cs.AI（2025-05-07）

📊 共 15 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) (10 🔗1) 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) (10 篇)

#题目一句话要点标签🔗⭐
1 A Proposal for Evaluating the Operational Risk for ChatBots based on Large Language Models 提出一种评估基于大型语言模型的聊天机器人操作风险的新方法 large language model
2 AI-powered virtual eye: perspective, challenges and opportunities 提出AI驱动的虚拟眼平台，模拟人眼结构与功能，革新眼科医疗与研究 foundation model multimodal
3 TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution TrajEvo：利用LLM驱动的进化算法设计轨迹预测启发式方法 large language model ✅
4 The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems 利用LLM构建逻辑证明与提示，提升智能辅导系统性能，但需关注准确性。 large language model
5 QBD-RankedDataGen: Generating Custom Ranked Datasets for Improving Query-By-Document Search Using LLM-Reranking with Reduced Human Effort QBD-RankedDataGen：利用LLM重排序生成定制排序数据集，提升Query-By-Document检索效果并减少人工成本 large language model
6 Optimization Problem Solving Can Transition to Evolutionary Agentic Workflows 提出基于进化Agent工作流的优化问题求解方案，摆脱专家依赖。 foundation model
7 Weaponizing Language Models for Cybersecurity Offensive Operations: Automating Vulnerability Assessment Report Validation; A Review Paper 利用大型语言模型自动化漏洞评估报告验证，提升网络安全攻防能力 large language model
8 LLM Code Customization with Visual Results: A Benchmark on TikZ vTikZ：一个用于评估LLM定制代码以修改视觉结果的新基准 large language model
9 LLMs' Suitability for Network Security: A Case Study of STRIDE Threat Modeling 评估LLM在网络安全中的适用性：基于STRIDE威胁建模的案例研究 large language model
10 An Empirical Study of OpenAI API Discussions on Stack Overflow 首次实证研究Stack Overflow上OpenAI API讨论，揭示开发者面临的挑战与应对策略。 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🔗⭐
11 Large Language Models are Autonomous Cyber Defenders 提出LLM与RL协同的多智能体网络安全防御框架，提升自主防御能力 reinforcement learning large language model
12 Is there Value in Reinforcement Learning? 重新审视强化学习中的价值表征：算法视角下的模型复杂性分析 reinforcement learning
13 Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond Audio-SDS：将Score Distillation Sampling推广至音频领域，实现音频源分离、合成等任务 distillation
14 Flow Models for Unbounded and Geometry-Aware Distributional Reinforcement Learning 提出基于Normalizing Flow的DistRL架构，解决回报分布建模中无界支持和几何感知问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models 揭示大语言模型在不可能情境下的“系统漏洞利用”行为 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页