Code for “It’s never too late: Noise optimization for collapse recovery in trained diffusion models”, CVPR 2026

ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE

LSEP : No Alignment Needed for Generation: Learning Linearly Separable Representations in Diffusion Models

Code for "Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale"

[CVPR 2026 Best Paper Finalist] Pixel Diffusion Transformers for Image Generation

Image classification with any-order AR models

[ECCV 2026] Official code of "Representation Alignment for Just Image Transformers is not Easier than You Think"

Materials for the VisualGenAI course at YSDA2026

[ICLR 2026] Rethinking Global Text Conditioning in Diffusion Transformers

[ICLR 2026 Oral] Neon: Negative Extrapolation From Self-Training Improves Image Generation

PyTorch-implementations of Flow Models for toy data

Official pytorch implementation of "AlphaFlow: Understanding and Improving MeanFlow Models"

Research on Tabular Deep Learning: Papers & Packages

Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache

[ICLR'2026] Scale-wise Distillation of Diffusion Models

(CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

InstructPix2Pix with distilled diffusion models

(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

[CVPR'2024] Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

Codes of PostEdit

Author's Implementation for E-LatentLPIPS