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 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training | 提出R&B框架以解决数据混合训练中的效率问题 | foundation model multimodal | ||
| 2 | Toward Automated Regulatory Decision-Making: Trustworthy Medical Device Risk Classification with Multimodal Transformers and Self-Training | 提出多模态Transformer框架以解决医疗设备风险分类问题 | multimodal | ||
| 3 | NeMo-Inspector: A Visualization Tool for LLM Generation Analysis | 提出NeMo-Inspector以简化合成数据集分析问题 | large language model | ||
| 4 | T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation | 提出T2VPhysBench以评估文本到视频生成中的物理一致性问题 | instruction following | ||
| 5 | Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing | 提出混合稀疏注意力机制以解决自注意力计算复杂度问题 | 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Density-Aware Safety Perception以解决离线强化学习中的状态分布偏移问题 | reinforcement learning offline reinforcement learning | ||
| 7 | Learning Conservative Neural Control Barrier Functions from Offline Data | 提出离线数据训练的保守神经控制屏障函数以解决安全控制问题 | reinforcement learning offline reinforcement learning conservative q-learning | ✅ |