facebookresearch / capiLinks
Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
☆116Updated 4 months ago
Alternatives and similar repositories for capi
Users that are interested in capi are comparing it to the libraries listed below
Sorting:
- WIP☆94Updated last year
- ☆103Updated 4 months ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆176Updated last year
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆283Updated last month
- ☆34Updated 3 months ago
- Train VAE like a boss☆292Updated 10 months ago
- ☆294Updated 4 months ago
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆82Updated 8 months ago
- Focused on fast experimentation and simplicity☆76Updated 8 months ago
- ☆87Updated last year
- My take on Flow Matching☆70Updated 7 months ago
- Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).☆178Updated 3 months ago
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆172Updated last year
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆65Updated 2 months ago
- ☆51Updated last year
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length☆242Updated 2 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆96Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆131Updated last year
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.☆91Updated 3 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆199Updated 5 months ago
- Clarity: A Minimalist Website Template for AI Research☆130Updated 7 months ago
- ☆27Updated last year
- NeuMeta transforms neural networks by allowing a single model to adapt on the fly to different sizes, generating the right weights when n…☆43Updated 9 months ago
- [ICCV25] Official Implementation of LeGrad☆78Updated 10 months ago
- Implementation of a multimodal diffusion transformer in Pytorch☆103Updated last year
- ☆21Updated 10 months ago
- Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"☆90Updated 2 months ago
- ☆53Updated last year
- ☆133Updated this week
- ☆307Updated last year