Xinyu Huang

recognize-anything. Open-source and strong foundation image recognition models.

robust-loss-mlml. Code for paper: Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

IDEA-pytorch. Code for paper: IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training [ACM MM2022]

verl. verl: Volcano Engine Reinforcement Learning for LLMs

MGPO. High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning

Implementation-and-hiding-analysis-of-reversible-steganography-algorithm-based-on-deep-learning. Jupyter Notebook

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

xinyu1205.github.io. HTML