Xingyu Zhu

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (2)Eval Frameworks & Benchmarks (1)Computer Vision (1)Natural Language Processing (1)

Frequent co-authors

Junfeng Fang (1)Shuo Wang (1)Beier Zhu (1)Zhicai Wang (1)

Papers (2)

Apr 22, 2026

Xingyu Zhu +61w ago·also University of Science and Technology, Zhongguancun Academy

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation

Hallucination mitigation in LVLMs doesn't have to come at the cost of general performance: MPD reduces hallucinations by 23.4% while *improving* overall generative capabilities.

Xingyu Zhu, Junfeng Fang, Shuo Wang +4

Eval Frameworks & Benchmarks Multimodal Models

Mar 13, 2026

Mar 13, 2026·also HUST, Imperial, KCL, NJU +1

Multimodal OCR: Parse Anything from Documents

Forget treating document graphics as mere pixels: this new OCR system parses them into reusable code, unlocking multimodal supervision and outperforming existing systems.

Handong Zheng, Kaile Zhang, Liang Xin +14

Computer Vision Multimodal Models Natural Language Processing

Search

Xingyu Zhu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)