Xiaofeng ZhangPh.D student, SJTU
Key Laboratory of System Control and Information Processing
|
 |
News
|
About Me
I am currently an third-year Ph.D student at SJTU, Shang Hai Jiao Tong University . Prior to that, I received my master degree in NJUPT. My current research focuses on large vision-language models.
Biography
Publications
|
Hallucination Begins Where Saliency Drops Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Xiaosong Yuan, Qiyan Zhao, Jiawei Cao, Feilong Tang, Sinan Fan, Yaomin Shen, Chen Shen, Hao Tang ICLR 2026 [Openreview] [Code] |
| | |
|
Context Tokens are Anchors: Understanding the Repetition Curse in Diffusion MLLMs from an Information Flow Perspective Qiyan Zhao, Xiaofeng Zhang*, Shuochen Chang, Qianyu Chen, Xiaosong Yuan, Xuhang Chen, Luoqi Liu, Jiajun Zhang, Xu-Yao Zhang, Da-Han Wang ICLR 2026, corresponding author [Openreview] |
| | |
|
Remember Me: Bridging the Long‑Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies Peng Gao, Yujian Lee, Xiaofeng Zhang*, Zailong Chen, Hui Zhang AAAI 2026, corresponding author [Arxiv] |
| | |
|
D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs Shuochen Chang, Xiaofeng Zhang*, Qingyang Liu, Li Niu* AAAI 2026, projector leader [Arxiv] [Code] |
| | |
|
What Drives Attention Sinks? A Study of Massive Activations and Rotational Positional Encoding in Large Vision-Language Models Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Jiawei Cao, Hao Cheng, Kaijie Wu Information Processing & Mangement (中科院一区). |
| | |
|
Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs Xiaofeng Zhang*, Yihao Quan*, Chaochen Gu, Chen Shen, Xiaosong Yuan, Shaotian Yan, Jieping Ye EMNLP 2025 Oral🏆 [Arxiv] [Code] |
| | |
|
MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models Qiyan Zhao*, Xiaofeng Zhang*, Yiheng Li, Yun Xing, Xiaosng Yuan, Feilong Tang, Sinan Fan, Xuhang Chen ACM MM 2025 (corresponding author/projector leader) [Arxiv] [Code] |
| | |
|
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Chaochen Gu, Hao Tang, Jieping Ye NAACL 2025 Oral🏆 [arXiv] [Code] |
| | |
|
Enhancing Multimodal Large Language Models Complex Reasoning via Similarity Computation Xiaofeng Zhang, Fanshuo Zeng, Yihao Quan, Zheng Hui, Jiawei Yao AAAI, 2025 [Code] |
| | |
|
Simignore:Enhancing Multimodal Large Language Models Complex Reasoning via Similarity Computation Xiaofeng Zhang, Fanshuo Zeng, Chaochen Gu Neural Network (中科院一区) [Code] |
| | |
|
DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer Jingfeng Wei*, Xiaofeng Zhang* ACM MM, 2024🏆, (corresponding author/projector leader) [arXiv] |
| | |
|
Improving complex reasoning with dynamic prompt corruption: a soft prompt optimization approch Sinan Fan, Liang Xie, Chen Shen, Ge Teng, Xiaosong Yuan, Xiaofeng Zhang, Jieping Ye ICLR, 2025. |
| | |
|
Instance-adaptive Zero-shot Chain-of-Thought Prompting Xiaosong Yuan, Chen Shen, Shaotian Yan, Xiaofeng Zhang, Liang Xie, Wenxiao Wang, Renchu Guan, Ying Wang, Jieping Ye NeurIPS, 2024. [arXiv] |
| | |
|
Wakeup-Darkness: When Multimodal Meets Unsupervised Low-light Image Enhancement Xiaofeng Zhang, Zishan Xu, Hao Tang, Chaochen Gu, Wei Chen ACM Transactions on Multimedia Computing, Communications, 2025 [arXiv] [Code] |
| | |
|
Memory augment is All You Need for image restoration Xiaofeng Zhang, Chaochen Gu, Shanying Zhu IEEE Transactions on Consumer Electronics (中科院二区), 2025. [arXiv] [Code] |
| | |
|
SpA-Former: An Effective and lightweight Transformer for image shadow removal Xiaofeng Zhang, Yudi Zhao, Chaochen Gu International Joint Conference on Neural Networks, (IJCNN), 2023. [arXiv] [Code] |
| | |
|
Sienet: Siamese expansion network for image extrapolation Xiaofeng Zhang, Feng Chen, Cailing Wang IEEE Signal Processing Letters (SPL), 2021. [Paper] [Code] |
| |
Awards
| |
Services
| |