cs.AI（2024-10-19）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 A Prompt Refinement-based Large Language Model for Metro Passenger Flow Forecasting under Delay Conditions 提出一种基于Prompt优化的LLM框架，用于解决延误条件下地铁客流预测难题。 large language model chain-of-thought
2 AutoFPDesigner: Automated Flight Procedure Design Based on Multi-Agent Large Language Model 提出AutoFPDesigner，基于多智能体大语言模型实现飞行程序自动设计 large language model
3 Do Large Language Models Truly Grasp Mathematics? An Empirical Exploration From Cognitive Psychology 基于认知心理学视角，探究大语言模型数学能力局限性 large language model
4 Bias Amplification: Large Language Models as Increasingly Biased Media 提出政治偏见放大基准，揭示LLM迭代训练中偏见加剧现象及神经机制 large language model
5 AutoFLUKA: A Large Language Model Based Framework for Automating Monte Carlo Simulations in FLUKA AutoFLUKA：基于大语言模型的FLUKA蒙特卡洛模拟自动化框架 large language model
6 Optimizing Large Language Models for Dynamic Constraints through Human-in-the-Loop Discriminators 提出人机协作框架以优化大语言模型应对动态约束问题 large language model
7 A Prompt Engineering Approach and a Knowledge Graph based Framework for Tackling Legal Implications of Large Language Model Answers 提出基于提示工程和知识图谱的框架，解决大语言模型回复中潜在的法律风险问题 large language model
8 GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization GlitchMiner：通过梯度引导的离散优化挖掘大语言模型中的Glitch Token large language model ✅
9 SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation SPA-Bench：用于评估智能手机Agent的综合性基准测试平台。 large language model multimodal ✅
10 MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification MCCoder：利用LLM辅助代码生成和严格验证，简化运动控制 large language model
11 MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration MorphAgent：提出一种自演化角色和去中心化协作的多智能体系统 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
12 GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets 提出GDPO：利用GFlowNets学习直接对齐语言模型并提升多样性 reinforcement learning RLHF DPO
13 Cooperation and Fairness in Multi-Agent Reinforcement Learning 提出基于Min-Max公平目标分配的MARL方法，提升多智能体导航的公平性和效率。 reinforcement learning
14 Augmented Lagrangian-Based Safe Reinforcement Learning Approach for Distribution System Volt/VAR Control 提出基于增广拉格朗日的安全强化学习方法，解决配电系统电压/无功控制问题 reinforcement learning
15 A Novel Reinforcement Learning Model for Post-Incident Malware Investigations 提出一种新型强化学习模型，用于优化恶意软件事件后的调查取证。 reinforcement learning
16 Improving Pronunciation and Accent Conversion through Knowledge Distillation And Synthetic Ground-Truth from Native TTS 提出基于知识蒸馏和原生TTS合成数据的口音转换与发音改进方法 distillation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页