cs.LG（2025-06-24）

📊 共 5 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) (3 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱四：生成式动作 (Generative Motion) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models	提出Outlier-Safe预训练以解决大语言模型量化中的异常值问题	large language model	✅
2	Orthogonal Finetuning Made Scalable	提出OFTv2以解决正交微调的计算瓶颈问题	foundation model
3	Scaling Speculative Decoding with Lookahead Reasoning	提出前瞻推理以提升推测解码速度	chain-of-thought	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
4	Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models	提出利用大语言模型进行开放式指令重标定以提升指令跟随策略	reinforcement learning large language model instruction following

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
5	Cross-Layer Discrete Concept Discovery for Interpreting Language Models	提出跨层离散概念发现方法以解析语言模型	VQ-VAE large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页