I am a computer vision researcher working on 3D scene reconstruction and generation, geometry-grounded foundation models, world models, and Gaussian Splatting. My current research focuses on how machines can perceive space beyond point clouds and pixels: reconstructing geometry, grounding it semantically, and reasoning about dynamic scenes at scale.

I recently completed a Master of Research in Computer Vision at MBZUAI, supervised by Prof. Ian Reid. I have conducted research with Astra-Vision at Inria Paris, CVI2 at the University of Luxembourg, FBK E3DA, and CovisionLab. Across these experiences, I have worked on 3D foundation models, camera-aware reconstruction, CAD-oriented multimodal agents, TinyML vision pipelines, and physics-grounded benchmarks for foundation models.

My longer-term goal is to build perception systems that combine 3D structure, language-based reasoning, and efficient representations in ways that can generalize beyond narrow reconstruction settings.

News

• 2026: Started as a Research Intern at CovisionLab, working on diffusion-driven synthesis and robustness evaluation for perception models.
• 2025: Collaborated with Inria Paris on NewtPhys, a physics-grounded benchmark for evaluating foundation models on Newtonian reasoning.
• 2025: CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers accepted at ICCV 2025. Paper
• 2025: Graduated from MBZUAI with a Master of Research in Computer Vision.
• 2025: All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages accepted at CVPR 2025. Paper
• 2024: Does Complexity Pay Off? received Best Paper Award at HEALTHINFO 2024. Paper
• 2023: Graduated from the Free University of Bozen-Bolzano with a B.Sc. in Computer Science.