Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Deformable ConvNets V2 (DCNv2) in PyTorch

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Python library for Room Impulse Response (RIR) simulation with GPU acceleration

A UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.

NTIRE 2020 NonHomogeneous Dehazing Challenge (CVPR Workshop 2020) 1st Solution.