2 papers
cs.LG2026
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding
Alexander Samarin, Sergei Krutikov, Anton Shevtsov +3
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parall…
cs.LG2025
Challenging Gradient Boosted Decision Trees with Tabular Transformers for Fraud Detection at Booking.com
Sergei Krutikov, Bulat Khaertdinov, Rodion Kiriukhin +3
Transformer-based neural networks, empowered by Self-Supervised Learning (SSL), have demonstrated unprecedented performance across various domains. However, related literature sugg…