← Search

Xinpei Gao

1 accepted papers

2026

AD-BTS: Adaptive Dual-Branch Token Sparsification via Spatial Information Density

ICML 2026poster

High-resolution visual encoders in multimodal large language models (MLLMs) substantially improve fine-grained perception, yet incur prohibitive computational costs.Existing token pruning methods are effective on natural images but struggle with spatially sparse structured inputs (e.g., charts), whe…

Cited by 0SourceScholar