Ahmed Roman — accepted AI-conference papers

2025

HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class

James V Roggeveen, Erik Y. Wang, David Ettel, Will Flintoft, Peter Donets, Raglan Ward +39

NeurIPS 2025poster

Large language models (LLMs) have shown remarkable progress in mathematical problem-solving, but evaluation has largely focused on problems that have exact analytical solutions or involve formal proofs, often overlooking approximation-based problems ubiquitous in applied science and engineering. To…

Cited by 0 Source ↗code ↗Scholar ↗

2024

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai +7

ACL 2024long

We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs). First, during training we apply layer dropout, with low dropout rates for earlier layers and higher dropout rates for later layers, and an early exit loss where all transformer layers share the same e…

Cited by 85 Source ↗PDF ↗code ↗Scholar ↗