cs.LG（2024-06-29）
📊 共 5 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation | 提出基于两阶段强化学习的多实体任务分配方法，解决动态环境下的任务分配问题。 | reinforcement learning | ✅ | |
| 2 | A Bayesian Solution To The Imitation Gap | 提出贝叶斯模仿差距解决方案(BIG)，解决专家与智能体观测差异下的模仿学习问题 | reinforcement learning imitation learning inverse reinforcement learning | ||
| 3 | Time Series Clustering with General State Space Models via Stochastic Variational Inference | 提出基于随机变分推断的通用状态空间模型混合时间序列聚类方法 | state space model |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks | 提出知识驱动的简约学习框架，克服深度网络过度依赖规模扩张的局限性 | foundation model | ||
| 5 | VcLLM: Video Codecs are Secretly Tensor Codecs | VcLLM：利用视频编解码器作为张量编解码器，实现高效LLM训练与推理 | large language model |