Alternatives and similar repositories for jepa

Users that are interested in jepa are comparing it to the libraries listed below

• facebookresearch / ijepa
  Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised…
  ☆3,203Updated last year
• apple / ml-4m
  4M: Massively Multimodal Masked Modeling
  ☆1,789Updated 7 months ago
• facebookresearch / DiT
  Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
  ☆8,295Updated last year
• apple / ml-aim
  This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.
  ☆1,395Updated 5 months ago
• facebookresearch / chameleon
  Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
  ☆2,081Updated last year
• JIA-Lab-research / MGM
  Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
  ☆3,332Updated last year
• google-research / big_vision
  Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
  ☆3,339Updated 8 months ago
• allenai / OLMo
  Modeling, training, eval, and inference code for OLMo
  ☆6,294Updated 2 months ago
• openai / transformer-debugger
  ☆4,113Updated last year
• cambrian-mllm / cambrian
  Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
  ☆1,979Updated 2 months ago
• LargeWorldModel / LWM
  Large World Model -- Modeling Text and Video with Millions Context
  ☆7,391Updated last year
• baaivision / Emu
  Emu Series: Generative Multimodal Models from BAAI
  ☆1,763Updated 2 weeks ago
• Alpha-VLLM / LLaMA2-Accessory
  An Open-source Toolkit for LLM Development
  ☆2,802Updated last year
• PKU-YuanGroup / MoE-LLaVA
  【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models
  ☆2,298Updated 6 months ago
• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,702Updated 11 months ago
• google / gemma_pytorch
  The official PyTorch implementation of Google's Gemma models
  ☆5,599Updated 8 months ago
• meta-pytorch / gpt-fast
  Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
  ☆6,181Updated 5 months ago
• PKU-YuanGroup / Video-LLaVA
  【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
  ☆3,445Updated last year
• NVlabs / VILA
  VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…
  ☆3,731Updated 2 months ago
• facebookresearch / MetaCLIP
  NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024
  ☆1,807Updated 2 months ago
• AnswerDotAI / fsdp_qlora
  Training LLMs with QLoRA + FSDP
  ☆1,536Updated last year
• mlfoundations / open_flamingo
  An open-source framework for training large multimodal models.
  ☆4,064Updated last year
• meta-pytorch / torchtune
  PyTorch native post-training library
  ☆5,654Updated this week
• pytorch / torchtitan
  A PyTorch native platform for training generative AI models
  ☆5,004Updated this week
• Vchitect / Latte
  [TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.
  ☆1,910Updated 2 months ago
• baaivision / Emu3
  Next-Token Prediction is All You Need
  ☆2,281Updated 2 weeks ago
• facebookresearch / schedule_free
  Schedule-Free Optimization in PyTorch
  ☆2,257Updated 8 months ago
• openai / consistencydecoder
  Consistency Distilled Diff VAE
  ☆2,206Updated 2 years ago
• invictus717 / MetaTransformer
  Meta-Transformer for Unified Multimodal Learning
  ☆1,651Updated 2 years ago
• NUS-HPC-AI-Lab / VideoSys
  VideoSys: An easy and efficient system for video generation
  ☆2,016Updated 5 months ago