mit-han-lab / vila-u
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
☆122Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for vila-u
- VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation☆84Updated 2 months ago
- Empowering Unified MLLM with Multi-granular Visual Generation☆104Updated 3 weeks ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆76Updated last month
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆79Updated last week
- Official implementation of the Law of Vision Representation in MLLMs☆128Updated 2 months ago
- ✨✨Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models☆137Updated this week
- The paper collections for the autoregressive models in vision.☆95Updated last week
- The official code of the paper "PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction".☆41Updated last week
- [NeurIPS'24 Spotlight] EVE: Encoder-Free Vision-Language Models☆227Updated last month
- ☆126Updated last week
- 🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook☆40Updated 4 months ago
- [NeurIPS 2024] This repo contains evaluation code for the paper "Are We on the Right Way for Evaluating Large Vision-Language Models"☆147Updated last month
- ☆189Updated 3 months ago
- Explore the Limits of Omni-modal Pretraining at Scale☆86Updated 2 months ago
- This is a repo to track the latest autoregressive visual generation papers.☆42Updated last month
- 🔥 Aurora Series: A more efficient multimodal large language model series for video.☆41Updated 2 weeks ago
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆324Updated 3 weeks ago
- [NeurIPS 2024] Efficient Multi-modal Models via Stage-wise Visual Context Compression☆38Updated 3 months ago
- [ECCV 2024] AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation☆31Updated 2 months ago
- The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A su…☆164Updated last week
- Official implement of MIA-DPO☆32Updated last week
- LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture☆178Updated last month
- 📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.☆205Updated this week
- [ACL 2024 Findings] "TempCompass: Do Video LLMs Really Understand Videos?", Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, Shuhuai Ren, …☆83Updated 3 weeks ago
- [CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs☆132Updated 3 months ago
- Long Context Transfer from Language to Vision☆328Updated 2 weeks ago
- [NeurIPS 2024] Official implementation of the paper "Interfacing Foundation Models' Embeddings"☆110Updated 2 months ago
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input☆54Updated 2 months ago
- Implements VAR+CLIP for image generation☆78Updated 3 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆71Updated 3 months ago