WM
Weijia Mao
cs.CVcs.AI
On Valency
published · living versionsW_yspzx7a9·v1 · currentpublished
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
with Liaoyuan Fan, Yuhao Zheng, Dongxing Mao, Hangyu Ran +16
1 version
Preprints & journals
14 papers in the corpus · 2022–2026AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation2605.13724v1 · Yuchao Gu, Guian Fang, Yuxin Jiang et al.2026 · 0 citationsarXiv
BitDance: Scaling Autoregressive Generative Models with Binary Tokens2602.14041v2 · Yuang Ai, Jiaming Han, Shaobin Zhuang et al.2026 · 0 citationsarXiv
UniWeTok: An Unified Binary Tokenizer with Codebook Size for Unified Multimodal Large Language Model2602.14178v3 · Shaobin Zhuang, Yuang Ai, Jiaming Han et al.2026 · 0 citationsarXiv
Mitty: Diffusion-based Human-to-Robot Video Generation2512.17253v1 · Yiren Song, Cheng Liu, Weijia Mao et al.2025 · 0 citationsarXiv
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation2511.20256v1 · Weijia Mao, Hao Chen, Zhenheng Yang et al.2025 · 0 citationsarXiv
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning2505.23380v1 · Weijia Mao, Zhenheng Yang, Mike Zheng Shou2025 · 0 citationsarXiv
Long-Context Autoregressive Video Modeling with Next-Frame Prediction2503.19325v3 · Yuchao Gu, Weijia Mao, Mike Zheng Shou2025 · 0 citationsarXiv
DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles2503.03651v1 · Rui Zhao, Weijia Mao, Mike Zheng Shou2025 · 1 citationarXiv
UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths2502.06474v1 · Weijia Mao, Zhenheng Yang, Mike Zheng Shou2025 · 0 citationsarXiv
Show-o: One Single Transformer to Unify Multimodal Understanding and Generation2408.12528v7 · Jinheng Xie, Weijia Mao, Zechen Bai et al.2024 · 3 citationsarXiv
ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors2312.13324v1 · Weijia Mao, Yan-Pei Cao, Jia-Wei Liu et al.2023 · 0 citationsarXiv
DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing2310.10624v2 · Jia-Wei Liu, Yan-Pei Cao, Jay Zhangjie Wu et al.2023 · 12 citationsarXiv
Novel View Synthesis for High-fidelity Headshot Scenes2205.15595v1 · Satoshi Tsutsui, Weijia Mao, Sijing Lin et al.2022 · 4 citationsarXiv
DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes2205.15723v2 · Jia-Wei Liu, Yan-Pei Cao, Weijia Mao et al.2022 · 66 citationsarXiv
Career total: 15 works. 14 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.