Liu, Yuliang
33 publications
ICCV
2025
LIRA: Inferring Segmentation in Large Multi-Modal Models with Local Interleaved Region Assistance
NeurIPS
2025
OCRBench V2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
CVPR
2025
SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-End Text Spotting
ICCV
2025
Towards Comprehensive Lecture Slides Understanding: Large-Scale Dataset and Effective Method
NeurIPS
2024
AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
ICMLW
2024
CD-POS: Long Context Generalization in LLMs Through Continuous and Discrete Position Synthesis
CVPR
2024
OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition
ICML
2024
Video-LaVIT: Unified Video-Language Pre-Training with Decoupled Visual-Motional Tokenization
ECCV
2022
Don’t Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context
NeurIPS
2022
MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification