5 papers · 1 filter
What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior
Débora Oliveira Makowski, Samiran Gode, Abhijeet Nayak +4
Modern Vision-Language Navigation (VLN) models rely mostly on pre-trained large Vision-Language Models (VLMs) to predict navigation actions. While this fusion of language instructi…
Spatially Aware World Action Model via Geometric Latent Diffusion
Javier Alejandro Lopetegui Gonzalez, Paul Pacaud, Cordelia Schmid
World Action Models (WAMs) leverage the capabilities of large-scale pretrained video diffusion models to jointly predict future observations and actions, inheriting rich visual and…
PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
Shizhe Chen, Paul Pacaud, Cordelia Schmid
Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most exi…
BrickNet: Graph-Backed Generative Brick Assembly
Peter Kulits, Cordelia Schmid
We train a language model to generate LEGO-brick build sequences. While prior work has been restricted to discrete, voxel-like towers, we consider a much broader set of pieces, enc…
HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
Zerui Chen, Rolandos Alexandros Potamias, Shizhe Chen +3
Generating realistic 3D hand-object interactions (HOI) is a fundamental challenge in computer vision and robotics, requiring both temporal coherence and high-fidelity physical plau…