👋 Welcome to My Personal Website!

About Me

Hi, I’m Benteng Sun (SMARK, 孙奔腾).

I’m an undergraduate student in Data Science (Mathematics Category) at Harbin Institute of Technology, Shenzhen (graduating in 2026).
My research centers on machine learning, sparse representation, and computational imaging, advised by Prof. Yongyong Chen.

I have published at ICLR and participated in top-tier competitions.
Currently, I am exploring efficient and controllable generation paradigms, aiming to build scalable frameworks for images, videos, and 3D content.

I am actively seeking PhD opportunities for Fall 2026, focusing on structured generation, sparsity-aware modelling, and computational imaging.

Feel free to reach out at SMARK2019@outlook.com.

Selected Publications

Haijin Zeng*, Benteng Sun*, Yongyong Chen, Jingyong Su, Yong Xu
ICLR 2025 Accepted (Spotlight) • Top 4.79%📄 Paper | 💻 Code | 🌐 Project

Developed a novel subspace diffusion refinement framework for spectral compressive imaging (SCI), recovering high-frequency details from minimal measurements. Achieved 38.14 dB PSNR on KAIST dataset with 10× speedup over existing diffusion models. Keywords: spectral imaging, sparsity modelling, diffusion refinement

Research Experience & Interests

Research Projects

Spectral Compressive Imaging via Unmixing-driven Subspace Diffusion Refinement (Apr–Oct 2024)
Developed the PSR-SCI framework to solve ill-posed SCI reconstruction, leveraging spectral embedding and RGB diffusion models. Achieved 38.14 dB PSNR on KAIST with 10× faster inference. Spotlight paper at ICLR 2025 (Top 4.79%).
Multimodal Fusion for Target Detection (Nov 2024)
Integrated radar and infrared data for small object detection under limited samples and noise. Achieved 95% accuracy with 36 ms/frame latency. National First Prize, 19th “Challenge Cup.”
Fast MRI Reconstruction via Diffusion Models (Nov 2024–Present)
Developed innovative approaches for accelerated MRI reconstruction, integrating prior knowledge for efficient and reliable recovery. Submitted to a top-tier conference.
Sparsity-aware Conditioning for Generative Models (Ongoing)
Working on scalable and controllable generation methods leveraging structured sparsity for diverse modalities.

Research Interests

My research bridges theoretical modelling and practical algorithm design, currently focusing on:

Generative Modeling and Controllable Generation
(sparsity-aware generation, structure-guided diffusion, efficient sampling)
Compressed Sensing and Sparse Optimization
(signal reconstruction, structural sparsity, underdetermined recovery)
Image, Video, and 3D Reconstruction/Generation
Low-Level Vision and Computational Imaging
(spectral imaging, MRI acceleration, physics-driven restoration)

I am particularly interested in advancing new generation paradigms that integrate sparse structures, efficient computation, and general-purpose applicability across modalities.

Competitions & Projects

The 19th “Challenge Cup” National Competition (First Prize)
Achieved over 95% accuracy in radar-infrared fusion object detection under limited-sample, noise-intensive conditions.
NTIRE Challenge (CVPR 2025)
Developed a novel diffusion-based image restoration system, compressing model parameters from 1.77B to 2.2M while retaining high visual quality.
MetaMusic: Cross-Modal Music-Driven Visual Generation (Top 1/83 in Freshman Project)
Designed a cross-modal generation pipeline using CLIP embeddings for music-to-image translation. 💻 Project

Honors & Awards

First Prize (National), “Challenge Cup” (MoE, PRC, 2024)
Meritorious Winner (Top 6%), Mathematical Contest in Modeling (COMAP, USA, 2024)
First Prize, 15th Chinese Mathematics Competition (2023)
Champion (1/83), Freshman Annual Research Project (HITSZ, 2023)

Scholarships

High-Level Innovation Award (Top 0.1%), HIT (2024, Awarded 50,000 RMB)
Second-Class Scholarship, Undergraduate Academic Excellence Award (2023 & 2024, HITSZ)

Feel free to explore my GitHub for open-source projects, or reach out via email for potential collaborations!

Thanks for visiting! 🌟