cs.AI（2024-08-23）

📊 共 13 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities 提出Inner-Adaptor架构IAA，赋予冻结LLM多模态能力，避免NLP性能下降 large language model multimodal visual grounding ✅
2 DrugAgent: Multi-Agent Large Language Model-Based Reasoning for Drug-Target Interaction Prediction DrugAgent：基于多智能体大语言模型的药物-靶标相互作用预测 large language model chain-of-thought
3 LalaEval: A Holistic Human Evaluation Framework for Domain-Specific Large Language Models LalaEval：领域特定大语言模型的人工评估整体框架 large language model
4 Understanding Defects in Generated Codes by Language Models 通过缺陷分析与提示工程提升大语言模型代码生成可靠性 large language model chain-of-thought
5 Collaboration Dynamics and Reliability Challenges of Multi-Agent LLM Systems in Finite Element Analysis 研究多智能体LLM系统在有限元分析中的协作动态与可靠性挑战 large language model
6 DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation DOMAINEVAL：一个自动构建的多领域代码生成基准评测，用于评估LLM的代码能力。 large language model ✅
7 CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution CRUXEval-X：一个用于多语言代码推理、理解和执行的基准测试。 large language model
8 Trustworthy, Responsible, and Safe AI: A Comprehensive Architectural Framework for AI Safety with Challenges and Mitigations 提出AI安全架构框架，从可信、负责、安全三个维度分析并缓解AI系统风险。 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🔗⭐
9 Leveraging Contrastive Learning and Self-Training for Multimodal Emotion Recognition with Limited Labeled Samples 针对多模态情感识别，提出结合对比学习与自训练的半监督学习框架，提升小样本场景性能。 contrastive learning multimodal ✅
10 EUR-USD Exchange Rate Forecasting Based on Information Fusion with Large Language Models and Deep Learning Methods 提出IUS框架，融合大语言模型和深度学习，提升欧元/美元汇率预测精度 MAE large language model
11 Transforming Location Retrieval at Airbnb: A Journey from Heuristics to Reinforcement Learning Airbnb利用强化学习改进位置检索，提升搜索系统效率 reinforcement learning
12 Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning 利用范畴论进行组合强化学习，实现技能的归约、复用与循环 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 Avatar Visual Similarity for Social HCI: Increasing Self-Awareness 研究虚拟化身视觉相似度对社交人机交互中自我意识提升的影响 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页