collaborators

6 papers

cs.CV2026

DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models

Pengjie Wang, Linger Deng, Zujia Zhang +6

Current Unified Large Multimodal Models (ULMMs) support interleaved multimodal reasoning through textual reasoning and intermediate visual states, but typically generate each visua…

cs.CV2026

PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling

Xudong Xie, Hao Yan, Liang Yin +6

Multimodal document understanding is a challenging task to process and comprehend large amounts of textual and visual information. Recent advances in Large Language Models (LLMs) h…

cs.CV2026

GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solving

Linger Deng, Yuliang Liu, Wenwen Yu +4

Geometry problem-solving remains a significant challenge for Large Multimodal Models (LMMs), requiring not only global shape recognition but also attention to intricate local relat…

cs.CV2025

MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling

Liang Yin, Xudong Xie, Zhang Li +2

Scene text retrieval has made significant progress with the assistance of accurate text localization. However, existing approaches typically require costly bounding box annotations…

cs.CV2025

TokBench: Evaluating Your Visual Tokenizer before Visual Generation

Junfeng Wu, Dongliang Luo, Weizhi Zhao +6

In this work, we reveal the limitations of visual tokenizers and VAEs in preserving fine-grained features, and propose a benchmark to evaluate reconstruction performance for two ch…

cs.CV2025

SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting

Dongliang Luo, Hanshen Zhu, Ziyang Zhang +4

Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text s…