activity
20242026
collaborators

6 papers

cs.AI2026

DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding

Hao Yan, Yuliang Liu, Xingchen Liu +5

Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems f…

cs.LG2026

Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers

Hao Yan, Haolin Yang, Yiqiao Zhong

Transformers are effective at inferring the latent task from context via two inference modes: recognizing a task seen during training, and adapting to a novel one. Recent interpret…

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.CV2025

VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning

Hao Yan, Xingchen Liu, Hao Wang +11

Recent strides in multimodal large language models (MLLMs) have significantly advanced their performance in many reasoning tasks. However, Abstract Visual Reasoning (AVR) remains a…

cs.CV2025

HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language Model

Zhenhao Zhang, Hanqing Wang, Xiangyu Zeng +10

Understanding and recognizing human-object interaction (HOI) is a pivotal application in AR/VR and robotics. Recent open-vocabulary HOI detection approaches depend exclusively on l…

cs.CV2024

VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization

Yuliang Liu, Mingxin Huang, Hao Yan +6

Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-…