12 papers
SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
Niccolo Avogaro, Nayanika Debnath, Li Mi +6
Despite recent successes, test-time scaling -- i.e., dynamically expanding the token budget during inference as needed -- remains brittle for vision-language models (VLMs). Unstruc…
Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision
Mateo Diaz-Bone, Daniel Caraballo, Florian Scheidegger +11
Recent Anomaly Detection methods achieve perfect detection and segmentation scores on well-established datasets, such as MVTec. However, many of these methods face challenges when…
Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
Nicola Farronato, Niccolo Avogaro, Thomas Frick +6
Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed to accurately assess structu…
GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
Mattia Rigotti, Nicholas Thumiger, Thomas Frick
Neural operators on irregular meshes face a fundamental tension. Spectral positional encodings, the natural choice for capturing geometry, require cubic-complexity eigendecompositi…
GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
Brown Ebouky, Gabriele Carrino, Niccolo Avogaro +3
Human visual reasoning is governed by active vision, a process where metacognitive control drives top-down goal-directed attention, dynamically routing foveal focus toward task-rel…
Faster by Design: Interactive Aerodynamics via Neural Surrogates Trained on Expert-Validated CFD
Nicholas Thumiger, Andrea Bartezzaghi, Mattia Rigotti +5
Computational Fluid Dynamics (CFD) is central to race-car aerodynamic development, yet its cost -- tens of thousands of core-hours per high-fidelity evaluation -- severely limits t…