cs.LG（2025-09-10）
📊 共 13 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) (7 🔗1)
支柱九：具身大模型 (Embodied Foundation Models) (4)
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) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Merge-of-Thought Distillation | 提出Merge-of-Thought Distillation，解决长链CoT模型蒸馏中多教师冲突问题。 | distillation chain-of-thought | ||
| 2 | Tokenizing Loops of Antibodies | 提出Igloo抗体环区Tokenizer，提升蛋白语言模型性能并促进抗体设计 | contrastive learning foundation model multimodal | ||
| 3 | NurseSchedRL: Attention-Guided Reinforcement Learning for Nurse-Patient Assignment | 提出NurseSchedRL以解决护士-患者分配问题 | reinforcement learning PPO | ||
| 4 | AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning | AgentGym-RL：通过多轮强化学习训练LLM智能体进行长程决策 | reinforcement learning | ||
| 5 | Replicable Reinforcement Learning with Linear Function Approximation | 针对线性函数逼近的强化学习，提出可复现算法以提升实验一致性。 | reinforcement learning | ||
| 6 | MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents | 提出MobileRL框架，通过在线强化学习提升移动GUI智能体的任务完成能力 | reinforcement learning | ✅ | |
| 7 | Using AI to Optimize Patient Transfer and Resource Utilization During Mass-Casualty Incidents: A Simulation Platform | 提出基于深度强化学习的决策支持AI，优化大规模伤亡事件中的患者转运和资源利用。 | reinforcement learning deep 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 | LLM-VeriPPA: Power, Performance, and Area Optimization aware Verilog Code Generation with Large Language Models | VeriPPA：利用大语言模型实现功耗、性能和面积优化的Verilog代码生成 | large language model | ||
| 9 | Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics | 利用视觉-语言模型进行高能物理中微子事件分类 | large language model multimodal | ||
| 10 | Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities | 探索AI在信号处理教育中的应用：挑战与机遇 | large language model | ||
| 11 | ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System | ChemBOMAS：利用LLM增强的多智能体系统加速化学领域的贝叶斯优化 | large language model |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | Fast attention mechanisms: a tale of parallelism | 提出ANNA注意力机制，加速Transformer并保持大规模并行计算能力 | MPC |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 13 | Energy-convergence trade off for the training of neural networks on bio-inspired hardware | 提出能量收敛权衡方法以优化神经网络训练 | PULSE |