Jonathan Wu — accepted AI-conference papers

2026

Decoupling Vision and Language: Codebook Anchored Visual Adaptation

Jason Wu, Tianchen Zhao, Chang Liu, Jiarui Cai, Zheng Zhang, Zhuowei Li +4

CVPR 2026

Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or fine-grained classification, where representation errors can cascad

Cited by 0 Source ↗Scholar ↗

2024

Robustness Preserving Fine-tuning using Neuron Importance

Guangrui Li, Rahul Duggal*, Aaditya Singh, Kaustav Kundu, Bing Shuai, Jonathan Wu

ECCV 2024poster

"Robust fine-tuning aims to adapt a vision-language model to downstream tasks while preserving its zero-shot capabilities on unseen data. Recent studies have introduced fine-tuning strategies to improve in-distribution (ID) performance on the downstream tasks while minimizing deterioration in out-of…

Cited by 0 Source ↗PDF ↗Scholar ↗