cs.AI（2024-11-06）

📊 共 15 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces	UniTraj：学习十亿级全球轨迹数据的通用轨迹基础模型	foundation model
2	Navigating the landscape of multimodal AI in medicine: a scoping review on technical challenges and clinical applications	综述医学多模态AI：分析技术挑战、临床应用及未来方向	multimodal
3	PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology	PhDGPT：构建心理测量与语言数据集，探索LLM对心理学研究生和教授的认知。	large language model
4	AutoGameUI: Constructing High-Fidelity Game UIs via Multimodal Learning and Interactive Web-Based Tool	AutoGameUI：通过多模态学习和交互式Web工具构建高保真游戏UI	multimodal
5	Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators	提出在线有害视频分类体系，并验证MLLM作为标注器的可行性，优于众包。	large language model multimodal
6	To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation	提出基于注意力机制的指令模糊度估计模块，提升视觉语言导航中智能体的询问能力。	vision-language-navigation VLN
7	Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding	提出LaTRO框架以提升大语言模型的推理能力	large language model chain-of-thought	✅
8	LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration	LEGO-GraphRAG：模块化图检索增强生成框架，用于设计空间探索	large language model
9	Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization	Eguard：通过文本互信息优化防御LLM嵌入的逆向攻击	large language model
10	Long-Form Text-to-Music Generation with Adaptive Prompts: A Case Study in Tabletop Role-Playing Games Soundtracks	提出Babel Bardo系统，利用自适应提示生成长时序、高质量的TRPG游戏配乐。	large language model
11	MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue	提出MRJ-Agent以解决多轮对话中的越狱攻击问题	large language model
12	Crystal: Illuminating LLM Abilities on Language and Code	Crystal：通过优化预训练策略，提升LLM在自然语言和代码领域的综合能力	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
13	From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning	StepAgent：基于步进式强化学习优化LLM Agent策略，解决稀疏奖励问题	reinforcement learning policy learning inverse reinforcement learning
14	Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC	提出Beyond The Rainbow算法，在桌面PC上实现Atari和3D游戏强化学习新高度	reinforcement learning deep reinforcement learning	✅
15	Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation	FiGRet：利用LLM细粒度反馈指导检索器，提升RAG性能	curriculum learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页