Long-WAM: Scaling the Context of World-Action Models

Wei Huang*, Bohan Zhang*, Chenzhi Liu, Isabella Liu, Shuai Yang, Weian Mao, Luozhou Wang, Yicheng Xiao, Weifeng Lin, Qixin Hu, Bryan Chu, Sifei Liu, Linxi Fan, Xiaojuan Qi, Song Han, Yukang Chen.

Long-context world-action models with streaming visual memory, deployed on YAM, Franka and Unitree G1.

Paper Page Video Code

LongLive-Plug: Once-for-All Distillation for Video Generation

Shuai Yang*, Luozhou Wang*, Wei Huang, ZhiFei Chen, Bohan Zhang, Xiao Fu, Qianli Ma, Chen-Hsuan Lin, Weian Mao, Bryan Chu, Song Han, Yukang Chen.

Distills CFG, few-step sampling and long-context correction into reusable LoRAs once per backbone, then plugs them into downstream models without retraining.

Paper Page Model Video Code

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation

Qixin Hu, Shuai Yang, Wei Huang, Song Han, Yukang Chen.

Treats long video generation as retrieval: an autoregressive generator pulls the most relevant past latents back into context to reduce drift, with the base model frozen.

Paper Page Model Code

LongLive 2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Yukang Chen, Luozhou Wang, Wei Huang, Shuai Yang, Bohan Zhang, Yicheng Xiao, Ruihang Chu, Weian Mao, Qixin Hu, Shaoteng Liu, Yuyang Zhao, Huizi Mao, Yingcong Chen, Enze Xie, Xiaojuan Qi, Song Han.

NVFP4 quantization, sequence parallelism and multi-shot support for AR training, DMD distillation and inference (45.7 FPS).

Paper Page Docs Video Code

LongLive: Real-time Interactive Long Video Generation

Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, Song Han, Yukang Chen.

Hugging Face Daily Paper Top 1 · Weekly Paper Top 2 · Monthly Paper Top 8

Paper Page Model Video Code

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Wei Huang, Yi Ge, Shuai Yang, Yicheng Xiao, Huizi Mao, Yujun Lin, Hanrong Ye, Sifei Liu, Ka Chun Cheung, Hongxu Yin, Yao Lu, Xiaojuan Qi, Song Han, Yukang Chen.

Paper Code

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie.

Paper Page Code

Code of Long-RL: Scaling RL to Long Sequences

Yukang Chen, Wei Huang, Shuai Yang, Qinghao Hu, Baifeng Shi, Hanrong Ye, Ligeng Zhu.

The third most active code contributor to the Long-RL repository.

Code

SEED-Story: Multimodal Long Story Generation with Large Language Model

Shuai Yang, Yuying Ge, Yang Li, Yukang Chen, Yixiao Ge, Ying Shan, Yingcong Chen.

Hugging Face Daily Paper

Paper Model Data Code

Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics

Shuai Yang*, Zhifei Chen*, Pengguang Chen, Xi Fang, Shu Liu, Yingcong Chen.

Paper Page Data Code

Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs

Lin Song, Yukang Chen, Shuai Yang, Xiaohan Ding, Yixiao Ge, Yingcong Chen, Ying Shan.

Denoising Diffusion Step-aware Models

Shuai Yang, Yukang Chen, Luozhou Wang, Shu Liu, Yingcong Chen.

Paper Code

Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation

Luozhou Wang*, Shuai Yang*, Shu Liu, Yingcong Chen.

Paper Code