cs.AI（2025-05-14）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (5) 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 A Multimodal Multi-Agent Framework for Radiology Report Generation 提出多模态多Agent框架，解决放射报告生成中的不一致、幻觉和跨模态不对齐问题。 large language model multimodal
2 Contextual Phenotyping of Pediatric Sepsis Cohort Using Large Language Models 利用大型语言模型进行儿科脓毒症队列的上下文表型分析 large language model
3 Evaluating Large Language Models for the Generation of Unit Tests with Equivalence Partitions and Boundary Values 利用大语言模型生成单元测试，关注等价划分和边界值分析 large language model
4 Customizing a Large Language Model for VHDL Design of High-Performance Microprocessors 定制大语言模型用于高性能微处理器VHDL设计的代码解释 large language model
5 Evaluating GPT- and Reasoning-based Large Language Models on Physics Olympiad Problems: Surpassing Human Performance and Implications for Educational Assessment 评估GPT和推理型大语言模型在物理奥赛题上的表现，超越人类水平并探讨对教育评估的影响 large language model
6 ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor ELIS：基于响应长度预测的高效LLM迭代调度系统，优化平均任务完成时间。 large language model
7 Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models 提出变分前缀调整(VPT)方法，利用预训练语言模型生成多样且准确的代码摘要。 large language model
8 Extracting Knowledge Graphs from User Stories using LangChain 提出User Story Graph Transformer，利用LangChain和LLM自动构建用户故事知识图谱 large language model
9 The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners 研究人类启发式智能对LLM驱动的战略推理器性能的影响 large language model
10 Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures DeepSeek-V3：硬件感知模型协同设计，突破大模型扩展瓶颈 large language model
11 Reproducibility Study of "Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents" 复现并扩展GovSim框架，评估LLM在资源共享场景下的合作决策能力。 large language model
12 Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer TransKT：利用概念图引导知识迁移的对比跨课程知识追踪 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🔗⭐
13 Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical Approach 通过程序修辞分析RLHF，揭示其在伦理、偏见和人际关系上的潜在影响 reinforcement learning RLHF large language model
14 Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer 提出CRDT，利用反事实推理增强Decision Transformer在有限数据下的决策能力 reinforcement learning decision transformer
15 General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement Learning 提出GC-AURA和Meta-AURA，解决动态环境下通用目标识别问题 reinforcement learning
16 Quantum-Enhanced Parameter-Efficient Learning for Typhoon Trajectory Forecasting 提出量子参数自适应(QPA)方法，用于台风轨迹预测中的参数高效学习。 reinforcement learning large language model
17 TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search 提出TensorRL-QAS以解决量子电路设计的可扩展性问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Understanding Gen Alpha Digital Language: Evaluation of LLM Safety Systems for Content Moderation 评估大型语言模型在内容审核中对Alpha世代数字语言的理解能力 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页