2 citations · 2 across the 10 of their papers we have counts for
10 papers
SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation
Luke James Miller, Yugyung Lee
Thin-structure segmentation--power lines, cracks, lane markings at 1-3 pixel width--requires preserving connectivity that standard representations preclude: patching severs continu…
SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
Luke James Miller, Yugyung Lee
Segmenting small and sparse structures in large-scale images is fundamentally constrained by voxel-level, lattice-bound computation and extreme class imbalance -- dense, full-resol…
QuIC: A Training-Free Quantum Graph Embedding from Ideal Analysis to Practical Hardware Evaluation
Luke Miller, Yugyung Lee
We introduce QuIC, a training-free quantum graph embedding that maps graphs to sorted output distributions via a fixed parameterized circuit. In the ideal one-repetition setting, w…
Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models
Mike Farmer, Abhinav Kochar, Yugyung Lee
Large language models increasingly rely on inference-time procedures such as chain-of-thought reasoning, self-refinement, retrieval augmentation, and verifier-guided revision, yet…
Transient Acceleration and Cross-Dissipation Interference in Fisher-Regularized Wasserstein Gradient Flows
Michael Farmer, Abhinav Kochar, Yugyung Lee
We study transient nonequilibrium dynamics in Fisher-regularized Wasserstein gradient flows and identify a sign-changing cross-dissipation mechanism generated by the coupling betwe…
MATEX: Multi-scale Attention and Text-guided Explainability of Medical Vision-Language Models
Muhammad Imran, Chi Lee, Yugyung Lee
We introduce MATEX (Multi-scale Attention and Text-guided Explainability), a novel framework that advances interpretability in medical vision-language models by incorporating anato…
Predicting When to Trust Vision-Language Models for Spatial Reasoning
Muhammad Imran, Yugyung Lee
Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP…
DGTEN: A Robust Deep Gaussian based Graph Neural Network for Dynamic Trust Evaluation with Uncertainty-Quantification Support
Muhammad Usman, Yugyung Lee
Dynamic trust evaluation in large, rapidly evolving graphs demands models that capture changing relationships, express calibrated confidence, and resist adversarial manipulation. D…
Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models
Muhammad Imran, Yugyung Lee
Recent advances in vision-language models have significantly expanded the frontiers of automated image analysis. However, applying these models in safety-critical contexts remains…
Re-Imagining Multimodal Instruction Tuning: A Representation View
Yiyang Liu, James Chenhao Liang, Ruixiang Tang +8
Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instructi…