cs.AI（2025-05-12）

📊 共 22 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) (14) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Bridging Large Language Models and Single-Cell Transcriptomics in Dissecting Selective Motor Neuron Vulnerability 利用大语言模型桥接单细胞转录组学，解析选择性运动神经元脆弱性 large language model multimodal
2 Multimodal Assessment of Classroom Discourse Quality: A Text-Centered Attention-Based Multi-Task Learning Approach 提出一种文本中心的多模态注意力多任务学习方法，用于评估课堂话语质量。 multimodal
3 Circuit Partitioning Using Large Language Models for Quantum Compilation and Simulations 利用大语言模型进行量子电路划分，优化量子编译与模拟 large language model
4 Evaluating Large Language Models for Real-World Engineering Tasks 构建真实工程任务数据集，评估大语言模型在产品设计、预测和诊断中的能力。 large language model
5 YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models YuLan-OneSim：基于大语言模型的下一代社会模拟器，实现代码零生成与大规模演化。 large language model
6 Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding 提出基于双向评论互通的交互式代码生成方法，提升LLM代码生成质量。 large language model
7 A Case Study Investigating the Role of Generative AI in Quality Evaluations of Epics in Agile Software Development 利用生成式AI评估敏捷史诗质量，提升软件开发效率 large language model
8 GRADA: Graph-based Reranking against Adversarial Documents Attack 提出GRADA，通过图重排序对抗检索增强生成中的对抗文档攻击 large language model
9 Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks 提出Web-Bench，一个基于Web标准与框架的大语言模型代码生成基准测试，解决现有基准饱和问题。 large language model
10 Can Generative AI agents behave like humans? Evidence from laboratory market experiments 利用生成式AI模拟人类经济行为：基于市场实验的LLM智能体研究 large language model
11 How well do LLMs reason over tabular data, really? 评估LLM在表格数据推理能力，揭示其对现实世界表格数据变化的脆弱性 large language model
12 AI in Money Matters 通过访谈调研金融科技行业对大型语言模型（LLM）的采用情况与未来潜力。 large language model
13 Examining the Role of LLM-Driven Interactions on Attention and Cognitive Engagement in Virtual Classrooms 利用LLM驱动的交互提升虚拟课堂中的注意力和认知参与度 large language model
14 Internet of Agents: Fundamentals, Applications, and Challenges 构建以Agent为中心的互联互通基础设施，实现大规模异构Agent的协同编排。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
15 S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models 提出S-GRPO，通过强化学习实现推理模型的早期退出，提升效率和准确率。 reinforcement learning large language model chain-of-thought
16 Explainable Reinforcement Learning Agents Using World Models 提出基于世界模型的解释性强化学习方法，提升用户对智能体策略的理解 reinforcement learning world model model-based RL
17 A Survey on Collaborative Mechanisms Between Large and Small Language Models 综述LLM与SLM协同机制，探索高效、可定制的边缘AI应用 distillation embodied AI large language model
18 Online Learning-based Adaptive Beam Switching for 6G Networks: Enhancing Efficiency and Resilience 针对6G网络，提出基于在线学习的自适应波束切换方法，提升效率和稳定性。 reinforcement learning deep reinforcement learning DRL
19 Multi-source Plume Tracing via Multi-Agent Reinforcement Learning 提出基于多智能体强化学习的烟羽追踪算法，用于快速定位多个污染源。 reinforcement learning
20 Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving 提出ZeroTIR：通过强化学习训练LLM自主执行代码解决数学问题，并揭示其scaling law reinforcement learning large language model ✅
21 Measuring General Intelligence with Generated Games 提出gg-bench：通过生成游戏评估语言模型的通用智能 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity Comet：通过预测激活稀疏性加速大语言模型私有推理 MPC spatiotemporal large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页