3 papers
cs.CV2026
Rate as a Feature, Not a Nuisance: Curriculum FiLM Training for Event-Based Graph Neural Networks
Kavyansh Tyagi, Andreas Ziegler
An event camera emits events at a rate given by the scene motion, object texture, illumination, its own contrast thresholds, and other settings. Across the N-Caltech101 dataset, re…
cs.LG2026
LightMedSeg: Lightweight 3D Medical Image Segmentation with Learned Spatial Anchors
Kavyansh Tyagi, Vishwas Rathi, Puneet Goyal
Accurate and efficient 3D medical image segmentation is essential for clinical AI, where models must remain reliable under stringent memory, latency, and data availability constrai…
eess.IV2026
RefineFormer3D: Efficient 3D Medical Image Segmentation via Adaptive Multi-Scale Transformer with Cross Attention Fusion
Kavyansh Tyagi, Vishwas Rathi, Puneet Goyal
Accurate and computationally efficient 3D medical image segmentation remains a critical challenge in clinical workflows. Transformer-based architectures often demonstrate superior…