cs.AI（2024-12-18）

📊 共 15 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Clinical Trials Ontology Engineering with Large Language Models 利用大型语言模型进行临床试验本体工程，提升效率并降低成本 large language model
2 A Survey on Large Language Model-based Agents for Statistics and Data Science 综述：基于大型语言模型的数据科学智能体，简化数据分析流程。 large language model
3 Cognition Chain for Explainable Psychological Stress Detection on Social Media 提出认知链（Cognition Chain）方法，用于社交媒体上可解释的心理压力检测。 large language model chain-of-thought
4 LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research 提出基于LLM的组合创造力框架，用于科学研究中生成创新性想法 large language model
5 Design choices made by LLM-based test generators prevent them from finding bugs LLM测试生成器设计缺陷导致其无法有效发现代码缺陷，反而可能验证错误代码。 large language model
6 Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification Rango：自适应检索增强证明，用于自动化软件验证。 large language model
7 Retrieving Classes of Causal Orders with Inconsistent Knowledge Bases 提出一种基于LLM一致性的因果顺序发现方法，提升复杂场景下的因果关系推断可靠性。 large language model
8 On the Role of Model Prior in Real-World Inductive Reasoning 揭示大语言模型归纳推理中模型先验的主导作用，并提出有效利用先验的潜力。 large language model
9 Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates 提出GVIC框架，通过渐进式警戒和区间通信增强多智能体辩论中的价值对齐。 large language model
10 Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs 提出Transducer Tuning，利用代码属性图高效适配软件任务大模型。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 Alignment faking in large language models 揭示大型语言模型中的对齐伪装现象，模型策略性地遵守训练目标以避免行为被修改。 reinforcement learning large language model
12 Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective 从强化学习视角解析OpenAI o1的复现路线图，聚焦策略、奖励、搜索与学习。 reinforcement learning distillation reward design
13 Multi-task Representation Learning for Mixed Integer Linear Programming 提出用于混合整数线性规划的多任务表征学习框架，提升求解效率。 representation learning
14 ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics ARTEMIS-DA：用于数据分析中多步洞察合成的先进推理与转换引擎 predictive model large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 Quantified Linear and Polynomial Arithmetic Satisfiability via Template-based Skolemization 提出基于模板的Skolem化方法，高效解决量化线性/多项式算术公式的可满足性问题 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页