cs.AI（2025-05-21）

📊 共 25 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes	Moonbeam：一种利用绝对和相对音乐属性的MIDI基础模型	foundation model
2	An Inclusive Foundation Model for Generalizable Cytogenetics in Precision Oncology	CHROMA：用于精准肿瘤学中染色体核型分析的通用基础模型	foundation model
3	Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects	利用大型语言模型检测Python开源项目中的命令注入漏洞	large language model
4	Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization	提出基于密度驱动的群体智能增强推理框架，提升LLM在复杂推理场景下的优化能力。	large language model chain-of-thought
5	Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval	提出安全上下文检索(SCR)方法，提升LLM抵抗恶意越狱攻击的防御能力	large language model
6	CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution	CRAKEN：基于知识的LLM网络安全Agent，提升漏洞检测与利用能力	large language model	✅
7	ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges	提出ModelingAgent，桥接LLM与数学建模，解决真实世界复杂问题	large language model
8	How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior	研究LLM Agent记忆管理对长期性能的影响，揭示经验跟随行为及应对策略	large language model
9	SPhyR: Spatial-Physical Reasoning Benchmark on Material Distribution	SPhyR：提出基于材料分布的空间物理推理基准测试，评估LLM的推理能力	large language model
10	NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction	NEXT-EVAL：提出一个Web数据记录抽取的综合评估框架，支持传统算法和LLM的公平比较。	large language model
11	Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey	构建大型音频语言模型评测体系：提出全面评估框架与系统性分类	large language model
12	PhyX: Does Your Model Have the "Wits" for Physical Reasoning?	提出PhyX：一个大规模物理推理基准，揭示现有模型在物理场景理解上的不足。	multimodal	✅
13	HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement	HybridProver：结合LLM驱动的证明合成与细化的定理证明框架	large language model
14	A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics	评估LLM生成的多语言代码注释质量，揭示现有自动评估指标的局限性	large language model
15	Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries	提出IKEA隐式知识提取攻击，通过良性查询从RAG系统中提取知识。	large language model
16	ClickSight: Interpreting Student Clickstreams to Reveal Insights on Learning Strategies via LLMs	ClickSight：利用LLM解释学生点击流数据，揭示学习策略	large language model
17	Adaptive Plan-Execute Framework for Smart Contract Security Auditing	提出SmartAuditFlow，通过自适应规划执行框架提升智能合约安全审计能力。	large language model
18	ThinkRec: Thinking-based recommendation via LLM	ThinkRec：通过大语言模型进行基于思考的推荐，提升推荐精度和可解释性。	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
19	SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation	提出SynEVO框架以解决跨领域适应问题	curriculum learning spatiotemporal
20	UNet with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning for Medical Image Segmentation	提出SAMA-UNet，结合自适应Mamba注意力与因果共振学习，提升医学图像分割精度。	Mamba SSM
21	Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives	提出基于平均奖励强化学习的框架，解决Omega-正则和平均收益目标下的持续学习问题。	reinforcement learning
22	lmgame-Bench: How Good are LLMs at Playing Games?	lmgame-Bench：评估LLM在游戏中的表现，解决评估难题并促进能力迁移	reinforcement learning large language model	✅
23	HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning	HAVA：通过奖励加权混合方法实现强化学习中的价值对齐	reinforcement learning

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
24	Unraveling the iterative CHAD	扩展CHAD至包含迭代结构的程序，实现结构保持的自动微分	OMOMO

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
25	Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning	提出基于上下文学习和韵律自适应音频编解码器的零样本语音转换模型	manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页