cs.AI（2025-10-29）

📊 共 8 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) (4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱八：物理动画 (Physics-based Animation) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Large Language Model-assisted Autonomous Vehicle Recovery from Immobilization	提出StuckSolver，利用大语言模型辅助自动驾驶车辆脱困	large language model
2	Lost in Phonation: Voice Quality Variation as an Evaluation Dimension for Speech Foundation Models	提出语音质量评估方法，用于评估语音基础模型对音质变化的敏感性	foundation model
3	CLINB: A Climate Intelligence Benchmark for Foundational Models	CLINB：用于评估基础模型气候智能的综合性基准测试	large language model multimodal
4	Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters	通过推断思维轨迹，提升LLM评估者在主观任务中的可靠性	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	🔗	⭐
5	RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models	提出RAVR：参考答案引导的变分推理框架，提升大语言模型推理能力	reinforcement learning large language model
6	Approximating Human Preferences Using a Multi-Judge Learned System	提出一种基于多评判器学习系统的人类偏好近似方法，用于校准LLM评判。	reinforcement learning RLHF

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
7	H3M-SSMoEs: Hypergraph-based Multimodal Learning with LLM Reasoning and Style-Structured Mixture of Experts	提出H3M-SSMoEs模型，利用超图、LLM和专家混合网络提升股票预测精度。	spatiotemporal large language model multimodal	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning	提出基于图的智能体规划GAP，通过并行工具使用和强化学习提升多步推理效率。	manipulation reinforcement learning large language model	✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页