FoundationVision
Hello! This is the GitHub space for the FoundationVision @ ByteDance.
We are dedicated to exploring the frontiers of multimodal intelligence, with the ultimate goal of building Artificial General Intelligence systems (AGI).
Our research focuses on deep learning and multimodal intelligence. We are particularly interested in:
- Visual Foundation Models, Generative Pretrained Models and Large Language Models.
- Multimodal Foundation Models and Representation Learning.
- Open World Interaction via Unified Multi-modal generation and understanding.
- Large-scale Multi-modal generative Pretraining and Alignment.
Our group strives to push the boundaries of multimodal intelligence and has produced highly influential works in the field, including:
- Generative Models: VAR, Waver, Infinity, LLamaGen, InfinityStar, OmniTokenizer
- Object Recognition and Representation Learning: Sparse-RCNN, ByteTrack, SparK, UNINEXT, Unicorn, DanceTrack, VNext, Referformer
- Multimodal Foundation Models: Groma, Liquid, UniTok, GLEE
Popular repositories Loading
Repositories
- Liquid Public
(Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators
- InfinityStar Public
[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
- Infinity Public
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
- .github Public
- VAR Public
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
- Waver Public
Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…