facebookresearch / capiLinks
Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
☆122Updated 6 months ago
Alternatives and similar repositories for capi
Users that are interested in capi are comparing it to the libraries listed below
Sorting:
- WIP☆93Updated last year
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆181Updated last year
- Train VAE like a boss☆295Updated last year
- ☆104Updated 6 months ago
- ☆34Updated 5 months ago
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆86Updated 10 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆320Updated 3 months ago
- My take on Flow Matching☆80Updated 9 months ago
- Focused on fast experimentation and simplicity☆75Updated 10 months ago
- ☆302Updated 6 months ago
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length☆256Updated 4 months ago
- Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).☆187Updated 5 months ago
- Synthetic Alphabet Dataset☆19Updated 6 months ago
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.☆116Updated last month
- ☆22Updated last year
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆72Updated 5 months ago
- Clarity: A Minimalist Website Template for AI Research☆153Updated 9 months ago
- Implementation of a multimodal diffusion transformer in Pytorch☆106Updated last year
- VIT inference in triton because, why not?☆31Updated last year
- Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"☆85Updated last month
- ☆53Updated 2 years ago
- ☆91Updated last year
- [ICCV25] Official Implementation of LeGrad☆80Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- ConceptAttention: A method for interpreting multi-modal diffusion transformers.☆338Updated 6 months ago
- ☆28Updated 3 weeks ago
- 📄Small Batch Size Training for Language Models☆63Updated 3 weeks ago
- ☆150Updated last week
- ☆53Updated last year
- Official PyTorch Implementation of "Rosetta Neurons: Mining the Common Units in a Model Zoo"☆31Updated 2 years ago