cs.AI（2025-07-25）

📊 共 28 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) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoring PhysDrive：首个大规模多模态车载驾驶员生理监测数据集，助力智能座舱研究 multimodal
2 The wall confronting large language models 大型语言模型面临预测不确定性瓶颈，提升可靠性面临根本性挑战 large language model
3 Differentiating hype from practical applications of large language models in medicine -- a primer for healthcare professionals 探讨大型语言模型在医疗领域的应用，区分炒作与实际价值，为医疗专业人员提供指导。 large language model
4 The ISLab Solution to the Algonauts Challenge 2025: A Multimodal Deep Learning Approach to Brain Response Prediction 提出基于功能网络的深度学习方法，预测复杂多模态电影刺激下的大脑反应。 multimodal ✅
5 Automated Code Review Using Large Language Models at Ericsson: An Experience Report 爱立信利用大型语言模型实现自动化代码审查，提升软件质量。 large language model
6 Adaptive XAI in High Stakes Environments: Modeling Swift Trust with Multimodal Feedback in Human AI Teams 提出自适应XAI框架，通过多模态反馈在紧急场景中建模快速信任。 multimodal
7 Ultracoarse Equilibria and Ordinal-Folding Dynamics in Operator-Algebraic Models of Infinite Multi-Agent Games 提出算子代数框架，用于分析无限多智能体博弈中的超粗略均衡与序数折叠动态。 large language model
8 OneShield -- the Next Generation of LLM Guardrails OneShield：下一代LLM安全防护方案，提供模型无关且可定制的安全策略。 large language model
9 DeltaLLM: A Training-Free Framework Exploiting Temporal Sparsity for Efficient Edge LLM Inference DeltaLLM：一种免训练框架，利用时间稀疏性实现高效边缘LLM推理 large language model
10 Generative Logic: A New Computer Architecture for Deterministic Reasoning and Knowledge Generation 提出Generative Logic架构，用于确定性推理和知识生成。 large language model
11 CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback CodeEvo：通过混合迭代反馈，交互式合成代码中心数据 large language model
12 Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security 提出CIRCLE基准测试，评估LLM代码解释器在资源耗尽攻击下的安全性 large language model
13 Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, Scissors 利用Hypothetical Minds模型探究石头剪刀布游戏中人类序列推理的认知局限性 large language model
14 ReCatcher: Towards LLMs Regression Testing for Code Generation ReCatcher：面向代码生成大语言模型的回归测试框架 large language model
15 PEMUTA: Pedagogically-Enriched Multi-Granular Undergraduate Thesis Assessment PEMUTA：一种用于本科毕业论文多粒度评估的教学增强框架 large language model
16 From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems TrustTrack：面向可验证多智能体系统的信任原生协议，保障高风险场景下的行为可信。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
17 Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges 大型语言模型对齐与安全：综述对齐机制、训练范式与新兴挑战 DPO direct preference optimization large language model
18 Oranits: Mission Assignment and Task Offloading in Open RAN-based ITS using Metaheuristic and Deep Reinforcement Learning Oranits：基于元启发式算法和深度强化学习的Open RAN智能交通系统任务分配与卸载 reinforcement learning deep reinforcement learning DRL
19 Hierarchical Deep Reinforcement Learning Framework for Multi-Year Asset Management Under Budget Constraints 提出分层深度强化学习框架，解决预算约束下多年资产管理问题 reinforcement learning deep reinforcement learning
20 Quantum Reinforcement Learning by Adaptive Non-local Observables 提出基于自适应非局域观测的量子强化学习方法，提升智能体性能。 reinforcement learning
21 Controlling Topological Defects in Polar Fluids via Reinforcement Learning 利用强化学习控制极性流体中的拓扑缺陷 reinforcement learning
22 Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation 提出基于效用的知识选择蒸馏方法，提升检索增强生成效果 distillation large language model
23 Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges 探讨LLM在Agent-Based社会模拟中的应用：机遇与挑战 predictive model large language model
24 PennyCoder: Efficient Domain-Specific LLMs for PennyLane-Based Quantum Code Generation PennyCoder：高效的领域特定LLM，用于基于PennyLane的量子代码生成 reinforcement learning large language model
25 Virne: A Comprehensive Benchmark for Deep RL-based Network Resource Allocation in NFV Virne：NFV中基于深度强化学习的网络资源分配综合基准测试框架 reinforcement learning deep reinforcement learning ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
26 Success in Humanoid Reinforcement Learning under Partial Observation 提出基于历史编码器的强化学习方法，首次在部分观测下成功训练Humanoid-v4环境中的人形机器人。 humanoid humanoid locomotion locomotion
27 PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models PrompTrend：提出持续社区驱动的大语言模型漏洞发现与评估系统 manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
28 Large Language Model Powered Automated Modeling and Optimization of Active Distribution Network Dispatch Problems 提出基于大语言模型的配电网自动化建模与优化方法，解决专家依赖问题。 penetration large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页