cs.AI（2025-01-27）

📊 共 24 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) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Gensors: Authoring Personalized Visual Sensors with Multimodal Foundation Models and Reasoning Gensors：利用多模态基础模型和推理能力，构建个性化视觉传感器 large language model foundation model multimodal
2 Brain-Adapter: Enhancing Neurological Disorder Analysis with Adapter-Tuning Multimodal Large Language Models 提出Brain-Adapter，利用Adapter调优多模态大语言模型，提升神经系统疾病分析能力 large language model multimodal
3 MetaDecorator: Generating Immersive Virtual Tours through Multimodality MetaDecorator：通过多模态方法生成沉浸式虚拟旅游 large language model multimodal
4 Evaluating The Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology 利用大型语言模型自动总结放疗CT模拟医嘱，显著提升工作效率 large language model
5 TombRaider: Entering the Vault of History to Jailbreak Large Language Models TombRaider：利用历史知识破解大型语言模型的越狱攻击 large language model
6 Intelligent Code Embedding Framework for High-Precision Ransomware Detection via Multimodal Execution Path Analysis 提出基于多模态执行路径分析的智能代码嵌入框架，用于高精度勒索软件检测。 multimodal
7 Regulatory Science Innovation for Generative AI and Large Language Models in Health and Medicine: A Global Call for Action 针对医疗健康领域生成式AI监管，提出全球合作的创新监管科学方法 large language model
8 Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data? 提出FTCT任务，验证Transformer在分离知识间进行组合推理的能力 chain-of-thought
9 The Last Dependency Crusade: Solving Python Dependency Conflicts with LLMs 提出PLLM：利用LLM和RAG解决Python依赖冲突问题 large language model
10 A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions 全面调研计算机使用智能体：奠基、挑战与未来方向 foundation model
11 Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation 提出Skeleton-Guided-Translation框架，用于代码仓库级Java到C#的翻译，并提供细粒度质量评估。 large language model
12 PRISMe: A Novel LLM-Powered Tool for Interactive Privacy Policy Assessment PRISMe：一种基于LLM的交互式隐私政策评估工具 large language model
13 Membership Inference Attacks Against Vision-Language Models 针对视觉-语言模型的成员推理攻击，揭示数据泄露风险。 large language model
14 Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs 提出MAKGED多智能体框架，利用LLM增强知识图谱错误检测。 large language model ✅
15 Propositional Interpretability in Artificial Intelligence 提出命题可解释性，以理解AI系统内部机制与行为 chain-of-thought

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

#题目一句话要点标签🔗⭐
16 Flexible Blood Glucose Control: Offline Reinforcement Learning from Human Feedback PAINT：基于人类反馈的离线强化学习用于个性化血糖控制 reinforcement learning offline RL offline reinforcement learning
17 Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspection 提出ConMIL框架，结合大语言模型和小模型提升生理信号视觉检测精度 SSM large language model
18 Sample-Efficient Behavior Cloning Using General Domain Knowledge 提出KIM模型，利用领域知识提升行为克隆的样本效率和泛化能力 behavior cloning large language model
19 Reinforcement Learning for Quantum Circuit Design: Using Matrix Representations 提出基于强化学习的量子电路设计方法以应对自动化挑战 reinforcement learning deep reinforcement learning
20 Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach 提出量子自然策略梯度算法以加速量子强化学习 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
21 FDLLM: A Dedicated Detector for Black-Box LLMs Fingerprinting 提出FDLLM，一种基于LoRA微调的黑盒大语言模型指纹识别方法 manipulation large language model foundation model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
22 Decrypting the temperature field in flow boiling with latent diffusion models 利用潜扩散模型从相指示图中重建流动沸腾温度场 VQ-VAE

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
23 From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs 利用LLM将自然语言需求转化为可验证的形式化证明，并进行评估 IMoS

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

#题目一句话要点标签🔗⭐
24 MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation MultiPDENet：融合多时间步进的PDE嵌入学习加速流动模拟 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页