bfshi / TOAST
Official code for "TOAST: Transfer Learning via Attention Steering"
☆189Updated last year
Alternatives and similar repositories for TOAST:
Users that are interested in TOAST are comparing it to the libraries listed below
- ☆179Updated 7 months ago
- Object Recognition as Next Token Prediction (CVPR 2024 Highlight)☆176Updated this week
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆165Updated last year
- [NeurIPS 2024] Official implementation of the paper "Interfacing Foundation Models' Embeddings"☆124Updated 8 months ago
- ☆50Updated last year
- Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"☆105Updated last year
- Official implementation for the paper "Prompt Pre-Training with Over Twenty-Thousand Classes for Open-Vocabulary Visual Recognition"☆259Updated last year
- [ICML 2024] This repository includes the official implementation of our paper "Rejuvenating image-GPT as Strong Visual Representation Lea…☆98Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆286Updated last month
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆101Updated 7 months ago
- Matryoshka Multimodal Models☆101Updated 3 months ago
- [ICML 2025] This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"☆129Updated 10 months ago
- Open source implementation of "Vision Transformers Need Registers"☆176Updated last month
- Densely Captioned Images (DCI) dataset repository.☆180Updated 10 months ago
- Official implementation of "Describing Differences in Image Sets with Natural Language" (CVPR 2024 Oral)☆119Updated last year
- Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).☆100Updated last week
- When do we not need larger vision models?☆391Updated 2 months ago
- A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…☆298Updated last year
- Learning from synthetic data - code and models☆315Updated last year
- Official repository of paper "Subobject-level Image Tokenization"☆70Updated last month
- Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch☆100Updated last year
- [CVPR 2024] ViT-Lens: Towards Omni-modal Representations☆175Updated 3 months ago
- Patching open-vocabulary models by interpolating weights☆91Updated last year
- ☆37Updated 9 months ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆314Updated 11 months ago
- Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders☆108Updated 3 weeks ago
- Sparse Linear Concept Embeddings☆93Updated last month
- Code and models for the paper "The effectiveness of MAE pre-pretraining for billion-scale pretraining" https://arxiv.org/abs/2303.13496☆89Updated 3 weeks ago
- Code base of SynthCLIP: CLIP training with purely synthetic text-image pairs from LLMs and TTIs.☆98Updated last month
- [CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"☆203Updated 10 months ago