6 papers
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
Yasaman Haghighi, Alexandre Alahi
Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated…
Communication-Inspired Tokenization for Structured Image Representations
Aram Davtyan, Yusuf Sahin, Yasaman Haghighi +4
Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, mo…
LayerSync: Self-aligning Intermediate Layers
Yasaman Haghighi, Bastien van Delft, Mariam Hassan +1
We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection…
EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity
Dominik Hollidt, Paul Streli, Jiaxi Jiang +4
Research on egocentric tasks in computer vision has mostly focused on head-mounted cameras, such as fisheye cameras or embedded cameras inside immersive headsets. We argue that the…
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…
HEADS-UP: Head-Mounted Egocentric Dataset for Trajectory Prediction in Blind Assistance Systems
Yasaman Haghighi, Celine Demonsant, Panagiotis Chalimourdas +6
In this paper, we introduce HEADS-UP, the first egocentric dataset collected from head-mounted cameras, designed specifically for trajectory prediction in blind assistance systems.…