cs.AI（2026-01-05）

📊 共 20 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) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise Applications	Yuan3.0 Flash：面向企业应用，开源多模态大语言模型，采用RAPO优化推理。	large language model multimodal	✅
2	Streaming Hallucination Detection in Long Chain-of-Thought Reasoning	提出流式幻觉检测方法，用于长链式思考推理中实时识别和解释幻觉。	large language model chain-of-thought
3	MMP-A*: Multimodal Perception Enhanced Incremental Heuristic Search on Path Planning	MMP-A*:多模态感知增强的路径规划增量启发式搜索	large language model multimodal
4	Perish or Flourish? A Holistic Evaluation of Large Language Models for Code Generation in Functional Programming	FPEval：全面评估LLM在函数式编程代码生成中的性能与风格	large language model
5	Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models	探索大语言模型中推荐系统数据记忆的检测方法，并评估自动化提示工程的潜力	large language model
6	MindChat: A Privacy-preserving Large Language Model for Mental Health Support	提出MindChat：一种保护隐私的心理健康支持大语言模型	large language model
7	LIA: Supervised Fine-Tuning of Large Language Models for Automatic Issue Assignment	LIA：通过监督式微调大型语言模型实现自动问题分配	large language model
8	Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents	Project Ariadne：提出基于结构因果模型的LLM Agent推理忠实性审计框架	large language model chain-of-thought
9	Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling	Falcon-H1R：利用混合模型和高效测试时扩展，突破推理性能边界	chain-of-thought
10	Placement Semantics for Distributed Deep Learning: A Systematic Framework for Analyzing Parallelism Strategies	提出Placement Semantics框架，系统分析分布式深度学习并行策略。	large language model
11	Theory Trace Card: Theory-Driven Socio-Cognitive Evaluation of LLMs	提出Theory Trace Card，用于理论驱动的大语言模型社会认知能力评估。	large language model
12	Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios	Jenius Agent：面向真实场景，经验驱动的LLM Agent精度优化框架	large language model
13	COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs	COMPASS：评估LLM在组织特定策略对齐的框架	large language model
14	Yukthi Opus: A Multi-Chain Hybrid Metaheuristic for Large-Scale NP-Hard Optimization	提出Yukthi Opus混合元启发式算法，解决大规模NP难优化问题，适用于评估预算受限场景。	multimodal
15	A New Benchmark for the Appropriate Evaluation of RTL Code Optimization	RTL-OPT：用于评估LLM在RTL代码优化能力的新基准测试集	large language model
16	Query-Document Dense Vectors for LLM Relevance Judgment Bias Analysis	提出基于密集向量聚类的框架，用于分析LLM在相关性判断中的偏差	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	🔗	⭐
17	FormuLLA: A Large Language Model Approach to Generating Novel 3D Printable Formulations	FormuLLA：利用大型语言模型生成新型3D打印药物配方	predictive model large language model
18	AI Agent Systems: Architectures, Applications, and Evaluation	综述AI Agent系统：架构、应用与评估，弥合自然语言意图与现实计算的鸿沟	world model foundation model multimodal
19	Higher-Order Action Regularization in Deep Reinforcement Learning: From Continuous Control to Building Energy Management	提出高阶动作正则化深度强化学习方法，解决控制不平滑问题，应用于建筑能源管理。	reinforcement learning deep reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Can Large Language Models Solve Engineering Equations? A Systematic Comparison of Direct Prediction and Solver-Assisted Approaches	对比直接预测与求解器辅助方法，评估大语言模型求解工程方程能力	manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页