6 papers
MAD: Motion Appearance Decoupling for efficient Driving World Models
Ahmad Rahimi, Valentin Gerard, Eloi Zablocki +2
Recent video diffusion models generate photorealistic, temporally coherent videos, yet they fall short as reliable world models for autonomous driving, where structured motion and…
Rethinking Visual Intelligence: Insights from Video Pretraining
Pablo Acuaviva, Aram Davtyan, Mariam Hassan +4
Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This su…
Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations
Ahmad Rahimi, Po-Chien Luan, Yuejiang Liu +2
Modeling spatial-temporal interactions among neighboring agents is at the heart of multi-agent problems such as motion forecasting and crowd navigation. Despite notable progress, i…
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…
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…
A Multi-Loss Strategy for Vehicle Trajectory Prediction: Combining Off-Road, Diversity, and Directional Consistency Losses
Ahmad Rahimi, Alexandre Alahi
Trajectory prediction is essential for the safety and efficiency of planning in autonomous vehicles. However, current models often fail to fully capture complex traffic rules and t…