cs.LG（2025-02-25）

📊 共 8 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) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Data Augmentation for Instruction Following Policies via Trajectory Segmentation	提出基于轨迹分割的数据增强方法，提升指令跟随策略的性能	imitation learning instruction following
2	ARBoids: Adaptive Residual Reinforcement Learning With Boids Model for Cooperative Multi-USV Target Defense	提出ARBoids，结合Boids模型与自适应残差强化学习，解决多无人艇协同目标防御问题。	reinforcement learning deep reinforcement learning DRL
3	Larger or Smaller Reward Margins to Select Preferences for Alignment?	提出对齐潜力指标，提升基于偏好学习的大语言模型对齐效果	preference learning large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
4	Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems	提出基于贝叶斯优化的多目标超参数优化方法，提升LLM和RAG系统性能。	large language model
5	AMPO: Active Multi-Preference Optimization for Self-play Preference Selection	提出AMPO，通过主动多偏好优化实现自博弈偏好选择，提升语言模型对齐效果。	large language model	✅
6	A General Framework to Enhance Fine-tuning-based LLM Unlearning	提出GRUN框架，提升基于微调的大语言模型遗忘能力和通用性。	large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
7	MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks	提出MM-PoisonRAG框架，揭示多模态RAG易受知识投毒攻击的脆弱性。	manipulation large language model multimodal
8	Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale	提出卷积多混合架构，加速大规模语言模型训练并提升性能。	manipulation linear attention

⬅️ 返回 cs.LG 首页 · 🏠 返回主页