cs.AI（2024-09-11）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1) 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 Understanding Foundation Models: Are We Back in 1924? 探讨基础模型：我们是否回到了1924年？ foundation model
2 Safety challenges of AI in medicine in the era of large language models 综述LLM时代AI医疗安全挑战，聚焦功能、沟通及固有风险，旨在促进安全AI的医学应用。 large language model
3 DrLLM: Prompt-Enhanced Distributed Denial-of-Service Resistance Method with Large Language Models DrLLM：基于大语言模型的提示增强分布式拒绝服务攻击防御方法 large language model ✅
4 Large Language Models and the Extended Church-Turing Thesis 分析大型语言模型计算能力，揭示其与扩展丘奇-图灵论题的关联 large language model
5 AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs 提出AdaPPA，一种自适应位置预填充的LLM越狱攻击方法 large language model instruction following ✅
6 Deep Learning Techniques for Hand Vein Biometrics: A Comprehensive Review 综述深度学习在手部静脉生物识别中的应用，分析挑战与未来方向。 multimodal
7 A Novel Mathematical Framework for Objective Characterization of Ideas 提出一种客观量化创意的新数学框架，用于评估AI或人类产生的想法。 large language model
8 "My Grade is Wrong!": A Contestable AI Framework for Interactive Feedback in Evaluating Student Essays 提出CAELF框架，利用可辩论AI提升LLM在学生论文评估中的交互式反馈效果 large language model
9 SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories SUPER：评估LLM自主执行科研代码库任务的能力，填补了该领域benchmark的空白。 large language model
10 CLNX: Bridging Code and Natural Language for C/C++ Vulnerability-Contributing Commits Identification 提出CLNX，桥接代码与自然语言，轻量级提升LLM的C/C++漏洞识别能力。 large language model
11 Demo: SGCode: A Flexible Prompt-Optimizing System for Secure Generation of Code SGCode：一个灵活的提示优化系统，用于安全代码生成 large language model
12 FreeRide: Harvesting Bubbles in Pipeline Parallelism FreeRide：利用流水线并行中的气泡，提升LLM训练效率 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
13 Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendation 提出mccHRL框架，通过分层强化学习进行列表推荐中的时序抽象，提升推荐效果。 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 A Novel Perturb-ability Score to Mitigate Evasion Adversarial Attacks on Flow-Based ML-NIDS 提出扰动性评分以缓解基于流的ML-NIDS的规避对抗攻击 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页