(ICCV 2025) "Principal Components" Enable A New Language of Images

PyTorch implementation of NEPA

Official repo for consistency models.

This is the offical repository of InfiniteVL

Towards Scalable Pre-training of Visual Tokenizers for Generation

Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?

Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”

[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

A high-throughput and memory-efficient inference and serving engine for LLMs

[AAAI 2026 Oral] LENS: Learning to Segment Anything with Unified Reinforced Reasoning

[AAAI 2026] MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning

[AAAI 2026] Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

[npjDigitalMed (Nature Portfolio)] EVA-X: A foundation model for general chest X-ray analysis with self-supervised learning

[ArXiv 2025] MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

Visual Generation Tuning

Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs

🧡 Folo is the AI Reader

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Official Implementation of "UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation"

[NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

[ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models

Reference PyTorch implementation and models for DINOv3

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

Vector (and Scalar) Quantization, in Pytorch