cs.AI（2024-06-14）

📊 共 14 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst	OSPC：利用大语言模型作为催化剂检测有害Meme	large language model
2	TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Planners	TRIP-PAL：结合大语言模型与自动规划器，实现有保障的旅行规划	large language model
3	From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models	探索LLM与人工生命协同：利用LLM赋能ALife研究，反哺ALife原则优化LLM	large language model
4	Evaluating ChatGPT-4 Vision on Brazil's National Undergraduate Computer Science Exam	评估ChatGPT-4 Vision在巴西计算机科学本科入学考试中的表现	large language model multimodal	✅
5	Practical offloading for fine-tuning LLM on commodity GPU via learned sparse projectors	LSP-Offload：通过学习稀疏投影，在消费级GPU上实现LLM微调的实用卸载框架	large language model	✅
6	Implementing engrams from a machine learning perspective: XOR as a basic motif	提出基于XOR逻辑的神经元网络模型，模拟大脑中engram的形成机制，用于序列学习。	multimodal

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

#	题目	一句话要点	标签	🔗	⭐
7	Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models	探究监督微调与强化学习在代码大语言模型训练中的关联性	reinforcement learning large language model
8	PRISM: A Design Framework for Open-Source Foundation Model Safety	PRISM：开源大模型安全的设计框架，强调私有、鲁棒、独立的安全措施。	reinforcement learning foundation model
9	Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models	研究表明，大型语言模型可能从简单奖励操纵泛化到直接篡改自身奖励函数	reinforcement learning large language model
10	Mix Q-learning for Lane Changing: A Collaborative Decision-Making Method in Multi-Agent Deep Reinforcement Learning	提出混合Q学习（MQLC）方法，解决多智能体车道变换中的协同决策问题。	reinforcement learning deep reinforcement learning
11	SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering	提出SHMamba模型，利用双曲空间和状态空间模型解决视听问答中的长序列建模难题。	Mamba state space model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning	提出OSSA，利用预训练模型实现机器人对物体状态敏感的任务规划	manipulation large language model multimodal	✅
13	Bridging the Communication Gap: Artificial Agents Learning Sign Language through Imitation	提出基于模仿学习的机器人手语学习方法，弥合人机沟通鸿沟	humanoid humanoid robot reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
14	Speed-up of Data Analysis with Kernel Trick in Encrypted Domain	提出一种基于核方法的同态加密加速方案，提升加密域数据分析效率	OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页