Oren Tropp — accepted AI-conference papers

2025

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Akhiad Bercovich, Mohammed Dabbah, Omri Puny, Ido Galil, Amnon Geifman, Yonatan Geifman +11

NeurIPS 2025spotlight

We introduce \textit{FFN Fusion}, an architectural optimization technique that reduces sequential computation in large language models by identifying and exploiting natural opportunities for parallelization. Our key insight is that sequences of Feed-Forward Network (FFN) layers, particularly those r…

Cited by 0 Source ↗Scholar ↗

2025

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Akhiad Bercovich, Tomer Ronen, Talor Abramovich, Nir Ailon, Nave Assaf, Mohammed Dabbah +20

ICML 2025poster

Large language models (LLMs) offer remarkable capabilities, yet their high inference costs restrict wider adoption. While increasing parameter counts improves accuracy, it also broadens the gap between state-of-the-art capabilities and practical deployability. We present **Puzzle**, a hardware-aware…

Cited by 2 Source ↗PDF ↗Scholar ↗