← Search

Huiling Liu

2 accepted papers

2026

ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models

CVPR 2026

Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens. Token pruning alleviates this issue, yet existing approaches face limitations. Attention-based methods rely on raw attention scores, which are often unstable across la

Cited by 0SourcecodeScholar
2025

Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment

NeurIPS 2025poster

Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference. Despite notable advances, several challenges still limit its broader applicability. First, most methods rely on backpropagation or iterative optimization, which…

Cited by 0SourceScholar