2 citations · 6 across the 13 of their papers we have counts for
13 papers · 1 filter
Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
Wuyang Li, Wentao Pan, Po-Chien Luan +2
We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming story…
OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Prediction
Yang Gao, Po-Chien Luan, Kaouther Messaoud +2
While large-scale pre-training has advanced human trajectory prediction, a critical challenge remains: zero-shot transfer to unseen dataset with varying temporal dynamics. State-of…
From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models
Pablo Acuaviva, Aram Davtyan, Mariam Hassan +4
Video Diffusion Models (VDMs) have emerged as powerful generative tools, capable of synthesizing high-quality spatiotemporal content. Yet, their potential goes far beyond mere vide…
COARSE: Collaborative Pseudo-Labeling with Coarse Real Labels for Off-Road Semantic Segmentation
Aurelio Noca, Xianmei Lei, Jonathan Becktor +6
Autonomous off-road navigation faces challenges due to diverse, unstructured environments, requiring robust perception with both geometric and semantic understanding. However, scar…
Unified Human Localization and Trajectory Prediction with Monocular Vision
Po-Chien Luan, Yang Gao, Celine Demonsant +1
Conventional human trajectory prediction models rely on clean curated data, requiring specialized equipment or manual labeling, which is often impractical for robotic applications.…
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
Mariam Hassan, Sebastian Stapf, Ahmad Rahimi +17
We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, ou…