cs.AI（2025-03-11）

📊 共 12 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3)

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

#题目一句话要点标签🔗⭐
1 Chain-of-Thought Reasoning In The Wild Is Not Always Faithful 揭示大语言模型在真实场景中思维链推理的非忠实性问题，并分析其成因 chain-of-thought
2 YuE: Scaling Open Foundation Models for Long-Form Music Generation YuE：扩展开放的LLaMA2基础模型，实现长篇歌词到歌曲的生成 foundation model
3 Mellow: a small audio language model for reasoning 提出Mellow：一种用于音频推理的小型音频语言模型，性能超越同规模模型。 large language model multimodal
4 Stakeholder Perspectives on Whether and How Social Robots Can Support Mediation and Advocacy for Higher Education Students with Disabilities 探索社交机器人辅助残疾大学生进行调解和权益维护的潜力 large language model
5 Llms, Virtual Users, and Bias: Predicting Any Survey Question Without Human Data 利用LLM生成虚拟用户预测调查结果，无需人工数据，但存在偏见问题。 large language model
6 Reasoning and Sampling-Augmented MCQ Difficulty Prediction via LLMs 提出基于LLM推理增强和抽样增强的MCQ难度预测方法 large language model
7 GoAI: Enhancing AI Students' Learning Paths and Idea Generation via Graph of AI Ideas GoAI：利用AI知识图谱增强AI学生学习路径规划与创新想法生成 large language model
8 Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidation 利用LLM的化学推理能力实现策略感知的合成路线规划和反应机理推导 large language model
9 AI-native Memory 2.0: Second Me 提出AI原生记忆管理系统SECOND ME，利用LLM实现个性化知识的持久化、组织和动态利用。 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
10 HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents HASARD：基于视觉的安全强化学习具身智能体基准测试 reinforcement learning egocentric egocentric vision
11 Imitation Learning of Correlated Policies in Stackelberg Games 提出LSDN，解决Stackelberg博弈中模仿学习相关策略的难题 imitation learning
12 Combining Local Symmetry Exploitation and Reinforcement Learning for Optimised Probabilistic Inference -- A Work In Progress 结合局部对称性与强化学习优化概率图模型推理的消除顺序 reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页