5 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…
Stitched Value Model for Diffusion Alignment
Hyojun Go, Hyungjin Chung, Prune Truong +8
For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challen…
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…
VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation
Niccolo Avogaro, Thomas Frick, Yagmur G. Cinar +12
Large-scale pretrained vision backbones have transformed computer vision by providing powerful feature extractors that enable various downstream tasks, including training-free appr…
Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation
Niccolo Avogaro, Thomas Frick, Mattia Rigotti +5
Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training.…