StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold (NeurIPS 2025 Spotlight)

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Official Codes for "Demystifying Singular Defects in Large Language Models" (ICML 2025)

PyTorch media decoding and encoding

PyTorch native quantization and sparsity for training and inference

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

SINDER: Repairing the Singular Defects of DINOv2 (ECCV 2024 Oral)

Monocular Depth Estimation Toolbox based on MMSegmentation.

Mitsuba 3: A Retargetable Forward and Inverse Renderer

EPFL Machine Learning Course, Fall 2025

Official repository for ICCV 2023: Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class

Setup a new machine without sudo!

Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22

Official repository for CVPR2022 publication, ViM: Out-Of-Distribution with Virtual-logit Matching

Benchmarking Generalized Out-of-Distribution Detection

Datasets, Transforms and Models specific to Computer Vision