I am a Master’s student in
Communication Systems
at EPFL, supported by the Excellence Scholarship.
My research interests are computer vision, foundation models, and 3D scene understanding.
My earlier research was in computer vision and in detection and estimation. I am now interested in foundation models, multimodal data, 3D scene understanding, and diffusion models.
A unified any-to-any multimodal model that bridges 1D, 2D, and 3D representations, enabling generation, retrieval, and object decomposition across text, images, and 3D modalities within a single framework.
Test-Space Training (TST) pretrains vision models only on rich multimodal data from the environment they will be deployed in, instead of internet datasets, and asks whether scaling the modalities within a fixed test space can replace data generalism.
An iOS app that records the camera, depth (LiDAR, or estimated on the phone), 6-DoF camera pose, IMU, GPS, 3D body skeleton, gaze, ambient light and air pressure in sync, frame by frame, with Python tools that turn recordings into training data and 3D reconstructions.
Sketch abstraction, extended from 2D to 3D: Bézier curves are optimized through constrained Gaussian splatting, with Gaussians restricted to matte spherical blobs along each curve, so a few strokes form a wireframe-like sketch that captures an object's geometry.
An intelligent reflecting surface (IRS), optimized with the Cramér–Rao lower bound, lets a receiver be localized indoors with a single LED transmitter.