Code
Open-source releases accompanying the papers above. More at github.com/dbaranchuk.
yandex-research/switti (CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis yandex-research/swd [ICLR'2026] Scale-wise Distillation of Diffusion Models yandex-research/ar-classifier [ECCV 2026] Official code of "Revisiting Autoregressive Models for Generative Image Classification" yandex-research/invertible-cd [NeurIPS'2024] Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps yandex-research/vqdm Official repo for VQDM, a paper on compressing text-to-image diffusion models with vector quantization yandex-research/adaptive-diffusion [CVPR'2024] Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models yandex-research/tab-ddpm [ICML 2023] The official implementation of the paper "TabDDPM: Modelling Tabular Data with Diffusion Models" yandex-research/ddpm-segmentation Label-Efficient Semantic Segmentation with Diffusion Models (ICLR'2022) bigscience-workshop/petals Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading harsha-simhadri/big-ann-benchmarks Framework for evaluating ANNS algorithms on billion scale datasets. dbaranchuk/ivf-hnsw Code for ECCV2018 paper: Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors dbaranchuk/learning-to-route Code for ICML2019 paper: Learning to Route in Similarity Graphs dbaranchuk/nns-meets-deep-rl Code for paper: Towards Similarity Graphs Constructed by Deep Reinforcement Learning ratschlab/GP-VAE TensorFlow implementation for the GP-VAE model described in https://arxiv.org/abs/1907.04155 dbaranchuk/memory-efficient-maml Memory efficient MAML using gradient checkpointing yandex-research/distill-nf Code for the paper: Distilling the Knowledge from Conditional Normalizing Flows yandex-research/learnable-init Code for the paper: Discovering Weight Initializers with Meta-Learning