cs.AI（2023-12-13）

📊 共 6 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)	通过对比学习重新审视推荐系统中的损失函数	contrastive learning
2	(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)	针对推荐系统，提出并研究了去偏对比学习损失，显著提升模型性能。	contrastive learning
3	How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning	MARL评估体系年度分析：揭示性能报告问题并呼吁更严格的实验标准	reinforcement learning
4	The Effective Horizon Explains Deep RL Performance in Stochastic Environments	提出SQIRL算法，通过有效视野解释随机环境下的深度强化学习性能	reinforcement learning PPO	✅

#	题目	一句话要点	标签	🔗	⭐
5	Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI	mPnP-LLM：即插即用模态，为具身AI实现多模态LLM的弹性模态适配	embodied AI large language model multimodal
6	PromptBench: A Unified Library for Evaluation of Large Language Models	PromptBench：用于评估大型语言模型的统一库	large language model	✅