HuggingFace 每日AI论文速递

duan

每天10分钟,带您快速了解当日HuggingFace热门AI论文内容。每个工作日更新,欢迎订阅。 📢播客节目在小宇宙、Apple Podcast平台搜索【HuggingFace 每日AI论文速递】 🖼另外还有图文版,可在小红书搜索并关注【AI速递】

  1. -16 T

    2025.11.05 | 向量草图测代码;先画后想补视觉

    本期的 15 篇论文如下: [00:21] 🖼 VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation(VCode:以SVG为符号视觉表征的多模态代码评测基准) [01:12] 🧠 When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought(当可视化成为推理第一步:MIRA视觉思维链基准测试) [01:48] ⚖ When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs(当模态冲突时:单模态推理不确定性如何左右多模态大模型的偏好) [02:36] 🪙 Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR(更短却更好:用易题作长度正则化实现节俭推理) [03:11] 🧠 Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer(Brain-IT:基于脑交互Transformer的fMRI图像重建) [03:49] 👁 Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization(别让VLA变盲:对齐视觉表征实现分布外泛化) [04:33] 🎨 LTD-Bench: Evaluating Large Language Models by Letting Them Draw(LTD-Bench:让大模型画画来测评空间推理力) [05:15] 🤖 TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System(TWIST2:可扩展、便携且全面的人形机器人数据采集系统) [06:01] 🗜 Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models(视觉输入能否被压缩?面向大型多模态模型的视觉Token压缩基准) [06:46] 🏆 CodeClash: Benchmarking Goal-Oriented Software Engineering(CodeClash:面向目标的软件工程基准测试) [07:29] 🎭 VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models(VidEmo:面向情感中心视频基础模型的情感树推理) [08:03] 🧠 BRAINS: A Retrieval-Augmented System for Alzheimer's Detection and Monitoring(BRAINS:用于阿尔茨海默病检测与监测的检索增强系统) [08:42] 📊 ChartM$^3$: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension(ChartM³:面向图表理解的多维多步视觉推理数据构建的多阶段代码驱动流水线) [09:45] 📊 TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data(TabDSR:表格复杂数值推理的分解-清洗-推理框架) [10:17] 🤖 iFlyBot-VLA Technical Report(iFlyBot-VLA技术报告:大规模视觉-语言-动作模型新框架) 【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

    12 min
  2. -1 D.

    2025.11.04 | 超稀疏MoE激活万亿参数;视觉模型看图胜GNN

    本期的 15 篇论文如下: [00:23] 🧠 Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation(全激活赋能:将通用推理模型扩展到万亿参数的开放语言基座) [01:03] 👁 The Underappreciated Power of Vision Models for Graph Structural Understanding(被低估的视觉模型在图结构理解中的强大潜能) [01:38] 💡 UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback(UniLumos:基于物理可信反馈的统一图像与视频快速重打光框架) [02:37] 🕸 Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph(将测试时计算最优扩展泛化为可优化的图) [03:11] 🤖 PHUMA: Physically-Grounded Humanoid Locomotion Dataset(PHUMA:基于物理的人形机器人运动数据集) [03:48] 🔭 ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use(ToolScope:面向视觉引导与长程工具使用的智能体框架) [04:30] 🧠 UniREditBench: A Unified Reasoning-based Image Editing Benchmark(UniREditBench:基于统一推理的图像编辑评测基准) [05:23] 🔄 ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation(ROVER:统一多模态生成中的双向跨模态推理基准测试) [06:04] 🌍 Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum(迈向通用视频检索:通过合成多模态金字塔课程泛化视频嵌入) [06:44] 🌍 World Simulation with Video Foundation Models for Physical AI(基于视频基础模型的物理AI世界仿真) [07:20] 🧠 TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning(TIR-Bench:面向“图像思维”智能体推理的综合评测基准) [08:03] 🧭 NaviTrace: Evaluating Embodied Navigation of Vision-Language Models(NaviTrace:评测视觉-语言模型具身导航能力) [08:45] 📏 Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench(视觉语言模型能否胜任?基于MeasureBench的视觉测量读数基准测试) [09:23] 🧭 Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models(激活多模态大语言模型的空间推理能力) [10:07] 🐱 LongCat-Flash-Omni Technical Report(LongCat-Flash-Omni技术报告:5600亿参数开源全模态实时音视频交互模型) 【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

    11 min
  3. -2 D.

    2025.11.03 | OS-Sentinel实时守护手机操作安全;ThinkMorph让小模型边想边画

    本期的 15 篇论文如下: [00:21] 🛡 OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows(OS-Sentinel:在真实工作流中通过混合验证提升移动GUI代理安全性) [01:13] 🧠 ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning(ThinkMorph:多模态交错思维链中的涌现特性) [01:49] ⚔ INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats(INT对决FP:细粒度低比特量化格式的综合研究) [02:38] 🤖 $π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models(π_RL:面向流式视觉-语言-动作模型的在线强化学习微调) [03:26] 🚀 Continuous Autoregressive Language Models(连续自回归语言模型) [03:54] 🧭 Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning(Spatial-SSRL:通过自监督强化学习增强空间理解) [04:37] 🎯 HyperClick: Advancing Reliable GUI Grounding via Uncertainty Calibration(HyperClick:通过不确定性校准推动可靠GUI定位) [05:15] 🎯 Defeating the Training-Inference Mismatch via FP16(用FP16打败训练-推理失配) [05:52] 🪜 Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals(分阶段DMD:在子区间内做分数匹配实现少步分布匹配蒸馏) [06:28] 🧭 Revisiting Multimodal Positional Encoding in Vision-Language Models(再探视觉-语言模型中的多模态位置编码) [07:09] ⚡ Higher-order Linear Attention(高阶线性注意力机制) [07:55] 🌐 Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model(双流扩散助力世界模型增强视觉-语言-动作模型) [08:36] 🔬 The Denario project: Deep knowledge AI agents for scientific discovery(Denario项目:面向科学发现的深度知识AI智能体) [09:14] 🎯 Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning(面向具身决策的多模态大模型视觉后门攻击:对比触发学习方法) [09:51] 🏙 Mask-to-Height: A YOLOv11-Based Architecture for Joint Building Instance Segmentation and Height Classification from Satellite Imagery(Mask-to-Height:基于YOLOv11的联合建筑实例分割与高度分类架构) 【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

    11 min
  4. -3 D.

    【月末特辑】10月最火AI论文 | 幼龙BDH稀疏可解释;迷你递归7兆碾压大模型

    本期的 10 篇论文如下: [00:30] TOP1(🔥522) | 🐣 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) [02:31] TOP2(🔥462) | 🧠 Less is More: Recursive Reasoning with Tiny Networks(小而精:用微型网络递归推理) [04:48] TOP3(🔥255) | 🌱 Agent Learning via Early Experience(基于早期经验的主体学习) [07:04] TOP4(🔥182) | 🔄 Scaling Latent Reasoning via Looped Language Models(通过循环语言模型扩展潜在推理能力) [09:11] TOP5(🔥170) | 🔥 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) [11:18] TOP6(🔥169) | 🚀 QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs(QeRL:超越效率——面向大语言模型的量化增强强化学习) [13:10] TOP7(🔥167) | 🎼 Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations(Concerto:2D-3D联合自监督学习涌现空间表征) [15:38] TOP8(🔥160) | 🧠 Diffusion Transformers with Representation Autoencoders(基于表示自编码器的扩散Transformer) [17:59] TOP9(🔥144) | 🧠 A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning(大模型推理中内部概率与自洽性桥接的理论研究) [20:09] TOP10(🔥142) | 🎯 Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model(空间强迫:面向视觉-语言-动作模型的隐式空间表征对齐) 【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

    23 min
  5. -5 D.

    2025.10.31 | Emu3.5统一预测时空;扩散提示驱动机器人

    本期的 15 篇论文如下: [00:26] 🌍 Emu3.5: Native Multimodal Models are World Learners(Emu3.5:原生多模态世界模型让AI看懂并预测未来) [01:04] 🤖 Exploring Conditions for Diffusion models in Robotic Control(探索扩散模型在机器人控制中的条件化策略) [01:42] 🎬 Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark(视频模型已准备好做零样本推理了吗?基于MME-CoF基准的实证研究) [02:22] ⚡ Kimi Linear: An Expressive, Efficient Attention Architecture(Kimi线性:一种富有表现力的高效注意力架构) [02:55] 🧮 AMO-Bench: Large Language Models Still Struggle in High School Math Competitions(AMO-Bench:大语言模型在高中数学奥赛级难题前仍举步维艰) [03:35] 🕺 The Quest for Generalizable Motion Generation: Data, Model, and Evaluation(可泛化动作生成之路:数据、模型与评测) [04:17] 🌐 Surfer 2: The Next Generation of Cross-Platform Computer Use Agents(Surfer 2:下一代跨平台计算机使用智能体) [04:42] 🌍 OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes(OmniX:从统一全景生成与感知到可渲染3D场景) [05:21] 🤝 The Era of Agentic Organization: Learning to Organize with Language Models(智能体组织时代:用语言模型学会协同) [05:57] 🧠 Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning(监督式强化学习:从专家轨迹到逐步推理) [06:32] 🕹 Can Agent Conquer Web? Exploring the Frontiers of ChatGPT Atlas Agent in Web Games(智能体能征服网络吗?探索 ChatGPT Atlas 在网络游戏中的能力边界) [07:10] 🏥 EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis(EHR-R1:面向电子健康记录分析的推理增强型基础语言模型) [07:55] 📄 OmniLayout: Enabling Coarse-to-Fine Learning with LLMs for Universal Document Layout Generation(OmniLayout:基于LLM的粗到细通用文档版面生成) [08:38] 🎯 MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency(MIRO:多奖励条件预训练提升文本到图像生成质量与效率) [09:09] 🤖 Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets(Magentic市集:一个用于研究智能代理市场的开源环境) 【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

    10 min
  6. -6 D.

    2025.10.30 | 看图写码7B逆袭;视频思维RL破局

    本期的 15 篇论文如下: [00:22] 👁 JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence(JanusCoder:面向代码智能的基础视觉-编程接口) [01:00] 🧠 Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning(Video-Thinker:用强化学习点燃“视频思维”) [01:55] 🔄 ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization(ReForm:基于前瞻性有界序列优化的反思式自动化形式化) [02:42] 🔄 Scaling Latent Reasoning via Looped Language Models(通过循环语言模型扩展潜在推理能力) [03:22] 🧠 Reasoning-Aware GRPO using Process Mining(基于过程挖掘的推理感知GRPO方法) [03:52] 🎬 VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning(VFXMaster:通过上下文学习解锁动态视觉特效生成) [04:33] 🏆 The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution(工具十项全能:面向多样、真实、长周期任务的语言智能体基准测试) [05:11] 🖼 RegionE: Adaptive Region-Aware Generation for Efficient Image Editing(RegionE:面向高效图像编辑的自适应区域感知生成) [06:22] 🎮 ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks(ChronoPlay:面向游戏RAG评测的双动态与真实性建模框架) [06:58] 🧭 Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks(大模型时代的多模态空间推理:综述与基准) [07:44] 🔗 PairUni: Pairwise Training for Unified Multimodal Language Models(PairUni:面向统一多模态语言模型的成对训练) [08:33] ⚡ Parallel Loop Transformer for Efficient Test-Time Computation Scaling(并行循环Transformer:零延迟的测试时计算扩展) [09:08] 🚗 Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks(重新审视驾驶世界模型:面向感知任务的合成数据生成器) [09:55] 🧬 ODesign: A World Model for Biomolecular Interaction Design(ODesign:面向生物分子相互作用设计的全原子生成式世界模型) [10:31] 🧬 Evolving Diagnostic Agents in a Virtual Clinical Environment(虚拟临床环境中进化诊断智能体) 【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

    11 min
  7. 29. OKT.

    2025.10.29 | 通义深度研究报告;小模型折记忆胜671B巨模型

    本期的 10 篇论文如下: [00:23] 🔍 Tongyi DeepResearch Technical Report(通义深度研究报告:面向长程深度信息检索任务的智能体大模型) [01:00] 🧠 AgentFold: Long-Horizon Web Agents with Proactive Context Management(AgentFold:面向长程任务的主动式上下文管理智能体) [01:36] 🤖 RoboOmni: Proactive Robot Manipulation in Omni-modal Context(RoboOmni:全模态上下文下的主动机器人操作) [02:33] 🎮 Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents(Game-TARS:面向可扩展通才多模态游戏智能体的预训练基础模型) [03:05] 🎬 Uniform Discrete Diffusion with Metric Path for Video Generation(面向视频生成的度量路径均匀离散扩散模型) [03:42] 🛠 OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents(OSWorld-MCP:评测计算机代理调用MCP工具能力的基准) [04:28] 🎨 Group Relative Attention Guidance for Image Editing(基于群组相对注意力引导的图像编辑方法) [05:14] 🚀 WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking(WebLeaper:通过富信息搜索赋能网络智能体效率与效能) [06:04] 🧭 Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance(MoE路由关乎成败:显式路由引导扩散Transformer扩容) [07:01] 🧠 ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking(并行缪斯:面向深度信息搜寻的主体化并行思考) 【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

    8 min

Om

每天10分钟,带您快速了解当日HuggingFace热门AI论文内容。每个工作日更新,欢迎订阅。 📢播客节目在小宇宙、Apple Podcast平台搜索【HuggingFace 每日AI论文速递】 🖼另外还有图文版,可在小红书搜索并关注【AI速递】

Kanskje du også liker