cs.LG（2025-04-24）

📊 共 20 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗2) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models 提出NPE-PFN，利用表格型预训练模型高效解决模拟推理中的样本效率问题 foundation model
2 A Simple Review of EEG Foundation Models: Datasets, Advancements and Future Perspectives 综述脑电图(EEG)基础模型：数据集、进展与未来展望 foundation model
3 Class-Conditional Distribution Balancing for Group Robust Classification 提出类条件分布平衡方法，无需偏见标注实现群体鲁棒分类 foundation model
4 Statistical Runtime Verification for LLMs via Robustness Estimation 提出基于鲁棒性估计的LLM统计运行时验证方法RoMA large language model
5 L3: DIMM-PIM Integrated Architecture and Coordination for Scalable Long-Context LLM Inference 提出L3架构以解决长文本序列推理中的内存瓶颈问题 large language model
6 Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks 探索大模型与小模型协同，加速领域任务自适应 large language model
7 On-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration 提出基于AWQ量化与FPGA加速的Qwen2.5模型端侧高效推理框架 large language model
8 Symbolic Representation for Any-to-Any Generative Tasks 提出一种基于符号表示的通用生成框架，无需训练即可完成多模态任务。 multimodal
9 High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services 利用LLM生成高保真复杂测试数据，用于Google SQL代码生成服务 large language model

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

#题目一句话要点标签🔗⭐
10 Training Large Language Models to Reason via EM Policy Gradient 提出EM策略梯度算法，提升LLM在复杂推理任务中的性能与可解释性 reinforcement learning PPO large language model
11 Cooperative Task Offloading through Asynchronous Deep Reinforcement Learning in Mobile Edge Computing for Future Networks 提出基于异步深度强化学习的协同任务卸载框架CTO-TP，优化未来网络MEC中的延迟和能耗。 reinforcement learning deep reinforcement learning
12 Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning Plasticine：加速塑性驱动的深度强化学习研究的开源框架 reinforcement learning deep reinforcement learning ✅
13 RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning RAGEN：通过多轮强化学习理解LLM Agent的自我进化 reinforcement learning large language model ✅
14 CaRL: Learning Scalable Planning Policies with Simple Rewards CaRL：通过简单奖励学习可扩展的规划策略，应用于自动驾驶。 reinforcement learning PPO imitation learning
15 ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders ExOSITO：结合辅助信息的ICU血检医嘱可解释离线策略学习 policy learning privileged information
16 Do We Need Transformers to Play FPS Video Games? 在第一人称射击游戏中使用Transformer不如传统方法 reinforcement learning offline reinforcement learning decision transformer
17 Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization 提出TCTO框架，通过图驱动路径优化实现自动化特征工程，提升下游任务性能。 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
18 High-Performance Reinforcement Learning on Spot: Optimizing Simulation Parameters with Distributional Measures 在Spot机器人上实现高性能强化学习：利用分布度量优化仿真参数 locomotion sim2real reinforcement learning
19 The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks 研究Hessian特征值谱密度类型对神经网络泛化能力评估的影响 manipulation

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

#题目一句话要点标签🔗⭐
20 OmegAMP: Targeted AMP Discovery through Biologically Informed Generation OmegAMP：通过生物信息指导的生成方法实现靶向抗菌肽发现 AMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页