👋 Welcome to My Personal Website!

About Me

Hi, I’m Benteng Sun (SMARK, 孙奔腾).

I’m an undergraduate student majoring in Data Science (Mathematics Category) at Harbin Institute of Technology, Shenzhen (expected graduation in 2026). My research focuses on machine learning, compressed sensing, and computational imaging under the supervision of Prof. Yongyong Chen.

I have published research at prestigious venues like ICLR and participated in top-tier competitions. I’m currently exploring innovative computational methods to tackle challenging problems in image reconstruction, spectral imaging, and medical imaging.

I am actively seeking PhD opportunities for Fall 2026, aiming to deepen my research in advanced machine learning and computational imaging.

Feel free to contact me at SMARK2019@outlook.com.

Selected Publications

Spectral Compressive Imaging via Unmixing-driven Subspace Diffusion Refinement

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

Developed a novel subspace diffusion refinement framework for SCI to recover high-frequency details using minimal MSI data reconstruction. Achieved 38.14 dB PSNR on KAIST dataset with 10× speedup over prior diffusion methods. Keywords: spectral imaging, subspace decomposition, diffusion refinement, hardware-algorithm co-design

Research Experience & Interests

Research Projects

• Efficient Low-Rank and Sparse Model Compression (Oct 2023–Feb 2024)
  Developed a Frank-Wolfe algorithm-based approach, achieving 10× compression on AlexNet with minimal accuracy loss.

• Unified Low-Rank Adaptation Framework (LoRA variants) (Jan–Apr 2024)
  Conducted comparative analysis and proposed a unified abstraction for efficient large-model fine-tuning techniques.

Research Interests

My work bridges theoretical innovation and practical algorithmic solutions, focusing on:

• Machine Learning & Deep Learning
• Compressed Sensing & Sparse Optimization
• Image Reconstruction & Enhancement
• Multispectral and Medical Imaging

I aim to leverage computational advancements to develop scalable, efficient imaging technologies, facilitating their adoption in both scientific research and clinical practice.

Competitions & Projects

• The 19th “Challenge Cup” National Competition (First Prize)
  Achieved over 95% accuracy in radar-infrared fused object detection under limited data conditions.

• NTIRE Challenge (CVPR 2025)
  Achieved 4th place in visual quality ranking by developing a novel diffusion model, compressed from 1.77B to 2.2M parameters while maintaining high performance.

• MetaMusic: Cross-Modal Music-Driven Visual Generation (Top 1/83 in Freshman Project)
  Developed an innovative cross-modal generation system 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 contributions, or connect via email for potential collaborations!

Thanks for visiting! 😊