cs.LG（2024-05-18）

📊 共 6 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving	针对长文本大语言模型服务，提出CAP原则以指导成本、精度与性能的权衡。	large language model
2	Preparing for Black Swans: The Antifragility Imperative for Machine Learning	提出基于反脆弱性的机器学习设计范式，提升模型在动态环境下的适应能力。	foundation model
3	LinkedIn Post Embeddings: Industrial Scale Embedding Generation and Usage across LinkedIn	LinkedIn提出基于多任务微调Transformer的Post Embedding，提升Feed流和视频推荐排序效果。	large language model
4	Towards Modular LLMs by Building and Reusing a Library of LoRAs	构建和复用LoRA库，实现模块化LLM并提升泛化能力	large language model

#	题目	一句话要点	标签	🔗	⭐
5	Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses	提出对抗攻击与防御框架，提升离线强化学习策略的鲁棒性	reinforcement learning offline RL offline reinforcement learning
6	The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedback	提出主动多任务学习框架，提升RLHF中人类反馈利用率	reinforcement learning RLHF representation learning