I am Haoxiang Sun, an undergraduate student in Computer Science and Engineering at Sichuan University (September 2023 – expected June 2027), with a GPA of 3.8/4.0.
Since December 2024, I have been a research intern at DICALab at Sichuan University (Data Intelligence and Computing Art Laboratory), supervised by Dr. Tao Wang.
Since July 2026, I have been a research intern at YuanGroup at Peking University, supervised by Dr. Li Yuan.
Since September 2026, I have been a pre-training intern at StepFun.
My current research focuses on multimodal understanding and generation.
Updated in September 2026.
🔥 News
- 2026.09: Joined StepFun as a pre-training intern.
- 2026.08: UniWorld-Design: From Pixel Generation to Layer-Native Design technical report released.
- 2026.07: V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning preprint released on arXiv.
- 2026.05: I will join YuanGroup @ Peking University in Fall 2027.
- 2026.03: From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models accepted by Information Fusion (CAS Q1 Top Journal).
- 2026.02: Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design accepted by CVPR 2026 (CCF-A).
- 2024.12: Joined DICALab @ Sichuan University as a research intern.
🧩 Open Source Contributions
- 2026.01 - now, Contributor @ vLLM-speculators
🧑⚖️ Academic Service
- 2026 - 2027, Reviewer @ AAAI 2027 ICLR 2027
💻 Internships
- 2026.09 - now, Pre-training Intern, StepFun.
- 2026.07 - now, Research Intern, YuanGroup @ Peking University, Shenzhen, China.
- 2024.12 - now, Research Intern, DICALab @ Sichuan University (Data Intelligence and Computing Art Laboratory), Chengdu, China.
🛠 Technical Skills
- Languages: Mandarin (native), English (fluent)
- Programming Languages: C/C++, Python
- Frameworks: PyTorch, vLLM, VeRL