[arXiv] On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices

S2cap ♥: A Benchmark and a Baseline for Singing Style Captioning (CIKM 2025 resource paper)

Research Papers on Efficient Neural Fields from EffL Group

Official Implementation of "The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers (ECCV 2024)”

AudioBERT 📢 : Audio Knowledge Augmented Language Model (ICASSP 2025)

Visualization of cache-optimized matrix multiplication

Model Stock: All we need is just a few fine-tuned models

Transformer related optimization, including BERT, GPT

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

An official code release of the paper RGB no more: Minimally Decoded JPEG Vision Transformers

Archiving the material about Paper-Seminar of EffL

Efficient Deep Learning Systems course materials (HSE, YSDA)

Collaborative Score Distillation for Consistent Visual Synthesis (NeurIPS 2023)

Code for "Just Train Twice: Improving Group Robustness without Training Group Information"

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 2…

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

Code repository for the paper - "Matryoshka Representation Learning"

Masked World Models for Visual Control

Pytorch implementation of High-Fidelity Generative Image Compression + Routines for neural image compression

Repo for external large-scale work

[EMNLP 2022] TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Lossless compression using Probabilistic Circuits

Complete implementations from "Algorithms for Modern Hardware"

A computer science textbook

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).