cs.LG（2026-01-23）

📊 共 10 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Rethinking Large Language Models For Irregular Time Series Classification In Critical Care	针对ICU不规则时间序列分类，研究并优化大语言模型中的编码器与对齐策略。	large language model multimodal	✅
2	Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs	提出SARE，通过对抗扰动增强多模态LLM的幻觉消除鲁棒性	multimodal
3	Predicting Startup Success Using Large Language Models: A Novel In-Context Learning Approach	提出kNN-ICL框架，利用大语言模型解决早期创业公司成功预测的数据稀缺问题	large language model
4	DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs	DANCE：动态、可用、邻居门控的联邦文本属性图压缩学习	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
5	Towards a Theoretical Understanding to the Generalization of RLHF	提出RLHF理论框架以解决高维设置中的泛化问题	reinforcement learning RLHF large language model
6	A Regularized Actor-Critic Algorithm for Bi-Level Reinforcement Learning	提出一种正则化Actor-Critic算法，用于解决双层强化学习问题	reinforcement learning RLHF
7	The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning	提出Soft-TAC，用于从人类偏好数据中学习奖励函数，提升强化学习效果	reinforcement learning reward design
8	Endless Terminals: Scaling RL Environments for Terminal Agents	提出Endless Terminals，用于大规模生成终端任务以训练强化学习Agent。	reinforcement learning PPO

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints	GRIP：通过几何路由约束实现MoE模型算法无关的机器遗忘	manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Auto-Regressive Masked Diffusion Models	提出自回归掩码扩散模型(ARMD)，提升语言建模效率和并行生成能力。	MDM

⬅️ 返回 cs.LG 首页 · 🏠 返回主页