cs.LG（2024-04-09）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (8 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning 提出多样化随机价值函数以解决离线强化学习中的不确定性问题 reinforcement learning policy learning offline reinforcement learning
2 Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosus 提出深度强化学习以优化电子健康记录中的个性化诊断路径 reinforcement learning deep reinforcement learning DRL
3 Policy-Guided Diffusion 提出政策引导扩散以解决离线数据分布偏移问题 reinforcement learning offline reinforcement learning world model
4 Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction 提出任务特定动作修正以解决多任务强化学习问题 reinforcement learning policy learning
5 Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective 提出图强化学习以解决组合优化问题 reinforcement learning
6 Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning 提出FormulaGPT以解决符号回归中的推理效率问题 reinforcement learning
7 CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as Teachers 提出CLIP-Embed-KD以解决知识蒸馏中的计算效率问题 distillation ✅
8 Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis 提出AFedPG框架以解决异步联邦强化学习中的延迟问题 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
9 Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models 提出FedPipe以解决大语言模型的隐私保护微调问题 large language model
10 Zero-Shot Relational Learning for Multimodal Knowledge Graphs 提出一种新框架以解决多模态知识图谱的零-shot关系学习问题 multimodal
11 Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models 提出多种技术评估大型语言模型对表格数据的记忆与学习能力 large language model ✅
12 CausalBench: A Comprehensive Benchmark for Causal Learning Capability of LLMs 提出CausalBench以评估大语言模型的因果学习能力 large language model
13 AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts 提出AEGIS以解决生成AI内容安全风险问题 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
14 Quantum State Generation with Structure-Preserving Diffusion Model 提出基于去噪扩散模型的量子态生成方法以满足物理约束 classifier-free guidance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页