Brian Qu

MPP-LLaVA. Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.

IP-IQA. [ICME2024, Official Code] for paper "Bringing Textual Prompt to AI-Generated Image Quality Assessment"

IE-Critic-R1. IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment

TriVQA. [CVPRW2024, Official Code] for paper "Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gap".

reproduce-heart-in-Lighter-and-Princess. 本仓库参考bilibili码农高天的讲解，实现了电视剧《点燃我，温暖你》中李峋的爱心。代码和实现结果见仓库

Context-Encoder. Python

Vibe_MCPs. MCP Tools/Servers generated by Vibe-Coding.

Coobiw.

mmpretrain. OpenMMLab Pre-training Toolbox and Benchmark

ChartMoE-20250306. [ICLR2025 Oral] ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding

pytorch-word2vec-glove. This repository implements the Word2Vec and GloVe by pytorch deep learning framework. Refer to the d2l(https://zh-v2.d2l.ai/) and self-implement the GloVe. So maybe this is a record of my learning start for NLP.:)

modelhub.

Awesome-MLLM-Reasoning-Collection. A collection of multimodal reasoning papers, codes, datasets, benchmarks and resources.

xhs-hotsearch-vibe. Kimi-K2-0905 Vibe-Coding Test: Get XiaoHongShu hot-search, analyze, then output a html report. All the project is completed by Kimi-K2-0905 + Claude Code.

CC-Cmds. My usually used Claude-Code Commands.