gaasher / I-JEPALinks
Implementation of I-JEPA from "Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture"
☆272Updated 6 months ago
Alternatives and similar repositories for I-JEPA
Users that are interested in I-JEPA are comparing it to the libraries listed below
Sorting:
- Fine-tuning "ImageBind One Embedding Space to Bind Them All" with LoRA☆185Updated last year
- A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…☆301Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆304Updated 3 months ago
- Official code for "TOAST: Transfer Learning via Attention Steering"☆189Updated last year
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆411Updated 6 months ago
- Code release for "Dropout Reduces Underfitting"☆313Updated 2 years ago
- ☆203Updated last year
- Implementation of Block Recurrent Transformer - Pytorch☆220Updated 10 months ago
- This is the repository for the Photorealistic Unreal Graphics (PUG) datasets for representation learning.☆237Updated last year
- Code release for "Learning Video Representations from Large Language Models"☆525Updated last year
- Hiera: A fast, powerful, and simple hierarchical vision transformer.☆1,003Updated last year
- Internet Explorer explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desi…☆163Updated 2 years ago
- ☆185Updated last year
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆173Updated 3 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆350Updated last year
- Experiments in Joint Embedding Predictive Architectures (JEPAs).☆40Updated last year
- Learning from synthetic data - code and models☆319Updated last year
- This is the official repository for the LENS (Large Language Models Enhanced to See) system.☆352Updated last year
- Official code for VisProg (CVPR 2023 Best Paper!)☆736Updated 10 months ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆474Updated last year
- Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch☆89Updated last year
- ☆616Updated last year
- Documentation, notes, links, etc for streams.☆81Updated last year
- LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills☆750Updated last year
- [ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters☆564Updated 5 months ago
- [TMLR23] Official implementation of UnIVAL: Unified Model for Image, Video, Audio and Language Tasks.☆228Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆214Updated 10 months ago
- Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch☆1,249Updated 2 years ago
- Build high-performance AI models with modular building blocks☆533Updated last week
- Open reproduction of MUSE for fast text2image generation.☆354Updated last year