cs.AI（2025-09-26）

📊 共 14 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) (6) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
1 Patient-specific Biomolecular Instruction Tuning 提出KRONOS图-LLM框架，结合CPTAC-PROTSTRUCT数据集，提升肿瘤精准医疗中患者个体化蛋白质组学理解。 large language model multimodal
2 You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors 提出SysVec，通过系统向量编码缓解大语言模型中的提示泄露问题 large language model instruction following
3 Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research 提出LLM可解释性研究中的泛化性理论框架，并验证1-back注意力头的泛化能力。 large language model
4 Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time 提出动态专家搜索(DES)，提升MoE LLMs在推理时的性能和稳定性 large language model
5 SecureAgentBench: Benchmarking Secure Code Generation under Realistic Vulnerability Scenarios SecureAgentBench：在真实漏洞场景下评估代码Agent的安全代码生成能力 large language model
6 The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging 通过模型融合实现LLM可调推理能力：一项实证研究 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
7 WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities WaveMind：面向文本和视觉模态对齐的会话式脑电图基础模型 representation learning large language model foundation model
8 InfiMed-Foundation: Pioneering Advanced Multimodal Medical Models with Compute-Efficient Pre-Training and Multi-Stage Fine-Tuning InfiMed-Foundation：提出高效预训练和多阶段微调的医学多模态大模型 distillation large language model multimodal ✅
9 Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective 理论分析强化学习提升语言模型规划能力的优势与局限性 reinforcement learning policy learning reward design
10 Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback 提出在线RLHF高效探索算法，解决奖励模型不确定性问题 reinforcement learning RLHF large language model
11 From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascades 提出Inter-Cascade框架，通过在线知识蒸馏提升LLM级联系统的效率与准确率。 distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
12 EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer EMMA：基于生成式视觉迁移的通用真实世界机器人操作 manipulation vision-language-action VLA

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
13 Red Teaming Quantum-Resistant Cryptographic Standards: A Penetration Testing Framework Integrating AI and Quantum Security 提出AI驱动的量子密码协议红队评估框架，提升量子网络安全性 penetration

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

#题目一句话要点标签🔗⭐
14 Generative Modeling and Decision Fusion for Unknown Event Detection and Classification Using Synchrophasor Data 提出基于生成模型和决策融合的框架，用于电力系统未知事件检测与分类。 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页