JCruan519

spacedrive

Spacedrive is an open source cross-platform file explorer, powered by a virtual distributed filesystem written in Rust.

mem0

The Memory layer for your AI apps

firecrawl

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

rnote

Sketch and take handwritten notes.

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

llm_interview_note

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

gptpdf

Using GPT to parse PDF

llm_aided_ocr

Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.

Awesome-Diffusion-Models-in-Medical-Imaging

Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)

nano-llama31

nanoGPT style version of Llama 3.1

SimPO

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

U-KAN

[ArXiv' 24] U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

CRUD_RAG

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

EVE

[NeurIPS'24 Spotlight] EVE: Encoder-Free Vision-Language Models

RWKV-CLIP

[EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner

Genixer

(ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generator

VL-RLHF

A RLHF Infrastructure for Vision-Language Models

VIGC

AAAI 2024: Visual Instruction Generation and Correction

ControlMLLM

[NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'

VLFeedback

LLaVA-Align

This is the official repo for Debiasing Large Visual Language Models, including a Post-Hoc debias method and Visual Debias Decoding strategy.

GMS

Official repository of Generative Medical Segmentation

MoE-SFT

🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts

VEGA

OVCamo

(ECCV 2024) Open-Vocabulary Camouflaged Object Segmentation

polyp-ddpm

Polyp dataset generation

corruption

The code for generating natural distribution shifts on image and text datasets.

MM-CamObj

(ARXIV24) This is the official code repository for "MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios".

JCruan519.github.io