cs.AI（2024-08-18）

📊 共 9 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

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

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

#	题目	一句话要点	标签	🔗	⭐
1	Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition	提出Foal-Net，通过对齐和标签匹配增强多模态情感识别中的模态融合效果	contrastive learning multimodal
2	Beyond Local Views: Global State Inference with Diffusion Models for Cooperative Multi-Agent Reinforcement Learning	提出基于扩散模型的全局状态推断方法SIDIFF，提升部分可观测多智能体强化学习性能	reinforcement learning
3	ELASTIC: Efficient Linear Attention for Sequential Interest Compression	ELASTIC：一种高效线性注意力机制，用于序列兴趣压缩，加速长序列推荐。	linear attention
4	Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting	提出概念蒸馏（CD）方法，通过假设到理论的提示优化弱语言模型性能。	distillation

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

#	题目	一句话要点	标签	🔗	⭐
5	Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language Models	探讨纯粹思维的可能性：论证大型语言模型无需感官基础亦可思考	large language model
6	Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning	Antidote：针对有害微调，为大语言模型提供后微调安全对齐方案	large language model	✅
7	MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair	MergeRepair：探索代码LLM中合并任务特定适配器用于自动程序修复	large language model
8	Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting	提出ProRBP框架，利用检索行为增强提示，提升LLM驱动的相关性建模效果	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	VRCopilot: Authoring 3D Layouts with Generative AI Models in VR	VRCopilot：在VR中利用生成式AI模型进行3D布局创作	manipulation multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页