HuggingFace 每日AI论文速递

本期的 10 篇论文如下：[00:29] TOP1(🔥640) | 🤝 Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing（共享即关爱：基于集体RL经验共享的高效大模型后训练）[02:49] TOP2(🔥341) | 🔒 A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code（A.S.E：一个用于评估AI生成代码安全的仓库级基准）[04:59] TOP3(🔥218) | 🤖 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model（VLA-Adapter：面向小型视觉-语言-动作模型的有效范式）[07:07] TOP4(🔥212) | 🤖 The Landscape of Agentic Reinforcement Learning for LLMs: A Survey（面向大语言模型的智能体强化学习全景：一项综述）[09:17] TOP5(🔥207) | 🤔 Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth（废话学：用深度解读无意义内容挑战大型语言模型）[11:19] TOP6(🔥183) | 🤔 Why Language Models Hallucinate（语言模型为何产生幻觉）[13:06] TOP7(🔥174) | 🧠 A Survey of Reinforcement Learning for Large Reasoning Models（大型推理模型的强化学习综述）[15:32] TOP8(🔥160) | 🎬 LongLive: Real-time Interactive Long Video Generation（LongLive：实时交互式长视频生成框架）[18:13] TOP9(🔥145) | 💡 Reverse-Engineered Reasoning for Open-Ended Generation（面向开放式生成的逆向工程推理）[20:27] TOP10(🔥140) | 🤖 A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers（科学大型语言模型综述：从数据基础到智能体前沿）【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

本期的 15 篇论文如下：[00:20] 🎮 Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play（Vision-Zero：基于策略化博弈自对弈的可扩展视觉语言模型自我提升）[00:59] 🔥 MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use（MCPMark：面向真实且全面的MCP应用场景的压力测试基准）[01:36] 🐣 The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain（幼龙破壳： Transformer 与大脑模型之间缺失的环节）[02:10] 🤥 TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning（TruthRL：通过强化学习激励大模型说真话）[02:55] 🌊 OceanGym: A Benchmark Environment for Underwater Embodied Agents（OceanGym：面向水下具身智能体的综合基准环境）[03:41] ⚡ DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder（DC-VideoGen：基于深度压缩视频自编码器的高效视频生成）[04:14] 🔍 Who's Your Judge? On the Detectability of LLM-Generated Judgments（谁是你的评审？大模型生成评审意见的检测性研究）[04:59] ✂ Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning（赢得剪枝豪赌：统一样本-令牌剪枝的高效监督微调新方法）[05:45] 👁 Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training（未见先识：从语言预训练解密大模型视觉先验）[06:24] 🧠 Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training（思维火花！后训练阶段推理模型中涌现的专用注意力头）[07:09] 🧪 VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications（VitaBench：面向真实场景多功能交互任务的LLM智能体评测基准）[07:42] ⚡ dParallel: Learnable Parallel Decoding for dLLMs（dParallel：面向扩散大语言模型的可学习并行解码）[08:28] 🎯 IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance（IMG：通过隐式多模态引导校准扩散模型）[09:15] 🎬 MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation（MotionRAG：基于运动检索增强的图像到视频生成）[10:12] 🐬 Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention（基于离散唇部语义与多尺度全局-局部注意力的高效视听语音分离）【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

本期的 15 篇论文如下：[00:22] ⚡ SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention（SLA：通过可微调稀疏线性注意力突破扩散Transformer的稀疏性极限）[01:05] 🗣 StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs（StableToken：一种面向韧性SpeechLLM的噪声鲁棒语义语音分词器）[01:54] 🎮 Multiplayer Nash Preference Optimization（多玩家纳什偏好优化）[02:57] 🔗 RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark（RealUnify：统一模型真的因“统一”而更强吗？综合基准揭晓答案）[03:44] 🎨 OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing（OpenGPT-4o-Image：面向高级图像生成与编辑的大规模综合数据集）[04:28] 🧠 Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR（超越探索-利用权衡：面向RLVR中LLM推理的隐状态方法）[05:05] 🧩 Visual Jigsaw Post-Training Improves MLLMs（视觉拼图后训练提升多模态大模型）[05:37] 🎬 SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer（SANA-Video：基于分块线性注意力Transformer的高效视频扩散生成模型）[06:15] 🔬 Democratizing AI scientists using ToolUniverse（用ToolUniverse普及AI科学家）[06:59] 🧠 When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance（推理何时真正奏效？对推理贡献度的受控研究）[07:31] 📊 GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts（GSM8K-V：视觉语言模型能否解决视觉语境下的小学数学应用题？）[08:04] 🖼 EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling（EditScore：借助高保真奖励建模解锁图像编辑在线强化学习）[08:54] 🚀 SparseD: Sparse Attention for Diffusion Language Models（SparseD：面向扩散语言模型的稀疏注意力机制）[09:40] 🎛 EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering（EasySteer：高性能可扩展LLM推理控制统一框架）[10:32] 🧠 Towards Personalized Deep Research: Benchmarks and Evaluations（迈向个性化深度研究：基准与评估）【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

本期的 15 篇论文如下：[00:20] 🎬 LongLive: Real-time Interactive Long Video Generation（LongLive：实时交互式长视频生成框架）[00:56] 🎯 Quantile Advantage Estimation for Entropy-Safe Reasoning（用于熵安全推理的分位数优势估计）[01:34] 📄 MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing（MinerU2.5：面向高效高分辨率文档解析的解耦视觉-语言模型）[02:11] 🧠 EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning（EPO：面向LLM智能体强化学习的熵正则策略优化）[03:08] 🧠 Variational Reasoning for Language Models（语言模型的变分推理框架）[03:37] 💬 Language Models Can Learn from Verbal Feedback Without Scalar Rewards（无需标量奖励，语言模型也能从语言反馈中学习）[04:32] 🔍 ReviewScore: Misinformed Peer Review Detection with Large Language Models（ReviewScore：用大模型揪出“跑偏”的同行评审）[05:12] 🎯 CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning（CapRL：用强化学习激发稠密图像描述潜能）[05:49] 🪄 MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning（MesaTask：面向任务驱动的桌面场景生成与3D空间推理）[06:32] 🎯 No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping（零方差提示不浪费：基于熵引导优势塑造的LLM强化学习新范式）[07:14] 🗣 VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing（VoiceAssistant-Eval：横跨听、说、看的AI助手基准测评）[07:58] 🧭 UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios（UltraHorizon：在长周期场景中评估智能体能力的基准）[08:29] 🖼 LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer（LucidFlux：无需文字描述的大规模扩散Transformer通用图像修复）[09:16] 🌐 WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning（WebGen-Agent：借助多级反馈与步骤级强化学习提升交互式网页生成）[09:49] 🔄 SPARK: Synergistic Policy And Reward Co-Evolving Framework（SPARK：策略与奖励协同演化的强化学习框架）【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

本期的 5 篇论文如下：[00:38] TOP1(🔥116) | 📜 Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR（Baseer：面向阿拉伯文档OCR的视觉-语言模型）[02:43] TOP2(🔥113) | 🌐 Qwen3-Omni Technical Report（Qwen3-Omni技术报告：首个无性能损耗的全模态大模型）[05:23] TOP3(🔥112) | 🗺 RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation（RPG：用于统一可扩展代码库生成的仓库规划图）[07:45] TOP4(🔥104) | 📈 VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models（VCRL：面向大语言模型的方差驱动课程强化学习）[10:05] TOP5(🔥89) | 🚀 LIMI: Less is More for Agency（LIMI：少即是多，打造AI智能体）【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

本期的 15 篇论文如下：[00:20] 🔬 SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines（SciReasoner：跨学科夯实科学推理基石）[01:00] 🧠 MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources（MMR1：基于方差感知采样与开放资源的多模态推理增强）[01:41] 📈 VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models（VCRL：面向大语言模型的方差驱动课程强化学习）[02:26] 🌳 Tree Search for LLM Agent Reinforcement Learning（基于树搜索的大语言模型智能体强化学习）[03:06] 🖼 Seedream 4.0: Toward Next-generation Multimodal Image Generation（Seedream 4.0：面向下一代多模态图像生成）[03:40] 🎯 Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets（Hunyuan3D-Omni：统一可控3D资产生成框架）[04:29] 🤖 AutoIntent: AutoML for Text Classification（AutoIntent：面向文本分类任务的自动化机器学习框架）[05:10] ⚖ TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them（TrustJudge：LLM-as-a-Judge的评分不一致性及缓解之道）[05:43] 🎢 CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning（CE-GPPO：通过梯度保留裁剪策略优化控制强化学习中的熵）[06:30] 🖼 Does FLUX Already Know How to Perform Physically Plausible Image Composition?（FLUX已掌握物理可信图像合成？）[07:31] ✂ CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling（CHARM：基于控制点的3D动漫发型自回归建模）[08:26] 🧠 Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution（Recon-Act：基于网络侦察、工具生成与任务执行的自我演化多智能体浏览器操作系统）[09:12] 🎮 V-GameGym: Visual Game Generation for Code Large Language Models（V-GameGym：面向代码大模型的视觉游戏生成基准）[09:49] 🗣 Interactive Recommendation Agent with Active User Commands（支持主动用户指令的交互式推荐智能体）[10:22] 🔍 BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback（BESPOKE：基于诊断反馈的搜索增强大模型个性化评测基准）【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

本期的 10 篇论文如下：[00:22] 🎥 Video models are zero-shot learners and reasoners（视频模型是零样本学习者与推理者）[01:09] 🧠 SIM-CoT: Supervised Implicit Chain-of-Thought（SIM-CoT：基于监督式隐式思维链的高效推理）[01:55] 🪶 EmbeddingGemma: Powerful and Lightweight Text Representations（EmbeddingGemma：强大而轻量的文本表征模型）[02:29] 🗣 Advancing Speech Understanding in Speech-Aware Language Models with GRPO（基于GRPO提升语音感知大模型开放域理解能力）[03:06] 🌍 LLMs4All: A Review on Large Language Models for Research and Applications in Academic Disciplines（LLMs4All：面向各学科研究与应用的通用大模型综述）[03:52] 🎬 EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning（EditVerse：用上下文学习统一图像与视频编辑生成）[04:29] 🌀 Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation（Lavida-O：弹性大掩码扩散模型统一多模态理解与生成）[05:19] 🎬 PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation（PhysCtrl：基于生成式物理的可控且物理真实的视频生成框架）[05:58] 📄 Logics-Parsing Technical Report（Logics-Parsing 技术报告：基于强化学习的大模型端到端文档解析）[06:44] 🤖 On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub（关于自主编码的实证研究：GitHub上由AI代理发起的拉取请求分析）【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

本期的 15 篇论文如下：[00:24] 📜 Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR（Baseer：面向阿拉伯文档OCR的视觉-语言模型）[00:58] 🚀 Reinforcement Learning on Pre-Training Data（基于预训练数据的强化学习）[01:37] 👁 Do You Need Proprioceptive States in Visuomotor Policies?（无需本体感觉状态的视觉-运动策略是否可行？）[02:36] 🚀 MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe（MiniCPM-V 4.5：通过架构、数据与训练配方烹饪高效多模态大模型）[03:24] 🎯 MAPO: Mixed Advantage Policy Optimization（混合优势策略优化：解决GRPO中优势分配难题）[04:06] 🚀 Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation（Hyper-Bagel：统一加速多模态理解与生成的一体化框架）[04:44] 🎯 VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction（VolSplat：基于体素对齐预测的前馈3D高斯抛雪球重建新范式）[05:31] 🌌 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation（Lyra：基于视频扩散模型自蒸馏的生成式3D场景重建）[06:08] 🧩 What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT（有效推理的密码：重新审视思维链长度、回顾与结构）[06:41] 🗣 Large Language Models Discriminate Against Speakers of German Dialects（大型语言模型对德语方言使用者的歧视）[07:32] 📊 OpenGVL - Benchmarking Visual Temporal Progress for Data Curation（OpenGVL——面向数据整理的视觉时序进展评测基准）[08:19] 🪄 HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis（HyRF：混合辐射场实现内存高效且高质量的新视角合成）[09:07] 🛠 CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching（条件感知重参数化对齐源域与目标域的流匹配）[09:41] 🛰 Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications（零样本多光谱学习：让通用多模态Gemini 2.5模型在遥感任务中重焕新生）[10:28] 🌍 VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction（VIR-Bench：通过旅行视频行程重建评测多模态大模型的地理-时空理解力）【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

本期的 15 篇论文如下：[00:21] 🚀 LIMI: Less is More for Agency（LIMI：少即是多，打造AI智能体）[00:55] 🎬 OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models（无需掩膜的视频任意主体插入：基于扩散Transformer模型）[01:28] 🧩 OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System（OnePiece：面向工业级级联排序系统的上下文工程与推理融合框架）[02:19] 🌐 Qwen3-Omni Technical Report（Qwen3-Omni技术报告：首个无性能损耗的全模态大模型）[02:55] 🎬 TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs（TempSamp-R1：面向视频时序定位任务的高效离策略强化微调框架）[03:28] 📐 GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning（GeoPQA：弥合多模态大模型几何推理中的视觉感知鸿沟）[04:15] 🎯 DiffusionNFT: Online Diffusion Reinforcement with Forward Process（DiffusionNFT：基于前向过程在线扩散强化学习）[05:05] 🤖 ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces（ByteWrist：面向狭窄空间的可穿戴并行机器人腕关节）[05:42] 💬 EpiCache: Episodic KV Cache Management for Long Conversational Question Answering（EpiCache：面向长对话问答的情景式KV缓存管理）[06:24] 🧠 SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?（SWE-Bench Pro：AI智能体能攻克长周期软件工程难题吗？）[07:01] 🧠 FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions（FlagEval发现报告：大推理模型在可自动验证文本与视觉问题上的初步测评）[08:05] 🎬 VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models（VideoFrom3D：基于互补图像与视频扩散模型的3D场景视频生成）[08:53] 🧪 ARE: Scaling Up Agent Environments and Evaluations（ARE：扩展智能体环境与评测规模）[09:28] 🧩 QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models（QWHA：面向大模型量化部署的沃尔什-哈达玛参数高效微调方法）[10:17] 🔍 Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels（从token与参数双视角解析监督微调对模型知识的影响）【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

本期的 13 篇论文如下：[00:25] 🗺 RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation（RPG：用于统一可扩展代码库生成的仓库规划图）[01:00] 🌉 MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer（MANZANO：基于混合视觉词元器的简洁可扩展统一多模态模型）[01:42] 🧩 Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification（潜区分网络：生成建模、表示学习与分类的统一原理）[02:25] 🎯 BaseReward: A Strong Baseline for Multimodal Reward Model（BaseReward：多模态奖励模型的强力基线）[02:56] 🏠 SPATIALGEN: Layout-guided 3D Indoor Scene Generation（SpatialGen：布局引导的3D室内场景生成）[03:46] 🧠 BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent（BTL-UI：面向GUI智能体的“眨眼-思考-连接”脑启发推理模型）[04:30] 🎭 Lynx: Towards High-Fidelity Personalized Video Generation（Lynx：面向高保真个性化视频生成）[05:20] 🤖 A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning（用于机器人真实强化学习的视觉-语言-动作-评价模型）[05:54] 📹 RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes（动态场景下仅基于RGB视频监督的相机参数优化）[06:21] 🗣 Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems（你听见的是我想表达的吗？量化指令感知差距的表达型文本转语音系统研究）[07:07] 🎬 Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents（Video2Roleplay：面向视频引导角色扮演智能体的多模态数据集与框架）[07:50] 🗣 WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers（WhisTLE：面向预训练语音识别Transformer的纯文本深度监督域适应方法）[08:30] 🗣 Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue（主动询问以澄清：通过多轮对话消解指令歧义）【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

本期的 5 篇论文如下：[00:43] TOP1(🔥95) | 🌍 OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling（OmniWorld：面向4D世界建模的多领域多模态大规模数据集）[02:51] TOP2(🔥93) | 🔍 WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research（WebWeaver：面向开放型深度研究的动态提纲式网络证据结构化框架）[05:09] TOP3(🔥91) | 🤖 Scaling Agents via Continual Pre-training（基于持续预训练扩展智能体系统规模的研究）[07:33] TOP4(🔥88) | 🖥 ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data（ScaleCUA：基于跨平台数据的开源计算机智能体规模化方案）[10:48] TOP5(🔥79) | 🌊 FlowRL: Matching Reward Distributions for LLM Reasoning（FlowRL：通过流匹配奖励分布提升大语言模型推理能力）【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

本期的 15 篇论文如下：[00:26] 🖥 ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data（ScaleCUA：基于跨平台数据的开源计算机智能体规模化方案）[01:01] 🌊 FlowRL: Matching Reward Distributions for LLM Reasoning（FlowRL：通过流匹配奖励分布提升大语言模型推理能力）[01:57] 🧭 Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration（跨越边界推理：借助测试时深思提升规范对齐）[02:55] 🧬 Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation（无需标签即可让语言模型自我进化：多数选择驱动，新颖性促进变异）[03:34] 🎨 Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation（先理解再生成：面向自回归图像生成的自引导训练）[04:12] 🔍 FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning（FinSearchComp：迈向真实专家级金融搜索与推理评测）[04:56] 🤖 RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation（RynnVLA-001：利用人类示范提升机器人操作能力）[05:39] 🔮 AToken: A Unified Tokenizer for Vision（AToken：面向视觉的统一Tokenizer）[06:10] 🌌 WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance（WorldForge：无需训练即可在视频扩散模型中解锁3D/4D生成的涌现能力）[06:58] 🖼 MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks（MultiEdit：面向多样复杂任务的指令式图像编辑新突破）[07:54] 🎮 RecoWorld: Building Simulated Environments for Agentic Recommender Systems（RecoWorld：为智能推荐系统打造仿真训练沙盒）[08:28] 🎯 Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding（释放多模态大模型零样本时空视频定位潜能）[09:03] 🔍 Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs（留意空格：面向LLM选择题问答的Tokenization再审视）[09:51] 🩺 EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence（EchoVLM：面向通用超声智能的动态混合专家视觉-语言模型）[10:34] 🛰 FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection（FSG-Net：频-空协同门控网络用于高分辨率遥感变化检测）【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

本期的 14 篇论文如下：[00:19] 🐪 Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale（Hala技术报告：规模化构建阿拉伯语为中心的指令与翻译模型）[00:56] 🚀 SAIL-VL2 Technical Report（SAIL-VL2技术报告）[01:42] 🌐 PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era（全景视界：具身AI时代的360°视觉崛起）[02:33] 🎓 GenExam: A Multidisciplinary Text-to-Image Exam（GenExam：多学科文本到图像生成考试基准）[03:25] 🧹 Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning（擦除敏感记忆！用机器遗忘技术为代码大模型“去隐私”）[03:59] 🩺 MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework（MedResearcher-R1：基于知识引导轨迹合成的专家级医学深度研究智能体）[04:37] 🔍 MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook（MARS2 2025多模态推理挑战赛：数据集、方法、结果、讨论与展望）[05:22] 🎭 Wan-Animate: Unified Character Animation and Replacement with Holistic Replication（Wan-Animate：统一角色动画与替换的完整复现框架）[05:59] 🧮 THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning（THOR：融合工具的分层强化学习优化数学推理）[06:40] 🔍 Improving Context Fidelity via Native Retrieval-Augmented Reasoning（提升上下文保真度的原生检索增强推理方法）[07:20] 🌍 AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions（AERIS：面向可靠且高技巧地球系统预测的阿尔贡地球系统模型）[08:13] 🎛 SteeringControl: Holistic Evaluation of Alignment Steering in LLMs（SteeringControl：对大模型对齐操控的全景评估）[08:48] ⚛ Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks（量子变分激活函数赋能Kolmogorov-Arnold网络）[09:37] 🚀 Hybrid Quantum-Classical Model for Image Classification（用于图像分类的混合量子-经典模型）【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

本期的 11 篇论文如下：[00:27] 🔍 WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research（WebWeaver：面向开放型深度研究的动态提纲式网络证据结构化框架）[01:08] 🤖 Scaling Agents via Continual Pre-training（基于持续预训练扩展智能体系统规模的研究）[01:52] ⛵ WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning（WebSailor-V2：依托合成数据与可扩展强化学习跨越开源与私有代理鸿沟）[02:36] 🧠 Towards General Agentic Intelligence via Environment Scaling（迈向通用智能体的环境规模化之路）[03:09] 🔍 WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents（WebResearcher：在长程智能体中释放无界推理能力）[03:59] 🧠 ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization（ReSum：基于上下文压缩的无限视界搜索智能解锁）[04:39] 🚀 Single-stream Policy Optimization（单流策略优化：大语言模型强化学习的去组化革新）[05:19] 🎮 Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation（Hunyuan3D工作室：面向游戏级3D资产生成的端到端AI管线）[06:00] 🧩 3D Aware Region Prompted Vision Language Model（具备3D感知能力的区域提示视觉语言模型）[06:36] 💡 EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving（EconProver：面向自动定理证明的更经济测试时扩展方法）[07:07] ⚛ Exact Coset Sampling for Quantum Lattice Algorithms（量子格点算法的精确陪集采样）【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

本期的 14 篇论文如下：[00:24] 🌍 OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling（OmniWorld：面向4D世界建模的多领域多模态大规模数据集）[01:12] 🤖 UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning（UI-S1：基于半在线强化学习的图形界面自动化新进展）[01:51] 🏠 InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts（InternScenes：具备真实布局的大规模可模拟室内场景数据集）[02:27] 🖱 LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence（LazyDrag：通过显式对应关系在多模态扩散Transformer上实现稳定拖拽编辑）[02:58] 📊 Locality in Image Diffusion Models Emerges from Data Statistics（图像扩散模型中的局部性源于数据统计特性）[03:29] 🤔 Measuring Epistemic Humility in Multimodal Large Language Models（多模态大模型中的认知谦逊评估研究）[03:57] 🤖 Nav-R1: Reasoning and Navigation in Embodied Scenes（Nav-R1：具身场景中的推理与导航）[04:25] 🔍 Lost in Embeddings: Information Loss in Vision-Language Models（迷失在嵌入空间：视觉-语言模型中的信息损失）[04:54] 🌐 CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media（CognitiveSky：面向去中心化社交媒体的情感与叙事可扩展分析框架）[05:19] 🔍 Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models（再审视，慢思考：增强视觉语言模型的视觉反思能力）[05:57] 🧠 EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI（心理健康AI伦理推理的试验基准：EthicsMH）[06:30] ⚖ Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting（通过动态奖励加权实现多目标对齐优化学习）[07:16] 🧠 PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits（PersonaX：基于大语言模型推断行为特质的多模态数据集）[07:52] 🔍 GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings（GAPrune：面向领域感知嵌入的梯度对齐剪枝方法）【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

本期的 14 篇论文如下：[00:25] 📚 IntrEx: A Dataset for Modeling Engagement in Educational Conversations（IntrEx：面向教育对话中参与度建模的数据集）[01:02] 📏 The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs（“收益递减的幻觉”：衡量大语言模型的长时程执行能力）[01:54] 🧩 X-Part: high fidelity and structure coherent shape decomposition（X-Part：高保真且结构一致的三维形状分解）[02:33] 🖼 InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis（InfGen：分辨率无关的可扩展图像合成新范式）[03:04] 🔍 HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering（HANRAG：面向多跳问答的启发式精准抗噪检索增强生成方法）[03:50] 🎙 VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions（VStyle：基于语音指令的语音风格自适应基准）[04:44] 🌸 FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies（FLOWER：以高效视觉-语言-动作流策略普及通用机器人策略）[05:20] 🎨 Inpainting-Guided Policy Optimization for Diffusion Large Language Models（面向扩散大语言模型的基于文本补全引导的策略优化方法）[05:58] 🤖 Virtual Agent Economies（虚拟代理经济）[06:28] 📈 QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading（QuantAgent：面向高频交易的价格驱动多智能体大语言模型框架）[07:02] 🧪 MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools（MCP-AgentBench：基于MCP中介工具的通用语言智能体真实性能评测）[07:41] 🎨 Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generation（精准上色：连接感知色彩空间与文本嵌入以提升扩散生成质量）[08:31] 🦎 LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios（LoFT：面向开放世界长尾场景的参数高效半监督微调方法）[09:13] 🗞 CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China（CMHG：中国少数民族语言新闻标题生成数据集与评测基准）【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

本期的 5 篇论文如下：[00:40] TOP1(🔥455) | 🤝 Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing（共享即关爱：基于集体RL经验共享的高效大模型后训练）[03:19] TOP2(🔥163) | 🤖 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model（VLA-Adapter：面向小型视觉-语言-动作模型的有效范式）[05:44] TOP3(🔥156) | 🤔 Why Language Models Hallucinate（语言模型为何产生幻觉）[07:57] TOP4(🔥139) | 💡 Reverse-Engineered Reasoning for Open-Ended Generation（面向开放式生成的逆向工程推理）[10:35] TOP5(🔥131) | 🧠 A Survey of Reinforcement Learning for Large Reasoning Models（大型推理模型的强化学习综述）【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

本期的 15 篇论文如下：[00:27] 🎭 HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning（HuMo：通过协同多模态条件控制实现以人为中心的视频生成）[01:18] 🤖 SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning（SimpleVLA-RL：通过强化学习实现VLA训练规模化）[02:02] 🗣 EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs（EchoX：基于回声训练弥合声学-语义鸿沟的语音大模型研究）[02:37] 🎭 Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis（Kling-Avatar：面向级联长时化身动画合成的多模态指令语义落地方法）[03:11] 🧭 Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents（驾驭不确定性：面向长周期LLM智能体的熵调制策略梯度方法）[03:57] 🎨 FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark（FLUX-Reason-6M和PRISM-Bench：百万级文生图推理数据集与全面评测基准）[04:34] 🤖 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model（VLA-Adapter：面向小型视觉-语言-动作模型的有效范式）[05:14] 🔄 Can Understanding and Generation Truly Benefit Together -- or Just Coexist?（理解与生成真能互惠共进，抑或仅共存？）[05:46] 📹 SpatialVID: A Large-Scale Video Dataset with Spatial Annotations（SpatialVID大规模带空间标注的视频数据集）[06:16] 📊 Visual Programmability: A Guide for Code-as-Thought in Chart Understanding（视觉可编程性：面向图表理解的Code-as-Thought指南）[06:55] 🕵 Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval（梯度-注意力引导的双重掩码协同框架用于鲁棒的基于文本的人物检索）[07:35] 🖼 2D Gaussian Splatting with Semantic Alignment for Image Inpainting（面向图像修复的语义对齐2D高斯泼溅）[08:10] 📏 LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering（LoCoBench：面向复杂软件工程的长上下文大模型基准测试）[08:45] 🤖 OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning（OmniEVA：面向具身任务的自适应3D感知与本体约束联合规划器）[09:31] 🎯 The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward（散度选择：缓解可验证奖励强化学习多样性坍缩的关键）【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

本期的 10 篇论文如下：[00:24] 🧠 A Survey of Reinforcement Learning for Large Reasoning Models（大型推理模型的强化学习综述）[00:45] 🔄 RewardDance: Reward Scaling in Visual Generation（RewardDance：视觉生成中的奖励缩放）[01:08] 🌐 3D and 4D World Modeling: A Survey（3D和4D世界建模：一项综述）[01:41] 🤖 AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning（AgentGym-RL: 通过多轮强化学习训练用于长视野决策制定的LLM智能体）[02:08] 🧩 P3-SAM: Native 3D Part Segmentation（P3-SAM：原生3D部分分割）[02:40] 🌐 Hunyuan-MT Technical Report（Hunyuan-MT技术报告）[03:08] ⚠ <think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs（从LLM生成有毒文本中吸取的经验教训）[03:44] 🤖 EnvX: Agentize Everything with Agentic AI（EnvX：使用代理式AI实现万物代理化）[04:13] 🤔 The Majority is not always right: RL training for solution aggregation（多数并不总是正确：用于解决方案聚合的强化学习训练）[04:33] 🤖 HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants（HumanAgencyBench：AI助手中人类代理支持的规模化评估）【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

本期的 14 篇论文如下：[00:22] 🧠 Parallel-R1: Towards Parallel Thinking via Reinforcement Learning（Parallel-R1: 通过强化学习实现并行思维）[00:50] 🔍 Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search（Mini-o3：扩展视觉搜索中的推理模式与交互轮次）[01:15] 👁 Visual Representation Alignment for Multimodal Large Language Models（多模态大语言模型的视觉表征对齐）[01:54] 🔄 Reconstruction Alignment Improves Unified Multimodal Models（重建对齐改进统一多模态模型）[02:19] 🔄 UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward（UMO：通过匹配奖励扩展图像定制中的多身份一致性）[02:46] 🧠 Curia: A Multi-Modal Foundation Model for Radiology（Curia：一种用于放射学的多模态基础模型）[03:06] 🔮 F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions（F1：一种连接理解与生成到行动的视觉-语言-行动模型）[03:33] 🧠 Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding（保持在最佳状态：通过能力自适应提示脚手架实现响应式推理进化）[03:56] 🔄 Language Self-Play For Data-Free Training（语言自我博弈用于无数据训练）[04:22] 🔍 Causal Attention with Lookahead Keys（带前瞻键的因果注意力）[04:43] 🎨 Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference（直接将完整扩散轨迹与细粒度人类偏好对齐）[05:07] ✅ SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge（SimpleQA Verified：衡量参数化知识的可靠事实性基准）[05:30] 🚀 Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling（Q-Sched：通过量化感知调度推动少步扩散模型的边界）[06:01] 📈 $ΔL$ Normalization: Rethink Loss Aggregation in RLVR（$ΔL$ 归一化：重新思考RLVR中的损失聚合）【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