cs.LG（2024-04-19）

📊 共 12 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 Data-Incremental Continual Offline Reinforcement Learning 提出数据增量持续离线强化学习以解决主动遗忘问题 reinforcement learning offline RL offline reinforcement learning
2 R3L: Relative Representations for Reinforcement Learning 提出相对表示法以解决视觉强化学习中的模型重用问题 reinforcement learning representation learning
3 Dynamic Temperature Knowledge Distillation 提出动态温度知识蒸馏以解决知识转移不足问题 teacher-student distillation ✅
4 UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender Systems 提出UnifiedRL以解决大规模推荐系统中的多任务融合问题 reinforcement learning offline RL
5 Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning 提出GEASD框架以提升目标条件强化学习的探索效率 reinforcement learning
6 Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation 提出BEER以自适应正则化表示秩解决DRL性能问题 reinforcement learning deep reinforcement learning DRL ✅
7 Continuous-time Risk-sensitive Reinforcement Learning via Quadratic Variation Penalty 提出连续时间风险敏感强化学习以应对模型不确定性问题 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
8 CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models 提出CyberSecEval 2以评估大型语言模型的网络安全风险 large language model
9 STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases 提出STaRK以解决复杂查询的半结构化检索问题 large language model ✅
10 Towards Logically Consistent Language Models via Probabilistic Reasoning 通过概率推理实现语言模型的逻辑一致性 large language model
11 Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank 提出过生成与排序方法以提升数学选择题干扰项生成质量 large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
12 A Weight-aware-based Multi-source Unsupervised Domain Adaptation Method for Human Motion Intention Recognition 提出基于权重的多源无监督领域适应方法以解决人类运动意图识别问题 human motion

⬅️ 返回 cs.LG 首页 · 🏠 返回主页