Alert button
Picture for Mohsen Fayyaz

Mohsen Fayyaz

Alert button

DecompX: Explaining Transformers Decisions by Propagating Token Decomposition

Jun 05, 2023
Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar

Figure 1 for DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
Figure 2 for DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
Figure 3 for DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
Figure 4 for DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
Viaarxiv icon

RET-LLM: Towards a General Read-Write Memory for Large Language Models

May 23, 2023
Ali Modarressi, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze

Figure 1 for RET-LLM: Towards a General Read-Write Memory for Large Language Models
Figure 2 for RET-LLM: Towards a General Read-Write Memory for Large Language Models
Figure 3 for RET-LLM: Towards a General Read-Write Memory for Large Language Models
Figure 4 for RET-LLM: Towards a General Read-Write Memory for Large Language Models
Viaarxiv icon

Diffusion Models for Medical Image Analysis: A Comprehensive Survey

Nov 14, 2022
Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Moein Heidari, Reza Azad, Mohsen Fayyaz, Ilker Hacihaliloglu, Dorit Merhof

Figure 1 for Diffusion Models for Medical Image Analysis: A Comprehensive Survey
Figure 2 for Diffusion Models for Medical Image Analysis: A Comprehensive Survey
Figure 3 for Diffusion Models for Medical Image Analysis: A Comprehensive Survey
Figure 4 for Diffusion Models for Medical Image Analysis: A Comprehensive Survey
Viaarxiv icon

BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning

Nov 10, 2022
Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Mohammad Taher Pilehvar, Yadollah Yaghoobzadeh, Samira Ebrahimi Kahou

Figure 1 for BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
Figure 2 for BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
Figure 3 for BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
Figure 4 for BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
Viaarxiv icon

GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers

May 06, 2022
Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar

Figure 1 for GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
Figure 2 for GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
Figure 3 for GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
Figure 4 for GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
Viaarxiv icon

Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages

Mar 26, 2022
Ehsan Aghazadeh, Mohsen Fayyaz, Yadollah Yaghoobzadeh

Figure 1 for Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
Figure 2 for Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
Figure 3 for Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
Figure 4 for Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
Viaarxiv icon

ATS: Adaptive Token Sampling For Efficient Vision Transformers

Nov 30, 2021
Mohsen Fayyaz, Soroush Abbasi Kouhpayegani, Farnoush Rezaei Jafari, Eric Sommerlade, Hamid Reza Vaezi Joze, Hamed Pirsiavash, Juergen Gall

Figure 1 for ATS: Adaptive Token Sampling For Efficient Vision Transformers
Figure 2 for ATS: Adaptive Token Sampling For Efficient Vision Transformers
Figure 3 for ATS: Adaptive Token Sampling For Efficient Vision Transformers
Figure 4 for ATS: Adaptive Token Sampling For Efficient Vision Transformers
Viaarxiv icon

Taylor Swift: Taylor Driven Temporal Modeling for Swift Future Frame Prediction

Oct 27, 2021
Mohammad Saber Pourheydari, Mohsen Fayyaz, Emad Bahrami, Mehdi Noroozi, Juergen Gall

Figure 1 for Taylor Swift: Taylor Driven Temporal Modeling for Swift Future Frame Prediction
Figure 2 for Taylor Swift: Taylor Driven Temporal Modeling for Swift Future Frame Prediction
Figure 3 for Taylor Swift: Taylor Driven Temporal Modeling for Swift Future Frame Prediction
Figure 4 for Taylor Swift: Taylor Driven Temporal Modeling for Swift Future Frame Prediction
Viaarxiv icon

Long Short View Feature Decomposition via Contrastive Video Representation Learning

Sep 23, 2021
Nadine Behrmann, Mohsen Fayyaz, Juergen Gall, Mehdi Noroozi

Figure 1 for Long Short View Feature Decomposition via Contrastive Video Representation Learning
Figure 2 for Long Short View Feature Decomposition via Contrastive Video Representation Learning
Figure 3 for Long Short View Feature Decomposition via Contrastive Video Representation Learning
Figure 4 for Long Short View Feature Decomposition via Contrastive Video Representation Learning
Viaarxiv icon

Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations

Sep 15, 2021
Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar

Figure 1 for Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
Figure 2 for Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
Figure 3 for Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
Figure 4 for Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
Viaarxiv icon