cs.LG(2025-02-10)

📊 共 5 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (2) 支柱一:机器人控制 (Robot Control) (2 🔗1) 支柱四:生成式动作 (Generative Motion) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗
1 Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysis 提出不确定性感知的LLM自适应方法,用于提升蛋白质互作分析的可靠性。 large language model
2 MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations MATH-Perturb:通过难题扰动评估LLM的数学推理能力 large language model

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
3 Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects 提出几何感知强化学习以解决变形物体操控问题 manipulation reinforcement learning
4 Select before Act: Spatially Decoupled Action Repetition for Continuous Control 提出空间解耦动作重复框架SDAR,提升连续控制任务的样本效率和策略性能。 locomotion manipulation reinforcement learning

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
5 History-Guided Video Diffusion 提出历史引导视频扩散方法,解决变长历史帧条件下的视频生成问题。 classifier-free guidance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页