😎 About Me

I am Hongbo Wang, a second-year PhD student at NLPR@CASIA, Institute of Automation of the Chinese Academy of Sciences, supervised by Prof. Ran He. Before that, I received my B.E. degree from Beijing Institute of Technology in 2024. I am fortunate to have internships and collaborations with Kuaishou.

My current research interests include VLM Alignment and Generative Vision.

🔥 News

  • 2026-05 : 🎉 Our paper ASASR is accepted to ICML 2026.
  • 2026-02 : 🎉 Our paper Thoughtful3D and IAPO are accepted to CVPR 2026.
  • 2025-12 : 🎉 Our paper CoGrad3D is accepted to AAAI 2026.
  • 2025-10 : 🏆 Awarded the National Scholarship for Graduate Students (Top 0.2% Nationwide).
  • 2024-09 : 🎉 Our paper Hallo3D is accepted to NeurIPS 2024.

📝 Publications

ASASR teaser

Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution

Hongbo Wang, Huaibo Huang, Pin Wang, Jinhua Hao, Chao Zhou, Ran He

ICML 2026 [Paper] [Code]

Highlight
Thoughtful3D teaser

Think-Then-Generate: Structural Chain-of-Thought Reasoning for Consistent 3D Generation

Xinyue Liu, Jin Liu, Hongbo Wang, Ran He, Huaibo Huang

CVPR 2026 [Paper]

IAPO teaser

Towards Fine-Grained Attribution: Instance-Aware Preference Optimization for Aligning Diffusion Models

Jiayang Sun, Pin Wang, Hongbo Wang, Xinyue Liu, Huaibo Huang, Ran He

CVPR 2026 [Paper]

CoGrad3D teaser

CoGrad3D: Spatially-Coupled Timestep Optimization with Orthogonal Gradient Fusion for 3D Generation

Haoyang Tong, Hongbo Wang, Jin Liu, Qi Wang, Jie Cao, Ran He

AAAI 2026 [Paper]

Hallo3D teaser

Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation

Hongbo Wang, Jie Cao, Jin Liu, Xiaoqiang Zhou, Huaibo Huang, Ran He

NeurIPS 2024 [Paper]

🎖 Honors and Awards

  • 2025    National Scholarship for Graduate Students (Top 0.2% Nationwide)
  • 2024    Outstanding Graduate of Beijing (Top 0.5%)