cs.AI（2026-09-23）

📊 共 17 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) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Listening and Mirroring: The Effects of Verbal Attunement and Behavioral Mimicry on Social and Empathic Perceptions of Embodied AI Agents in VR 提出多模态同步以提升虚拟现实中AI代理的社交感知 embodied AI multimodal
2 BiCFlow-MER: Orchestrating Discriminative and Generative Multimodal Emotion Recognition via Conditional Transport 提出BiCFlow-MER以解决多模态情感识别中的信息融合问题 multimodal
3 CART: Closed-Loop Adaptive Red Teaming for Large Language Models 提出CART框架以解决自动化红队测试的局限性 large language model
4 Evaluation of pre-trained models for pedagogical assessment of novel AI-assisted educational questions 评估预训练模型以解决AI辅助教育问题的教学评估 large language model
5 StudentBench: AI and human tutoring yield equivalent GRE learning gains 提出StudentBench以评估AI与人类辅导的GRE学习效果 large language model
6 Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark 提出SWE-Flux基准以解决LLMs在运行时行为推理的挑战 large language model
7 Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer 提出Tool-Lab以优化AI购物代理的决策过程 large language model
8 EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory 提出EnSIMem以解决长期智能体记忆中的实体识别问题 multimodal ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
9 Hunyuan-A13B Technical Report 提出Hunyuan-A13B以提升大语言模型的推理能力与效率 reinforcement learning large language model chain-of-thought
10 Evolutionary Stability Does Not Guarantee Learning Accessibility: A Multi-Agent Reinforcement Learning Perspective on Cooperation Emergence 提出多智能体强化学习框架以解决合作出现问题 reinforcement learning IQL
11 SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference 提出SlackDrive以解决自适应驾驶推理中的计算预算问题 dreamer multimodal
12 Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents 提出GUI-SD-v2以解决多轮GUI交互中的自蒸馏问题 distillation
13 Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination 提出有限样本概率安全认证框架以解决AI决策模型安全性问题 reinforcement learning imitation learning
14 SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design 提出SHRAV框架以解决物理建模与逆向设计问题 world model world models

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
15 An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice 提出系统风险指数以提升AI安全评估透明度 manipulation
16 Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models 提出心理声学对齐的潜在平滑方法以增强全双工语音对话模型的对抗鲁棒性 manipulation

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

#题目一句话要点标签🔗⭐
17 Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound 提出Passing以实现非线性时空重构与音频生成的交互体验 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页