Mohsen Fayyaz - RankMe

60 papers A* 4A 1Journal 41Unranked 13

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence. ACL (1) Mohsen Fayyaz, Ali Modarressi, Hinrich Schütze, Nanyun Peng
2025	J	`jnl`	Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence. CoRR Mohsen Fayyaz, Ali Modarressi, Hinrich Schütze, Nanyun Peng
2025	J	`jnl`	DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights. CoRR Liana Mikaelyan, Ayyoob Imani, Mathew Salvaris, Parth Pathak, Mohsen Fayyaz
2025	J	`jnl`	DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding. CoRR Tanveer Hannan, Dimitrios Mallios, Parth Pathak, Faegheh Sardari, Thomas Seidl, Gedas Bertasius, Mohsen Fayyaz, Sunando Sengupta
2025	J	`jnl`	Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders. CoRR Ali Rasekh, Erfan Bagheri Soula, Omid Daliran, Simon Gottschalk, Mohsen Fayyaz
2025	A*	`conf`	MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models. ICLR Wenbo Hu, Jia-Chen Gu, Zi-Yi Dou, Mohsen Fayyaz, Pan Lu, Kai-Wei Chang, Nanyun Peng
2025	J	`jnl`	MemLLM: Finetuning LLMs to Use Explicit Read-Write Memory. Trans. Mach. Learn. Res. Ali Modarressi, Abdullatif Köksal, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze
2025	J	`jnl`	Multilingual Routing in Mixture-of-Experts. CoRR Lucas Bandarkar, Chenyuan Yang, Mohsen Fayyaz, Junlin Hu, Nanyun (Violet) Peng
2025	J	`jnl`	Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices. CoRR Saeid Ghafouri, Mohsen Fayyaz, Xiangchen Li, Deepu John, Bo Ji, Dimitrios S. Nikolopoulos, Hans Vandierendonck
2025	J	`jnl`	Steering MoE LLMs via Expert (De)Activation. CoRR Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Ryan A. Rossi, Trung Bui, Hinrich Schütze, Nanyun Peng
2024	J	`jnl`	Evaluating Human Alignment and Model Faithfulness of LLM Rationale. CoRR Mohsen Fayyaz, Fan Yin, Jiao Sun, Nanyun Peng
2024	—	`—`	Holistic Video Understanding: Spatio-Temporal Modeling and Efficiency. Mohsen Fayyaz
2024	J	`jnl`	MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models. CoRR Wenbo Hu, Jia-Chen Gu, Zi-Yi Dou, Mohsen Fayyaz, Pan Lu, Kai-Wei Chang, Nanyun Peng
2024	J	`jnl`	MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory. CoRR Ali Modarressi, Abdullatif Köksal, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze
2024	—	`conf`	Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding. ECCV (13) Niloofar Azizi, Mohsen Fayyaz, Horst Bischof
2024	J	`jnl`	Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding. CoRR Niloofar Azizi, Mohsen Fayyaz, Horst Bischof
2024	—	`conf`	SkipPLUS: Skip the First Few Layers to Better Explain Vision Transformers. CVPR Workshops Faridoun Mehri, Mohsen Fayyaz, Mahdieh Soleymani Baghshah, Mohammad Taher Pilehvar
2023	—	`conf`	DecompX: Explaining Transformers Decisions by Propagating Token Decomposition. ACL (1) Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
2023	J	`jnl`	DecompX: Explaining Transformers Decisions by Propagating Token Decomposition. CoRR Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
2023	J	`jnl`	Diffusion models in medical imaging: A comprehensive survey. Medical Image Anal. Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Moein Heidari, Reza Azad, Mohsen Fayyaz, Ilker Hacihaliloglu, Dorit Merhof
2023	J	`jnl`	RET-LLM: Towards a General Read-Write Memory for Large Language Models. CoRR Ali Modarressi, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze
2022	—	`conf`	Adaptive Token Sampling for Efficient Vision Transformers. ECCV (11) Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari, Sunando Sengupta, Hamid Reza Vaezi Joze, Eric Sommerlade, Hamed Pirsiavash, Jürgen Gall
2022	J	`jnl`	BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning. CoRR Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Mohammad Taher Pilehvar, Yadollah Yaghoobzadeh, Samira Ebrahimi Kahou
2022	J	`jnl`	Diffusion Models for Medical Image Analysis: A Comprehensive Survey. CoRR Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Moein Heidari, Reza Azad, Mohsen Fayyaz, Ilker Hacihaliloglu, Dorit Merhof
2022	J	`jnl`	Fast Weakly Supervised Action Segmentation Using Mutual Consistency. IEEE Trans. Pattern Anal. Mach. Intell. Yaser Souri, Mohsen Fayyaz, Luca Minciullo, Gianpiero Francesca, Juergen Gall
2022	—	`conf`	GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers. NAACL-HLT Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
2022	J	`jnl`	GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers. CoRR Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
2022	—	`conf`	Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages. ACL (1) Ehsan Aghazadeh, Mohsen Fayyaz, Yadollah Yaghoobzadeh
2022	J	`jnl`	Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages. CoRR Ehsan Aghazadeh, Mohsen Fayyaz, Yadollah Yaghoobzadeh
2022	A	`conf`	TaylorSwiftNet: Taylor Driven Temporal Modeling for Swift Future Frame Prediction. BMVC Mohammad Saber Pourheydari, Emad Bahrami Rad, Mohsen Fayyaz, Gianpiero Francesca, Mehdi Noroozi, Jürgen Gall
2021	A*	`conf`	3D CNNs With Adaptive Temporal Feature Resolutions. CVPR Mohsen Fayyaz, Emad Bahrami Rad, Ali Diba, Mehdi Noroozi, Ehsan Adeli, Luc Van Gool, Jürgen Gall
2021	J	`jnl`	ATS: Adaptive Token Sampling For Efficient Vision Transformers. CoRR Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari, Eric Sommerlade, Hamid Reza Vaezi Joze, Hamed Pirsiavash, Juergen Gall
2021	A*	`conf`	Long Short View Feature Decomposition via Contrastive Video Representation Learning. ICCV Nadine Behrmann, Mohsen Fayyaz, Juergen Gall, Mehdi Noroozi
2021	J	`jnl`	Long Short View Feature Decomposition via Contrastive Video Representation Learning. CoRR Nadine Behrmann, Mohsen Fayyaz, Juergen Gall, Mehdi Noroozi
2021	—	`conf`	Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations. BlackboxNLP@EMNLP Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar
2021	J	`jnl`	Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations. CoRR Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar
2021	J	`jnl`	Taylor Swift: Taylor Driven Temporal Modeling for Swift Future Frame Prediction. CoRR Mohammad Saber Pourheydari, Mohsen Fayyaz, Emad Bahrami Rad, Mehdi Noroozi, Juergen Gall
2020	J	`jnl`	3D CNNs with Adaptive Temporal Feature Resolutions. CoRR Mohsen Fayyaz, Emad Bahrami Rad, Ali Diba, Mehdi Noroozi, Ehsan Adeli, Luc Van Gool, Juergen Gall
2020	—	`conf`	Large Scale Holistic Video Understanding. ECCV (5) Ali Diba, Mohsen Fayyaz, Vivek Sharma, Manohar Paluri, Jürgen Gall, Rainer Stiefelhagen, Luc Van Gool
2020	A*	`conf`	SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation. CVPR Mohsen Fayyaz, Jürgen Gall
2020	J	`jnl`	SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation. CoRR Mohsen Fayyaz, Juergen Gall
2019	J	`jnl`	Holistic Large Scale Video Understanding. CoRR Ali Diba, Mohsen Fayyaz, Vivek Sharma, Manohar Paluri, Jürgen Gall, Rainer Stiefelhagen, Luc Van Gool
2019	J	`jnl`	Weakly Supervised Action Segmentation Using Mutual Consistency. CoRR Yaser Souri, Mohsen Fayyaz, Juergen Gall
2018	—	`conf`	AVID: Adversarial Visual Irregularity Detection. ACCV (6) Mohammad Sabokrou, Masoud PourReza, Mohsen Fayyaz, Rahim Entezari, Mahmood Fathy, Jürgen Gall, Ehsan Adeli
2018	J	`jnl`	AVID: Adversarial Visual Irregularity Detection. CoRR Mohammad Sabokrou, Masoud PourReza, Mohsen Fayyaz, Rahim Entezari, Mahmood Fathy, Jürgen Gall, Ehsan Adeli
2018	J	`jnl`	Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes. Comput. Vis. Image Underst. Mohammad Sabokrou, Mohsen Fayyaz, Mahmood Fathy, Zahra Moayed, Reinhard Klette
2018	J	`jnl`	Online Signature Verification using Deep Representation: A new Descriptor. CoRR Mohammad Hajizadeh Saffar, Mohsen Fayyaz, Mohammad Sabokrou, Mahmood Fathy
2018	J	`jnl`	Semantic Video Segmentation: A Review on Recent Approaches. CoRR Mohammad Hajizadeh Saffar, Mohsen Fayyaz, Mohammad Sabokrou, Mahmood Fathy
2018	J	`jnl`	Spatio-Temporal Channel Correlation Networks for Action Classification. CoRR Ali Diba, Mohsen Fayyaz, Vivek Sharma, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool
2018	—	`conf`	Spatio-temporal Channel Correlation Networks for Action Classification. ECCV (4) Ali Diba, Mohsen Fayyaz, Vivek Sharma, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool
2018	—	`conf`	Temporal 3D ConvNets Using Temporal Transition Layer. CVPR Workshops Ali Diba, Mohsen Fayyaz, Vivek Sharma, Amir Hossein Karami, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Luc Van Gool
2018	J	`jnl`	Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet. CoRR Seyyed Hossein HasanPour, Mohammad Rouhani, Mohsen Fayyaz, Mohammad Sabokrou, Ehsan Adeli
2017	J	`jnl`	Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes. IEEE Trans. Image Process. Mohammad Sabokrou, Mohsen Fayyaz, Mahmood Fathy, Reinhard Klette
2017	J	`jnl`	Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification. CoRR Ali Diba, Mohsen Fayyaz, Vivek Sharma, Amir Hossein Karami, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Luc Van Gool
2016	J	`jnl`	Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes. CoRR Mohammad Sabokrou, Mohsen Fayyaz, Mahmood Fathy, Reinhard Klette
2016	J	`jnl`	Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures. CoRR Seyyed Hossein HasanPour, Mohammad Rouhani, Mohsen Fayyaz, Mohammad Sabokrou
2016	J	`jnl`	STFCN: Spatio-Temporal FCN for Semantic Video Segmentation. CoRR Mohsen Fayyaz, Mohammad Hajizadeh Saffar, Mohammad Sabokrou, Mahmood Fathy, Reinhard Klette
2016	—	`conf`	STFCN: Spatio-Temporal Fully Convolutional Neural Network for Semantic Segmentation of Street Scenes. ACCV Workshops (1) Mohsen Fayyaz, Mohammad Hajizadeh Saffar, Mohammad Sabokrou, Mahmood Fathy, Fay Huang, Reinhard Klette
2015	J	`jnl`	A Novel Approach For Finger Vein Verification Based on Self-Taught Learning. CoRR Mohsen Fayyaz, Masoud PourReza, Mohammad Hajizadeh Saffar, Mohammad Sabokrou, Mahmood Fathy
2015	J	`jnl`	Feature Representation for Online Signature Verification. CoRR Mohsen Fayyaz, Mohammad Hajizadeh Saffar, Mohammad Sabokrou, Mahmood Fathy