Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning framework that filters out non-informative background regions from document images prior to VLM processing. A binary patch-level classifier removes non-text areas, and a max-pooling refinement step recovers fragmented text regions to enhance spatial coherence. Experiments on real-world document datasets demonstrate that our approach substantially lowers computational costs, while maintaining comparable accuracy.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Study on Token Pruning for ColBERT
The ColBERT model has recently been proposed as an effective BERT based ranker. By adopting a late interaction mechanism, a major advantage of ColBERT is that document representations can be precomputed in advance. Howev…
Faster Learned Sparse Retrieval with Block-Max Pruning
Learned sparse retrieval systems aim to combine the effectiveness of contextualized language models with the scalability of conventional data structures such as inverted indexes. Nevertheless, the indexes generated by th…
RetrievalLeveraging KV Similarity for Online Structured Pruning in LLMs
Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not general…
Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index storage overhead. Existing training-free pruning methods either rely on heuristic…
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs
Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing O…