cs.AI（2026-07-15）

📊 共 15 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System 提出MEDA系统以自动发现生物系统的常微分方程 large language model
2 Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models 提出深度交互方法以高效纠正大型推理模型的错误 large language model chain-of-thought
3 UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following 提出UESF-Bench以解决人类寻觅与跟随的统一评估问题 vision-language-action VLA
4 Experience Memory Graph: One-Shot Error Correction for Agents 提出经验记忆图以解决智能体的一次性错误修正问题 large language model
5 AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities 提出AgentCompass以解决评估LLM代理能力的统一性问题 large language model
6 Social Simulations: from Agent-Based Modeling to Digital Twins 从代理基础建模到数字双胞胎的社会模拟研究 large language model
7 How Far Can Root Cause Analysis Go on Real-World Telemetry Data? 提出结构化多智能体RCA管道以解决微服务故障根因分析问题 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
8 Grounded world models in biological organisms and future embodied AI 提出基于生物智能的世界模型以推动未来的具身AI发展 world model world models affordance
9 Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models 提出基于音频感知大语言模型的细粒度反馈框架以改善文本到音频指令跟随 direct preference optimization large language model instruction following
10 Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling 提出UrbanAgent框架以解决城市区域分析中的跨模态不一致问题 reinforcement learning representation learning multimodal
11 Explaining Reinforcement Learning Agents via Inductive Logic Programming 通过归纳逻辑编程提升强化学习代理的可解释性 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
12 Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation 重新思考AI系统的渗透测试以解决行为目标违反问题 manipulation penetration
13 Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection 提出交通感知随机平滑以增强LLM网络入侵检测的鲁棒性 manipulation large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
14 Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities 提出保护能力幻觉以解决大型语言模型的能力误认问题 affordance large language model

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

#题目一句话要点标签🔗⭐
15 Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations 提出Kaleido以解决视频扩散变换器计算效率问题 spatiotemporal large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页