Pablo Acuaviva — accepted AI-conference papers

2026

Composition of Memory Experts for Diffusion World Models

Sebastian Stapf, Pablo Acuaviva, Aram Davtyan, Paolo Favaro

ICLR 2026poster

World models aim to predict plausible futures consistent with past observations, a capability central to planning and decision-making in reinforcement learning. Yet, existing architectures face a fundamental memory trade-off: transformers preserve local detail but are bottlenecked by quadratic atten…

Cited by 0 Source ↗Scholar ↗

2026

Rethinking Visual Intelligence: Insights from Video Pretraining

Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Alexandre Alahi +1

ICML 2026poster

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the visual domain, where models, including LLMs, continue to strugg…

Cited by 4 Source ↗Scholar ↗