UCSC-VLAA / Recap-DataComp-1B
This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"
☆128Updated 9 months ago
Alternatives and similar repositories for Recap-DataComp-1B:
Users that are interested in Recap-DataComp-1B are comparing it to the libraries listed below
- Matryoshka Multimodal Models☆98Updated last month
- Davidsonian Scene Graph (DSG) for Text-to-Image Evaluation (ICLR 2024)☆85Updated 3 months ago
- Densely Captioned Images (DCI) dataset repository.☆171Updated 8 months ago
- [CVPR 2024] CapsFusion: Rethinking Image-Text Data at Scale☆204Updated last year
- Official repo for StableLLAVA☆94Updated last year
- [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegr…☆68Updated 3 months ago
- ☆133Updated last year
- [TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"☆130Updated 4 months ago
- Official implementation of our paper "Finetuned Multimodal Language Models are High-Quality Image-Text Data Filters".☆44Updated 2 months ago
- ☆166Updated last year
- ✨✨Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models☆154Updated 2 months ago
- This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.or…☆115Updated 8 months ago
- ☆63Updated last month
- Code base of SynthCLIP: CLIP training with purely synthetic text-image pairs from LLMs and TTIs.☆96Updated last week
- Official implementation of the Law of Vision Representation in MLLMs☆151Updated 4 months ago
- DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception☆136Updated 3 months ago
- [CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs☆142Updated 7 months ago
- LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation☆127Updated last year
- TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering☆155Updated 10 months ago
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆68Updated 3 months ago
- CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts☆143Updated 9 months ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆71Updated 9 months ago
- [ICML 2024] On Discrete Prompt Optimization for Diffusion Models - Google☆49Updated 7 months ago
- EVE Series: Encoder-Free Vision-Language Models from BAAI☆313Updated 2 weeks ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆197Updated 2 weeks ago
- ☆96Updated 10 months ago
- LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture☆199Updated 2 months ago
- Official code for 'Paragraph-to-Image Generation with Information-Enriched Diffusion Model'☆102Updated 3 months ago
- ☆138Updated 2 months ago