activity
20242026
collaborators

19 papers

cs.CV2026

VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval

Haocheng Wang, Tongkun Guan, Wei Shen +1

Visual document retrieval has recently become increasingly important in applications such as enterprise search, scientific literature discovery, and retrieval-augmented generation.…

cs.CV2026

NEARL: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding

Zelin Peng, Yichen Zhao, Yu Huang +5

Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning. While vision-language models (VLMs) such as CLIP exhibit strong generalization abilit…

cs.CV2026

LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement

Tongkun Guan, Haocheng Wang, Wei Shen +1

Visual document retrieval requires rapidly locating relevant pages from large multi-modal corpora in response to user queries. While recent methods powered by Multi-modal Large Lan…

cs.CV2026

CodePercept: Code-Grounded Visual STEM Perception for MLLMs

Tongkun Guan, Zhibo Yang, Jianqiang Wan +10

When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limit…

cs.CV2026

Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge

Yu Huang, Zelin Peng, Changsong Wen +2

Affordance segmentation aims to decompose 3D objects into parts that serve distinct functional roles, enabling models to reason about object interactions rather than mere recogniti…

cs.CL2026

Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning

Chongjie Si, Zhiyi Shi, Shifan Zhang +3

Large language models demonstrate impressive performance on downstream tasks, yet they require extensive resource consumption when fully fine-tuning all parameters. To mitigate thi…