FoundationVision ORG

[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!

VAR is a 2024 NeurIPS Best Paper AI image generation project that builds images coarse-to-fine across scales using next-scale prediction, outperforming diffusion models in several benchmarks. Pretrained models from 310M to 2.3B parameters are available on Hugging Face.

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

(Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators

Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

[AAAI-2026]FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

[Tech Report] Alive: A Unified Audio-Video Generation Model

[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

[ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces

[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection

🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook

official training and inference code of bitwise tokenizer

No description.

No description.

No description.