cs.AI（2025-01-30）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Retrieval Augmented Generation Based LLM Evaluation For Protocol State Machine Inference With Chain-of-Thought Reasoning 提出基于RAG的LLM评估方法，用于协议状态机推理，提升协议模糊测试效率 large language model chain-of-thought
2 Survey and Improvement Strategies for Gene Prioritization with Large Language Models 利用大型语言模型和分治策略改进基因优先级排序，助力罕见病诊断 large language model
3 Enhancing Large Language Model Efficiencyvia Symbolic Compression: A Formal Approach Towards Interpretability 提出基于符号压缩的LLM效率提升方法，解决代码生成和逻辑推理中的token效率瓶颈。 large language model
4 Normative Evaluation of Large Language Models with Everyday Moral Dilemmas 利用日常道德困境评估大型语言模型的规范性，揭示其与人类判断的差异 large language model
5 Semantic Web and Creative AI -- A Technical Report from ISWS 2023 ISWS 2023探索语义网技术与创造性AI的交叉，聚焦LLM在知识工程及创意内容生成中的应用 large language model multimodal
6 Successor-Generator Planning with LLM-generated Heuristics 利用LLM生成启发式函数的后继生成器规划方法，提升领域无关规划性能。 large language model
7 BounTCHA: A CAPTCHA Utilizing Boundary Identification in Guided Generative AI-extended Videos BounTCHA：利用生成式AI扩展视频中的边界识别，设计新型CAPTCHA机制 large language model
8 ChatGPT vs. DeepSeek: A Comparative Study on AI-Based Code Generation 对比ChatGPT与DeepSeek在代码生成任务中的性能，DeepSeek在算法问题上表现更优 large language model
9 Leveraging LLM Agents for Automated Optimization Modeling for SASP Problems: A Graph-RAG based Approach 提出基于图检索增强的LLM Agent，用于传感器阵列信号处理问题的自动优化建模 large language model
10 Economic Rationality under Specialization: Evidence of Decision Bias in AI Agents 专业化AI决策易偏离理性：基于GARP和CCEI的决策偏差分析 large language model
11 Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge 提出EvalPlanner，通过规划与推理提升LLM作为裁判的评估能力 chain-of-thought
12 Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation 提出Cogito，一种神经生物学启发的代码生成认知-记忆-增长系统 large language model

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

#题目一句话要点标签🔗⭐
13 Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI 提出Simulation Streams编程范式，用于高效控制大语言模型并构建复杂生成式AI系统。 reinforcement learning large language model
14 Neural Operator based Reinforcement Learning for Control of first-order PDEs with Spatially-Varying State Delay 提出基于神经算子的强化学习方法，用于控制具有空间变化状态延迟的一阶偏微分方程 reinforcement learning deep reinforcement learning SAC
15 Joint Optimization of Prompt Security and System Performance in Edge-Cloud LLM Systems 针对边缘云LLM系统，提出联合优化提示安全与系统性能的方案 reinforcement learning RLHF large language model
16 Model-Free RL Agents Demonstrate System 1-Like Intentionality 提出基于认知心理学框架，将无模型强化学习智能体的行为类比为人类认知中的“系统1”反应模式 reinforcement learning model-based RL

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Exploring Audio Editing Features as User-Centric Privacy Defenses Against Large Language Model(LLM) Based Emotion Inference Attacks 利用音频编辑特性，针对LLM情感推断攻击，提出用户中心隐私保护方案 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页