cs.AI（2025-06-01）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning	GeoChain：用于地理推理的多模态思维链基准	large language model multimodal visual grounding
2	Behavioral Augmentation of UML Class Diagrams: An Empirical Study of Large Language Models for Method Generation	利用大型语言模型自动生成UML类图方法，加速软件设计迭代	large language model
3	CoP: Agentic Red-teaming for Large Language Models using Composition of Principles	提出CoP框架，通过组合原则驱动Agent进行大语言模型红队测试，提升安全性	large language model
4	Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision	ReasonTSC：通过定制化推理和融合决策增强LLM在时间序列分类中的能力	large language model
5	Do not Abstain! Identify and Solve the Uncertainty	提出ConfuseBench，用于评估和提升大语言模型在不确定性场景下的识别与解决能力	large language model
6	Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components	针对阿拉伯语，系统分析RAG Pipeline核心组件并优化性能	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	🔗	⭐
7	Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning	提出Jailbreak-R1，利用强化学习提升LLM越狱攻击的有效性和多样性。	reinforcement learning imitation learning large language model
8	Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges	利用强化学习在密码学CTF挑战中提升LLM Agent性能	reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
9	HouseTS: A Large-Scale, Multimodal Spatiotemporal U.S. Housing Dataset	HouseTS：一个大规模多模态时空美国房价数据集，用于长时程预测。	spatiotemporal foundation model multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	SafeGenes: Evaluating the Adversarial Robustness of Genomic Foundation Models	SafeGenes框架：评估基因组基础模型对抗对抗攻击的鲁棒性	manipulation foundation model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页