cs.AI（2025-11-07）

📊 共 15 篇论文 | 🔗 3 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) (2 🔗2) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization	提出CoT-X框架，通过自适应推理摘要实现跨模型CoT迁移与优化，降低推理开销。	large language model chain-of-thought
2	The LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications	提出LLM Pro Finance Suite，一套面向金融应用的多语言大语言模型。	large language model instruction following	✅
3	Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being	通过共创设计，提升大型语言模型在青少年心理健康支持中的个性化体验。	large language model
4	SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models	提出SWE-Compass，用于全面评估大型语言模型在软件工程中的智能编码能力。	large language model
5	Generating Software Architecture Description from Source Code using Reverse Engineering and Large Language Model	提出一种基于逆向工程和大型语言模型的软件架构描述自动生成方法	large language model
6	Assessing the Reliability of Large Language Models in the Bengali Legal Context: A Comparative Evaluation Using LLM-as-Judge and Legal Experts	评估大语言模型在孟加拉语法律场景下的可靠性：LLM-as-Judge与法律专家对比评估	large language model
7	Cleaning Maintenance Logs with LLM Agents for Improved Predictive Maintenance	利用LLM Agent清洗维护日志，提升预测性维护效果	large language model
8	Characterizing and Understanding Energy Footprint and Efficiency of Small Language Model on Edges	边缘设备上小型语言模型能耗与效率评估及优化策略研究	large language model
9	Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs	通过行为和归因分析揭示LLM中存在的锚定偏差	large language model
10	AdvisingWise: Supporting Academic Advising in Higher Education Settings Through a Human-in-the-Loop Multi-Agent Framework	AdvisingWise：一种人机协同的多智能体框架，用于支持高等教育中的学业指导	large language model
11	TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems	TAMAS：多智能体LLM系统中对抗风险的基准测试	large language model
12	Enhancing Public Speaking Skills in Engineering Students Through AI	提出基于多模态AI的公共演讲评估系统，提升工科学生沟通能力	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
13	BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait Prediction	提出BrainCSD以解决脑连接组合成与多任务脑特征预测问题	MAE foundation model multimodal	✅
14	TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework	TeaRAG通过压缩检索内容和推理步骤，提升Agentic RAG的token效率。	reinforcement learning DPO direct preference optimization	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Robust Neural Audio Fingerprinting using Music Foundation Models	利用音乐基础模型，提升音频指纹在失真环境下的鲁棒性	manipulation foundation model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页