Publications

Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro, Subramanian Ramamoorthy, Matteo Matteucci, Alessandro Suglia (2026). Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs. CoRR.

Amit Parekh, Sabrina McCallum, Kareem Al-Hasan, Malvina Nikandrou, Alessandro Suglia, Ioannis Konstas (2026). GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes. TMLR 2026.

Matteo Attimonelli, Alessandro De Bellis, Aryo Pradipta Gema, Rohit Saxena, Monica Sekoyan, Wai-Chung Kwan, Claudio Pomo, Alessandro Suglia, Dietmar Jannach, Tommaso Di Noia, Pasquale Minervini (2026). Do Composed Image Retrieval Benchmarks Require Multimodal Composition?. NeurIPS 2026.

Chen Hu, Yintao Tai, Antonio Vergari, Frank Keller, Alessandro Suglia (2026). MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts. CoRR.

Ethan Smyth, Alessandro Suglia (2026). VoyagerVision: Investigating the Role of Multi-modal Information for Open-ended Learning Systems. Advances in Intelligent Systems and Computing ((AISC,volume 1468)).

Rohit Saxena, Alessandro Suglia, Pasquale Minervini (2026). VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models. ICML 2026.

Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena, Aryo Pradipta Gema, Wai-Chung Kwan, Fazl Barez, Maria Sofia Bucarelli, Fabrizio Silvestri, Pasquale Minervini (2026). Same Answer, Different Representations: Hidden instability in VLMs. CoRR.

Georgios Pantazopoulos, Malvina Nikandrou, Ioannis Konstas, Alessandro Suglia (2026). Retrievit: In-context Retrieval Capabilities of Transformers, State Space Models, and Hybrid Architectures. TMLR 2026.

Hamza Mooraj, Georgios Pantazopoulos, Alessandro Suglia (2026). AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification. TMLR 2026.

Malvina Nikandrou, Georgios Pantazopoulos, Nikolas Vitsakis, Ioannis Konstas, Alessandro Suglia (2025). CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts. NAACL 2025.