Mehdi Rezagholizadeh

157 papers A* 9A 5B 4Misc 4Journal 83Unranked 51

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Dynamic Chunking Diffusion Transformer. CoRR Akash Haridas, Utkarsh Saxena, Parsa Ashrafi Fashi, Mehdi Rezagholizadeh, Vikram Appia, Emad Barsoum
2025	A*	`conf`	Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models. EMNLP Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh, Parsa Farinneya, Hossein Rajabzadeh, Aref Jafari, Boxing Chen, Marzieh S. Tahaei
2025	J	`jnl`	Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models. CoRR Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh, Parsa Farinneya, Hossein Rajabzadeh, Aref Jafari, Boxing Chen, Marzieh S. Tahaei
2025	J	`jnl`	DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers. CoRR Aman Sharma, Saeed Najafi, Parsa Farinneya, Benyamin Jamialahmadi, Marzieh S. Tahaei, Yuhe Fan, Mehdi Rezagholizadeh, Boxing Chen, Aref Jafari
2025	—	`conf`	Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination. ACL (Findings) Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Boxing Chen, Sarath Chandar
2025	—	`conf`	ReGLA: Refining Gated Linear Attention. NAACL (Long Papers) Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh, Boxing Chen, Philippe Langlais
2025	J	`jnl`	ReGLA: Refining Gated Linear Attention. CoRR Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh, Boxing Chen, Philippe Langlais
2025	J	`jnl`	The Order Effect: Investigating Prompt Sensitivity in Closed-Source LLMs. CoRR Bryan Guan, Tanya G. Roosta, Peyman Passban, Mehdi Rezagholizadeh
2025	J	`jnl`	X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression. CoRR Guihong Li, Mehdi Rezagholizadeh, Mingyu Yang, Vikram Appia, Emad Barsoum
2025	J	`jnl`	Zebra-Llama: Towards Extremely Efficient Hybrid Models. CoRR Mingyu Yang, Mehdi Rezagholizadeh, Guihong Li, Vikram Appia, Emad Barsoum
2024	—	`conf`	"Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation. EMNLP (Findings) Nandan Thakur, Luiz Bonifacio, Xinyu Zhang, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Boxing Chen, Mehdi Rezagholizadeh, Jimmy Lin
2024	J	`jnl`	An Efficient End-to-End Approach to Noise Invariant Speech Features via Multi-Task Learning. CoRR Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Boxing Chen, Tiago H. Falk
2024	J	`jnl`	Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression. CoRR Michael R. Metel, Boxing Chen, Mehdi Rezagholizadeh
2024	A*	`conf`	Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models. IJCAI Xindi Wang, Mahsa Salmani, Parsa Omidi, Xiangyu Ren, Mehdi Rezagholizadeh, Armaghan Eshaghi
2024	J	`jnl`	Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models. CoRR Xindi Wang, Mahsa Salmani, Parsa Omidi, Xiangyu Ren, Mehdi Rezagholizadeh, Armaghan Eshaghi
2024	—	`conf`	CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems. ACL (Findings) Abbas Ghaddar, David Alfonso-Hermelo, Philippe Langlais, Mehdi Rezagholizadeh, Boxing Chen, Prasanna Parthasarathi
2024	J	`jnl`	CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems. CoRR Abbas Ghaddar, David Alfonso-Hermelo, Philippe Langlais, Mehdi Rezagholizadeh, Boxing Chen, Prasanna Parthasarathi
2024	A*	`conf`	CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search. EMNLP Fengran Mo, Abbas Ghaddar, Kelong Mao, Mehdi Rezagholizadeh, Boxing Chen, Qun Liu, Jian-Yun Nie
2024	J	`jnl`	CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search. CoRR Fengran Mo, Abbas Ghaddar, Kelong Mao, Mehdi Rezagholizadeh, Boxing Chen, Qun Liu, Jian-Yun Nie
2024	A*	`conf`	CIRAL: A Test Collection for CLIR Evaluations in African Languages. SIGIR Mofetoluwa Adeyemi, Akintunde Oladipo, Xinyu Zhang, David Alfonso-Hermelo, Mehdi Rezagholizadeh, Boxing Chen, Abdul-Hakeem Omotayo, Idris Abdulmumin, Naome A. Etori, Toyib Babatunde Musa, Samuel Fanijo, Oluwabusayo Olufunke Awoyomi, Saheed Abdullahi Salahudeen, Labaran Adamu Mohammed, Daud Olamide Abolade, Falalu Ibrahim Lawan, Maryam Sabo Abubakar, Ruqayya Nasir Iro, Amina Abubakar Imam, Shafie Abdi Mohamed, Hanad Mohamud Mohamed, Tunde Oluwaseyi Ajayi, Jimmy Lin
2024	A*	`conf`	Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models. EMNLP Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar
2024	J	`jnl`	Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models. CoRR Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar
2024	J	`jnl`	Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination. CoRR Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Boxing Chen, Sarath Chandar
2024	—	`conf`	Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity. EMNLP (Findings) Michael R. Metel, Peng Lu, Boxing Chen, Mehdi Rezagholizadeh, Ivan Kobyzev
2024	J	`jnl`	Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity. CoRR Michael R. Metel, Peng Lu, Boxing Chen, Mehdi Rezagholizadeh, Ivan Kobyzev
2024	—	`conf`	EWEK-QA : Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems. ACL (1) Mohammad Dehghan, Mohammad Ali Alomrani, Sunyam Bagga, David Alfonso-Hermelo, Khalil Bibi, Abbas Ghaddar, Yingxue Zhang, Xiaoguang Li, Jianye Hao, Qun Liu, Jimmy Lin, Boxing Chen, Prasanna Parthasarathi, Mahdi Biparva, Mehdi Rezagholizadeh
2024	J	`jnl`	EWEK-QA: Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems. CoRR Mohammad Dehghan, Mohammad Ali Alomrani, Sunyam Bagga, David Alfonso-Hermelo, Khalil Bibi, Abbas Ghaddar, Yingxue Zhang, Xiaoguang Li, Jianye Hao, Qun Liu, Jimmy Lin, Boxing Chen, Prasanna Parthasarathi, Mahdi Biparva, Mehdi Rezagholizadeh
2024	—	`conf`	EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models. ENLSP Hossein Rajabzadeh, Aref Jafari, Aman Sharma, Benyamin Jami, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	J	`jnl`	EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models. CoRR Hossein Rajabzadeh, Aref Jafari, Aman Sharma, Benyamin Jami, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	—	`conf`	Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification. NAACL-HLT (Findings) Marzieh S. Tahaei, Aref Jafari, Ahmad Rashid, David Alfonso-Hermelo, Khalil Bibi, Yimeng Wu, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	—	`ed.`	NeurIPS Efficient Natural Language and Speech Processing Workshop, 14 December 2024, Vancouver, British Columbia, Canada. ENLSP Mehdi Rezagholizadeh, Peyman Passban, Soheila Samiee, Vahid Partovi Nia, Yu Cheng, Yue Deng, Qun Liu, Boxing Chen
2024	—	`conf`	OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection. ACL (Findings) Chenyang Huang, Abbas Ghaddar, Ivan Kobyzev, Mehdi Rezagholizadeh, Osmar Zaïane, Boxing Chen
2024	J	`jnl`	OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection. CoRR Chenyang Huang, Abbas Ghaddar, Ivan Kobyzev, Mehdi Rezagholizadeh, Osmar R. Zaïane, Boxing Chen
2024	J	`jnl`	On the importance of Data Scale in Pretraining Arabic Language Models. CoRR Abbas Ghaddar, Philippe Langlais, Mehdi Rezagholizadeh, Boxing Chen
2024	—	`conf`	QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning. EMNLP (Industry Track) Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu, Marzieh S. Tahaei, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	J	`jnl`	QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning. CoRR Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu, Marzieh S. Tahaei, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	—	`conf`	Resonance RoPE: Improving Context Length Generalization of Large Language Models. ACL (Findings) Suyuchen Wang, Ivan Kobyzev, Peng Lu, Mehdi Rezagholizadeh, Bang Liu
2024	J	`jnl`	Resonance RoPE: Improving Context Length Generalization of Large Language Models. CoRR Suyuchen Wang, Ivan Kobyzev, Peng Lu, Mehdi Rezagholizadeh, Bang Liu
2024	J	`jnl`	S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models. CoRR Parsa Kavehzadeh, Mohammadreza Pourreza, Mojtaba Valipour, Tinashu Zhu, Haoli Bai, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	—	`conf`	Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference. EACL (Findings) Parsa Kavehzadeh, Mojtaba Valipour, Marzieh S. Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	J	`jnl`	Towards Practical Tool Usage for Continually Learning LLMs. CoRR Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar
2023	J	`jnl`	An Exploration into the Performance of Unsupervised Cross-Task Speech Representations for "In the Wild" Edge Applications. CoRR Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk
2023	—	`conf`	AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing. ACL (Findings) Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar
2023	J	`jnl`	AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing. CoRR Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar
2023	—	`conf`	Attribute Controlled Dialogue Prompting. ACL (Findings) Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart
2023	J	`jnl`	Attribute Controlled Dialogue Prompting. CoRR Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart
2023	—	`conf`	CIRAL at FIRE 2023: Cross-Lingual Information Retrieval for African Languages. FIRE Mofetoluwa Adeyemi, Akintunde Oladipo, Xinyu Zhang, David Alfonso-Hermelo, Mehdi Rezagholizadeh, Boxing Chen, Jimmy Lin
2023	A	`conf`	Do we need Label Regularization to Fine-tune Pre-trained Language Models? EACL Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh, Tianda Li, Alan Do-Omri, Peng Lu, Pascal Poupart, Ali Ghodsi
2023	A	`conf`	DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation. EACL Mojtaba Valipour, Mehdi Rezagholizadeh, Ivan Kobyzev, Ali Ghodsi
2023	A*	`conf`	Efficient Classification of Long Documents via State-Space Models. EMNLP Peng Lu, Suyuchen Wang, Mehdi Rezagholizadeh, Bang Liu, Ivan Kobyzev
2023	—	`conf`	Evaluating Embedding APIs for Information Retrieval. ACL (industry) Ehsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-Hermelo, Mehdi Rezagholizadeh, Jimmy Lin
2023	J	`jnl`	Evaluating Embedding APIs for Information Retrieval. CoRR Ehsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-Hermelo, Mehdi Rezagholizadeh, Jimmy Lin
2023	J	`jnl`	Improved knowledge distillation by utilizing backward pass knowledge in neural networks. CoRR Aref Jafari, Mehdi Rezagholizadeh, Ali Ghodsi
2023	—	`conf`	LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization. ACL (Findings) Peng Lu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Philippe Langlais
2023	J	`jnl`	LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization. CoRR Peng Lu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Philippe Langlais
2023	J	`jnl`	MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages. Trans. Assoc. Comput. Linguistics Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin
2023	—	`conf`	Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models. EMNLP (Findings) Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi, Sarath Chandar
2023	J	`jnl`	Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models. CoRR Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi, Sarath Chandar
2023	J	`jnl`	Multimodal Audio-textual Architecture for Robust Spoken Language Understanding. CoRR Anderson R. Avila, Mehdi Rezagholizadeh, Chao Xing
2023	J	`jnl`	NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation. CoRR Nandan Thakur, Luiz Bonifacio, Xinyu Zhang, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Boxing Chen, Mehdi Rezagholizadeh, Jimmy Lin
2023	J	`jnl`	On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild". CoRR Arthur Pimentel, Heitor R. Guimarães, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk
2023	J	`jnl`	On the Transferability of Whisper-based Representations for "In-the-Wild" Cross-Task Downstream Speech Applications. CoRR Vamsikrishna Chemudupati, Marzieh S. Tahaei, Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Boxing Chen, Tiago H. Falk
2023	B	`conf`	On the utility of enhancing BERT syntactic bias with Token Reordering Pretraining. CoNLL Yassir El Mesbahi, Atif Mahmud, Abbas Ghaddar, Mehdi Rezagholizadeh, Philippe Langlais, Prasanna Parthasarathi
2023	—	`conf`	Overview of the CIRAL Track at FIRE 2023: Cross-lingual Information Retrieval for African Languages. FIRE (Working Notes) Mofetoluwa Adeyemi, Akintunde Oladipo, Xinyu Crystina Zhang, David Alfonso-Hermelo, Mehdi Rezagholizadeh, Boxing Chen, Jimmy Lin
2023	—	`conf`	Practical Takes on Federated Learning with Pretrained Language Models. EACL (Findings) Ankur Agarwal, Mehdi Rezagholizadeh, Prasanna Parthasarathi
2023	J	`jnl`	RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness. CoRR Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Boxing Chen, Tiago H. Falk
2023	Misc	`conf`	Robustdistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness. ICASSP Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Boxing Chen, Tiago H. Falk
2023	J	`jnl`	Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval. CoRR Jimmy Lin, David Alfonso-Hermelo, Vitor Jeronymo, Ehsan Kamalloo, Carlos Lassance, Rodrigo Nogueira, Odunayo Ogundepo, Mehdi Rezagholizadeh, Nandan Thakur, Jheng-Hong Yang, Xinyu Zhang
2023	J	`jnl`	Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT). CoRR Parsa Kavehzadeh, Mojtaba Valipour, Marzieh S. Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2023	J	`jnl`	SortedNet, a Place for Every Network and Every Network in its Place: Towards a Generalized Solution for Training Many-in-One Neural Networks. CoRR Mojtaba Valipour, Mehdi Rezagholizadeh, Hossein Rajabzadeh, Marzieh S. Tahaei, Boxing Chen, Ali Ghodsi
2023	—	`conf`	Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation. EACL (Findings) Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia
2022	B	`conf`	CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation. COLING Md. Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais, Pascal Poupart
2022	J	`jnl`	CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation. CoRR Md. Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais, Pascal Poupart
2022	—	`conf`	Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization. EMNLP (Findings) Aref Jafari, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart, Ali Ghodsi
2022	J	`jnl`	Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization. CoRR Aref Jafari, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart, Ali Ghodsi
2022	J	`jnl`	DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation. CoRR Mojtaba Valipour, Mehdi Rezagholizadeh, Ivan Kobyzev, Ali Ghodsi
2022	B	`conf`	Dynamic Position Encoding for Transformers. COLING Joyce Zheng, Mehdi Rezagholizadeh, Peyman Passban
2022	J	`jnl`	Dynamic Position Encoding for Transformers. CoRR Joyce Zheng, Mehdi Rezagholizadeh, Peyman Passban
2022	A*	`conf`	From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables. AAAI Krtin Kumar, Peyman Passban, Mehdi Rezagholizadeh, Yiu Sing Lau, Qun Liu
2022	—	`conf`	Huawei Noah's Ark Lab at TREC NeuCLIR 2022. TREC Ehsan Kamalloo, David Alfonso-Hermelo, Mehdi Rezagholizadeh
2022	—	`conf`	Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging. EMNLP (Findings) Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh, Ahmad Rashid, Ali Ghodsi, Philippe Langlais
2022	J	`jnl`	Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging. CoRR Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh, Ahmad Rashid, Ali Ghodsi, Philippe Langlais
2022	J	`jnl`	Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement. CoRR Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk
2022	J	`jnl`	Integer Fine-tuning of Transformer-based Models. CoRR Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia
2022	J	`jnl`	KronA: Parameter Efficient Tuning with Kronecker Adapter. CoRR Ali Edalati, Marzieh S. Tahaei, Ivan Kobyzev, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
2022	—	`conf`	Kronecker Decomposition for GPT Compression. ACL (2) Ali Edalati, Marzieh S. Tahaei, Ahmad Rashid, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
2022	—	`conf`	KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation. NAACL-HLT Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia, Ali Ghodsi, Mehdi Rezagholizadeh
2022	J	`jnl`	Learning Functions on Multiple Sets using Multi-Set Transformers. CoRR Kira A. Selby, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart
2022	A	`conf`	Learning functions on multiple sets using multi-set transformers. UAI Kira A. Selby, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart
2022	J	`jnl`	Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages. CoRR Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin
2022	B	`conf`	Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher. COLING Mehdi Rezagholizadeh, Aref Jafari, Puneeth S. M. Saladi, Pranav Sharma, Ali Saheb Pasand, Ali Ghodsi
2022	—	`conf`	RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation. NAACL-HLT (Findings) Md. Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart
2022	A*	`conf`	Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing. EMNLP Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Philippe Langlais
2022	J	`jnl`	Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding. CoRR Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Duan Xinyu, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Philippe Langlais
2022	—	`conf`	Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval. TREC Jimmy Lin, David Alfonso-Hermelo, Vitor Jeronymo, Ehsan Kamalloo, Carlos Lassance, Rodrigo Nogueira, Odunayo Ogundepo, Mehdi Rezagholizadeh, Nandan Thakur, Jheng-Hong Yang, Xinyu Zhang
2022	J	`jnl`	Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models. CoRR Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh, Tianda Li, Alan Do-Omri, Peng Lu, Ali Ghodsi, Pascal Poupart
2022	—	`conf`	When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation. ACL (Findings) Ehsan Kamalloo, Mehdi Rezagholizadeh, Ali Ghodsi
2022	J	`jnl`	When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation. CoRR Ehsan Kamalloo, Mehdi Rezagholizadeh, Ali Ghodsi
2021	J	`jnl`	A Short Study on Compressing Decoder-Based Language Models. CoRR Tianda Li, Yassir El Mesbahi, Ivan Kobyzev, Ahmad Rashid, Atif Mahmud, Nithin Anchuri, Habib Hajimolahoseini, Yang Liu, Mehdi Rezagholizadeh
2021	A*	`conf`	ALP-KD: Attention-Based Layer Projection for Knowledge Distillation. AAAI Peyman Passban, Yimeng Wu, Mehdi Rezagholizadeh, Qun Liu
2021	A	`conf`	Annealing Knowledge Distillation. EACL Aref Jafari, Mehdi Rezagholizadeh, Pranav Sharma, Ali Ghodsi
2021	J	`jnl`	Annealing Knowledge Distillation. CoRR Aref Jafari, Mehdi Rezagholizadeh, Pranav Sharma, Ali Ghodsi
2021	J	`jnl`	Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition. CoRR Abbas Ghaddar, Philippe Langlais, Ahmad Rashid, Mehdi Rezagholizadeh
2021	J	`jnl`	Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition. Trans. Assoc. Comput. Linguistics Abbas Ghaddar, Philippe Langlais, Ahmad Rashid, Mehdi Rezagholizadeh
2021	—	`conf`	End-to-End Self-Debiasing Framework for Robust NLU Training. ACL/IJCNLP (Findings) Abbas Ghaddar, Philippe Langlais, Mehdi Rezagholizadeh, Ahmad Rashid
2021	J	`jnl`	End-to-End Self-Debiasing Framework for Robust NLU Training. CoRR Abbas Ghaddar, Philippe Langlais, Mehdi Rezagholizadeh, Ahmad Rashid
2021	Misc	`conf`	Fine-Tuning of Pre-Trained End-to-End Speech Recognition with Generative Adversarial Networks. ICASSP Md. Akmal Haidar, Mehdi Rezagholizadeh
2021	J	`jnl`	Fine-tuning of Pre-trained End-to-end Speech Recognition with Generative Adversarial Networks. CoRR Md. Akmal Haidar, Mehdi Rezagholizadeh
2021	—	`conf`	How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding. EMNLP (Findings) Tianda Li, Ahmad Rashid, Aref Jafari, Pranav Sharma, Ali Ghodsi, Mehdi Rezagholizadeh
2021	J	`jnl`	How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding. CoRR Tianda Li, Ahmad Rashid, Aref Jafari, Pranav Sharma, Ali Ghodsi, Mehdi Rezagholizadeh
2021	J	`jnl`	Improving Neural Machine Translation with Compact Word Embedding Tables. CoRR Krtin Kumar, Mehdi Rezagholizadeh, Yiu Sing Lau, Qun Liu
2021	J	`jnl`	JABER: Junior Arabic BERt. CoRR Abbas Ghaddar, Yimeng Wu, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Duan Xinyu, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Philippe Langlais
2021	—	`conf`	Knowledge Distillation with Noisy Labels for Natural Language Understanding. W-NUT Shivendra Bhardwaj, Abbas Ghaddar, Ahmad Rashid, Khalil Bibi, Chengyang Li, Ali Ghodsi, Philippe Langlais, Mehdi Rezagholizadeh
2021	J	`jnl`	Knowledge Distillation with Noisy Labels for Natural Language Understanding. CoRR Shivendra Bhardwaj, Abbas Ghaddar, Ahmad Rashid, Khalil Bibi, Chengyang Li, Ali Ghodsi, Philippe Langlais, Mehdi Rezagholizadeh
2021	J	`jnl`	Kronecker Decomposition for GPT Compression. CoRR Ali Edalati, Marzieh S. Tahaei, Ahmad Rashid, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
2021	J	`jnl`	KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation. CoRR Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia, Ali Ghodsi, Mehdi Rezagholizadeh
2021	—	`conf`	MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation. ACL/IJCNLP (1) Ahmad Rashid, Vasileios Lioutas, Mehdi Rezagholizadeh
2021	J	`jnl`	MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation. CoRR Ahmad Rashid, Vasileios Lioutas, Mehdi Rezagholizadeh
2021	—	`conf`	NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation. NeurIPS Datasets and Benchmarks David Alfonso-Hermelo, Ahmad Rashid, Abbas Ghaddar, Philippe Langlais, Mehdi Rezagholizadeh
2021	J	`jnl`	NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation. CoRR David Alfonso-Hermelo, Ahmad Rashid, Abbas Ghaddar, Philippe Langlais, Mehdi Rezagholizadeh
2021	—	`conf`	Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax. ACL/IJCNLP (Findings) Ehsan Kamalloo, Mehdi Rezagholizadeh, Peyman Passban, Ali Ghodsi
2021	J	`jnl`	Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax. CoRR Ehsan Kamalloo, Mehdi Rezagholizadeh, Peyman Passban, Ali Ghodsi
2021	J	`jnl`	Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher. CoRR Mehdi Rezagholizadeh, Aref Jafari, Puneeth Salad, Pranav Sharma, Ali Saheb Pasand, Ali Ghodsi
2021	J	`jnl`	RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation. CoRR Md. Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart
2021	—	`conf`	RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation. EMNLP (Findings) Peng Lu, Abbas Ghaddar, Ahmad Rashid, Mehdi Rezagholizadeh, Ali Ghodsi, Philippe Langlais
2021	J	`jnl`	Robust Embeddings Via Distributions. CoRR Kira A. Selby, Yinong Wang, Ruizhe Wang, Peyman Passban, Ahmad Rashid, Mehdi Rezagholizadeh, Pascal Poupart
2021	—	`conf`	Towards Zero-Shot Knowledge Distillation for Natural Language Processing. EMNLP (1) Ahmad Rashid, Vasileios Lioutas, Abbas Ghaddar, Mehdi Rezagholizadeh
2021	A	`conf`	Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation. Interspeech Md. Akmal Haidar, Chao Xing, Mehdi Rezagholizadeh
2021	J	`jnl`	Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation. CoRR Md. Akmal Haidar, Chao Xing, Mehdi Rezagholizadeh
2021	—	`conf`	Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation. EMNLP (1) Yimeng Wu, Mehdi Rezagholizadeh, Abbas Ghaddar, Md. Akmal Haidar, Ali Ghodsi
2020	J	`jnl`	ALP-KD: Attention-Based Layer Projection for Knowledge Distillation. CoRR Peyman Passban, Yimeng Wu, Mehdi Rezagholizadeh, Qun Liu
2020	J	`jnl`	From Unsupervised Machine Translation To Adversarial Text Generation. CoRR Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh
2020	Misc	`conf`	From Unsupervised Machine Translation to Adversarial Text Generation. ICASSP Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh
2020	—	`conf`	Fully Quantized Transformer for Machine Translation. EMNLP (Findings) Gabriele Prato, Ella Charlaix, Mehdi Rezagholizadeh
2020	—	`conf`	Improving Word Embedding Factorization for Compression using Distilled Nonlinear Neural Decomposition. EMNLP (Findings) Vasileios Lioutas, Ahmad Rashid, Krtin Kumar, Md. Akmal Haidar, Mehdi Rezagholizadeh
2020	J	`jnl`	Towards Zero-Shot Knowledge Distillation for Natural Language Processing. CoRR Ahmad Rashid, Vasileios Lioutas, Abbas Ghaddar, Mehdi Rezagholizadeh
2020	—	`conf`	Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers. EMNLP (1) Yimeng Wu, Peyman Passban, Mehdi Rezagholizadeh, Qun Liu
2020	J	`jnl`	Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers. CoRR Yimeng Wu, Peyman Passban, Mehdi Rezagholizadeh, Qun Liu
2019	J	`jnl`	Bilingual-GAN: A Step Towards Parallel Text Generation. CoRR Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh
2019	J	`jnl`	Distilled embedding: non-linear embedding factorization using knowledge distillation. CoRR Vasileios Lioutas, Ahmad Rashid, Krtin Kumar, Md. Akmal Haidar, Mehdi Rezagholizadeh
2019	—	`conf`	EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing. ACL (1) Yue Dong, Zichao Li, Mehdi Rezagholizadeh, Jackie Chi Kit Cheung
2019	J	`jnl`	EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing. CoRR Yue Dong, Zichao Li, Mehdi Rezagholizadeh, Jackie Chi Kit Cheung
2019	J	`jnl`	Fully Quantized Transformer for Improved Translation. CoRR Gabriele Prato, Ella Charlaix, Mehdi Rezagholizadeh
2019	J	`jnl`	Fully Quantizing a Simplified Transformer for End-to-end Speech Recognition. CoRR Alex Bie, Bharat Venkitesh, Joao Monteiro, Md. Akmal Haidar, Mehdi Rezagholizadeh
2019	—	`conf`	Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation. NAACL-HLT (1) Md. Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri, Ahmad Rashid
2019	J	`jnl`	Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation. CoRR Md. Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri, Ahmad Rashid
2019	—	`conf`	SALSA-TEXT: Self Attentive Latent Space Based Adversarial Text Generation. Canadian AI Jules Gagnon-Marchand, Hamed Sadeghi, Md. Akmal Haidar, Mehdi Rezagholizadeh
2019	—	`conf`	TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks. Canadian AI Md. Akmal Haidar, Mehdi Rezagholizadeh
2019	J	`jnl`	TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks. CoRR Md. Akmal Haidar, Mehdi Rezagholizadeh
2018	Misc	`conf`	Reg-Gan: Semi-Supervised Learning Based on Generative Adversarial Networks for Regression. ICASSP Mehdi Rezagholizadeh, Md. Akmal Haidar
2018	J	`jnl`	SALSA-TEXT : self attentive latent space based adversarial text generation. CoRR Jules Gagnon-Marchand, Hamed Sadeghi, Md. Akmal Haidar, Mehdi Rezagholizadeh
2016	—	`conf`	A Retargeting Approach for Mesopic Vision: Simulation and Compensation. Color Imaging: Displaying, Processing, Hardcopy, and Applications Mehdi Rezagholizadeh, Tara Akhavan, Afsoon Soudi, Hannes Kaufmann, James J. Clark
2015	—	`conf`	Image Sensor Modeling: Noise and Linear Transformation Impacts on the Color Gamut. CRV Mehdi Rezagholizadeh, James J. Clark
2014	—	`conf`	Image Sensor Modeling: Color Measurement at Low Light Levels. CIC Mehdi Rezagholizadeh, James J. Clark
2014	—	`conf`	Photon Detection and Color Perception at Low Light Levels. CRV Mehdi Rezagholizadeh, James J. Clark
2013	—	`conf`	Edge-Based and Efficient Chromaticity Spatio-spectral Models for Color Constancy. CRV Mehdi Rezagholizadeh, James J. Clark
2013	—	`conf`	Maximum Entropy Spectral Modeling Approach to Mesopic Tone Mapping. CIC Mehdi Rezagholizadeh, James J. Clark