9 citations · 33 across the 67 of their papers we have counts for
8 papers · 1 filter
Direction-Scale Decomposition in Action Representation: Rethinking What to Tokenize for Vision-Language-Action Models
Yufei Duan, Hang Yin, Alberta Longhini +2
Action representation plays a central role in discrete-token vision-language-action (VLA) learning but remains underexamined. Under conventional pose-increment representations, act…
DLO-Splatting: Tracking Deformable Linear Objects Using 3D Gaussian Splatting
Holly Dinkel, Marcel Büsching, Alberta Longhini +5
This work presents DLO-Splatting, an algorithm for estimating the 3D shape of Deformable Linear Objects (DLOs) from multi-view RGB images and gripper state information through pred…
Human-Aligned Image Models Improve Visual Decoding from the Brain
Nona Rajabi, Antônio H. Ribeiro, Miguel Vasco +3
Decoding visual images from brain activity has significant potential for advancing brain-computer interaction and enhancing the understanding of human perception. Recent approaches…
Cloth-Splatting: 3D Cloth State Estimation from RGB Supervision
Alberta Longhini, Marcel Büsching, Bardienus P. Duisterhof +4
We introduce Cloth-Splatting, a method for estimating 3D states of cloth from RGB images through a prediction-update framework. Cloth-Splatting leverages an action-conditioned dyna…
Scalable Motion Style Transfer with Constrained Diffusion Generation
Wenjie Yin, Yi Yu, Hang Yin +2
Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of do…
TD-GEM: Text-Driven Garment Editing Mapper
Reza Dadfar, Sanaz Sabzevari, Mårten Björkman +1
Language-based fashion image editing allows users to try out variations of desired garments through provided text prompts. Inspired by research on manipulating latent representatio…
Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models
Wenjie Yin, Ruibo Tu, Hang Yin +3
Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics. Challenges remain i…
EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamics
Alberta Longhini, Marco Moletta, Alfredo Reichlin +4
We study the problem of learning graph dynamics of deformable objects that generalizes to unknown physical properties. Our key insight is to leverage a latent representation of ela…