cs.LG（2025-08-21）
📊 共 2 篇论文
🎯 兴趣领域导航
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks | 提出SafeLLM以解决大型语言模型的监狱突破攻击问题 | direct preference optimization large language model |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 2 | End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost | 提出ZeroQAT以解决LLMs量化训练中的高内存消耗问题 | large language model |