Paper List of Inference/Test Time Scaling/Computing

(TPAMI 2024) A Survey on Open Vocabulary Learning

[T-PAMI-2024] Transformer-Based Visual Segmentation: A Survey

This is a repo to track the latest autoregressive visual generation papers.

Fast and memory-efficient exact attention

Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

CogView4, CogView3-Plus and CogView3(ECCV 2024)

A Unified Tokenizer for Visual Generation and Understanding

[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Open reproduction of MUSE for fast text2image generation.

Wan: Open and Advanced Large-Scale Video Generative Models

PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

FlashMLA: Efficient MLA decoding kernels

Official Repo for Open-Reasoner-Zero

Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

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

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Fully open reproduction of DeepSeek-R1

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Janus-Series: Unified Multimodal Understanding and Generation Models

[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…