duan

HuggingFace 每日AI论文速递

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】

Author

duan

Category

Technology

Podcast website

www.xiaoyuzhoufm.com

Latest episode

Jul 10, 2026

Where to listen?

Podcasts in the app Replaio Radio Coming soon

Podcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts

Get it on Google Play Install for free Android 5M+ downloads · 4.8 rating iOS soon

Episodes

2025.07.07 | GPT-4o在语义任务中表现良好;潜在空间模拟精度高。 07.07.2025

本期的 4 篇论文如下: [00:27] 🖼 How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks(GPT-4o的视觉理解能力如何?在标准计算机视觉任务上评估多模态基础模型) [01:09] 🌌 Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation(迷失于潜在空间:用于物理模拟的潜在扩散模型实证研究) [01:45] 🇮 Eka-Eval : A Compre...

【周末特辑】7月第1周最火AI论文 | 多模态推理模型提升;短视频理解领先。 06.07.2025

本期的 5 篇论文如下: [00:35] TOP1(🔥165) | 🧠 GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning(GLM-4.1V-Thinking:基于可扩展强化学习的通用多模态推理) [02:53] TOP2(🔥108) | 🎬 Kwai Keye-VL Technical Report(Kwai Keye-VL 技术报告) [05:17] TOP3(🔥67) | 🎨 LongAnimation: Long Animation Generation with Dynamic Global-Local Memory(LongAnimation:基于动...

【月末特辑】6月最火AI论文 | LLM通过自我反思提升性能;MiniMax-M1高效扩展测试计算。 05.07.2025

本期的 10 篇论文如下: [00:37] TOP1(🔥258) | 💡 Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning(反思、重试、奖励:通过强化学习实现LLM的自我提升) [02:51] TOP2(🔥249) | 💡 MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention(MiniMax-M1:利用闪电注意力高效扩展测试时计算) [05:24] TOP3(🔥240) | 🤖 Reinforcement Pre-Training(强化预训练) [07:54] TOP4(🔥1...

2025.07.04 | WebSailor提升LLM推理能力;LangScene-X优化3D场景重建。 04.07.2025

本期的 15 篇论文如下: [00:22] 🧭 WebSailor: Navigating Super-human Reasoning for Web Agent(WebSailor:为Web Agent导航超人推理) [00:59] 🖼 LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion(LangScene-X:通过TriMap视频扩散重建可泛化的3D语言嵌入场景) [01:44] 🧬 IntFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure P...

2025.07.03 | 多模态模型提升短视频理解;动画生成保持颜色一致。 04.07.2025

本期的 9 篇论文如下: [00:21] 🎬 Kwai Keye-VL Technical Report(Kwai Keye-VL 技术报告) [01:02] 🎨 LongAnimation: Long Animation Generation with Dynamic Global-Local Memory(LongAnimation:基于动态全局-局部记忆的长期动画生成) [01:50] 👁 Depth Anything at Any Condition(任意条件下的深度感知) [02:28] 🤖 A Survey on Vision-Language-Action Models: An Action Tokenization Perspective(视觉-语言-动作模...

2025.07.02 | 多模态推理提升;双向嵌入优化 02.07.2025

本期的 12 篇论文如下: [00:23] 💡 GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning(GLM-4.1V-Thinking:基于可扩展强化学习的通用多模态推理) [01:00] 🖼 MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings(MoCa:模态感知持续预训练提升双向多模态嵌入效果) [01:35] 🔬 SciArena: An Open Evaluation Platform for Foundati...

2025.07.01 | 多模态生成领先;视频扩散效率提升 01.07.2025

本期的 15 篇论文如下: [00:21] 🖼 Ovis-U1 Technical Report(Ovis-U1 技术报告) [00:58] 🎬 VMoBA: Mixture-of-Block Attention for Video Diffusion Models(VMoBA:用于视频扩散模型的混合块注意力机制) [01:36] ✍ Calligrapher: Freestyle Text Image Customization(书法家:自由风格的文本图像定制) [02:21] 🖼 Listener-Rewarded Thinking in VLMs for Image Preferences(图像偏好:视觉语言模型中基于监听者奖励的思考...

2025.06.30 | 3D视觉编辑;视频令牌压缩 01.07.2025

本期的 14 篇论文如下: [00:26] 🎨 BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing(BlenderFusion:基于3D的视觉编辑和生成式合成) [00:59] ✂ LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs(LLaVA-Scissor:基于语义连通分量的视频LLM令牌压缩) [01:42] 🖼 XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation...

【周末特辑】6月第5周最火AI论文 | 拖拽式大模型提升效率;法线光照恢复高精度。 28.06.2025

本期的 5 篇论文如下: [00:42] TOP1(🔥107) | 🧲 Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights(拖拽式大语言模型:零样本提示到权重) [02:39] TOP2(🔥80) | 💡 Light of Normals: Unified Feature Representation for Universal Photometric Stereo(法线光照:用于通用光度立体的统一特征表示) [04:59] TOP3(🔥79) | 🖼 Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding(...

2025.06.27 | 强化学习提升搜索效率;记忆增强生成逼真驾驶场景。 28.06.2025

本期的 15 篇论文如下: [00:25] 🔍 MMSearch-R1: Incentivizing LMMs to Search(MMSearch-R1:激励大型多模态模型进行搜索) [00:59] 🚗 MADrive: Memory-Augmented Driving Scene Modeling(MADrive:基于记忆增强的驾驶场景建模) [01:43] 🤖 WorldVLA: Towards Autoregressive Action World Model(WorldVLA:面向自回归动作世界模型) [02:23] 💡 Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Gener...

2025.06.26 | 高质量多模态模型;4比特量化提升性能 26.06.2025

本期的 14 篇论文如下: [00:23] 🖼 ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation(ShareGPT-4o-Image:通过GPT-4o级别的图像生成能力对齐多模态模型) [01:05] 🛡 Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models(面向稳健4比特量化的异常值安全预训练大语言模型) [01:49] 🎨 Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistenc...

2025.06.25 | AnimaX提升3D非生物体动画效果;Matrix-Game优化游戏世界模型。 26.06.2025

本期的 15 篇论文如下: [00:25] 🤖 AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models(AnimaX:利用联合视频-姿态扩散模型为3D非生物体赋予动画效果) [01:11] 🎮 Matrix-Game: Interactive World Foundation Model(矩阵游戏:交互式世界基础模型) [01:50] 🧠 GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning(GRPO-CARE:一致性感知的多模态推理强化学习) [02:...

2025.06.24 | 法线光照新方法提升细节;多模态生成模型表现优异。 25.06.2025

本期的 15 篇论文如下: [00:24] 💡 Light of Normals: Unified Feature Representation for Universal Photometric Stereo(法线光照:用于通用光度立体的统一特征表示) [01:00] 🎨 OmniGen2: Exploration to Advanced Multimodal Generation(OmniGen2:迈向更高级的多模态生成探索) [01:39] ✍ LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning(LongWriter-Zero:通过强化学习掌握超长文本...

2025.06.23 | DnD降低计算开销;视觉引导提升RAG性能。 23.06.2025

本期的 12 篇论文如下: [00:23] 🧲 Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights(拖拽式大语言模型:零样本提示到权重) [01:04] 🖼 Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding(视觉引导分块:增强RAG的多模态文档理解方案) [01:49] 🔀 PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models(PAROAtt...

【周末特辑】6月第4周最火AI论文 | 高效扩展推理能力;多模态金融评估基准。 21.06.2025

本期的 5 篇论文如下: [00:36] TOP1(🔥216) | 💡 MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention(MiniMax-M1:利用闪电注意力高效扩展测试时计算) [02:44] TOP2(🔥82) | 📊 MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation(MultiFinBen:一个多语言、多模态和难度感知的金融领域大语言模型评估基准) [05:32] TOP3(🔥64) | 🔬 Scientis...

2025.06.20 | 强化学习提升跨领域推理;语音情感检测基准精细化。 20.06.2025

本期的 4 篇论文如下: [00:24] 🧠 Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective(跨领域视角下重新审视强化学习在大型语言模型推理中的应用) [01:00] 🗣 EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection(EmoNet-Voice:一个用于语音情感检测的精细化、专家验证的基准) [01:55] 🎵 SonicVerse: Multi-Task Learning for Music Feature-Informe...

2025.06.19 | SEKAI数据集提升视频生成;原型推理增强LLM泛化能力。 19.06.2025

本期的 15 篇论文如下: [00:22] 🌍 Sekai: A Video Dataset towards World Exploration(Sekai:一个面向世界探索的视频数据集) [01:02] 💡 ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs(原型推理:作为大型语言模型中通用推理基础的原型) [01:43] 💡 GenRecal: Generation after Recalibration from Large to Small Vision-Language Models(GenRecal:从大型到小型视觉-语言模型的重...

2025.06.18 | MultiFinBen揭示金融模型局限;测试时计算提升LLM Agent性能。 18.06.2025

本期的 15 篇论文如下: [00:23] 📊 MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation(MultiFinBen:一个多语言、多模态和难度感知的金融领域大语言模型评估基准) [01:03] 🤖 Scaling Test-time Compute for LLM Agents(扩展LLM Agent的测试时计算) [01:38] 🎼 CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following(CMI-Bench:一个评估...

2025.06.17 | MiniMax-M1提升推理性能;多模态模型认知测试创新。 17.06.2025

本期的 15 篇论文如下: [00:22] 💡 MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention(MiniMax-M1:利用闪电注意力高效扩展测试时计算) [01:00] 🔬 Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning(科学家的首次考试:通过感知、理解和推理来探索多模态大型语言模型的认知能力) [01:47] 🧐 DeepResearch Bench: A Comprehensive Benc...

2025.06.16 | 跨模态合成新视角图像;策略依从型智能体抗攻击 17.06.2025

本期的 15 篇论文如下: [00:23] 🖼 Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation(基于跨模态注意力提炼的对齐新视角图像与几何体合成) [01:02] 🛡 Effective Red-Teaming of Policy-Adherent Agents(有效对抗策略依从型智能体) [01:39] 🔄 The Diffusion Duality(扩散二元性) [02:20] 🤖 LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?...

【周末特辑】6月第3周最火AI论文 | 强化预训练提升语言模型推理能力;多语种分类器改善问答系统可信度。 15.06.2025

本期的 5 篇论文如下: [00:43] TOP1(🔥199) | 🤖 Reinforcement Pre-Training(强化预训练) [03:06] TOP2(🔥124) | 🕰 Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA(明日依旧为真吗?多语种常青问题分类以提升可信赖的问答系统) [05:07] TOP3(🔥105) | 🧠 Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models(自信即全部:基于语言模型的...

2025.06.13 | 医学推理模型新范式;自动化构建软件工程数据集 14.06.2025

本期的 15 篇论文如下: [00:22] 🩺 ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning(ReasonMed:一个用于推进医学推理的37万多智能体生成数据集) [01:12] 🏭 SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks(SWE-Factory:你的问题解决训练数据和评估基准自动化工厂) [01:55] 🖼 Text-Aware Image Restoration with Diffusion Models(...

2025.06.12 | 自信微调提升模型表现;视频生成模型高效优化。 12.06.2025

本期的 13 篇论文如下: [00:23] 🧠 Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models(自信即全部:基于语言模型的小样本强化学习微调) [01:07] 🎬 Seedance 1.0: Exploring the Boundaries of Video Generation Models(Seedance 1.0:探索视频生成模型的边界) [01:50] 🥽 PlayerOne: Egocentric World Simulator(PlayerOne:以自我为中心的真实世界模拟器) [02:30] 🎬 Autoregressive Adversarial...

2025.06.11 | LLM存在地缘政治偏见;RuleReasoner提升推理效率。 11.06.2025

本期的 15 篇论文如下: [00:22] 🌍 Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models(LLM中的地缘政治偏见:在当代语言模型中,哪些是“好”国家,哪些是“坏”国家?) [01:09] 🤖 RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling(RuleReasoner:基于领域感知动态采样的强化规则推理) [01:48] 🖼 Autoregressive Semantic...

2025.06.10 | 强化学习改进语言模型;医学多模态模型提升推理能力。 10.06.2025

本期的 15 篇论文如下: [00:21] 🤖 Reinforcement Pre-Training(强化预训练) [01:01] 🩺 Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning(灵枢:用于统一多模态医学理解与推理的通用基础模型) [01:42] 📱 MiniCPM4: Ultra-Efficient LLMs on End Devices(MiniCPM4:终端设备上的超高效大型语言模型) [02:30] 🛡 Saffron-1: Towards an Inference Scaling Paradigm for...

Listen to the HuggingFace 每日AI论文速递 podcast in Replaio

Radio and podcasts in one app - free, with no sign-up. Install today and do not miss the launch

Get it on Google Play

Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.