223 citations · 256 across the 34 of their papers we have counts for
14 papers · 1 filter
SyncVid: World-Equivariant Diffusion for Synchronized Video Generation
Farhad G. Zanjani, Animesh Karnewar, Fatih Porikli +1
Generating multiple videos of a dynamic scene from a single reference video requires synthesizing both observed and unobserved content consistently across viewpoints. Existing came…
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
Yanlong Chen, Yining Chen, Song Zhang +2
Smaller activation outliers do not necessarily imply better low-bit quantization: their alignment with the quantizer matters. We introduce PrismQuant, a quantizer-aware rotation fr…
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…
AVQ-Attention: Adaptive Vector-Quantized Attention
Winfried van den dool, Patrick Forré, Amir Habibian +2
The complexity of attention over tokens remains a computational bottleneck in transformer models. Vector-Quantized (VQ) attention reduces this to $\mathcal{O…
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…
HLA: Hadamard Linear Attention
Hanno Ackermann, Hong Cai, Mohsen Ghafoorian +1
The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of s…
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…