collaborators

5 papers

cs.LG2026

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

Christian Gumbsch, Leonardo Barcellona, Lennard Schünemann +7

Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics. Recent work has explored…

cs.CV2026

Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations

Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann +7

Accurately reconstructing complex full multi-object scenes from sparse observations remains a core challenge in computer vision and a key step toward scalable and reliable simulati…

cs.CV2025

SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering

Laura Bragagnolo, Leonardo Barcellona, Stefano Ghidoni

Accurate 3D human pose estimation is fundamental for applications such as augmented reality and human-robot interaction. State-of-the-art multi-view methods learn to fuse predictio…

cs.CV2025

Leveraging Multi-View Weak Supervision for Occlusion-Aware Multi-Human Parsing

Laura Bragagnolo, Matteo Terreran, Leonardo Barcellona +1

Multi-human parsing is the task of segmenting human body parts while associating each part to the person it belongs to, combining instance-level and part-level information for fine…

cs.RO2025

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro +3

A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. Current world models typically cannot direc…