activity
20242026
collaborators

18 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

Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning

Xuehui Wang, Xuankun Yang, Wei Shen

Visual token pruning is a crucial strategy for accelerating VLMs by compressing redundant image patches, yet existing methods often fail to preserve critical cues under dense instr…

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.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…

cs.LG2025

AdaMuon: Adaptive Muon Optimizer

Chongjie Si, Debing Zhang, Wei Shen

We propose AdaMuon, a novel optimizer that combines element-wise adaptivity with orthogonal updates for large-scale neural network training. AdaMuon incorporates two tightly couple…

cs.LG2025

Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations

Chongjie Si, Zhiyi Shi, Xuehui Wang +3

Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence. However, the wide range of tasks and high computational costs mak…