cs.AI（2025-01-17）

📊 共 13 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) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Large language models for automated scholarly paper review: A survey 综述性论文：大型语言模型在自动化学术论文评审中的应用与挑战 large language model
2 GaussMark: A Practical Approach for Structural Watermarking of Language Models GaussMark：一种实用的语言模型结构水印方法，通过高斯噪声嵌入模型权重实现版权保护。 large language model
3 Exploring the Impact of Generative Artificial Intelligence in Education: A Thematic Analysis 通过主题分析探讨生成式人工智能在教育领域的影响与挑战 large language model
4 Improved IR-based Bug Localization with Intelligent Relevance Feedback 提出BRaIn，利用LLM智能相关性反馈改进基于IR的缺陷定位 large language model
5 LegalScore: Development of a Benchmark for Evaluating AI Models in Legal Career Exams in Brazil LegalScore：构建巴西法律职业考试AI模型评估基准 large language model
6 Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems Agent4Edu：利用生成式Agent为智能教育系统生成学习者响应数据 large language model ✅
7 LLM Reasoner and Automated Planner: A new NPC approach 提出LLM推理器与自动规划器结合的新型NPC架构，提升智能体决策能力 large language model
8 Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude 对比ChatGPT与Claude等LLM，揭示其在伦理困境决策中的偏见与差异 large language model
9 Towards A Litmus Test for Common Sense 提出基于公理化方法的常识推理评测框架，用于评估AI的泛化能力和安全性。 large language model
10 Evolving Deeper LLM Thinking 提出Mind Evolution，通过演化搜索提升LLM在复杂推理任务中的性能。 large language model
11 Exploring the Implementation of AI in Early Onset Interviews to Help Mitigate Bias 利用AI面试系统降低早期招聘中的情感偏见，提升招聘公平性 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
12 ForestProtector: An IoT Architecture Integrating Machine Vision and Deep Reinforcement Learning for Efficient Wildfire Monitoring ForestProtector：结合机器视觉与深度强化学习的物联网野火监测系统 reinforcement learning deep reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
13 Spatiotemporal Prediction of Secondary Crashes by Rebalancing Dynamic and Static Data with Generative Adversarial Networks 提出VarFusiGAN-Transformer模型，用于解决二次事故时空预测中的数据不平衡问题。 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页