cs.LG（2025-09-29）

📊 共 12 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) (8) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1)

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

#题目一句话要点标签🔗⭐
1 World Model for AI Autonomous Navigation in Mechanical Thrombectomy 提出基于世界模型的TD-MPC2算法，提升机械取栓术中AI自主导航性能 reinforcement learning SAC world model
2 When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training 元-Bandit LLM训练中涌现的贪婪利用偏差研究 reinforcement learning reward design large language model
3 Safe In-Context Reinforcement Learning 提出安全上下文强化学习方法，解决无参数更新适应过程中的安全约束问题 reinforcement learning
4 SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression SIRI：通过交错压缩扩展迭代强化学习，提升大型推理模型的效率与准确性。 reinforcement learning
5 ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation 提出ORPO-Distill，通过混合策略偏好优化实现跨架构LLM蒸馏 distillation
6 Safe Reinforcement Learning-Based Vibration Control: Overcoming Training Risks with LQR Guidance 提出基于LQR引导的安全强化学习振动控制，解决训练过程中的安全风险。 reinforcement learning
7 Machine Learning Algorithms for Improving Black Box Optimization Solvers 综述：机器学习算法提升黑盒优化求解器性能 reinforcement learning Mamba
8 LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection LEAF：一种鲁棒的基于专家的少样本持续事件检测框架 contrastive learning distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
9 A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity 提出TRIANGLE以解决多模态对齐问题 multimodal
10 Discrete Variational Autoencoding via Policy Search 提出基于策略搜索的离散变分自编码器，提升高维图像重建质量。 multimodal
11 Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs 提出ALoRA：一种非对称多LoRA微调方法，提升LLM多任务和联邦学习性能。 large language model ✅
12 OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment OrthAlign：正交子空间分解解决大模型多目标对齐中的冲突问题 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页