Zhiqiu Lin's site

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

Streamlit LLM app

A deep learning library for video understanding research.

Collect user feedback from within your Streamlit app

[NeurIPS 2023 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

LPIPS metric. pip install lpips

Avalanche: an End-to-End Library for Continual Learning.

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

[CVPR 2022] Debiased Learning from Naturally Imbalanced Pseudo-Labels

Code for 'Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality', EMNLP 2022

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

A simple HTML visualization tool for computer vision research 🛠️