Shahram Khadivi

106 papers A* 4A 2B 4C 3Misc 2Journal 44Unranked 44
YearRankTypeTitle / Venue / Authors
2026 — conf
Adapting Vision-Language Models for E-commerce Understanding at Scale.
EACL (Industry Track)
Matteo Nulli, Orshulevich Vladimir, Tala Bazazo, Christian Herold, Michael Kozielski, Marcin Mazur, Szymon Tuzel, Cees G. M. Snoek, Seyyed Hadi Hashemi, Omar Javed, Yannick Versley, Shahram Khadivi
2026 J jnl
Adapting Vision-Language Models for E-commerce Understanding at Scale.
CoRR
Matteo Nulli, Vladimir Orshulevich, Tala Bazazo, Christian Herold, Michael Kozielski, Marcin Mazur, Szymon Tuzel, Cees G. M. Snoek, Seyyed Hadi Hashemi, Omar Javed, Yannick Versley, Shahram Khadivi
2026 — conf
CONGRAD: Conflicting Gradient Filtering for Multilingual Preference Alignment.
EACL (Volume 1: Long Papers)
Jiangnan Li, Thuy-Trang Vu, Christian Herold, Amirhossein Tebbifakhr, Shahram Khadivi, Gholamreza Haffari
2026 J jnl
Environment-Aware Code Generation: How far are We?
CoRR
Tongtong Wu, Rongyi Chen, Wenjie Du, Suyu Ma, Guilin Qi, Zhenchang Xing, Shahram Khadivi, Ramesh Periyathambi, Gholamreza Haffari
2026 J jnl
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT.
CoRR
Nicholas Santavas, Kareem Eissa, Patrycja Cieplicka, Piotr Florek, Matteo Nulli, Stefan Vasilev, Seyyed Hadi Hashemi, Antonios Gasteratos, Shahram Khadivi
2025 J jnl
CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment.
CoRR
Jiangnan Li, Thuy-Trang Vu, Christian Herold, Amirhossein Tebbifakhr, Shahram Khadivi, Gholamreza Haffari
2025 — conf
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning.
ACL (Findings)
Baohao Liao, Christian Herold, Seyyed Hadi Hashemi, Stefan Vasilev, Shahram Khadivi, Christof Monz
2025 J jnl
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning.
CoRR
Baohao Liao, Christian Herold, Seyyed Hadi Hashemi, Stefan Vasilev, Shahram Khadivi, Christof Monz
2025 — conf
Domain Adaptation of Foundation LLMs for e-Commerce.
ACL (6)
Christian Herold, Michael Kozielski, Tala Bazazo, Pavel Petrushkov, Yannick Versley, Seyyed Hadi Hashemi, Patrycja Cieplicka, Dominika Basaj, Shahram Khadivi
2025 J jnl
Domain Adaptation of Foundation LLMs for e-Commerce.
CoRR
Christian Herold, Michael Kozielski, Tala Bazazo, Pavel Petrushkov, Seyyed Hadi Hashemi, Patrycja Cieplicka, Dominika Basaj, Shahram Khadivi
2025 — conf
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation.
ACL (Findings)
Stefan Vasilev, Christian Herold, Baohao Liao, Seyyed Hadi Hashemi, Shahram Khadivi, Christof Monz
2025 J jnl
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation.
CoRR
Stefan Vasilev, Christian Herold, Baohao Liao, Seyyed Hadi Hashemi, Shahram Khadivi, Christof Monz
2025 J jnl
Vocabulary Customization for Efficient Domain-Specific LLM Deployment.
CoRR
Christian Herold, Michael Kozielski, Nicholas Santavas, Yannick Versley, Shahram Khadivi
2024 — conf
Active Continual Learning: On Balancing Knowledge Retention and Learnability.
AI (2)
Thuy-Trang Vu, Shahram Khadivi, Mahsa Ghorbanali, Dinh Q. Phung, Gholamreza Haffari
2024 A* conf
ApiQ: Finetuning of 2-Bit Quantized Large Language Model.
EMNLP
Baohao Liao, Christian Herold, Shahram Khadivi, Christof Monz
2024 — conf
IKUN for WMT24 General MT Task: LLMs Are Here for Multilingual Machine Translation.
WMT
Baohao Liao, Christian Herold, Shahram Khadivi, Christof Monz
2024 J jnl
IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation.
CoRR
Baohao Liao, Christian Herold, Shahram Khadivi, Christof Monz
2024 J jnl
LiLiuM: eBay's Large Language Models for e-commerce.
CoRR
Christian Herold, Michael Kozielski, Leonid Ekimov, Pavel Petrushkov, Pierre-Yves Vandenbussche, Shahram Khadivi
2023 J jnl
Active Continual Learning: Labelling Queries in a Sequence of Tasks.
CoRR
Thuy-Trang Vu, Shahram Khadivi, Dinh Q. Phung, Gholamreza Haffari
2023 — conf
Document-Level Language Models for Machine Translation.
WMT
Frithjof Petrick, Christian Herold, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
2023 J jnl
Document-Level Language Models for Machine Translation.
CoRR
Frithjof Petrick, Christian Herold, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
2023 A* conf
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation.
ICCV
Samitha Herath, Basura Fernando, Ehsan Abbasnejad, Munawar Hayat, Shahram Khadivi, Mehrtash Harandi, Hamid Rezatofighi, Gholamreza Haffari
2023 J jnl
ITEm: Unsupervised Image-Text Embedding Learning for eCommerce.
CoRR
Baohao Liao, Michael Kozielski, Sanjika Hewavitharana, Jiangbo Yuan, Shahram Khadivi, Tomer Lancewicki
2023 J jnl
LenM: Improving Low-Resource Neural Machine Translation Using Target Length Modeling.
Neural Process. Lett.
Mohammad Mahdi Mahsuli, Shahram Khadivi, Mohammad Mehdi Homayounpour
2023 — conf
Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking.
ACL (Findings)
Iñigo Urteaga, Moulay-Zaïdane Draïdia, Tomer Lancewicki, Shahram Khadivi
2023 A conf
Probabilistic Robustness for Data Filtering.
EACL
Yu Yu, Abdul Rafae Khan, Shahram Khadivi, Jia Xu
2022 — conf
A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings.
LoResMT@COLING
Mohaddeseh Bastan, Shahram Khadivi
2022 B conf
Can Data Diversity Enhance Learning Generalization?
COLING
Yu Yu, Shahram Khadivi, Jia Xu
2022 J jnl
Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?
CoRR
Thuy-Trang Vu, Shahram Khadivi, Xuanli He, Dinh Q. Phung, Gholamreza Haffari
2022 — conf
Can Domains Be Transferred across Languages in Multi-Domain Multilingual Neural Machine Translation?
WMT
Thuy-Trang Vu, Shahram Khadivi, Xuanli He, Dinh Phung, Gholamreza Haffari
2022 — conf
Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out Training.
ACL (Findings)
Thuy-Trang Vu, Shahram Khadivi, Dinh Q. Phung, Gholamreza Haffari
2022 J jnl
Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking.
CoRR
Iñigo Urteaga, Moulay-Zaïdane Draïdia, Tomer Lancewicki, Shahram Khadivi
2021 J jnl
A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings.
CoRR
Mohaddeseh Bastan, Shahram Khadivi
2021 — conf
Back-translation for Large-Scale Multilingual Machine Translation.
WMT@EMNLP
Baohao Liao, Shahram Khadivi, Sanjika Hewavitharana
2021 J jnl
Back-translation for Large-Scale Multilingual Machine Translation.
CoRR
Baohao Liao, Shahram Khadivi, Sanjika Hewavitharana
2021 — conf
Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer.
IWSLT
Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney
2021 J jnl
Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer.
CoRR
Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney
2021 J jnl
Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer.
CoRR
Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney
2020 — conf
Diving Deep into Context-Aware Neural Machine Translation.
WMT@EMNLP
Jingjing Huo, Christian Herold, Yingbo Gao, Leonard Dahlmann, Shahram Khadivi, Hermann Ney
2020 J jnl
Diving Deep into Context-Aware Neural Machine Translation.
CoRR
Jingjing Huo, Christian Herold, Yingbo Gao, Leonard Dahlmann, Shahram Khadivi, Hermann Ney
2020 J jnl
Kernel compositional embedding and its application in linguistic structured data classification.
Knowl. Based Syst.
Hamed Ganji, Mohammad Mehdi Ebadzadeh, Shahram Khadivi
2020 J jnl
Matching Graph, a Method for Extracting Parallel Information from Comparable Corpora.
ACM Trans. Asian Low Resour. Lang. Inf. Process.
Somayeh Bakhshaei, Reza Safabakhsh, Shahram Khadivi
2019 J jnl
Extracting parallel fragments from comparable documents using a generative model.
Comput. Speech Lang.
Somayeh Bakhshaei, Reza Safabakhsh, Shahram Khadivi
2019 — conf
Generalizing Back-Translation in Neural Machine Translation.
WMT (1)
Miguel Graça, Yunsu Kim, Julian Schamper, Shahram Khadivi, Hermann Ney
2019 J jnl
Generalizing Back-Translation in Neural Machine Translation.
CoRR
Miguel Graça, Yunsu Kim, Julian Schamper, Shahram Khadivi, Hermann Ney
2019 — conf
Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron.
RepL4NLP@ACL
Yunsu Kim, Hendrik Rosendahl, Nick Rossenbach, Jan Rosendahl, Shahram Khadivi, Hermann Ney
2019 J jnl
Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron.
CoRR
Yunsu Kim, Hendrik Rosendahl, Nick Rossenbach, Jan Rosendahl, Shahram Khadivi, Hermann Ney
2019 — conf
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages.
EMNLP/IJCNLP (1)
Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
2019 J jnl
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages.
CoRR
Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
2019 — ed.
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP, DeepLo@EMNLP-IJCNLP 2019, Hong Kong, China, November 3, 2019
DeepLo@EMNLP-IJCNLP
Colin Cherry, Greg Durrett, George F. Foster, Reza Haffari, Shahram Khadivi, Nanyun Peng, Xiang Ren, Swabha Swayamdipta
2019 J jnl
Support vector-based fuzzy classifier with adaptive kernel.
Neural Comput. Appl.
Hamed Ganji, Shahram Khadivi, Mohammad Mehdi Ebadzadeh
2019 J jnl
Word-based Domain Adaptation for Neural Machine Translation.
CoRR
Shen Yan, Leonard Dahlmann, Pavel Petrushkov, Sanjika Hewavitharana, Shahram Khadivi
2018 — conf
Can Neural Machine Translation be Improved with User Feedback?
NAACL-HLT (3)
Julia Kreutzer, Shahram Khadivi, Evgeny Matusov, Stefan Riezler
2018 J jnl
Can Neural Machine Translation be Improved with User Feedback?
CoRR
Julia Kreutzer, Shahram Khadivi, Evgeny Matusov, Stefan Riezler
2018 — conf
Learning from Chunk-based Feedback in Neural Machine Translation.
ACL (2)
Pavel Petrushkov, Shahram Khadivi, Evgeny Matusov
2018 J jnl
Learning from Chunk-based Feedback in Neural Machine Translation.
CoRR
Pavel Petrushkov, Shahram Khadivi, Evgeny Matusov
2018 — ed.
Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP, DeepLo@ACL 2018, Melbourne, Australia, July 19, 2018
DeepLo@ACL
Reza Haffari, Colin Cherry, George F. Foster, Shahram Khadivi, Bahar Salehi
2018 — conf
Word-based Domain Adaptation for Neural Machine Translation.
IWSLT
Shen Yan, Leonard Dahlmann, Pavel Petrushkov, Sanjika Hewavitharana, Shahram Khadivi
2017 J jnl
Detecting Community Structure in Dynamic Social Networks Using the Concept of Leadership.
CoRR
Saeed Haji Seyed Javadi, Pedram Gharani, Shahram Khadivi
2017 J jnl
Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data.
CoRR
Mohammad Aliannejadi, Masoud Kiaeeha, Shahram Khadivi, Saeed Shiry Ghidary
2017 A* conf
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search.
EMNLP
Leonard Dahlmann, Evgeny Matusov, Pavel Petrushkov, Shahram Khadivi
2017 J jnl
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search.
CoRR
Leonard Dahlmann, Evgeny Matusov, Pavel Petrushkov, Shahram Khadivi
2017 J jnl
Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English.
CoRR
Mohaddeseh Bastan, Shahram Khadivi, Mohammad Mehdi Homayounpour
2017 — conf
Neural and Statistical Methods for Leveraging Meta-information in Machine Translation.
MTSummit (1)
Shahram Khadivi, Patrick Wilken, Leonard Dahlmann, Evgeny Matusov
2017 J jnl
Neural and Statistical Methods for Leveraging Meta-information in Machine Translation.
CoRR
Shahram Khadivi, Patrick Wilken, Leonard Dahlmann, Evgeny Matusov
2016 — conf
Guided Alignment Training for Topic-Aware Neural Machine Translation.
AMTA (1)
Wenhu Chen, Evgeny Matusov, Shahram Khadivi, Jan-Thorsten Peter
2016 J jnl
Guided Alignment Training for Topic-Aware Neural Machine Translation.
CoRR
Wenhu Chen, Evgeny Matusov, Shahram Khadivi, Jan-Thorsten Peter
2016 J jnl
Phrase-boundary model for statistical machine translation.
Comput. Speech Lang.
Shahram Salami, Mehrnoush Shamsfard, Shahram Khadivi
2015 — conf
A Generative Model for Extracting Parallel Fragments from Comparable Documents.
BUCC@ACL/IJCNLP
Somayeh Bakhshaei, Shahram Khadivi, Reza Safabakhsh
2015 J jnl
A syntactically informed reordering model for statistical machine translation.
J. Exp. Theor. Artif. Intell.
Saeed Farzi, Heshaam Faili, Shahram Khadivi
2015 — conf
Improved search strategy for interactive predictions in computer-assisted translation.
MTSummit
Fatemeh Azadi, Shahram Khadivi
2015 J jnl
Predicting user click behaviour in search engine advertisements.
New Rev. Hypermedia Multim.
Mohammad Daryaie Zanjani, Shahram Khadivi
2015 J jnl
Rebuilding Phrase Table Scores from Monolingual Resources Using Neural Networks Vector Representations.
CoRR
Amir Pouya Aghasadeghi, Mohadeseh Bastan, Shahram Khadivi
2014 B conf
An ant colony optimization method to detect communities in social networks.
ASONAM
Saeed Haji Seyed Javadi, Shahram Khadivi, Mohammad Ebrahim Shiri, Jia Xu
2014 Misc conf
Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data.
ALTA
Mohammad Aliannejadi, Masoud Kiaeeha, Shahram Khadivi, Saeed Shiry Ghidary
2013 J jnl
A Novel Reordering Model for Statistical Machine Translation.
Res. Comput. Sci.
Saeed Farzi, Heshaam Faili, Shahram Khadivi, Jalal Maleki
2013 B conf
Meta-level Statistical Machine Translation.
IJCNLP
Sajad Ebrahimi, Kourosh Meshgi, Shahram Khadivi, Mohammad Ebrahim Shiri Ahmad Abady
2013 — conf
Using Context Vectors in Improving a Machine Translation System with Bridge Language.
ACL (2)
Samira Tofighi Zahabi, Somayeh Bakhshaei, Shahram Khadivi
2013 — conf
Web Spam Detection: New Approach with Hidden Markov Models.
AIRS
Ali Asghar Torabi, Kaveh Taghipour, Shahram Khadivi
2012 B conf
A Holistic Approach to Bilingual Sentence Fragment Extraction from Comparable Corpora.
LREC
Mahdi Khademian, Kaveh Taghipour, Saab Mansour, Shahram Khadivi
2012 — conf
A New Search Approach for Interactive-Predictive Computer-Assisted Translation.
COLING (Posters)
Zeinab Vakil, Shahram Khadivi
2012 — conf
A pool-based active learning method for improving Farsi-English Machine Translation system.
IST
Somayeh Bakhshaei, Shahram Khadivi
2012 — conf
Developing an Open-domain English-Farsi Translation System Using AFEC: Amirkabir Bilingual Farsi-English Corpus.
CAAS@AMTA
Fattaneh Jabbari, Somayeh Bakshaei, Seyyed Mohammad Mohammadzadeh Ziabary, Shahram Khadivi
2012 — conf
Document and sentence alignment in comparable corpora using bipartite graph matching.
IST
Zeinab Rahimi, Kaveh Taghipour, Shahram Khadivi, Nasim Afhami
2012 — conf
FUZZGY: A hybrid model for credit card fraud detection.
IST
Mohammad Reza Harati Nik, Mahdi Akrami, Shahram Khadivi, Mahdi Shajari
2012 — conf
Interactive-predictive speech-enabled computer-assisted translation.
IWSLT
Shahram Khadivi, Zeinab Vakil
2012 — conf
Persica: A Persian corpus for multi-purpose text mining and natural language processing.
IST
Hamid Eghbalzadeh, Behrooz Hosseini, Shahram Khadivi, Ali Khodabakhsh
2012 — conf
Use of linguistic features for improving English-Persian SMT.
KONVENS
Zakieh Shakeri, Neda Noormohammadi, Shahram Khadivi, Noushin Riahi
2011 — conf
ASVMFC: Adaptive Support Vector Machine Based Fuzzy Classifier.
AIRS
Hamed Ganji, Shahram Khadivi
2011 — conf
An Unsupervised Alignment Model for Sequence Labeling: Application to Name Transliteration.
NEWS@IJCNLP
Najmeh Mousavi Nejad, Shahram Khadivi
2011 — conf
Parallel Corpus Refinement as an Outlier Detection Algorithm.
MTSummit
Kaveh Taghipour, Shahram Khadivi, Jia Xu
2011 — conf
The Amirkabir Machine Transliteration System for NEWS 2011: Farsi-to-English Task.
NEWS@IJCNLP
Najmeh Mousavi Nejad, Shahram Khadivi, Kaveh Taghipour
2011 — conf
Using Genre Interest of Users to Detect Profile Injection Attacks in Movie Recommender Systems.
ICMLA (1)
Ghazaleh Aghili, Mehdi Shajari, Shahram Khadivi, Mohammad Amin Morid
2009 Misc conf
Recent advances in SRI'S IraqComm
ICASSP
Murat Akbacak, Horacio Franco, Michael W. Frandsen, Sasa Hasan, Huda Jameel, Andreas Kathol, Shahram Khadivi, Xin Lei, Arindam Mandal, Saab Mansour, Kristin Precoda, Colleen Richey, Dimitra Vergyri, Wen Wang, Mei Yang, Jing Zheng
2009 J jnl
Statistical Approaches to Computer-Assisted Translation.
Comput. Linguistics
Sergio Barrachina, Oliver Bender, Francisco Casacuberta, Jorge Civera, Elsa Cubel, Shahram Khadivi, Antonio L. Lagarda, Hermann Ney, Jesús Tomás, Enrique Vidal, Juan Miguel Vilar
2008 J jnl
Integration of Speech Recognition and Machine Translation in Computer-Assisted Translation.
IEEE Trans. Speech Audio Process.
Shahram Khadivi, Hermann Ney
2008 — —
Statistical computer assisted translation.
Shahram Khadivi
2007 — conf
A Sequence Alignment Model Based on the Averaged Perceptron.
EMNLP-CoNLL
Dayne Freitag, Shahram Khadivi
2007 C conf
The RWTH Arabic-to-English spoken language translation system.
ASRU
Oliver Bender, Evgeny Matusov, Stefan Hahn, Sasa Hasan, Shahram Khadivi, Hermann Ney
2006 C conf
A Flexible Architecture for CAT Applications.
EAMT
Sasa Hasan, Shahram Khadivi, Richard Zens, Hermann Ney
2006 A* conf
Integration of Speech to Computer-Assisted Translation Using Finite-State Automata.
ACL
Shahram Khadivi, Richard Zens, Hermann Ney
2006 — conf
Morpho-syntactic Arabic Preprocessing for Arabic to English Statistical Machine Translation.
WMT@HLT-NAACL
Anas El Isbihani, Shahram Khadivi, Oliver Bender, Hermann Ney
2005 C conf
Automatic Filtering of Bilingual Corpora for Statistical Machine Translation.
NLDB
Shahram Khadivi, Hermann Ney
2005 A conf
Automatic text dictation in computer-assisted translation.
INTERSPEECH
Shahram Khadivi, András Zolnay, Hermann Ney
2005 — conf
The RWTH phrase-based statistical machine translation system.
IWSLT
Richard Zens, Oliver Bender, Sasa Hasan, Shahram Khadivi, Evgeny Matusov, Jia Xu, Yuqi Zhang, Hermann Ney
2000 — conf
Document Skew Detection Using Minimum-Area Bounding Rectangle.
ITCC
Reza Safabakhsh, Shahram Khadivi