cs.AI（2025-07-17）

📊 共 12 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 GOFAI meets Generative AI: Development of Expert Systems by means of Large Language Models 提出一种基于大语言模型的专家系统开发方法，解决幻觉问题并保证可解释性。 large language model
2 The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations 提出GEA：一个将能耗纳入大语言模型人工评估的平台 large language model
3 SEER: Semantic Enhancement and Emotional Reasoning Network for Multimodal Fake News Detection 提出SEER网络，通过语义增强和情感推理提升多模态假新闻检测性能。 multimodal
4 Humans learn to prefer trustworthy AI over human partners 人类在合作博弈中逐渐倾向于选择更值得信任的AI伙伴而非人类 large language model
5 GraphTrafficGPT: Enhancing Traffic Management Through Graph-Based AI Agent Coordination GraphTrafficGPT：通过图结构AI Agent协同增强交通管理 large language model
6 Voxtral 提出Voxtral Mini和Voxtral Small多模态音频聊天模型，在音频理解任务上达到SOTA。 multimodal
7 Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM Era 针对LLM时代的道德AI，提出一套基于功能性的评估标准 large language model
8 Why Braking? Scenario Extraction and Reasoning Utilizing LLM 利用大语言模型进行驾驶场景理解与推理，解决车辆制动原因分析难题 large language model
9 MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models MCPEval：基于MCP的AI Agent模型自动化深度评估框架 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🔗⭐
10 From Roots to Rewards: Dynamic Tree Reasoning with Reinforcement Learning 提出基于强化学习的动态树推理框架，提升复杂问答系统的效率和准确性。 reinforcement learning chain-of-thought ✅
11 Assessing Adaptive World Models in Machines with Novel Games 提出基于新颖游戏基准的自适应世界模型评估框架，促进类人通用人工智能发展 world model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
12 PrefPalette: Personalized Preference Modeling with Latent Attributes PrefPalette：利用潜在属性进行个性化偏好建模，提升社交社区偏好预测。 HuMoR

⬅️ 返回 cs.AI 首页 · 🏠 返回主页