223 citations · 256 across the 34 of their papers we have counts for
31 papers · 1 filter
Where Compute Matters: Heterogeneous Attention for Efficient Video Diffusion
Olga Zatsarynna, Denis Korzhenkov, Juergen Gall +2
Efficient video generation requires reducing the quadratic cost of self-attention over long spatio-temporal token sequences. Existing efficient-attention methods typically apply th…
SQuad: Sub-Quadratic Attention Distillation for Efficient Video Generation
Animesh Karnewar, Denis Korzhenkov, Amirhossein Habibian +1
Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, , with the number of latent t…
MobileWan: Closing the Quality Gap for Mobile Video Diffusion
Mohsen Ghafoorian, Denis Korzhenkov, Adil Karjauv +9
Recent advances in video diffusion have been driven by scaling transformer-based architectures to billions of parameters, substantially improving visual fidelity and motion coheren…
Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation
Long Vu, Tan Ngo, Animesh Karnewar +5
Modern image-and-text-to-video diffusion models can synthesize highly realistic videos by iteratively denoising an initial Gaussian noise tensor conditioned on reference image and…
Knowledge Distillation for Visual Autoregressive Models
Elia Peruzzo, Aritra Bhowmik, Guillaume Sautiere +2
Autoregressive (AR) image generation models are highly expressive but computationally intensive, motivating effective model compression. Knowledge distillation (KD) is a natural ap…
PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
Denis Korzhenkov, Adil Karjauv, Animesh Karnewar +2
Recently proposed pyramidal models decompose the conventional forward and backward diffusion processes into multiple stages operating at varying resolutions. These models handle in…
ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers
Mohsen Ghafoorian, Amirhossein Habibian
Recent advances in video diffusion models have shifted towards transformer-based architectures, achieving state-of-the-art video generation but at the cost of quadratic attention c…
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
Yanlong Chen, Amirhossein Habibian, Luca Benini +1
Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss. Despite its pot…
Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion
Farhad G. Zanjani, Hong Cai, Amirhossein Habibian
We present SetDiff, a geometry-grounded multi-view diffusion framework that enhances novel-view renderings produced by 3D Gaussian Splatting. Our method integrates explicit 3D prio…
Multi-Scale Local Speculative Decoding for Image Generation
Elia Peruzzo, Guillaume Sautière, Amirhossein Habibian
Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints. Speculative Decoding offers a p…
Neodragon: Mobile Video Generation using Diffusion Transformer
Animesh Karnewar, Denis Korzhenkov, Ioannis Lelekas +10
We introduce Neodragon, a text-to-video system capable of generating 2s (49 frames @24 fps) videos at the 640x1024 resolution directly on a Qualcomm Hexagon NPU in a record 6.7s (7…
MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
Aritra Bhowmik, Denis Korzhenkov, Cees G. M. Snoek +2
Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models…
Hybrid Gaussian Splatting for Novel Urban View Synthesis
Mohamed Omran, Farhad Zanjani, Davide Abati +2
This paper describes the Qualcomm AI Research solution to the RealADSim-NVS challenge, hosted at the RealADSim Workshop at ICCV 2025. The challenge concerns novel view synthesis in…
Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer
Mohsen Ghafoorian, Denis Korzhenkov, Amirhossein Habibian
Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences…
Controllable 3D Placement of Objects with Scene-Aware Diffusion Models
Mohamed Omran, Dimitris Kalatzis, Jens Petersen +2
Image editing approaches have become more powerful and flexible with the advent of powerful text-conditioned generative models. However, placing objects in an environment with a pr…
Scene-Aware Location Modeling for Data Augmentation in Automotive Object Detection
Jens Petersen, Davide Abati, Amirhossein Habibian +1
Generative image models are increasingly being used for training data augmentation in vision tasks. In the context of automotive object detection, methods usually focus on producin…
Gaussian Splatting is an Effective Data Generator for 3D Object Detection
Farhad G. Zanjani, Davide Abati, Auke Wiggers +4
We investigate data augmentation for 3D object detection in autonomous driving. We utilize recent advancements in 3D reconstruction based on Gaussian Splatting for 3D object placem…
Mobile Video Diffusion
Haitam Ben Yahia, Denis Korzhenkov, Ioannis Lelekas +2
Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting their use on mobile devices. This paper intro…
MoViE: Mobile Diffusion for Video Editing
Adil Karjauv, Noor Fathima, Ioannis Lelekas +3
Recent progress in diffusion-based video editing has shown remarkable potential for practical applications. However, these methods remain prohibitively expensive and challenging to…
Imagining the Unseen: Generative Location Modeling for Object Placement
Jooyeol Yun, Davide Abati, Mohamed Omran +3
Location modeling, or determining where non-existing objects could feasibly appear in a scene, has the potential to benefit numerous computer vision tasks, from automatic object in…
Object-Centric Diffusion for Efficient Video Editing
Kumara Kahatapitiya, Adil Karjauv, Davide Abati +3
Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual ed…
VaLID: Variable-Length Input Diffusion for Novel View Synthesis
Shijie Li, Farhad G. Zanjani, Haitam Ben Yahia +3
Novel View Synthesis (NVS), which tries to produce a realistic image at the target view given source view images and their corresponding poses, is a fundamental problem in 3D Visio…
Clockwork Diffusion: Efficient Generation With Model-Step Distillation
Amirhossein Habibian, Amir Ghodrati, Noor Fathima +4
This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive UNet-based denoising operations in every generation…
ResQ: Residual Quantization for Video Perception
Davide Abati, Haitam Ben Yahia, Markus Nagel +1
This paper accelerates video perception, such as semantic segmentation and human pose estimation, by levering cross-frame redundancies. Unlike the existing approaches, which avoid…