Mohammad Rastegari

Orcid: 0000-0001-9606-3687

Affiliations:
  • AI2, Allen Institute for Artificial Intelligence, Seattle, USA


According to our database1, Mohammad Rastegari authored at least 67 papers between 2008 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Speculative Streaming: Fast LLM Inference without Auxiliary Models.
CoRR, 2024

eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models.
IEEE Comput. Archit. Lett., 2024

2023
Separable Self-attention for Mobile Vision Transformers.
Trans. Mach. Learn. Res., 2023

LLM in a flash: Efficient Large Language Model Inference with Limited Memory.
CoRR, 2023

Weight subcloning: direct initialization of transformers using larger pretrained ones.
CoRR, 2023

Label-efficient Training of Small Task-specific Models by Leveraging Vision Foundation Models.
CoRR, 2023

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding.
CoRR, 2023

CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement.
CoRR, 2023

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models.
CoRR, 2023

Diffusion Models as Masked Audio-Video Learners.
CoRR, 2023

(Dynamic) Prompting might be all you need to repair Compressed LLMs.
CoRR, 2023

On the Efficacy of Multi-scale Data Samplers for Vision Applications.
CoRR, 2023

Bytes Are All You Need: Transformers Operating Directly On File Bytes.
CoRR, 2023

Token Pooling in Vision Transformers for Image Classification.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
DiCENet: Dimension-Wise Convolutions for Efficient Networks.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

RangeAugment: Efficient Online Augmentation with Range Learning.
CoRR, 2022

CVNets: High Performance Library for Computer Vision.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Layer-Wise Data-Free CNN Compression.
Proceedings of the 26th International Conference on Pattern Recognition, 2022

MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer.
Proceedings of the Tenth International Conference on Learning Representations, 2022

DKM: Differentiable k-Means Clustering Layer for Neural Network Compression.
Proceedings of the Tenth International Conference on Learning Representations, 2022

SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks.
Proceedings of the Computer Vision - ECCV 2022, 2022

2021
LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time.
CoRR, 2021

Token Pooling in Vision Transformers.
CoRR, 2021

Learning Neural Network Subspaces.
Proceedings of the 38th International Conference on Machine Learning, 2021

2020
Enabling AI at the edge with XNOR-networks.
Commun. ACM, 2020

Supermasks in Superposition.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence Modeling.
Proceedings of the 8th International Conference on Learning Representations, 2020

What's Hidden in a Randomly Weighted Neural Network?
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Butterfly Transform: An Efficient FFT Based Neural Architecture Design.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
DeFINE: DEep Factorized INput Word Embeddings for Neural Sequence Modeling.
CoRR, 2019

Butterfly Transform: An Efficient FFT Based Neural Architecture Design.
CoRR, 2019

Discovering Neural Wirings.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

ELASTIC: Improving CNNs With Dynamic Scaling Policies.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Two Body Problem: Collaborative Visual Task Completion.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018
ELASTIC: Improving CNNs with Instance Specific Scaling Policies.
CoRR, 2018

Label Refinery: Improving ImageNet Classification through Label Progression.
CoRR, 2018

Pyramidal Recurrent Unit for Language Modeling.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31, 2018

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation.
Proceedings of the Computer Vision - ECCV 2018, 2018

IQA: Visual Question Answering in Interactive Environments.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017
LCNN: Lookup-Based Convolutional Neural Network.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2016
Rich and Efficient Visual Data Representation.
PhD thesis, 2016

CNN-aware binary MAP for general semantic segmentation.
Proceedings of the 2016 IEEE International Conference on Image Processing, 2016

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks.
Proceedings of the Computer Vision - ECCV 2016, 2016

"What Happens If..." Learning to Predict the Effect of Forces in Images.
Proceedings of the Computer Vision - ECCV 2016, 2016

G-CNN: An Iterative Grid Based Object Detector.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

2015
Action Recognition with Image Based CNN Features.
CoRR, 2015

On Large-Scale Retrieval: Binary or n-ary Coding?
CoRR, 2015

Class consistent multi-modal fusion with binary features.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Computationally bounded retrieval.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Discriminative and consistent similarities in instance-level Multiple Instance Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014
Comparing apples to apples in the evaluation of binary coding methods.
CoRR, 2014

2013
Predictable Dual-View Hashing.
Proceedings of the 30th International Conference on Machine Learning, 2013

Domain Adaptive Classification.
Proceedings of the IEEE International Conference on Computer Vision, 2013

Multi-attribute Queries: To Merge or Not to Merge?
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

Adding Unlabeled Samples to Categories by Learned Attributes.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
Semantic Understanding of Professional Soccer Commentaries.
Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, 2012

Attribute Discovery via Predictable Discriminative Binary Codes.
Proceedings of the Computer Vision - ECCV 2012, 2012

2011
Scalable object-class retrieval with approximate and top-k ranking.
Proceedings of the IEEE International Conference on Computer Vision, 2011

2010
Object Detection using Pictorial Structure of Gabor Template.
Proceedings of the VISAPP 2010 - Proceedings of the Fifth International Conference on Computer Vision Theory and Applications, Angers, France, May 17-21, 2010, 2010

2009
Cartoon Motion Capturing and Retargeting by Rigid Shape Manipulation.
Proceedings of the DICTA 2009, 2009

2008
Multi-scale Cartoon Motion Capture and Retargeting without Shape Matching.
Proceedings of the International Conference on Digital Image Computing: Techniques and Applications, 2008


  Loading...