JerryWu-code

TinyZero

Deepseek R1 zero tiny version own reproduce on two A100s.

SusGen

[NAACL Findings 2025] This is the official repository for SusGen-GPT.

awesome-generative-ai-guide

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Chat-UniVi

[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

chat-with-mlx

Chat with your data natively on Apple Silicon using MLX Framework.

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

generative-ai-for-beginners

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

Code-Memory

This is just for memorizing my quick-basic45 codes writing in elementary school, which won the 1-st Beijing Shunyi District Champion when I was 12.

dinov2_vitreg

PyTorch code and models for the DINOv2 self-supervised learning method.

DML-OpenProblem

Use this help them fix some bugs in code and description for mathematics formula.

GoT

Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"

gpt-oss

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

instruct-pix2pix

JerryWu-code

GitHub display page :)

jerrywu-code.github.io

For my personal academic website -- Jerry Qilong Wu

LAMP

[CVPR 2024] | LAMP: Learn a Motion Pattern for Few-Shot Based Video Generation

LLaDA

Official PyTorch implementation for "Large Language Diffusion Models"

llm-notebooks

Lumina-mGPT-2.0

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Generative Image Modeling

MagicQuill

Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

Music_AI

For crawling music data and testing MU-LLaMA.

open-r1

Fully open reproduction of DeepSeek-R1

Pyramid-Flow

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

Search-R1

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

simpleRL-reason

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

TokenFormer

Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Touchstone

[NeurIPS 2024] Touchstone - Benchmarking AI on 5,172 o.o.d. CT volumes and 9 anatomical structures

verl

verl: Volcano Engine Reinforcement Learning for LLMs

VideoLearningHub

Software Engineering Website Group Project for NUS IT5007 (AY24-25), collaborate with Lin and Tan.