SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
- Niccolo Avogaro
- Nayanika Debnath
- et al.
- 2026
- ICML 2026
Conference paper
Niccolo Avogaro
Title
Predoctoral Researcher
Bio
Niccolo Avogaro is a predoctoral researcher specializing in foundation models for dense image recognition. With a background in mechanical engineering, robotics, and artificial intelligence, his work focuses on advancing the capabilities of multimodal systems in complex visual environments.
Publications
VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation
- 2025
- CVPR 2025
Demo paperSegmentation of subretinal and intraretinal fluid on OCT B-scans using an easily fine-tunable and deployable, visual-prompting based computer vision model
- Rui Santos
- Thomas Frick
- et al.
- 2025
- ARVO 2025
PosterProbabilistic feature matching for fast scalable visual prompting
- Thomas Frick
- Cezary Skura
- et al.
- 2024
- IJCAI 2024
Demo paperAI for Bridge Inspection with IBM Inspecto
- Cristiano Malossi
- Roy Assaf
- et al.
- 2024
- IABMAS 2024
Conference paperInteractive Image Segmentation Guided by Visual Prompting
- Thomas Frick
- Cezary Skura
- et al.
- 2024
- CVPR 2024
Demo paper
Projects
Using AI to build computer vision models within minutes, through quick intuitive prompts, and with just a few images
Increasing speed and quality of enterprise visual inspection, leveraging AI and domain-specific Large Vision Models
Top collaborators
TF
Thomas Frick
Research Scientist
MR
Mattia Rigotti
Senior Research Scientist
CM
Cristiano Malossi
Principal RSM | AI for PDEs | Manager Frontiers of Computing and Simulation
CS
Cezary Skura
Software engineer