2 citations · 3 across the 5 of their papers we have counts for
8 papers
MIST: Multi-Scale Spatial Context for Gene Expression Prediction from Histology
Koushik Howlader, Tirtho Roy, Md Tauhidul Islam +1
Predicting spatial gene expression from standard H&E images could extend molecular analysis to tissues without spatial transcriptomic measurements. A standard Transformer applies s…
Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention
Samrajya Thapa, Daniel J. Quest, Timothy L. Kline +3
Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging. We introduce an easy-to-use, plug-and-play framework for concept-based inte…
bioMoR: Biology-Guided Mixture-of-Recursions for Effective Genomic Learning
Koushik Howlader, Tirtho Roy, Md Tauhidul Islam +1
Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation. Mixture-of-Recursions (MoR) improve…
BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios
Advait Tilak, Jiwon Choi, Nazifa Mouli +1
The rapid advancement of photorealistic Text-to-Video (T2V) generation brings in an urgent need for up-to-date evaluation methods. Existing benchmarks largely overlooked implausibl…
Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions
Shaila Sharmin, Anwar Hossain Zahid, Subhankar Bhattacharjee +3
Machine learning (ML) applications have become an integral part of our lives. ML applications extensively use floating-point computation and involve very large/small numbers; thus,…
MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report
Samrajya Thapa, Koushik Howlader, Subhankar Bhattacharjee +1
In this paper, we introduce a novel Multi-Modal Contrastive Pre-training Framework that synergistically combines X-rays, electrocardiograms (ECGs), and radiology/cardiology reports…
Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs
Anwar Hossain Zahid, Ignacio Laguna, Wei Le
As scientific codes are ported between GPU platforms, continuous testing is required to ensure numerical robustness and identify numerical differences. Compiler-induced numerical d…
MixQuant: Mixed Precision Quantization with a Bit-width Optimization Search
Eliska Kloberdanz, Wei Le
Quantization is a technique for creating efficient Deep Neural Networks (DNNs), which involves performing computations and storing tensors at lower bit-widths than f32 floating poi…