cs.AI（2025-12-26）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱八：物理动画 (Physics-based Animation) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

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

#题目一句话要点标签🔗⭐
1 Efficient Multi-Model Orchestration for Self-Hosted Large Language Models Pick and Spin：高效自托管大语言模型的多模型编排框架 large language model
2 Optimizing Resource Allocation for Geographically-Distributed Inference by Large Language Models 针对地理分布式LLM推理，提出资源分配优化方案，显著降低推理时间。 large language model
3 Beyond Single Bugs: Benchmarking Large Language Models for Multi-Vulnerability Detection 提出多漏洞检测基准，揭示大语言模型在复杂代码安全场景下的性能瓶颈 large language model
4 SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence SciEvalKit：一个用于评估科学通用智能的开源工具包 foundation model multimodal
5 Lightweight Inference-Time Personalization for Frozen Knowledge Graph Embeddings 提出GatedBias，用于冻结知识图谱嵌入的轻量级推理时个性化 foundation model
6 AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents 研究表明：AI生成的代码在干净环境中难以复现，存在显著依赖缺失问题 large language model
7 Cost-Aware Text-to-SQL: An Empirical Study of Cloud Compute Costs for LLM-Generated Queries 首次系统评估LLM生成SQL查询的云计算成本，揭示效率与成本优化差异 large language model
8 State-of-the-art Small Language Coder Model: Mify-Coder Mify-Coder：一种参数量为25亿的先进小型代码模型，在代码生成和函数调用基准测试中超越大型模型。 foundation model

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

#题目一句话要点标签🔗⭐
9 HalluMat: Detecting Hallucinations in LLM-Generated Materials Science Content Through Multi-Stage Verification 提出HalluMatDetector，通过多阶段验证检测LLM在材料科学内容生成中的幻觉问题 PHC large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
10 Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback Agent2World：通过自适应多智能体反馈学习生成符号世界模型 world model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页