cs.AI（2025-04-25）

📊 共 20 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) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Semantic-Aware Contrastive Fine-Tuning: Boosting Multimodal Malware Classification with Discriminative Embeddings	提出语义感知对比微调方法，提升多模态恶意软件分类的判别嵌入能力	large language model multimodal
2	MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind	MultiMind：融合多模态推理和心智理论增强狼人杀AI智能体	large language model multimodal
3	A Multimodal Deep Learning Approach for White Matter Shape Prediction in Diffusion MRI Tractography	Tract2Shape：利用多模态深度学习快速预测白质纤维束形态特征，提升脑部研究效率。	multimodal
4	Technical Challenges in Maintaining Tax Prep Software with Large Language Models	利用大语言模型自动维护税务软件，应对税法动态变化带来的挑战	large language model
5	Exploring a Large Language Model for Transforming Taxonomic Data into OWL: Lessons Learned and Implications for Ontology Development	利用大型语言模型ChatGPT-4将分类数据转换为OWL本体，提升本体构建效率。	large language model
6	Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation	提出LLM4CDSR模型，利用大语言模型增强跨域序列推荐性能	large language model
7	Large Language Model-Based Intelligent Antenna Design System	提出基于大语言模型的智能天线设计系统LADS，加速天线设计与优化。	large language model	✅
8	Spark: A System for Scientifically Creative Idea Generation	Spark：一个用于科学创意生成的系统，结合LLM和评审模型。	large language model
9	The Big Send-off: High Performance Collectives on GPU-based Supercomputers	PCCL：针对GPU超级计算机上大规模LLM训练的高性能集合通信库	large language model
10	Artificial Intelligence health advice accuracy varies across languages and contexts	评估AI健康建议在多语言和多情境下的准确性，揭示其在非英语环境中的性能差异。	large language model
11	An Integrated Framework for Contextual Personalized LLM-Based Food Recommendation	提出F-RLP框架，利用LLM进行上下文个性化食物推荐，解决传统方法在食物数据上的不足。	large language model
12	MODP: Multi Objective Directional Prompting	提出MODP，一种多目标定向Prompting框架，提升LLM在摘要任务和实际应用中的性能。	large language model
13	From Prompts to Propositions: A Logic-Based Lens on Student-LLM Interactions	提出Prompt2Constraints方法，通过命题逻辑约束分析学生与LLM交互中的prompt演变模式。	large language model
14	LLMpatronous: Harnessing the Power of LLMs For Vulnerability Detection	LLMpatronous：利用大型语言模型进行漏洞检测	large language model
15	Evolution of AI in Education: Agentic Workflows	提出基于Agentic Workflow的AI教育框架，提升教育场景下的AI应用效果	large language model
16	Towards Adaptive Software Agents for Debugging	提出自适应Agent调试框架，动态调整Agent数量与角色以优化LLM调试能力	large language model
17	LLM-hRIC: LLM-empowered Hierarchical RAN Intelligent Control for O-RAN	提出LLM-hRIC框架，利用LLM增强O-RAN中分层RIC的协同控制。	large language model
18	Validating Network Protocol Parsers with Traceable RFC Document Interpretation	利用可追溯RFC文档解释，验证网络协议解析器的正确性	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation	提出BoxMed-RL，通过链式思考和强化学习生成可验证的放射报告。	reinforcement learning large language model chain-of-thought

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

#	题目	一句话要点	标签	🔗	⭐
20	Adapting Probabilistic Risk Assessment for AI	提出AI概率风险评估框架，应对通用人工智能系统风险管理挑战	affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页