cs.LG（2025-07-24）

📊 共 14 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) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
1 Deep Reinforcement Learning for Real-Time Green Energy Integration in Data Centers 提出基于深度强化学习的能源管理系统，优化数据中心绿色能源实时集成 reinforcement learning deep reinforcement learning DRL
2 Market Making Strategies with Reinforcement Learning 提出基于强化学习的市场做市策略，解决库存风险和非平稳市场动态问题 reinforcement learning deep reinforcement learning DRL
3 Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning 提出改进的双仿射度量，提升强化学习中鲁棒表征的质量与适应性。 reinforcement learning representation learning
4 Optimizing Metachronal Paddling with Reinforcement Learning at Low Reynolds Number 利用强化学习优化低雷诺数下的后摆运动，探索最优划水策略 reinforcement learning
5 Even Faster Simulations with Flow Matching: A Study of Zero Degree Calorimeter Responses 利用Flow Matching加速零度量能器响应模拟，实现高能物理领域快速仿真 flow matching ✅
6 C2G-KD: PCA-Constrained Generator for Data-Free Knowledge Distillation 提出C2G-KD，一种基于PCA约束生成器的数据自由知识蒸馏框架 distillation
7 GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learning 提出GLANCE，通过逻辑推理、动态图精炼和自适应聚类增强异质图表示学习。 representation learning
8 Efficient Uncertainty in LLMs through Evidential Knowledge Distillation 提出基于证据知识蒸馏的高效LLM不确定性量化方法 distillation
9 Group Sequence Policy Optimization 提出GSPO算法，通过序列级策略优化提升大型语言模型强化学习训练的稳定性与效率。 reinforcement learning large language model
10 Hybrid quantum-classical algorithm for near-optimal planning in POMDPs 提出QBRL算法，加速部分可观测马尔可夫决策过程中的近优规划。 reinforcement learning model-based RL

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
11 Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents Explainable Mapper：利用扰动解释与验证Agent探索LLM嵌入空间 large language model
12 The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm 揭示GPTQ量化本质：将其等价于Babai最近平面算法，并提出改进方法 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 Test-time Offline Reinforcement Learning on Goal-related Experience 提出基于目标相关经验的测试时离线强化学习方法，提升泛化性能。 manipulation reinforcement learning offline reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
14 Gait Recognition Based on Tiny ML and IMU Sensors 提出基于TinyML和IMU的步态识别系统，实现低功耗实时活动分类。 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页