HuggingFace 每日AI论文速递 - 节目列表

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:32] 🔍 WildDet3D: Scaling Promptable 3D Detection in the Wild（WildDet3D：可扩展的野外可提示三维检测）[01:39] 🔧 FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios（FORGE：面向制造场景的细粒度多模态评估）[02:25] 🔍 RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details（RefineAnything：面向完美局部细节的多模态区域特定精细化）[02:58] 🔍 EXAONE 4.5 Technical Report（EXAONE 4.5 技术报告）[03:56] 🎮 Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory（Matrix-Game 3.0：具备长时记忆的实时流式交互世界模型）[04:47] ⚡ ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion（ECHO：基于一步块扩散的高效胸部X光报告生成）[05:40] ♻ ELT: Elastic Looped Transformers for Visual Generation（ELT：用于视觉生成的弹性循环Transformer）[06:25] 🔍 VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images（VisionFoundry：利用合成图像教授视觉语言模型视觉感知）[07:19] 🧠 Structured Causal Video Reasoning via Multi-Objective Alignment（通过多目标对齐实现结构化因果视频推理）[08:11] ⚠ Backdoor Attacks on Decentralised Post-Training（去中心化后训练中的后门攻击）[08:58] 🧠 AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents（AgentSwing：面向长视野网络智能体的自适应并行上下文管理路由）[09:55] ⚠ Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism（大语言模型通过一种独特且统一的机制生成有害内容）[10:49] 🎭 Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video（面向说话人脸视频情感编辑的跨模态情感迁移）[11:28] 🔍 ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery（ScheMatiQ：从研究问题到结构化数据——通过交互式模式发现）[12:17] 🔍 $p1$: Better Prompt Optimization with Fewer Prompts（p1：用更少的提示实现更好的提示优化）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 5 篇论文如下：[00:44] TOP1(🔥367) | 📈 Adam's Law: Textual Frequency Law on Large Language Models（亚当定律：大语言模型上的文本频率定律）[03:01] TOP2(🔥347) | 🏆 GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning（GrandCode：通过智能体强化学习在竞技编程中达到宗师级水平）[05:12] TOP3(🔥227) | 🧠 Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability（重新审视推理监督微调中的泛化问题：关于优化、数据与模型能力的条件性分析）[07:10] TOP4(🔥225) | 🤖 InCoder-32B-Thinking: Industrial Code World Model for Thinking（InCoder-32B-Thinking：面向思考的工业代码世界模型）[09:42] TOP5(🔥225) | 🎯 Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding（Video-MME-v2：迈向全面视频理解基准的下一个阶段）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:33] 🧬 SkillClaw: Let Skills Evolve Collectively with Agentic Evolver（SkillClaw：让技能在智能体演化器中集体进化）[01:24] 🔢 When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models（当数字说话：在文本到视频扩散模型中实现文本数字与视觉实例的对齐）[02:22] 🎨 MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping（MegaStyle：通过一致的文本到图像风格映射构建多样且可扩展的风格数据集）[03:15] 🤖 HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents（HY-Embodied-0.5：面向现实世界智能体的具身基础模型）[04:07] 🧠 Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability（重新审视推理监督微调中的泛化问题：关于优化、数据与模型能力的条件性分析）[04:52] 🤖 ClawBench: Can AI Agents Complete Everyday Online Tasks?（ClawBench：AI智能体能否完成日常在线任务？）[05:31] 📱 KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation（KnowU-Bench：迈向交互式、主动式与个性化的移动代理评估）[06:18] 🧠 Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering（LLM智能体中的外部化：对记忆、技能、协议与治理工程的一体化综述）[07:09] 🎭 LPM 1.0: Video-based Character Performance Model（LPM 1.0：基于视频的角色表演模型）[07:58] 🧠 OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence（OpenSpatial：一个赋能空间智能的原则性数据引擎）[08:50] 🧠 Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models（明智行动：在智能多模态模型中培养元认知工具使用能力）[09:41] ⚡ DMax: Aggressive Parallel Decoding for dLLMs（DMax：面向扩散语言模型的激进并行解码）[10:20] 🧠 Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills（技能图谱：面向海量智能体技能的依赖感知结构化检索方法）[11:02] 🧩 OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering（OmniJigsaw：通过模态编排重排序增强全模态推理）[11:41] 🧠 OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks（OpenVLThinkerV2：一个面向多领域视觉任务的通用多模态推理模型）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:31] 🧠 RAGEN-2: Reasoning Collapse in Agentic RL（RAGEN-2：智能体强化学习中的推理崩溃）[01:21] 🎨 Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning（以笔画思考，而非像素：通过交错推理实现过程驱动的图像生成）[02:00] ⚡ MARS: Enabling Autoregressive Models Multi-Token Generation（MARS：实现自回归模型的多令牌生成）[02:51] 🌍 INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling（INSPATIO-WORLD：基于时空自回归建模的实时4D世界模拟器）[03:48] 🔬 SEVerA: Verified Synthesis of Self-Evolving Agents（SEVerA：可验证自进化智能体的合成）[04:41] 🔍 TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders（TC-AE：解锁深度压缩自编码器的令牌容量）[05:26] ⚡ FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling（FP4探索，BF16训练：通过高效扩展rollout的扩散模型强化学习）[06:17] 🔄 FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching（FlowInOne：将多模态生成统一为图像输入-图像输出的流匹配）[07:00] 🧠 Neural Computers（神经计算机）[07:37] 🎯 Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization（个性化奖励模型基准：基于人类对齐个性化的奖励模型评估）[08:22] 💡 Learning to Hint for Reinforcement Learning（强化学习的提示学习）[09:11] 🧠 Fast Spatial Memory with Elastic Test-Time Training（基于弹性测试时训练的高速空间记忆）[09:44] 🎬 MoRight: Motion Control Done Right（MoRight：正确的运动控制）[10:21] 🌐 Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment（通过跨语言对齐提升信息检索中的语义邻近性）[11:02] 📊 Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval（超越困难负样本：知识蒸馏中分数分布对稠密检索的重要性）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:34] 🎯 Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding（Video-MME-v2：迈向全面视频理解基准的下一个阶段）[01:19] 🔬 Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents（Claw-Eval：迈向可信赖的自主智能体评估）[02:06] 🤖 Learning to Retrieve from Agent Trajectories（从智能体轨迹中学习检索）[02:53] 🧪 ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation（ACES：谁来测试测试？代码生成的留一法AUC一致性）[03:42] 👗 Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision（Vanast：基于合成三元组监督的虚拟试穿与人体图像动画）[04:31] ⏱ Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning（超越准确率：揭示工具集成推理中的低效模式）[05:23] 🧠 ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement（ThinkTwice：联合优化大型语言模型的推理与自我精炼能力）[06:03] 🔍 Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework（论文圈：一个开源的多智能体研究文献发现与分析框架）[06:52] 🔍 How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings（智能体技能在真实场景中的效用评估：基准测试LLM在现实环境下的技能使用）[07:33] 🚀 MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU（MegaTrain：在单GPU上全精度训练1000亿+参数大语言模型）[08:11] 🛠 DARE: Diffusion Large Language Models Alignment and Reinforcement Executor（DARE：扩散大语言模型的对齐与强化执行器）[08:54] 🧠 In-Place Test-Time Training（原位测试时训练）[09:39] 🎬 Watch Before You Answer: Learning from Visually Grounded Post-Training（先看后答：基于视觉基础的后训练学习）[10:13] 🔍 Demystifying When Pruning Works via Representation Hierarchies（通过表征层次解析剪枝何时有效）[10:59] 🤖 Action Images: End-to-End Policy Learning via Multiview Video Generation（动作图像：通过多视角视频生成的端到端策略学习）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:33] 🧠 OpenWorldLib: A Unified Codebase and Definition of Advanced World Models（OpenWorldLib：一个统一代码库与高级世界模型定义）[01:26] 📊 MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale（MinerU2.5-Pro：在规模上突破数据为中心文档解析的极限）[02:07] 🧠 TriAttention: Efficient Long Reasoning with Trigonometric KV Compression（TriAttention：基于三角函数的KV压缩实现高效长序列推理）[02:58] 🎥 AURA: Always-On Understanding and Real-Time Assistance via Video Streams（AURA：基于视频流的持续理解与实时辅助系统）[03:42] 🔍 LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models（LIBERO-Para：面向VLA模型的释义鲁棒性诊断基准与度量）[04:24] 🎯 SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing（SpatialEdit：细粒度图像空间编辑基准测试）[05:07] 📈 Adam's Law: Textual Frequency Law on Large Language Models（亚当定律：大语言模型上的文本频率定律）[05:56] 🗂 FileGram: Grounding Agent Personalization in File-System Behavioral Traces（FileGram：基于文件系统行为轨迹的智能体个性化研究）[06:45] 🧪 ClawArena: Benchmarking AI Agents in Evolving Information Environments（ClawArena：在演化信息环境中对AI智能体进行基准测试）[07:38] 🧠 LightThinker++: From Reasoning Compression to Memory Management（LightThinker++：从推理压缩到内存管理）[08:12] 🔄 Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing（通过样本路由统一组相对与自蒸馏策略优化）[08:50] 🧠 SkillX: Automatically Constructing Skill Knowledge Bases for Agents（SkillX：面向智能体的技能知识库自动构建框架）[09:39] 🤖 Self-Execution Simulation Improves Coding Models（自执行模拟提升代码模型性能）[10:22] 🧠 Vero: An Open RL Recipe for General Visual Reasoning（Vero：一种用于通用视觉推理的开放强化学习方案）[11:12] 🛡 Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw（你的智能体，他们的资产：OpenClaw 的现实世界安全性分析）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:29] 🧠 Self-Distilled RLVR（基于自蒸馏的强化学习与可验证奖励）[01:18] 🎯 A Simple Baseline for Streaming Video Understanding（流式视频理解的简单基线）[02:07] 🔍 Token Warping Helps MLLMs Look from Nearby Viewpoints（Token扭曲助力多模态大语言模型从邻近视角观察）[03:06] 🔍 Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?（Agentic-MME：能动性能力究竟为多模态智能带来了什么？）[03:57] 📈 Test-Time Scaling Makes Overtraining Compute-Optimal（测试时扩展使过度训练达到计算最优）[04:56] 🧠 Communicating about Space: Language-Mediated Spatial Integration Across Partial Views（空间交流：跨局部视角的语言中介空间整合）[05:39] 🏆 GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning（GrandCode：通过智能体强化学习在竞技编程中达到宗师级水平）[06:27] 🤖 InCoder-32B-Thinking: Industrial Code World Model for Thinking（InCoder-32B-Thinking：面向思考的工业代码世界模型）[07:22] 🛡 AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks（AgentSocialBench：评估以人为中心的代理社交网络中的隐私风险）[08:10] ⚠ AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents（AgentHazard：计算机使用智能体有害行为评估基准）[08:52] ⚡ Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression（Swift-SVD：理论最优性与实际效率在低秩大语言模型压缩中的结合）[09:39] 🔍 VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors（视觉语言模型需要词汇：视觉语言模型忽略视觉细节而依赖语义锚点）[10:30] 📊 Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation（Xpertbench：基于量规评估的专家级任务基准）[11:16] 🎬 Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation（Salt：用于快速视频生成的自洽分布匹配与缓存感知训练）[12:04] 🤝 CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning（CoME-VL：扩展互补多编码器视觉语言学习）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 10 篇论文如下：[00:48] TOP1(🔥415) | 🧠 AI Can Learn Scientific Taste（AI可以学习科学品味）[02:41] TOP2(🔥367) | 🧠 Demystifing Video Reasoning（揭秘视频推理机制）[04:53] TOP3(🔥306) | 🏭 InCoder-32B: Code Foundation Model for Industrial Scenarios（InCoder-32B：面向工业场景的代码基础模型）[06:57] TOP4(🔥248) | 🗣 SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models（SocialOmni：全模态模型中视听社交交互能力的基准测试）[08:40] TOP5(🔥210) | 🧠 Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning（强化学习中利用群体级自然语言反馈引导探索）[10:38] TOP6(🔥191) | 🤝 Heterogeneous Agent Collaborative Reinforcement Learning（异构智能体协作强化学习）[12:28] TOP7(🔥184) | 🧩 Utonia: Toward One Encoder for All Point Clouds（Utonia：迈向适用于所有点云的统一编码器）[14:15] TOP8(🔥184) | 🎬 Helios: Real Real-Time Long Video Generation Model（Helios：实时长视频生成模型）[16:46] TOP9(🔥184) | 🤖 MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification（MiroThinker-1.7与H1：通过验证迈向重型研究智能体）[18:47] TOP10(🔥171) | 🧠 Attention Residuals（注意力残差）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 5 篇论文如下：[00:40] TOP1(🔥309) | 🧠 FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization（FIPO：通过未来KL影响策略优化引导深度推理）[02:58] TOP2(🔥302) | 🚁 CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence（CARLA-Air：在CARLA世界中飞行无人机——面向空地具身智能的统一基础设施）[05:23] TOP3(🔥170) | 🛡 ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers（ClawKeeper：通过技能、插件和监视器为OpenClaw代理提供全面的安全保护）[07:56] TOP4(🔥151) | 🎬 ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling（ShotStream：用于交互式叙事的多镜头流式视频生成）[10:17] TOP5(🔥147) | 🧠 Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models（视野之外，记忆犹在：用于动态视频世界模型的混合记忆）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:41] 🔄 DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models（DataFlex：面向大语言模型数据中心化动态训练的统一框架）[01:48] 🧠 The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook（潜在空间：基础、演进、机制、能力与展望）[02:45] 🧠 SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization（SKILL0：用于技能内化的上下文智能体强化学习）[03:22] 🎮 Generative World Renderer（生成式世界渲染器）[04:09] 👁 EgoSim: Egocentric World Simulator for Embodied Interaction Generation（EgoSim：面向具身交互生成的第一人称世界模拟器）[05:24] 🧠 LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model（LatentUM：通过潜在空间统一模型释放交错跨模态推理的潜力）[06:06] 🧠 Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory（Omni-SimpleMem：基于自主研究引导的终身多模态智能体记忆发现）[06:47] 🚗 UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving（UniDriveVLA：统一自动驾驶中的理解、感知与动作规划）[07:35] 🎯 Steerable Visual Representations（可操控的视觉表示）[08:12] 🎬 VOID: Video Object and Interaction Deletion（VOID：视频对象与交互删除）[09:06] 🤖 Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time（探究自主编码代理在真实项目中的贡献：活动模式与代码随时间的变化）[09:47] 🚀 ASI-Evolve: AI Accelerates AI（ASI-Evolve：人工智能加速人工智能发展）[10:50] 🎭 Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models（Tex3D：通过对抗性3D纹理将物体作为视觉-语言-动作模型的攻击面）[11:36] 🤖 GPA: Learning GUI Process Automation from Demonstrations（GPA：通过演示学习图形用户界面流程自动化）[12:24] 🔍 VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification（VideoZeroBench：通过时空证据验证探究视频多模态大语言模型的极限）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:27] 🛡 ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers（ClawKeeper：通过技能、插件和监视器为OpenClaw代理提供全面的安全保护）[01:20] 💻 Terminal Agents Suffice for Enterprise Automation（终端智能体足以实现企业自动化）[02:03] 📊 MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome（MiroEval：面向过程和结果的多模态深度研究智能体基准测试）[02:54] 🧠 ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?（ViGoR-Bench：视觉生成模型距离零样本视觉推理器还有多远？）[03:40] 🔬 Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification（Vision2Web：基于智能体验证的视觉网站开发分层基准）[04:26] 📊 QuitoBench: A High-Quality Open Time Series Forecasting Benchmark（QuitoBench：一个高质量开放时间序列预测基准）[05:12] 🧠 Reasoning Shift: How Context Silently Shortens LLM Reasoning（推理偏移：上下文如何悄然缩短大语言模型的推理过程）[05:59] 📊 HippoCamp: Benchmarking Contextual Agents on Personal Computers（HippoCamp：在个人计算机上评估情境智能体的基准）[06:52] 🧠 PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning（PerceptionComp：面向复杂感知推理的视频基准测试）[07:34] ⚡ Universal YOCO for Efficient Depth Scaling（通用YOCO：实现高效深度扩展）[08:12] 🔄 Brevity Constraints Reverse Performance Hierarchies in Language Models（简洁性约束逆转语言模型的性能层级）[08:48] 🧠 GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation（GaussianGPT：迈向自回归3D高斯场景生成）[09:25] 📝 Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers（论文重构评估：评估AI撰写论文的呈现质量与幻觉问题）[10:11] 🚀 Embarrassingly Simple Self-Distillation Improves Code Generation（极其简单的自蒸馏提升代码生成能力）[10:54] 🤖 Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants（主动式智能体研究环境：通过模拟主动用户来评估主动式助手）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿

【赞助商】通勤路上就听AI每周谈。AI每周谈，每周带你回顾上周AI大事传送门 🔗https://www.xiaoyuzhoufm.com/podcast/688a34636f5a275f1cba40fd【目录】本期的 15 篇论文如下：[00:30] 🧠 FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization（FIPO：通过未来KL影响策略优化引导深度推理）[01:12] 🧩 LongCat-Next: Lexicalizing Modalities as Discrete Tokens（LongCat-Next：将多模态信息离散化为标记）[01:48] 🚁 CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence（CARLA-Air：在CARLA世界中飞行无人机——面向空地具身智能的统一基础设施）[02:31] 🧬 Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells（Lingshu-Cell：一种用于转录组建模的生成式细胞世界模型，迈向虚拟细胞）[03:33] 🤖 GEMS: Agent-Native Multimodal Generation with Memory and Skills（GEMS：具备记忆与技能的智能体原生多模态生成框架）[04:12] 🎬 VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward（VGGRPO：迈向具有4D潜在奖励的世界一致性视频生成）[05:04] 🤖 Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis（Unify-Agent：面向世界接地的图像合成的统一多模态智能体）[05:45] 🔬 daVinci-LLM:Towards the Science of Pretraining（daVinci-LLM：迈向预训练的科学）[06:19] 🎬 CutClaw: Agentic Hours-Long Video Editing via Music Synchronization（CutClaw：通过音乐同步实现代理式数小时视频编辑）[07:10] 🔍 MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models（MonitorBench：大型语言模型中思维链可监控性的综合基准）[07:58] 🧬 FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration（FlowPIE：基于流引导文献探索的测试时科学思想演化）[08:46] 🏙 Extend3D: Town-Scale 3D Generation（Extend3D：城镇尺度的三维生成）[09:28] 💭 Think Anywhere in Code Generation（代码生成中的随处思考）[10:18] ⚙ OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training（OptiMer：最优分布向量合并优于数据混合用于持续预训练）[11:03] 🎨 VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing（VectorGym：面向SVG代码生成、绘制与编辑的多任务基准）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿