Linqing Wang 王林青

Tencent Hunyuan · Multimodal Understanding & AIGC Generation

Hello! I work on large-scale multimodal foundation models at Tencent Hunyuan, focusing on omni-unified multimodal interaction, text-to-image and video generation, unified understanding–generation models, and post-training for diffusion systems.

I was previously involved in robotics and bionics research during graduate study at Beihang University (BUAA). Feel free to reach out if you would like to chat or discuss research ideas.

Google Scholar Email
Linqing Wang

news

selected works

  1. NeurIPS 2026 Under Review

    HY-SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models

    Y Qin, L Wang, H Fei, R Zimmermann, L Bo, Q Lu, C Wang

    Conference on Neural Information Processing Systems, 2026

    A scalable, reward-free post-training framework for rectified-flow diffusion models. Open-sourced at HY-SOAR.

    arXiv Code Website
  2. arXiv 2026

    Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

    J Guo, L Wang, J Wang, Y Yue, Z Liu, Z Zhao, Q Lu, G Huang, C Wang

    arXiv Code
  3. arXiv 2026

    Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

    X Xing, Z Xue, Z Li, W Liang, L Wang, Z Yang, T Hang, Z Yin, Q Lu, et al.

    arXiv Code
  4. CVPR Workshops 2026

    ChatUMM: Robust Context Tracking for Conversational Interleaved Generation

    W Dai, Z Zhao, Y Zhong, Y Cheng, J Zhang, L Wang, S Zhang, Y Lin, et al.

    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2026

    arXiv
  5. ICML 2026

    TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment

    J Wang, J Lu, G Xu, C Chen, H Yang, L Wang, P Chen, M Chen, Z Hu, et al.

    International Conference on Machine Learning, 2026

    arXiv
  6. CVPR 2026

    PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting

    L Wang, X Xing, Y Cheng, Z Zhao, D Li, T Hang, J Tao, Q Wang, R Li, et al.

    IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

    Universal prompt-rewriting framework with CoT rewriter and AlignEvaluator; powers Hunyuan Image 2.1.

    arXiv Code
  7. CVPR 2026

    JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization

    Y Lin, L Wang, K Lin, Z Lin, K Gong, W Li, B Lin, Z Li, S Zhang, Y Peng, et al.

    IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

    arXiv Code
  8. Technical Report 2025

    HunyuanImage 3.0 Technical Report

    S Cao, H Chen, …, L Wang, …

    First open-source unified understanding and generation image model; #1 on LMArena.

    arXiv Code
  9. arXiv 2025

    InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework

    J Tao, Y Zhang, Q Wang, Y Cheng, H Wang, X Bai, Z Zhou, R Li, L Wang, et al.

    arXiv Code
  10. arXiv 2025

    Hunyuan-game: Industrial-grade Intelligent Game Creation Model

    R Li, C Zhou, …, L Wang, …

    arXiv
  11. arXiv 2024

    HunyuanVideo: A Systematic Framework For Large Video Generative Models

    L Wang (core contributor, image-to-video) · Tencent Hunyuan Team

    Systematic framework for large video generative models; portrait image-to-video.

    arXiv Code
  12. Open Source 2024

    Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis

    L Wang (core contributor) · Kolors Team

    Bilingual photorealistic T2I; noise-schedule optimization for direct 1K output.

    Code

Full list and citation counts on Google Scholar.

contact

lqju95@gmail.com