LIBANN is a fast, portable and easy to use neural network library written in pure ANSI-C

MinImagen: A minimal implementation of the Imagen text-to-image model

CompBench evaluates the comparative reasoning of multimodal large language models (MLLMs) with 40K image pairs and questions across 8 dimensions of relative comparison: visual attribute, existence,…

LeetCodeGPT is a Chrome extension that integrates GPT (Generative Pre-trained Transformer) into LeetCode.

A random event driven text-based game engine.

VMamba: Visual State Space Models，code is based on mamba

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Consistent Koopman Autoencoders

Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation

PyTorch re-implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC datasets

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

SAM Enhance Mask Quality for WSSS: This repository provides tools for generating, evaluating, and visualizing enhanced pseudo masks for Weakly Supervised Semantic Segmentation (WSSS) using the Segm…

(ICLR) Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

Some Conferences' accepted paper lists (including AI, ML, Robotic)

[ICCV 2021] MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

KITTI Object Visualization (Birdview, Volumetric LiDar point cloud )

My personal webpage