cs.AI（2024-03-07）

📊 共 13 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) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Can Large Language Models Reason and Plan?	探讨大型语言模型的推理与规划能力	large language model
2	Automatic and Universal Prompt Injection Attacks against Large Language Models	提出统一框架与自动化方法以应对大语言模型的提示注入攻击	large language model
3	A Survey on Human-AI Collaboration with Large Foundation Models	综述人机协作与大型基础模型的整合以应对决策挑战	foundation model
4	A Modular End-to-End Multimodal Learning Method for Structured and Unstructured Data	提出MAGNUM以解决多模态数据处理的不足问题	multimodal
5	GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability	提出GraphInstruct以增强大语言模型的图理解与推理能力	large language model	✅
6	How Far Are We from Intelligent Visual Deductive Reasoning?	探讨视觉推理中的盲点，评估视觉语言模型的推理能力	chain-of-thought
7	iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries	提出iScore以解决语言模型评分透明性问题	large language model
8	Feedback-Generation for Programming Exercises With GPT-4	利用GPT-4生成编程作业反馈以提升学生学习效果	large language model
9	Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty	提出自适应任务平衡方法以解决视觉指令调优中的性能不平衡问题	multimodal	✅
10	Federated Recommendation via Hybrid Retrieval Augmented Generation	提出GPT-FedRec以解决联邦推荐中的数据稀疏与异质性问题	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Privacy-preserving Fine-tuning of Large Language Models through Flatness	提出一种通过平坦性保护隐私的语言模型微调方法	distillation large language model
12	Zero-shot cross-modal transfer of Reinforcement Learning policies through a Global Workspace	提出基于全球工作空间的零-shot跨模态强化学习策略转移方法	reinforcement learning contrastive learning multimodal
13	On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models	全面调查大模型对齐方法以解决人类价值偏差问题	reinforcement learning multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页