3 papers
cs.CV2026
Tinted Frames: Question Framing Blinds Vision-Language Models
Wan-Cyuan Fan, Jiayun Luo, Declan Kutscher +2
Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that V…
cs.LG2025
REOrdering Patches Improves Vision Models
Declan Kutscher, David M. Chan, Yutong Bai +2
Sequence models such as transformers require inputs to be represented as one-dimensional sequences. In vision, this typically involves flattening images using a fixed row-major (ra…
cs.LG2024
Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River Networks
Erhu He, Declan Kutscher, Yiqun Xie +4
This work introduces a novel graph neural networks (GNNs)-based method to predict stream water temperature and reduce model bias across locations of different income and education…