cs.LG（2025-05-01）

📊 共 7 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) (5) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
1 R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training R&B：通过领域重组和数据混合平衡实现高效的基础模型训练 foundation model multimodal
2 Toward Automated Regulatory Decision-Making: Trustworthy Medical Device Risk Classification with Multimodal Transformers and Self-Training 提出基于多模态Transformer和自训练的医疗器械风险自动分类方法 multimodal
3 NeMo-Inspector: A Visualization Tool for LLM Generation Analysis NeMo-Inspector：用于LLM生成数据分析的可视化工具，提升合成数据质量。 large language model
4 T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation T2VPhysBench：首个用于评估文本生成视频物理一致性的基准测试 instruction following
5 Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing 提出MoSA：通过专家选择路由实现内容感知的可学习稀疏注意力机制，提升计算效率。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
6 Variational OOD State Correction for Offline Reinforcement Learning 提出DASP方法，通过变分OOD状态校正提升离线强化学习性能 reinforcement learning offline reinforcement learning
7 Learning Conservative Neural Control Barrier Functions from Offline Data 提出基于离线数据的保守神经控制障碍函数学习方法，提升动态系统安全控制。 reinforcement learning offline reinforcement learning conservative q-learning ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页