cs.AI(2025-08-11)

📊 共 13 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) (11 🔗3) 支柱二:RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗
1 VGGSounder: Audio-Visual Evaluations for Foundation Models 提出VGGSounder以解决VGGSound数据集的评估局限性 foundation model
2 RedDino: A foundation model for red blood cell analysis 提出RedDino以解决红细胞分析的挑战 foundation model
3 FEAT: A Multi-Agent Forensic AI System with Domain-Adapted Large Language Model for Automated Cause-of-Death Analysis 提出FEAT系统以解决法医死亡原因分析中的挑战 large language model
4 SynLLM: A Comparative Analysis of Large Language Models for Medical Tabular Synthetic Data Generation via Prompt Engineering 提出SynLLM框架以生成高质量医疗合成数据 large language model
5 StreetReaderAI: Making Street View Accessible Using Context-Aware Multimodal AI 提出StreetReaderAI以解决盲人用户无法访问街景的问题 multimodal
6 GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games 提出GVGAI-LLM以评估大语言模型在无限游戏中的推理能力 large language model
7 Large Language Models as Oracles for Ontology Alignment 利用大型语言模型解决本体对齐问题 large language model
8 Temporal User Profiling with LLMs: Balancing Short-Term and Long-Term Preferences for Recommendations 提出LLM-TUP以解决用户偏好建模不足问题 large language model TAMP
9 OverFill: Two-Stage Models for Efficient Language Model Decoding 提出OverFill以解决大语言模型解码效率问题 large language model
10 A Data-driven ML Approach for Maximizing Performance in LLM-Adapter Serving 提出数据驱动的机器学习方法以优化LLM适配器服务性能 large language model
11 Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents 提出SkillNav框架以解决视觉语言导航中的技能泛化问题 VLN

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

#题目一句话要点标签🔗
12 Generating Query-Relevant Document Summaries via Reinforcement Learning 提出ReLSum以解决电商搜索引擎文档摘要生成问题 reinforcement learning large language model
13 ThinkTuning: Instilling Cognitive Reflections without Distillation 提出ThinkTuning以提升模型推理能力 distillation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页