Peter Schneider-Kamp — accepted AI-conference papers

2026

DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes

Mogens Henrik From, Jacob Nielsen, Lukas Galke, Peter Schneider-Kamp

AAAI 2026technical

Training large neural network models requires extensive computational resources, often distributed across several nodes and accelerators. Recent findings suggest that it may be sufficient to only exchange the fast moving components of the gradients, while accumulating momentum locally (Decoupled Mom

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?

Jacob Nielsen, Peter Schneider-Kamp, Lukas Galke

ACL 2025finding

Large language models (LLMs) require immense resources for training and inference. Quantization, a technique that reduces the precision of model parameters, offers a promising solution for improving LLM efficiency and sustainability. While post-training quantization methods typically achieve 4-8 bit…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗