← Search

Yidong Ma

2 accepted papers

2026

IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning

ICLR 2026poster

Large Vision-Language Models (LVLMs) achieve impressive performance across multiple tasks. A significant challenge, however, is their prohibitive inference cost when processing high-resolution visual inputs. While visual token pruning has emerged as a promising solution, existing methods that primar…

Cited by 0SourceScholar
2025

CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection

NeurIPS 2025poster

With the exponential growth of data, traditional object detection methods are increasingly struggling to handle vast vocabulary object detection tasks effectively. We analyze two key limitations of classification-based detectors: positive gradient dilution, where rare positive categories receive ins…

Cited by 0SourcecodeScholar