cs.AI（2025-04-11）

📊 共 24 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) (18 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	SynthFM: Training Modality-agnostic Foundation Models for Medical Image Segmentation without Real Medical Data	SynthFM：无需真实医学数据，训练模态无关的医学图像分割基础模型	foundation model
2	Adopting Large Language Models to Automated System Integration	利用大型语言模型实现自动化系统集成，简化服务组合流程。	large language model
3	SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting	SpecEE：基于推测性提前退出的LLM加速推理引擎，提升云端和PC场景下的推理速度。	large language model
4	How Good Are Large Language Models for Course Recommendation in MOOCs?	探索LLM在MOOC课程推荐中的潜力，性能媲美传统模型	large language model
5	Neural Encoding and Decoding at Scale	提出NEDS模型，实现大规模神经活动编码与解码的统一建模	foundation model multimodal
6	Mixed Signals: Decoding VLMs' Reasoning and Underlying Bias in Vision-Language Conflict	分析视觉-语言模型在冲突信息下的推理偏见，并提出缓解策略。	chain-of-thought
7	DocAgent: A Multi-Agent System for Automated Code Documentation Generation	提出DocAgent多智能体系统，用于自动化生成高质量代码文档	large language model
8	DRAFT-ing Architectural Design Decisions using LLMs	提出DRAFT框架，结合领域检索、少量样本学习和微调，提升LLM生成架构设计决策的质量。	large language model
9	AI-University: An LLM-based platform for instructional alignment to scientific classrooms	AI-University：一个基于LLM的教学对齐平台，应用于科学课堂	large language model
10	Toward Super Agent System with Hybrid AI Routers	提出基于混合AI路由器的Super Agent系统，优化效率与成本，实现边缘设备上的智能应用。	large language model
11	Voice Interaction With Conversational AI Could Facilitate Thoughtful Reflection and Substantive Revision in Writing	利用语音交互式对话AI促进写作中的深度反思和实质性修改	large language model
12	Once Upon an AI: Six Scaffolds for Child-AI Interaction Design, Inspired by Disney	提出六个支架以优化儿童与AI的互动设计	multimodal
13	Variability-Driven User-Story Generation using LLM and Triadic Concept Analysis	结合TCA和LLM，提出一种基于变异性的用户故事生成方法，用于软件产品线需求工程。	large language model
14	Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents	利用演化博弈论框架，研究LLM智能体在AI监管中的策略行为	large language model
15	Task Memory Engine (TME): Enhancing State Awareness for Multi-Step LLM Agent Tasks	提出任务记忆引擎TME，增强LLM Agent多步任务中的状态感知能力	large language model	✅
16	RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation	RTLRepoCoder：结合微调与检索增强，实现仓库级RTL代码补全	large language model
17	Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices	Jupiter：面向生成式LLM的快速、资源高效的边缘设备协同推理系统	large language model
18	X-Guard: Multilingual Guard Agent for Content Moderation	提出X-Guard：一种用于内容审核的透明多语言Guard Agent	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	🔗	⭐
19	MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models	MedRep：面向通用电子病历基础模型的医学概念表示方法	representation learning large language model foundation model
20	Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation	提出基于图神经网络、Transformer和深度强化学习的多智能体协同框架，解决复杂环境下的无人机任务规划问题。	reinforcement learning deep reinforcement learning DRL
21	Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observability	提出基于信念状态的合作多智能体强化学习方法，解决部分可观测问题	reinforcement learning
22	MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers	提出MCP Bridge轻量级RESTful代理，解决LLM与MCP服务器在资源受限环境下的连接难题。	reinforcement learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
23	USM-VC: Mitigating Timbre Leakage with Universal Semantic Mapping Residual Block for Voice Conversion	提出USM-VC，通过通用语义映射残差块缓解语音转换中的音色泄露问题	semantic mapping semantic map

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
24	Hybrid AI-Physical Modeling for Penetration Bias Correction in X-band InSAR DEMs: A Greenland Case Study	提出混合AI-物理模型，用于校正X波段InSAR DEM中的穿透偏差，以格陵兰岛为例。	penetration

⬅️ 返回 cs.AI 首页 · 🏠 返回主页