cs.AI（2025-04-04）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transition	利用3-SAT相变刻画大语言模型的推理能力	large language model chain-of-thought
2	Towards a Multimodal Document-grounded Conversational AI System for Education	提出MuDoC：一个面向教育的多模态文档对话AI系统，提升学习者参与度和信任度。	multimodal
3	Towards deployment-centric multimodal AI beyond vision and language	面向部署的多模态AI，超越视觉与语言，关注实际应用挑战	multimodal
4	OLAF: An Open Life Science Analysis Framework for Conversational Bioinformatics Powered by Large Language Models	OLAF：一个基于大语言模型的开放生命科学分析框架，赋能对话式生物信息学。	large language model
5	Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations	大型语言模型能否解决基于Agent建模的问题？对生成式社会模拟的批判性回顾	large language model
6	LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph	LightPROF：一种轻量级知识图谱驱动的大语言模型推理框架	large language model
7	A Human Digital Twin Architecture for Knowledge-based Interactions and Context-Aware Conversations	提出一种基于知识交互和情境感知对话的人类数字孪生架构，用于人机协作。	large language model multimodal
8	Hierarchically Encapsulated Representation for Protocol Design in Self-Driving Labs	提出分层封装表示方法，辅助自驱动实验室进行实验协议设计	large language model
9	Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency	评估量化LLM在边缘AI的能效、精度与延迟，实现可持续推理。	large language model
10	Bridging LMS and generative AI: dynamic course content integration (DCCI) for enhancing student satisfaction and engagement via the ask ME assistant	提出DCCI动态课程内容集成机制，提升LLM教育助手的准确性和学生参与度	large language model
11	Arti-"fickle" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences	利用LLM进行政治和社会科学推断：挑战、机遇与验证	large language model

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

#	题目	一句话要点	标签	🔗	⭐
12	DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments	DeepResearcher：通过强化学习在真实环境中扩展深度研究能力	reinforcement learning large language model	✅
13	Optimizing UAV Aerial Base Station Flights Using DRL-based Proximal Policy Optimization	提出基于DRL近端策略优化算法的无人机空中基站飞行优化方案	reinforcement learning DRL
14	Decentralized Collective World Model for Emergent Communication and Coordination	提出分散式集体世界模型，实现涌现通信与协同行为	world model contrastive learning
15	Improving World Models using Deep Supervision with Linear Probes	提出基于线性探针深度监督的世界模型改进方法，提升智能体在复杂环境中的推理能力。	world model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	Seeing is Believing: Belief-Space Planning with Foundation Models as Uncertainty Estimators	提出基于基础模型的置信空间规划方法，解决部分可观测环境下的机器人操作任务。	manipulation mobile manipulation foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Physics-informed 4D X-ray image reconstruction from ultra-sparse spatiotemporal data	提出4D-PIONIX，结合物理模型与深度学习，实现超稀疏时空数据下的4D X射线图像重建。	spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页