cs.AI（2025-12-04）

📊 共 11 篇论文

🎯 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) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions	STELLA：利用语义抽象引导大语言模型进行时间序列预测	large language model
2	Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective	面向伦理的多智能体LLM系统：一种基于机制可解释性的研究框架	large language model
3	Value Lens: Using Large Language Models to Understand Human Values	Value Lens：利用大型语言模型理解人类价值观，提升自主决策系统对齐	large language model
4	SIMA 2: A Generalist Embodied Agent for Virtual Worlds	SIMA 2：基于Gemini的通用具身智能体，用于交互式虚拟世界	foundation model
5	DABench-LLM: Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators for LLMs	提出DABench-LLM以解决数据流AI加速器性能评估问题	large language model
6	Learning to Code with Context: A Study-Based Approach	研究基于上下文感知的AI辅助编程学习方法，提升软件工程教育质量	large language model
7	Algorithmic Thinking Theory	提出算法思维理论框架，分析LLM迭代推理能力并指导新方法设计	large language model
8	Semantic Faithfulness and Entropy Production Measures to Tame Your LLM Demons and Manage Hallucinations	提出基于信息论和热力学的语义忠实度与熵产生指标，用于评估和控制LLM幻觉	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	🔗	⭐
9	Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification	提出Webshell家族分类基准，通过动态函数调用追踪和表示学习实现自动化分析。	representation learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Model-Free Assessment of Simulator Fidelity via Quantile Curves	提出一种基于分位数曲线的无模型模拟器逼真度评估方法	sim-to-real

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

#	题目	一句话要点	标签	🔗	⭐
11	Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs	提出MAMA框架以量化多智能体LLM系统中的记忆泄漏问题	spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页