Parsa Madinei

According to our database, Parsa Madinei authored at least 6 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

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

Ziqi Wen, Parsa Madinei, Miguel P. Eckstein

CoRR, May, 2026

IRIS: Intent Resolution via Inference-time Saccades for Open-Ended VQA in Large Vision-Language Models.

Parsa Madinei, Srijita Karmakar, Russell A. Cohen Hoffing, Felix Gervitz, Miguel P. Eckstein

CoRR, February, 2026

2025

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

Parsa Madinei, Ryan Solgi, Ziqi Wen, Jonathan Skaza, Miguel P. Eckstein, Ramtin Pedarsani

CoRR, November, 2025

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

Jonathan Skaza, Parsa Madinei, Ziqi Wen, Miguel P. Eckstein

CoRR, November, 2025

Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM.

Ryan Solgi, Parsa Madinei, Jiayi Tian, Rupak Vignesh Swaminathan, Jing Liu, Nathan Susanj, Zheng Zhang

CoRR, October, 2025

2024

ARChef: An iOS-Based Augmented Reality Cooking Assistant Powered by Multimodal Gemini LLM.

Rithik Vir, Parsa Madinei

CoRR, 2024