activity
20242026
collaborators

9 papers

cs.CL2026

Thinking into the Future: Latent Lookahead Training for Transformers

Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli +1

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to…

cs.LG2026

Don't be lazy: CompleteP enables compute-efficient deep transformers

Nolan Dey, Bin Claire Zhang, Lorenzo Noci +6

We study compute efficiency of LLM training when using different parameterizations, i.e., rules for adjusting model and optimizer hyperparameters (HPs) as model size changes. Some…

cs.LG2026

Universal Dynamics of Warmup Stable Decay: understanding WSD beyond Transformers

Annalisa Belloni, Lorenzo Noci, Antonio Orvieto

The Warmup Stable Decay (WSD) learning rate scheduler has recently become popular, largely due to its good performance and flexibility when training large language models. It remai…

cs.AI2026

On the Emergence of Induction Heads for In-Context Learning

Tiberiu Musat, Tiago Pimentel, Lorenzo Noci +3

Transformers have become the dominant architecture for natural language processing. Part of their success is owed to a remarkable capability known as in-context learning (ICL): the…

cs.LG2025

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Yihe Dong, Lorenzo Noci, Mikhail Khodak +1

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including ma…

cs.LG2025

The Importance of Being Lazy: Scaling Limits of Continual Learning

Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta +2

Despite recent efforts, neural networks still struggle to learn in non-stationary environments, and our understanding of catastrophic forgetting (CF) is far from complete. In this…