awesome-llm-papers

awesome-llm-projects | awesome-llm-datasets

English | 简体中文

😎 Awesome lists about all kinds of LLM related papers

Text / Information / Knowledge

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks: This paper introduces a general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation.
• Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering

Image

• Denoising Diffusion Probabilistic Models: This paper introduces a new class of generative models called denoising diffusion probabilistic models (DDPMs).
• Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs: Apple's paper on multimodal LLMs for mobile UI understanding.

Architecture

• Attention is All You Need: This paper introduces the Transformer architecture, which is based on the multi-head attention mechanism.
• Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention: This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation.
• A Primer on the Inner Workings of Transformer-based Language Models: This paper presents a technical introduction to current techniques used to interpret the inner workings of Transformer-based language models.
• KAN: Kolmogorov-Arnold Networks: Inspired by the Kolmogorov-Arnold representation theorem, the paper propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs)

Survey

• A Survey of Large Language Models
• A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?
• A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT
• Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers
• A Comprehensive Overview of Large Language Models
• RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing

Operating System

• AIOS: LLM Agent Operating System

Text To SQL

• Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
• KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

LLMs

• CodeGemma: Open Code Models Based on Gemma
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• Code Llama: Open Foundation Models for Code
• Advancing Multimodal Medical Capabilities of Gemini
• An Introduction to Vision-Language Modeling

LLM fine-tuning

• Efficient Training of Language Models to Fill in the Middle
• Better & Faster Large Language Models via Multi-token Prediction

Security

• LLM Agents can Autonomously Exploit One-day Vulnerabilities

Evaluation

• SWE-BENCH: CAN LANGUAGE MODELS RESOLVE REAL-WORLD GITHUB ISSUES?: SWE-bench is an evaluation framework comprising 2,294 software engineering problems from GitHub, designed to test language models on complex code-editing tasks requiring extensive contextual understanding and reasoning.
• GAIA: A Benchmark for General AI Assistants

Agents

• AutoDev: Automated AI-Driven Development
• Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
• Mixture-of-Agents Enhances Large Language Model Capabilities

Vision

• A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets
• Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning

Audio

• XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model
• VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers