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(基于扩散模型的文本感知图像修复)
02:36 🎬 VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos(VRBench:长篇叙事视频中多步骤推理的基准测试)
03:22 🎬 AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation(AniMaker:基于MCTS驱动的片段生成实现自动化多智能体动画故事叙述)
04:09 🧮 Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training(Domain2Vec:向量化数据集以在无训练情况下找到最优数据混合)
04:52 🎮 Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts(Optimus-3: 面向具有可扩展任务专家的通用多模态Minecraft智能体)
05:27 🧠 Magistral(Magistral:Mistral 的首个推理模型)
06:07 🤖 AutoMind: Adaptive Knowledgeable Agent for Automated Data Science(AutoMind:面向自动化数据科学的自适应知识型智能体)
06:53 🎨 PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework(PosterCraft:重新思考统一框架下的高质量美学海报生成)
07:43 🎬 VideoDeepResearch: Long Video Understanding With Agentic Tool Using(VideoDeepResearch:使用Agentic工具的长视频理解)
08:22 🚫 ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark(ChineseHarm-Bench:一个中文有害内容检测的基准)
09:01 🎨 CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation(CreatiPoster:面向可编辑和可控的多层图形设计生成)
09:48 💡 Resa: Transparent Reasoning Models via SAEs(Resa:基于稀疏自编码器的透明推理模型)
10:30 🤖 Ming-Omni: A Unified Multimodal Model for Perception and Generation(Ming-Omni:一个用于感知和生成的统一多模态模型)

【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