1 citations · 1 across the 13 of their papers we have counts for
14 papers
OVAL: Output-Aware Local Page Bases for KV Cache Retrieval
Ashkan Shahbazi, Chayne Thrash, Soheil Kolouri
Long context inference with large language models becomes increasingly expensive as attention must operate over an ever growing KV cache. Page sparse attention reduces this cost by…
Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein
Ashkan Shahbazi, Xinran Liu, Ping He +1
We propose min Generalized Sliced Gromov--Wasserstein (min-GSGW), a sliced formulation for the Gromov--Wasserstein (GW) problem using expressive generalized slicers. The key idea i…
SurgFormer: Scalable Learning of Organ Deformation with Resection Support and Real-Time Inference
Ashkan Shahbazi, Elaheh Akbari, Kyvia Pereira +7
We introduce SurgFormer, a multiresolution gated transformer for data driven soft tissue simulation on volumetric meshes. High fidelity biomechanical solvers are often too costly f…
Vector-Quantized Soft Label Compression for Dataset Distillation
Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash +1
Dataset distillation is an emerging technique for reducing the computational and storage costs of training machine learning models by synthesizing a small, informative subset of da…
LUNA: Linear Universal Neural Attention with Generalization Guarantees
Ashkan Shahbazi, Ping He, Ali Abbasi +6
Scaling attention faces a critical bottleneck: the quadratic computational cost of softmax attention, which limits its application in long-sequence domains. Whil…
LOTFormer: Doubly-Stochastic Linear Attention via Low-Rank Optimal Transport
Ashkan Shahbazi, Chayne Thrash, Yikun Bai +3
Transformers have proven highly effective across modalities, but standard softmax attention scales quadratically with sequence length, limiting long context modeling. Linear attent…
Neural-Augmented Kelvinlet for Real-Time Soft Tissue Deformation Modeling
Ashkan Shahbazi, Kyvia Pereira, Jon S. Heiselman +9
Accurate and efficient modeling of soft-tissue interactions is fundamental for advancing surgical simulation, surgical robotics, and model-based surgical automation. To achieve rea…
ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
Ashkan Shahbazi, Elaheh Akbari, Darian Salehi +3
While self-attention has been instrumental in the success of Transformers, it can lead to over-concentration on a few tokens during training, resulting in suboptimal information fl…
Understanding Learning with Sliced-Wasserstein Requires Rethinking Informative Slices
Huy Tran, Yikun Bai, Ashkan Shahbazi +2
The practical applications of Wasserstein distances (WDs) are constrained by their sample and computational complexities. Sliced-Wasserstein distances (SWDs) provide a workaround b…
Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data
Xinran Liu, Yikun Bai, Rocío Díaz Martín +5
Efficient comparison of spherical probability distributions becomes important in fields such as computer vision, geosciences, and medicine. Sliced optimal transport distances, such…
Expected Sliced Transport Plans
Xinran Liu, Rocío Díaz Martín, Yikun Bai +4
The optimal transport (OT) problem has gained significant traction in modern machine learning for its ability to: (1) provide versatile metrics, such as Wasserstein distances and t…
One Category One Prompt: Dataset Distillation using Diffusion Models
Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash +1
The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promi…
Stereographic Spherical Sliced Wasserstein Distances
Huy Tran, Yikun Bai, Abihith Kothapalli +4
Comparing spherical probability distributions is of great interest in various fields, including geology, medical domains, computer vision, and deep representation learning. The uti…
Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification
Abihith Kothapalli, Ashkan Shahbazi, Xinran Liu +2
Learning from set-structured data, such as point clouds, has gained significant attention from the machine learning community. Geometric deep learning provides a blueprint for desi…