Xiaoke Huang

yet-another-vectornet. Vectornet for trajectory prediction, implemented in PyTorch/Torch_geometric

segment-caption-anything. [CVPR'24] The repository provides code for running inference and training for "Segment and Caption Anything" (SCA) , links for downloading the trained model checkpoints, and example notebooks / gradio demo that show how to use the model.

OrdinalCLIP. [NeurIP'22] OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression

ema. [Preprint'23] "Efficient Meshy Neural Fields for Animatable Human Avatars" https://arxiv.org/abs/2303.12965

MethylProphet. [ICLR'26] This repository contains codes, data, protocols, models, and results of "MethylProphet: A New Paradigm for Genome-wide DNA Methylation Prediction Without Methylation Input"

yet-another-nerf. Yet another NeRF with extensibility and scalability. Support distributed training / evaluation. Implemented in PyTorch.

benchmark-referring-vllm. We benchmark VLLM for referring image captioning. From paper "Segment and Caption Anything"

Promptable-GRiT. Promptable GRiT: support inference with both automatic proposal generation and custom point/box prompts.

ATVGnet. (add docker, fix code) CVPR 2019

nerf.mindspore. Neural radiance field with mindspore. w/ checkpoint, re-imp. performance, and ipynb to play around.

med-adas. Automatic Design of Agentic Systems for Medical Domains

face-vid2vid. Python

c-minus-plus-plus. C Minus Plus Plus (c-++), a C Minus Compiler with C Features, also a course project for BNU Compiler Theory (2019)

phdrule. The Chinese version of the book: The Unwritten Rules of Ph.D. Research.

dotfiles. Shell

Wav2Lip. (add docker) This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.

MakeItTalk. add docker

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

star-vector. [customized] StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.