LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models Paper • 2609.32264 • Published 7 days ago • 43
Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers Paper • 2609.32814 • Published 7 days ago • 21
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus Paper • 2609.15504 • Published 19 days ago • 37