cs.LG（2026-06-03）
📊 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) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Validity Threats for Foundation Model Research | 提出评估框架以应对基础模型研究中的有效性威胁 | foundation model | ||
| 2 | Data Attribution in Large Language Models via Bidirectional Gradient Optimization | 通过双向梯度优化提出训练数据归因方法解决LLM可解释性问题 | large language model | ||
| 3 | STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations | 提出STRIDE以解决训练数据归因问题 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Reinforcement Learning from Rich Feedback with Distributional DAgger | 提出基于分布式DAgger的强化学习以利用丰富反馈 | reinforcement learning imitation learning distillation | ||
| 5 | Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning | 提出CHERRL以解决基于评分的强化学习中的奖励黑客问题 | reinforcement learning | ✅ |