Author

Alessandro Suglia

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs

This work proposes a framework that exposes backbone depth V, action expert depth A, and denoising steps $D$ as three jointly configurable compute axes in a VLA, and introduces a KV Cache synthesis mechanism that manages the missing keys and values of the skipped backbone layers, allowing the action expert to exit deep...

Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro et al. · 0 citations

#artificial intelligence Jun 2026

GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes

GPTNT is a benchmark built on the cooperative video game Keep Talking and Nobody Explodes, in which two agents must coordinate to defuse procedurally generated bomb puzzles against a live countdown, to expose how models collaborate versus how they perform alone.

Amit Parekh, Sabrina McCallum, Kareem Al-Hasan et al. · arXiv.org · 0 citations

Preprint Aug 2026

Investigating Knowledge Transfer Across Interactive Dialogue Games

This paper investigates how knowledge transfers across different dialogue games by finetuning LLM models on games from the clembench suite and finds that some games benefit more from transfer than finetuning, and that the visuospatial family transfers best.

Filippo Momentè, Mir Nafis Sharear Shopnil, Andrea Gregor de Varda et al. · 0 citations