MJ
Meiguang Jin
cs.CVcs.AIcs.CLeess.IVcs.LGcs.SD
On Valency
published · living versionsW_r8jdn6xd·v1 · currentpublished
TaoMate-FVSR: Audio-Guided Facial Video Restoration
with Xinyang Li, Zeran Xu, Jingna Sun, Qijun Gan +2
1 version
Preprints & journals
20 papers in the corpus · 2017–2026MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation2610.23234v2 · Yuhan Sun, Jiaxin Zhao, Yongdong Luo et al.2026 · 0 citationsarXiv
StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning2609.38809v1 · Naen Xu, Wanqing Cui, Yibo Hu et al.2026 · 0 citationsarXiv
SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTS2609.39088v1 · Longyu Lu, Zongwei Du, Mengtao Xing et al.2026 · 0 citationsarXiv
Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis2609.20124v1 · Zifan Guan, Longyu Lu, Junan Zhang et al.2026 · 0 citationsarXiv
TBDub: Production-Oriented Visual Dubbing2609.06144v1 · Bihan Li, Xinyang Li, Zeran Xu et al.2026 · 0 citationsarXiv
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming2608.20958v1 · Yibo Hu, Yu Qian, Mao Gu et al.2026 · 0 citationsarXiv
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report2608.15763v5 · TaoLive AIGC LLM Team: Yuhan Sun, Wenhao Lin, Yongdong Luo et al.2026 · 0 citationsarXiv
AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars2607.24013v2 · Hengyuan Zhang, Jingna Sun, Meiguang Jin et al.2026 · 0 citationsarXiv
TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation2607.24359v1 · Qijun Gan, Chenwei Zhang, Meiguang Jin et al.2026 · 0 citationsarXiv
OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models2607.23193v3 · Jinsen Su, Yongdong Luo, Yuexiao Ma et al.2026 · 0 citationsarXiv
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation2604.19636v1 · Xiangyang Luo, Xiaozhe Xin, Tao Feng et al.2026 · 0 citationsarXiv
LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement Learning2510.07685v1 · Yuhan Sun, Zhiwei Huang, Wanqing Cui et al.2025 · 0 citationsarXiv
Toward Tiny and High-quality Facial Makeup with Data Amplify Learning2403.15033v4 · Qiaoqiao Jin, Xuanhong Chen, Meiguang Jin et al.2024 · 5 citationsarXiv
Lightweight network towards real-time image denoising on mobile devices2211.04687v2 · Zhuoqun Liu, Meiguang Jin, Ying Chen et al.2022 · 9 citationsarXiv
SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement2207.08351v1 · Canqian Yang, Meiguang Jin, Yi Xu et al.2022 · 59 citationsarXiv
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results2205.05675v1 · Yawei Li, Kai Zhang, Radu Timofte et al.2022 · 94 citationsarXiv
AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement2204.13983v1 · Canqian Yang, Meiguang Jin, Xu Jia et al.2022 · 76 citationsarXiv
Learning to Extract a Video Sequence from a Single Motion-Blurred Image1804.04065v1 · Meiguang Jin, Givi Meishvili, Paolo Favaro2018 · 126 citationsarXiv
Plenoptic Image Motion Deblurring.29346091 · Chandramouli, Paramanand, Jin, Meiguang, Perrone, Daniele et al.2018 · 11 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2018;27(4):1723-1734
Deep Mean-Shift Priors for Image Restoration1709.03749v2 · Siavash Arjomand Bigdeli, Meiguang Jin, Paolo Favaro et al.2017 · 127 citationsarXiv
Career total: 43 works. 20 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.