cs.LG（2026-07-10）

📊 共 13 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection	提出Semantic Pareto-DQN以解决金融异常检测中的类不平衡问题	reinforcement learning large language model
2	CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding	提出CoCoT-EEG以优化EEG解码性能	contrastive learning foundation model
3	Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning	提出基于动作因子的多智能体强化学习以解决量子设备调谐问题	reinforcement learning
4	Similarity search generalisation in contrastive learning with InfoNCE loss	提出新连续性界限以改进对比学习中的相似性搜索	contrastive learning
5	EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDi	提出EXHOLD以解决大规模网约车匹配中的体验控制问题	predictive model spatiotemporal
6	Mach-Mind-4-Flash Technical Report	提出Mach-Mind-4-Flash以提升大规模强化学习性能	reinforcement learning distillation

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

#	题目	一句话要点	标签	🔗	⭐
7	All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models	提出Rashomon解释范式以解决可解释性与准确性之间的权衡问题	large language model
8	LLM for EDA in Front-End Design: Challenges and Opportunities	利用大型语言模型提升前端设计中的电子设计自动化效率	large language model
9	Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning	提出Super-Tuning以提高大语言模型的稀疏微调效率	large language model
10	COBS: Cumulant Order Block Sparse Attention	提出COBS以解决大语言模型中的KV缓存读取瓶颈问题	large language model
11	Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing	提出关联感知的上下文强盗算法以优化LLM路由	large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning	提出Shortcut Trajectory Planning以解决离线强化学习中的高推理成本问题	locomotion manipulation reinforcement learning
13	Learning More from Less: Reinforcement Learning from Hindsight	提出从失败中学习的方法以提升强化学习样本效率	manipulation reinforcement learning vision-language-action

⬅️ 返回 cs.LG 首页 · 🏠 返回主页