Xiao-Hui Li
6 papers · 2023–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Keywords
vision transformer
(2)
semantic segmentation
(1)
benchmark evaluation
(1)
scene understanding
(1)
visual question answering
(1)
question answering
(1)
multimodal learning
(1)
document understanding
(1)
scene parsing
(1)
explainable ai
(1)
visual grounding
(1)
instance segmentation
(1)
feature attribution
(1)
document layout analysis
(1)
saliency map
(1)
document analysis
(1)
deep neural network
(1)
vision-language model
(1)
graph attention network
(1)
multimodal large language model
(1)
Papers
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
CVPR 2026
DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning
CVPR 2025
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
ACL 2025
Two-stage holistic and contrastive explanation of image classification
UAI 2023
Visual Traffic Knowledge Graph Generation from Scene Images
ICCV 2023
ViT-CX: Causal Explanation of Vision Transformers
IJCAI 2023