#
michalwols
Follow
Starred repositories
Toolkit for linearizing PDFs for LLM datasets/training
Code for collecting, processing, and preparing datasets for the Common Pile
Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
[CVPR25] Official Implementation of CAV-MAE Sync
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models
The repository for Springer IJCV 2025 (LR-ASD: Lightweight and Robust Network for Active Speaker Detection)
The repository for IEEE CVPR 2023 (A Light Weight Model for Active Speaker Detection)
[Preprint] UCGM: Unified Continuous Generative Models
Official repository for the paper Multimodal Transformer Distillation for Audio-Visual Synchronization (ICASSP 2024).
An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution
[SIGGRAPH 2025] Official code of the paper "Cobra: Efficient Line Art COlorization with BRoAder References"
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
MAGI-1: Autoregressive Video Generation at Scale
A TTS model capable of generating ultra-realistic dialogue in one pass.
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
[ICLR 2025] Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitching"
Lets make video diffusion practical!
[Preprint] Efficient Generative Model Training via Embedded Representation Warmup
Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"
Liquid: Language Models are Scalable and Unified Multi-modal Generators
(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling