HuggingFace 每日AI论文速递

2025.04.21 | 强化学习未提升新推理能力;MIG优化指令微调数据选择。


Listen Later

本期的 9 篇论文如下:

[00:22] 🤔 Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?(强化学习真的能激励大语言模型产生超越基础模型的推理能力吗?)

[00:59] 🧠 MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space(MIG:通过最大化语义空间中的信息增益实现指令微调的自动数据选择)

[01:41] 🤔 Could Thinking Multilingually Empower LLM Reasoning?(多语思考能否增强大型语言模型的推理能力?)

[02:25] 🏙 AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis(AerialMegaDepth:学习空中-地面重建与视角合成)

[03:09] 🏠 HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation(HiScene:利用等距视图生成创建分层3D场景)

[03:52] 💡 NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes(NodeRAG:使用异构节点构建的基于图结构的RAG)

[04:30] 🧠 It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization(一切皆有关联:一次关于测试时记忆、注意力偏差、保留和在线优化的探索之旅)

[05:07] 🏞 Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images(令牌化图像块:用于大型图像中有效去雾的全局上下文融合)

[05:51] 🧠 Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models(思想操控:外部思想能够有效应用于大型推理模型)

【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

...more
View all episodesView all episodes
Download on the App Store

HuggingFace 每日AI论文速递By duan