cs.AI（2025-02-21）

📊 共 24 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱四：生成式动作 (Generative Motion) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search 利用大型语言模型自动标注电商搜索中的查询-商品相关性，降低标注成本。 large language model chain-of-thought
2 Chitrarth: Bridging Vision and Language for a Billion People Chitrarth：面向十亿印度人口的多语言视觉-语言模型 large language model foundation model multimodal
3 TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice TurboFuzzLLM：加速基于突变的模糊测试，有效破解大型语言模型 large language model ✅
4 Protein Large Language Models: A Comprehensive Survey 首个蛋白质大语言模型（Protein LLM）的全面综述，促进蛋白质科学发展。 large language model ✅
5 PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System PAPI：利用PIM的动态并行加速大语言模型解码 large language model
6 Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models 系统性分析ChatGPT、DeepSeek等SoTA大语言模型的透明度和可访问性 large language model
7 A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare 综述：医疗领域大语言模型的可信赖性评估与风险缓解 large language model
8 Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations 提出PTMRec，通过知识引导的参数高效微调弥合预训练多模态模型与推荐系统之间的领域差距。 multimodal
9 On the Effectiveness of Large Language Models in Writing Alloy Formulas 利用大型语言模型自动生成Alloy公式，提升软件规约编写效率 large language model
10 Identifying Features that Shape Perceived Consciousness in Large Language Model-based AI: A Quantitative Study of Human Responses 量化分析人类对LLM主观意识的感知：特征影响与个体差异 large language model
11 ARS: Automatic Routing Solver with Large Language Models 提出ARS：利用大语言模型自动解决具有复杂约束的车辆路径问题 large language model
12 Comparative Analysis of Large Language Models for Context-Aware Code Completion using SAFIM Framework 利用SAFIM框架对比分析大语言模型在上下文感知代码补全中的性能 large language model
13 LEDD: Large Language Model-Empowered Data Discovery in Data Lakes LEDD：利用大语言模型实现数据湖中的数据发现与语义搜索 large language model
14 Scale Up Composed Image Retrieval Learning via Modification Text Generation 提出基于修改文本生成的组合图像检索学习方法，解决数据稀缺问题。 multimodal
15 FormalSpecCpp: A Dataset of C++ Formal Specifications created using LLMs FormalSpecCpp：利用LLM创建的C++形式化规约数据集，促进程序验证研究 large language model ✅
16 AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling AutoToM：通过自动化智能体建模扩展基于模型的心理推断 large language model
17 AI Governance InternationaL Evaluation Index (AGILE Index) 2024 构建AI治理国际评估指标体系(AGILE Index)，评估全球AI治理水平。 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🔗⭐
18 Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network 提出基于技能的贝叶斯网络SEBN，自动生成强化学习课程以加速训练。 reinforcement learning curriculum learning
19 THFlow: A Temporally Hierarchical Flow Matching Framework for 3D Peptide Design 提出THFlow以解决3D肽设计中的多模态时间不一致问题 flow matching multimodal
20 TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning 提出TAG框架，实现去中心化多智能体分层强化学习，提升可扩展性。 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
21 Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk 提出风险优先评估框架以审计金融领域的LLM代理 manipulation ReMoS large language model
22 Deep Learning-based Dual Watermarking for Image Copyright Protection and Authentication 提出基于深度学习的双重水印技术，用于图像版权保护和来源认证。 manipulation

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
23 Bridging Structural Dynamics and Biomechanics: Human Motion Estimation through Footstep-Induced Floor Vibrations 利用足迹诱导的地面振动进行人体运动估计，实现非侵入式步态健康监测 human motion

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
24 An Audio-Visual Fusion Emotion Generation Model Based on Neuroanatomical Alignment 提出基于神经解剖对齐的视听融合情感生成模型，提升情感计算的效率与可解释性。 motion generation ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页