2 papers
cs.LG2026
SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference
Jeff Smith
Pre-trained Vision Kolmogorov-Arnold Networks (KANs) store a dense B-spline grid on every edge, inflating prediction-head parameter counts by more than 140X relative to a comparabl…
cs.CV2026
SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis
Rishav Pramanik, Ian E. Nielsen, Jeff Smith +3
The rapid progress of text-to-image (T2I) models has unlocked unprecedented creative potential, yet their ability to faithfully render complex prompts involving multiple objects, a…