Elastic Transformers Without Retraining: Differentiable Soft Pruning Ranks Every Neuron and Head

What the paper does Most model families ship in a few fixed sizes: small, base, large. If you pick one for typical traffic, it is too slow at peak and wasteful when load is light. "Your Transformer Is Secretly Elastic" (Simoncini, Varghese, Burghouts and Snoek, University of Amsterdam and TNO, posted 14 October 2026) proposes turning a single... Weiterlesen: Elastic Transformers Without Retraining: Differentiable Soft Pruning …