cs.AI（2025-12-13）

📊 共 10 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) (8) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
1	V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval	V-Rex：通过动态KV缓存检索加速实时流视频LLM推理	large language model multimodal
2	Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation	Floorplan2Guide：利用LLM引导的户型图解析，助力视障人士室内导航	large language model foundation model
3	AI Transparency Atlas: Framework, Scoring, and Real-Time Model Card Evaluation Pipeline	提出AI透明度评估框架与自动化流水线，解决模型文档碎片化问题。	multimodal
4	Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy	研究量化和图检索增强生成对大语言模型因果推理能力的影响	large language model
5	UniMark: Artificial Intelligence Generated Content Identification Toolkit	UniMark：用于人工智能生成内容识别的开源统一工具包	multimodal
6	Epistemoverse: Toward an AI-Driven Knowledge Metaverse for Intellectual Heritage Preservation	提出Epistemoverse：一个AI驱动的知识元宇宙，用于保护知识遗产。	large language model
7	Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective	提出TopK-SD方法，通过合成数据提升上下文学习中的标签一致性	large language model
8	Made-in China, Thinking in America:U.S. Values Persist in Chinese LLMs	中美LLM价值观对比研究：中国LLM表现出更强的美国价值观倾向	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	🔗	⭐
9	Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying	提出主动查询框架以解决不对称智能体中的特权信息偏见问题	privileged information large language model
10	MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs	提出MetaHGNIE框架，通过超图对比学习解决异构知识图谱中的节点重要性估计问题。	contrastive learning multimodal	✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页