4 papers
Looped Language Models Improve Compositional Tool Calling
Andrei Cristian Popescu, Haitz Sáez de Ocáriz Borde, Pietro Liò
Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We study this question in composit…
Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
Andrei Cristian Popescu, Haitz Sáez de Ocáriz Borde, Pietro Liò
Looped Transformers increase test-time computation by repeatedly applying a shared recurrent block. Learned halting objectives in looped Transformers typically use a single exit di…
Learning 3D Hypersonic Flow with Physics-Enhanced Neural Fields: A Case Study on the Orion Reentry Capsule
Haitz Sáez de Ocáriz Borde, Pietro Innocenzi, Flavio Savarino +2
We develop a 3D aerothermodynamic simulator for the Orion reentry capsule at hypersonic speeds, a timely case study given its role in upcoming lunar missions. The large computation…
Structured Captions Improve Prompt Adherence in Text-to-Image Models (Re-LAION-Caption 19M)
Nicholas Merchant, Haitz Sáez de Ocáriz Borde, Andrei Cristian Popescu +1
We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users…