cs.AI（2023-11-16）

📊 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) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities 提出SimToM框架以提升大型语言模型的心智理论能力 large language model chain-of-thought
2 Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination 提出CRISPR方法以消除指令跟随语言模型的偏见神经元 instruction following
3 INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair 提出INTERVENOR以提升大型语言模型的代码修复能力 large language model ✅
4 Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations 提出DOKE以增强大语言模型在领域推荐中的表现 large language model
5 Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis 提出Chemist-X以解决化学合成反应条件优化问题 large language model
6 Program-Aided Reasoners (better) Know What They Know 提出程序辅助推理模型以提升推理准确性和校准性 large language model chain-of-thought
7 Automatic Engineering of Long Prompts 提出自动化长提示工程方法以提升大语言模型性能 large language model
8 Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning 自动生成PDDL规划中的NL提示以提升LLM行动选择能力 large language model
9 OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning 提出Outcome-supervised Value Model以解决多步数学推理中的错误传播问题 large language model
10 "It's not like Jarvis, but it's pretty close!" -- Examining ChatGPT's Usage among Undergraduate Students in Computer Science 研究本科生如何利用ChatGPT辅助计算机科学学习 large language model
11 Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework 提出Bergeron框架以增强LLM对攻击的鲁棒性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
12 RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models 提出RankPoison以解决RLHF中的数据中毒问题 reinforcement learning RLHF large language model
13 Model Checking for Closed-Loop Robot Reactive Planning 提出基于模型检测的闭环机器人反应规划方法以解决障碍物规避问题 SAC egocentric

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Towards more Practical Threat Models in Artificial Intelligence Security 提出更实用的威胁模型以解决人工智能安全问题 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页