 scenarios from various regulations, including NHTSA and United Nations Vehicle Regulations, as well as other sources.

发现对 GPT 语言模型进行重复采样，是为困难 prompt 生成可用解的一种出乎意料的有效策略，并讨论了部署强大代码生成技术在安全性、安全保障与经济等方面的潜在更广泛影响。It is found that repeated sampling from the GPT language model is a surprisingly effective strategy for producing working solutions to difficult prompts, and the potential broader impacts of deploying powerful code generation technologies, covering safety, security, and economics are discussed.

提出 Flamingo，一个 VLM 系列，能够桥接强大的纯视觉与纯语言预训练模型，处理任意交错排列的图文序列，并无缝接收图像或视频作为输入。This work introduces Flamingo, a family of Visual Language Models (VLM) with this ability to bridge powerful pretrained vision-only and language-only models, handle sequences of arbitrarily interleaved visual and textual data, and seamlessly ingest images or videos as inputs.

提出 BloombergGPT，一个 500 亿参数的语言模型，在广泛的金融数据上训练而成，并基于 Bloomberg 丰富的数据源构建了包含 3630 亿 token 的数据集，可能是迄今最大的领域专用数据集。This work presents BloombergGPT, a 50 billion parameter language model that is trained on a wide range of financial data, and constructs a 363 billion token dataset based on Bloomberg's extensive data sources, perhaps the largest domain-specific dataset yet.

Gemini 1.5 在跨模态长上下文检索任务上取得近乎完美的召回率，在长文档 QA、长视频 QA 与长上下文 ASR 上刷新 SOTA，并在广泛基准上达到或超越 Gemini 1.0 Ultra 的 SOTA 表现。Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks.

Reflexion 是一个通过语言反馈而非更新权重来强化语言 agent 的新框架，在多种任务（序贯决策、编程、语言推理）上相较基线 agent 取得显著提升。Reflexion is a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback, which obtains significant improvements over a baseline agent across diverse tasks (sequential decision-making, coding, language reasoning).

HuggingGPT 是一个由 LLM 驱动的 Agent，利用 LLM（如 ChatGPT）连接机器学习社区中的各种 AI 模型以解决 AI 任务，能够处理跨模态、跨领域的大量复杂 AI 任务。HuggingGPT is an LLM-powered agent that leverages LLMs (e.g., ChatGPT) to connect various AI models in machine learning communities to solve AI tasks and can tackle a wide range of sophisticated AI tasks spanning different modalities and domains.

实验表明，与语言模型类似，视觉模型也会学习利用全局捷径，从而无法在任务长度或复杂度上泛化，但本文证明基于严格局部感知的循环视觉策略可以缓解这些失败，从而使模型在这些任务上具备泛化能力。The experiments reveal that, similar to language models, vision models can learn to exploit global shortcuts and thereby fail to generalize over task length or complexity, but it is shown that recurrent vision policies based on strictly local perception can mitigate these failures, thereby allowing models to generalize on these tasks.

综合评估表明，DeepSeek-V3 优于其他开源模型，并达到与领先闭源模型相当的性能。Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models.

本文在交通微观仿真器 SUMO 中应用现代深度强化学习方法构建一个真正自适应的交通信号控制智能体，并采用一种新的状态空间——离散交通状态编码——其信息密度较高。This work applies modern deep reinforcement learning methods to build a truly adaptive traffic signal control agent in the traffic microsimulator SUMO, using a new state space, the discrete traffic state encoding, which is information dense.

该模型在效果上匹配基于优化的方法，同时实现近 800 倍加速，并以明显更少的参数量和更低的训练/推理开销超越 SOTA 可泛化模型的零样本性能，整体效率显著提升。This model matches optimization-based methods while delivering nearly 800x speedup, and surpasses the zero-shot performance of state-of-the-art generalizable models with markedly fewer parameters and reduced training/inference overhead, achieving an overall efficiency improvement.

本文提出 token 时间连续扩散 (TTCD)，一种新的扩散语言模型，运行于连续空间，将高斯噪声确定性地映射到最终的 token canvas 而无需额外采样，并引入每个 token 时间的新概念。This paper introduces token time continuous diffusion (TTCD), a new diffusion language model which operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and incorporates a new notion of per-token times.

提出 Lucid，一个黑盒对抗框架，在严格的图像受限威胁模型下攻击多模态记忆管道，无需访问目标 MLLM、目标检索编码器或文本通道，揭示了多模态记忆管道中的结构性漏洞。Lucid is proposed, a black-box adversarial framework that compromises multimodal memory pipelines under a strictly image-bounded threat model, requiring no access to the target MLLM, target retrieval encoder, or the text channel, exposing a structural vulnerability in multimodal memory pipelines.

S1-Omni 基于 S1-Omni-Corpus 训练，覆盖 200 个科学任务并包含数百万推理样本，在 60 余个科学基准上进行了评估，为统一的科学建模提供了一条可行路径。S1-Omni is trained on S1-Omni-Corpus, which covers 200 scientific tasks and contains millions of reasoning samples, and is evaluated on over 60 scientific benchmarks, providing a practical path toward unified scientific modeling.

提出数据科学世界模型概念，通过基于当前工作流状态和候选操作预测环境状态转移来建模数据科学执行环境；提出DSWorld框架，结合结构化状态构建、成本感知路由、轻量级真实执行以及基于LLM的昂贵操作模拟器。The concept of Data Science World Model is introduced, which model the data science execution environment by predicting environment state transitions conditioned on current workflow states and candidate operations and proposes DSWorld, a practical framework that combines structured state construction, cost-aware routing, lightweight real execution, and an LLM-based simulator for expensive operations.

Xiaomi-Robotics-1是一个强大的机器人基础策略，能在复杂灵巧任务上以高数据效率高效微调，并在多个仿真基准上超越SOTA方法。Xiao-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency and across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods.

提出xHC（扩展型超连接），是首个在N=4之外实现有意义扩展的HC系列方法；引入xHC-Flash，将每个子层的内存访问量从73.5C降至40C（与mHC在N=4时的34C相当），同时保留完整xHC带来的性能增益。This work proposes xHC (Expanded Hyper-Connections), the first HC-family method to achieve meaningful expansion beyond $N{=}4$ and introduces xHC-Flash, which reduces the per-sublayer memory traffic from $73.5C$ to $40C, comparable to the $34C$ required by mHC at $N{=}4$, while retaining the gains of full xHC.

表明差值信号显著提升在策略蒸馏效果，提出新方法称为在策略差值蒸馏（OPD），使推理LLM仅需短暂的后训练即可获得强性能。It is shown that the delta signal substantially improves on-policy distillation and the new distillation method is referred to as On-Policy Delta Distillation (OPD), enabling reasoning LLMs to achieve strong performance with only a short post-training period.

VideoRAE是一种表征自编码器，利用冻结视频基础编码器的多尺度分层特征，并通过轻量级1D自注意力投影器进行压缩，验证了冻结VFM表征可作为通用且利于生成的视频潜变量。VideoRAE is a representation autoencoder that leverages multi-scale hierarchical features from a frozen video foundation encoder and compresses them with a lightweight 1D self-attention projector to validate frozen VFM representations as versatile and generation-friendly video latents.

RAGU是一个开源模块化GraphRAG引擎，通过将抽取与整合分离来解决抽取-整合问题：实体和关系经过两阶段类型化抽取、基于DBSCAN的去重、LLM摘要和Leiden社区检测。RAGU, an open-source modular GraphRAG engine, addresses extraction from consolidation by separating extraction from consolidation: entities and relations pass through two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection.

TARS是一个集成在Visual Studio Code中的LLM驱动Agent，通过直接锚定到被分析代码的自主解释来支持程序理解，基于轻量级心智理论范式构建。TARS is an LLM-powered agent integrated into Visual Studio Code that supports program comprehension through autonomous explanations anchored directly to the code under analysis, built around a lightweight Theory of Mind paradigm.

在一个 recipe 级操作机制中，fan-in Muon 在共享 KL 与 clipping 下支持更激进的稳定有效步长：该余量在优化仍有空间时最大，而在接近饱和、经 AdamW 调参后或使用 magnitude matching 时收缩。A recipe-level operating regime in which fan-in Muon supports a more aggressive stable effective step under shared KL and clipping is identified: the margin is largest when optimization headroom remains and contracts near saturation, after AdamW tuning, or under magnitude matching.

提出RESOURCE2SKILL框架，将教程视频、仓库、文章和参考制品等多模态资源蒸馏为软件Agent的可执行技能，并验证了多模态技能格式、层次化组织、来源多样性、选择策略与在线获取的价值。RESOURCE2SKILL is presented, a framework that distills multimodal resources, including tutorial videos, repositories, articles, and reference artifacts, into executable skills for software agents, and confirms the value of multimodal skill format, hierarchical organization, source diversity, selection strategy, and online acquisition.

本文回顾现有方法，并融合多种技术从数据与模型规模两方面扩展预训练，提出一条自动化流水线以构建专用、多样且经过筛选的图像数据集，替代自监督文献中常用的未筛选数据。This work revisits existing approaches and combines different techniques to scale the pretraining in terms of data and model size, and proposes an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature.

BLIP-2 在多种视觉-语言任务上取得 SOTA 性能，可训练参数远少于现有方法，并展现出遵循自然语言指令进行零样本图生文的新兴能力。BLIP-2 achieves state-of-the-art performance on various vision-language tasks, despite having significantly fewer trainable parameters than existing methods, and is demonstrated's emerging capabilities of zero-shot image-to-text generation that can follow natural language instructions.

一种面向语言模型推理的新框架 Tree of Thoughts (ToT)，推广了流行的 Chain of Thought 提示方法，允许在作为问题求解中间步骤的连贯文本单元（thoughts）上进行探索。A new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving.