cs.LG（2024-06-18）

📊 共 9 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity	提出BIOSCAN-5M数据集以推动昆虫多样性研究	contrastive learning multimodal zero-shot transfer	✅
2	Autonomous navigation of catheters and guidewires in mechanical thrombectomy using inverse reinforcement learning	提出基于逆强化学习的导管自主导航方法，用于机械取栓术。	reinforcement learning inverse reinforcement learning reward shaping
3	Variational Distillation of Diffusion Policies into Mixture of Experts	提出VDD：通过变分推断将扩散策略蒸馏为混合专家模型，提升行为学习效率。	diffusion policy distillation
4	A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo	提出一种仅使用车载视觉信息的超人水平强化学习赛车智能体，在Gran Turismo中实现自主驾驶	reinforcement learning deep reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
5	Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models	提出概率概念解释器(PACE)，为视觉Transformer提供可信的概念解释。	large language model foundation model
6	Dissecting Adversarial Robustness of Multimodal LM Agents	提出Agent Robustness Evaluation框架以解决多模态语言模型的对抗鲁棒性问题	multimodal	✅
7	GFM4MPM: Towards Geospatial Foundation Models for Mineral Prospectivity Mapping	GFM4MPM：面向矿产远景预测的地理空间基础模型	foundation model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning	提出C-LAIfO，通过对比学习实现视觉差异下的视频模仿学习	manipulation imitation learning contrastive learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Neural Approximate Mirror Maps for Constrained Diffusion Models	提出神经近似镜像映射，用于约束扩散模型以满足复杂约束条件。	MDM

⬅️ 返回 cs.LG 首页 · 🏠 返回主页