news

Jul 07, 2026 Our paper MobileWan: Closing the Quality Gap for Mobile Video Diffusion is now on arXiv! It’s the first 5B-parameter video diffusion model to run on a commercial mobile device, setting a new state-of-the-art for mobile video generation.
Jun 03, 2026 Heading to CVPR 2026 in Denver — looking forward to connecting, come say hi!
Feb 20, 2026 Our paper PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference has been accepted at CVPR 2026! It presents a low-cost recipe for turning any pretrained video diffusion transformer model into a faster, pyramidal one — no retraining from scratch, no quality loss.
Jan 25, 2026 Our paper Neodragon: Mobile Video Generation Using Diffusion Transformer has been accepted at ICLR 2026! It’s the first text-to-video generation model built specifically for mobile hardware, generating a 2-second video directly on-device in just ~6.7 seconds.
Dec 01, 2025 Promoted to Senior Machine Learning Researcher at Qualcomm AI Research!
Jun 12, 2025 Our paper AdapToR: Adaptive Token Reduction for Video Diffusion Transformers has been accepted at the CVPR 2025 2nd Workshop on Efficient and On-Device Generation (EDGE)! It’s a lightweight token reduction technique that cuts compute for video diffusion transformers by exploiting temporal redundancy — while matching or beating quality on standard benchmarks.
Dec 09, 2024 Our paper MoViE: Mobile Diffusion for Video Editing is now on arXiv — the fastest diffusion-based video editing model on-device. Check it out!
Nov 26, 2024 This page is now live!