3 papers
cs.CV2026
Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs
Shunjie Wen, Jaeyeon Lee, Dong-Wan Choi
Large vision-language models (LVLMs) incur substantial inference costs due to their long and highly redundant visual-token sequences. Diversity-based pruning mitigates this cost by…
cs.CV2026
Moving Beyond Diversity: Visual Token Pruning as Subspace Reconstruction for Efficient VLMs
Jaeyeon Lee, Shunjie Wen, Dong-Wan Choi
Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual tokens. While diversity maximization…
cs.LG2025
Balanced Online Class-Incremental Learning via Dual Classifiers
Shunjie Wen, Thomas Heinis, Dong-Wan Choi
Online class-incremental learning (OCIL) focuses on gradually learning new classes (called plasticity) from a stream of data in a single-pass, while concurrently preserving knowled…