- Champaign, IL
- https://hkchengrex.com
Starred repositories
Fast linear discrete time filtering in PyTorch.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Public release of the Sound Effect Foundation model by Sony AI.
HomeKit support for the impatient.
An immersion toolkit for learning Languages through games and other visual media.
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
MOVA: Towards Scalable and Synchronized Video–Audio Generation
A minimal implementation of DeepMind's Genie world model
Terminal image viewer with native support for iTerm and Kitty
[3DV 2026 Oral] CropCraft: Complete Structural Characterization of Crop Plants From Images
🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.
Code for the paper https://arxiv.org/abs/2205.14987v2
PyTorch building blocks for the OLMo ecosystem
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Official Jax Implementation of MD4 Masked Diffusion Models
A little guide to help you install & manage NVIDIA GPU driver on your Ubuntu system
[CVPR2026] Detect Anything via Next Point Prediction
[CoRL 2025] Human-like Navigation in a World Built for Humans
Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks [ICLR 2026]
Reference PyTorch implementation and models for DINOv3