[ICLR 2025] Diffusion Feedback Helps CLIP See Better
☆299Jan 23, 2025Updated last year
Alternatives and similar repositories for DIVA
Users that are interested in DIVA are comparing it to the libraries listed below
Sorting:
- EVE Series: Encoder-Free Vision-Language Models from BAAI☆368Jul 24, 2025Updated 7 months ago
- [COLM'25] Official implementation of the Law of Vision Representation in MLLMs☆175Oct 6, 2025Updated 4 months ago
- DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception☆159Dec 6, 2024Updated last year
- SEED-Voken: A Series of Powerful Visual Tokenizers☆996Nov 25, 2025Updated 3 months ago
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆86Jul 16, 2024Updated last year
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,936Aug 15, 2024Updated last year
- ☆124Jul 29, 2024Updated last year
- [ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"☆893Aug 13, 2024Updated last year
- [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.☆1,875Jan 8, 2026Updated last month
- [ICLR'25] Reconstructive Visual Instruction Tuning☆135Apr 9, 2025Updated 10 months ago
- ☆360Jan 27, 2024Updated 2 years ago
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆1,553Mar 16, 2025Updated 11 months ago
- [ECCV 2024] Official PyTorch implementation of DreamLIP: Language-Image Pre-training with Long Captions☆138May 8, 2025Updated 9 months ago
- [CVPR 2024] CapsFusion: Rethinking Image-Text Data at Scale☆213Feb 27, 2024Updated 2 years ago
- 📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.☆800Oct 10, 2025Updated 4 months ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆95Mar 1, 2025Updated last year
- [CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".☆438Aug 8, 2025Updated 6 months ago
- Multimodal Models in Real World☆555Feb 24, 2025Updated last year
- VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks☆391Jul 9, 2024Updated last year
- Next-Token Prediction is All You Need☆2,355Jan 12, 2026Updated last month
- Emu Series: Generative Multimodal Models from BAAI☆1,765Jan 12, 2026Updated last month
- EVA Series: Visual Representation Fantasies from BAAI☆2,647Aug 1, 2024Updated last year
- [NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"☆289Jan 14, 2024Updated 2 years ago
- LLM2CLIP significantly improves already state-of-the-art CLIP models.☆630Feb 1, 2026Updated last month
- This repo contains the code for 1D tokenizer and generator☆1,117Mar 20, 2025Updated 11 months ago
- [NeurIPS 2024] Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning☆72Feb 11, 2025Updated last year
- Cambrian-1 is a family of multimodal LLMs with a vision-centric design.☆1,986Nov 7, 2025Updated 3 months ago
- [NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training☆226Mar 20, 2025Updated 11 months ago
- This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.☆1,402Aug 4, 2025Updated 6 months ago
- High-performance Image Tokenizers for VAR and AR☆303Apr 25, 2025Updated 10 months ago
- Official implementation of the paper "Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention" (Neu…☆136Oct 3, 2024Updated last year
- Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?☆145Feb 11, 2025Updated last year
- Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)☆593Apr 23, 2024Updated last year
- Official Implementation for "MyVLM: Personalizing VLMs for User-Specific Queries" (ECCV 2024)☆186Jul 5, 2024Updated last year
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆418Apr 25, 2025Updated 10 months ago
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆54Mar 9, 2025Updated 11 months ago
- NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024☆1,815Nov 27, 2025Updated 3 months ago
- Official implementation of SEED-LLaMA (ICLR 2024).☆640Sep 21, 2024Updated last year
- [NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models☆120Nov 14, 2024Updated last year