Publications

2026

1. 

   Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency

   Ziqi Wen, Parsa Madinei, and Miguel P Eckstein

   Advances in Neural Information Processing Systems, 2026

   arXiv

2025

1. 

   DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction

   Jonathan Skaza, Parsa Madinei, Ziqi Wen, and 1 more author

   arXiv preprint arXiv:2511.16991, 2025

   arXiv

2. 

   INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models

   Parsa Madinei, Ryan Solgi, Ziqi Wen, and 3 more authors

   arXiv preprint arXiv:2511.19676, 2025

   arXiv Code HF

3. 

   A Deep Learning Framework for Predicting Functional Visual Performance in Bionic Eye Users

   Jonathan Skaza, Shravan Murlidaran, Apurv Varshney, and 4 more authors

   bioRxiv, 2025

4. 

   Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps

   Ziqi Wen, Jonathan Skaza, Shravan Murlidaran, and 2 more authors

   arXiv preprint arXiv:2505.12660, 2025

   arXiv

2024

1. 

   Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configuration

   Ziqi Wen, Tianqin Li, Zhi Jing, and 1 more author

   ICLR 2024 Workshop on Representational Alignment, 2024

   arXiv Code

2023

1. 

   Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity

   Tianqin Li, Ziqi Wen, Yangfan Li, and 1 more author

   Advances in Neural Information Processing Systems (Oral), 2023

   arXiv Code