Preprint
Aug 2026
Clustering and Token Denoising for Faster and More Robust VLMs
This study introduces ClustRS, a two-part, training-free algorithm for robust token pruning, demonstrating a simple yet powerful alternative to both score-only and diversity-only pruning rules, paving the way for compute-efficient and noise-resilient VLM deployment.
Baptiste Rossigneux, Inna Kucher, Vincent Lorrain et al.
· 0 citations