14 citations · 18 across the 6 of their papers we have counts for
7 papers · 1 filter
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov +6
Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality trade-offs, and allocate computation uniformly…
NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation
Ruozhen He, Moayed Haji-Ali, Ziyan Yang +1
Text-to-image diffusion models often degrade when sampled at resolutions outside the final training resolution set. Prior work has largely emphasized higher resolution generation,…
Improving Progressive Generation with Decomposable Flow Matching
Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov +4
Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fin…
AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation
Moayed Haji-Ali, Willi Menapace, Aliaksandr Siarohin +5
We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for t…
Fairness and Bias Mitigation in Computer Vision: A Survey
Sepehr Dehdashtian, Ruozhen He, Yi Li +4
Computer vision systems have witnessed rapid progress over the past two decades due to multiple advances in the field. As these systems are increasingly being deployed in high-stak…
ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation
Moayed Haji-Ali, Guha Balakrishnan, Vicente Ordonez
Diffusion models have revolutionized image generation in recent years, yet they are still limited to a few sizes and aspect ratios. We propose ElasticDiffusion, a novel training-fr…
Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations
Ziyan Yang, Kushal Kafle, Franck Dernoncourt +1
We propose a margin-based loss for tuning joint vision-language models so that their gradient-based explanations are consistent with region-level annotations provided by humans for…