HuggingFace 每日AI论文速递

2025.05.13 | 视觉-语言模型提升多模态能力;优化训练策略增强推理潜力。


Listen Later

本期的 15 篇论文如下:

[00:24] 💡 Seed1.5-VL Technical Report(Seed1.5-VL 技术报告)

[01:04] 🧠 MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining(MiMo:释放语言模型的推理潜力——从预训练到后训练)

[01:48] 🖼 Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets(Step1X-3D:迈向高质量和可控的纹理3D资产生成)

[02:29] 🤝 Learning from Peers in Reasoning Models(推理模型中的同伴学习)

[03:08] 🎨 Unified Continuous Generative Models(统一连续生成模型)

[03:49] 🤖 REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback(REFINE-AF:一种通过强化学习和自动反馈,以自生成指令对齐语言模型的任务无关框架)

[04:44] 💃 DanceGRPO: Unleashing GRPO on Visual Generation(DanceGRPO:在视觉生成领域释放GRPO的潜力)

[05:25] 🧠 AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection(AttentionInfluence:采用注意力头影响进行弱到强预训练数据选择)

[06:10] 🌐 WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch(WebGen-Bench:评估大型语言模型从零生成交互式和功能性网站的能力)

[06:53] 📈 Learning Dynamics in Continual Pre-Training for Large Language Models(大型语言模型持续预训练中的学习动态)

[07:28] 🏆 Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning(Skywork-VL Reward:一种用于多模态理解和推理的有效奖励模型)

[08:11] 🧠 Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent(用于高效自适应搜索代理的增强型内外知识协同推理)

[08:50] 🤖 H$^{\mathbf{3}}$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning(H$^{\mathbf{3}}$DP:用于视觉运动学习的三重分层扩散策略)

[09:36] 🎨 Continuous Visual Autoregressive Generation via Score Maximization(基于得分最大化的连续视觉自回归生成)

[10:26] 🧠 Overflow Prevention Enhances Long-Context Recurrent LLMs(溢出预防增强长文本循环LLM)

【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