近年來,人工智能(AI),尤其是生成式AI,逐步受到重視。
本系列希望通過閱讀發表在國際會議的論文,撰寫精簡內容,讓讀者了解近年來AI的研究方向。
本系列挑選了4個主題,每個主題各7篇,共計28篇論文。
Retrieval Augumented Generation (RAG)
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Retrieval-Augmented Multimodal Language Modeling
- Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
- Recommender Systems with Generative Retrieval
- Recitation-Augmented Language Models
- Benchmarking Large Language Models in Retrieval-Augmented Generation
- Diversify Question Generation with Retrieval-Augmented Style Transfer
Reinforcement Learning (RL)
- Reward Design with Language Models
- Pre-Trained Language Models for Interactive Decision-Making
- Guiding Pretraining in Reinforcement Learning with Large Language Models
- Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning
- TRAVEL: Tag-Aware Conversational FAQ Retrieval via Reinforcement Learning
- OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning
- ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation
Multi-model
- RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation
- Learning to Answer Questions in Dynamic Audio-Visual Scenarios
- Evaluating Object Hallucination in Large Vision-Language Models
- Compressing and Debiasing Vision-Language Pre-Trained Models for Visual Question Answering
- Visual Instruction Tuning
- ILLUME: Rationalizing Vision-Language Models through Human Interactions
- PaLM-E: An Embodied Multimodal Language Model
Graph
- MolCA: Molecular graph-language modeling with cross- modal projector and uni-modal adapter
- Harnessing explanations: Llm-to-lm interpreter for enhanced text-attributed graph representation learning
- Reasoning on graphs: Faithful and interpretable large language model reasoning
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models
- StructGPT: A General Framework for Large Language Model to Reason over Structured Data
- Graph Neural Prompting with Large Language Models
- Talk like a Graph: Encoding Graphs for Large Language Models
接下來每天會以以下格式撰寫
- 摘要
- Background survey
- 發表方法
- 實驗
- 額外資料補充