cs.LG（2025-06-29）
📊 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) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare Settings | 提出Forget-MI以解决医疗领域多模态信息遗忘问题 | multimodal | ✅ | |
| 2 | Do LLMs Dream of Discrete Algorithms? | 提出神经符号方法以增强大型语言模型的逻辑推理能力 | large language model | ||
| 3 | Masked Gated Linear Unit | 提出Masked Gated Linear Units以解决GLU的内存瓶颈问题 | large language model | ||
| 4 | Theoretical Modeling of LLM Self-Improvement Training Dynamics Through Solver-Verifier Gap | 提出自我提升训练动态模型以优化大语言模型性能 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | The language of time: a language model perspective on time-series foundation models | 提出时间序列基础模型的新视角以解决跨域迁移问题 | representation learning large language model foundation model | ||
| 6 | Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems | 提出MTORL以解决在线广告中的稀疏数据问题 | reinforcement learning offline RL offline reinforcement learning | ||
| 7 | Fractional Policy Gradients: Reinforcement Learning with Long-Term Memory | 提出分数策略梯度方法以解决长期记忆强化学习问题 | reinforcement learning |