News.

“MAP: Measuring Agents in Production” accepted at ICML 2026 as a Spotlight (top 2.2%).

3rd Place, Mathematics Doctoral Prize Competition, University of Waterloo.

Best Paper Award at ECIR 2026 for “ReFormeR: Learning and Applying Explicit Query Reformulation Patterns.”

Reproducibility Track Chair, SIGIR 2026.

Best Industry Talk Award at WSDM 2026 for “Can LLMs Uphold Research Integrity? Evaluating the Role of LLMs in Peer Review Quality.”

Area Chair, NeurIPS 2026.

Joined the panel discussion at the WSDM 2026 Doctoral Symposium.

Workshop Chair, ECIR 2026.

“QueryGym: A Toolkit for Reproducible LLM-Based Query Reformulation” accepted at The Web Conference 2026.

with Amin Bigdeli, Radin Hamidi Rad, Mert Incesu, Charles L. A. Clarke, Ebrahim Bagheri.

Publicity Chair, CHIIR 2026.

“PeeriScope: A Multi-Faceted Framework for Evaluating Peer Review Quality” accepted at The Web Conference 2026.

with Sajad Ebrahimi, Soroush Sadeghian, Ali Ghorbanpour, Sara Salamat, Seyed Mohammad Hosseini, Hai Son Le, Mahdi Bashari, Ebrahim Bagheri.

Area Chair, ACL Rolling Review (ARR).

Presented MAP: Measuring Agents in Production at a NICE Talk — insights from a year-long empirical study on real-world agent deployments.

Presented MAP: Measuring Agents in Production at Google Sense AI.

Runner-up Best Paper Award at SIGIR-AP 2025 for “Adversarial Attacks against Neural Ranking Models via In-Context Learning.”

Attended my first NeurIPS! It was pretty OVERWHELMING.

Presented three workshop papers at NeurIPS 2025: Restructuring the Corpus Makes RAG Work for Math (Math AI), DeepScholar-Bench (LLM Evaluation), and Towards Automatically Optimizing Retrieval Augmented AI Systems (ML for Systems).

Released MAP: Measuring Agents in Production — a whole-year-long project.

Workshop proposal accepted at NeurIPS 2025: Vision Language Models: Challenges of Real-World Deployment.

with Mozhgan Nasr Azadani, Yimu Wang, Krzysztof Czarnecki, Richard He Bai, Lukas Schmid.

“Can LLMs Uphold Research Integrity? Evaluating the Role of LLMs in Peer Review Quality” accepted at WSDM 2026 — Best Industry Paper Award.

with Sajad Ebrahimi, Soroush Sadeghian, Seyed Mohammad Hosseini, Alireza Daqiq, Hai Son Le, Mahdi Bashari, Ebrahim Bagheri.

Released QueryGym — toolkit for reproducible LLM-based query reformulation.

Attended CIKM in Seoul, South Korea — one applied research paper, one short paper, and an industry talk.

Participated in the CIKM 2025 Doctoral Symposium.

Joined the panel discussion at the ProAct LLM workshop, CIKM 2025.

Graduated with my PhD from the University of Waterloo — thesis nominated for the Gold Thesis Award.

“Query Performance Prediction Using Neural Query Space Proximity” accepted at TIST journal.

with Amin Bigdeli, Sajad Ebrahimi, Sara Salamat, Shirin Seyedsalehi, Maryam Khodabakhsh, Fattane Zarrinkalam, Ebrahim Bagheri.

First project release as a postdoc at the Sky Lab: DeepScholar-Bench — a live benchmark for generative research synthesis.

Three papers accepted at CIKM 2025: RottenReviews, Building Trustworthy Peer Review Quality Assessment Systems, LLM-as-a-Judge in Entity Retrieval.

Attended SIGIR in Padua, Italy.

Won the Best Reviewer Award at SIGIR 2025.

Honored to receive the SIGIR Student Travel Grant.

Successfully defended my PhD!

Moved to California and officially started my postdoc at UC Berkeley — can't believe this dream is now reality!

Four papers accepted at SIGIR 2025: Benchmarking LLM-based Relevance Judgment Methods, VAP³, A Human-AI Comparative Analysis of Prompt Sensitivity, and IDAT.

Attended SIGIR-AP in Tokyo, Japan. Tokyo became my favourite city. Two papers and a tutorial.

Attended ACML in Hanoi, Vietnam — two papers.

Two papers accepted at ECIR 2025: exHarmony and Benchmarking Prompt Sensitivity in LLMs.

Attended my first EMNLP in Miami, USA. WOW it was huge!

Attended CIKM in Boise, Idaho — gave my first industrial talk about Reviewer.ly.

“Assessing and Verifying Task Utility in LLM-Powered Applications” accepted at EMNLP 2024.

with Siqing Huo, Nikhil Mehta, Qingyun Wu, Chi Wang, Ahmed Hassan Awadallah, Charles L. A. Clarke, Julia Kiseleva.

Two papers and a tutorial accepted at SIGIR-AP 2024: Offline Evaluation of Set-Based Text-to-Image Generation and Evaluating Relative Retrieval Effectiveness with Normalized Residual Gain.

Three papers accepted at Machine Learning Journal: Robust QPP for Dense Retrievers, Gender Disentangled Representation Learning, A Contrastive Neural Disentanglement Approach.

Industrial talk “Reviewerly” and paper “Enhanced Retrieval Effectiveness through Selective Query Generation” accepted at CIKM 2024.

Gave a talk at the Sky Computing Lab, UC Berkeley, on Evaluation of Information Access Systems in the Generative Era.

Honored to receive the Ontario Graduate Scholarship (OGS).

Passed my PhD second comprehensive exam — officially a PhD candidate!

Honorable Mention Award at ECIR 2024 for “Context-Aware Query Term Difficulty Estimation for Performance Prediction.”

“Ranked List Truncation: From Retrieval to Re-ranking” accepted at SIGIR 2024.

Attended ECIR 2024 in Glasgow, Scotland; gave a keynote talk at WOWS2024 and a talk at the Search Futures workshop.

Attended EACL 2024 in Malta.

Started co-organizing the SIGIR Virtual Forum “Lean and Learn” series.

Gave a talk at UCL Web Intelligence Group.

“Fréchet Distance for Offline Evaluation of IR Systems with Sparse Labels” accepted at EACL 2024.

Finished my internship at Microsoft Research.

Six papers and a tutorial accepted at ECIR 2024: LaQuE, Adapting Standard Retrieval Benchmarks, Context-Aware QPP, Estimating QPP through Rich Contextualized Query Representations, plus BertPE, Learning to Jointly Transform and Rank, and KnowFIRES.

Gave a talk at the Information Retrieval Group, University of Glasgow.

Joined Microsoft Research Redmond as a Research Intern. Finally doing it in person — first time in the USA!

“A Self-Supervised Language Model Selection Strategy for Biomedical Question Answering” accepted in the Journal of Biomedical Informatics.

“Retrieving Supporting Evidence for Generative Question Answering” accepted at SIGIR-AP 2023.

with Siqing Huo, Charles Clarke.

Two papers accepted at CIKM 2023: Noisy Perturbations for Estimating Query Difficulty in Dense Retrievers and Neural Disentanglement of Query Difficulty and Semantics.

Attended SIGIR 2023 in Taipei, Taiwan.

Won the SIGIR Travel Award to attend SIGIR and ICTIR in Taiwan.

“A is for Adele: An Offline Evaluation Metric for Instant Search” accepted at ICTIR 2023.

with Oleksandra Kmet, Ben Carterette, Charles Clarke, Claudia Hauff, Praveen Chandar.

Won the AMII Talent Bursary to attend the Upper Bound conference in Edmonton, Alberta.

Won the Cheriton Scholarship for $20,000.

Presented our journal paper “Shallow Pooling for Sparse Labels” at ECIR 2023; tutorial “Understanding and Mitigating Gender Bias in IR Systems” at ECIR 2023.

Attended ECIR 2023 in Dublin, Ireland.

Three papers accepted at SIGIR 2023: QPP: From Ad-hoc to Conversational Search, A Preference Judgment Tool for Authoritative Assessment, Quantifying Ranker Coverage of Different Query Subspaces.

Gave a tutorial on Preference-based Offline Evaluation at WSDM 2023.

Attended WSDM 2023 in Singapore.

Finished my internship at Google Brain.

“PREME: Preference-Based Meeting Exploration through an Interactive Questionnaire” accepted at EACL 2023 — outcome of my MSR internship.

Four entries accepted at ECIR 2023: tutorial proposal, Learning Query-Space Document Representations, Don't Raise Your Voice, and De-Biasing Relevance Judgements.

Gave a talk on Gender Bias in Information Retrieval at MILA.

Tutorial proposal Preference-based Offline Evaluation accepted at WSDM 2023.

“Collecting Interactive Multi-Modal Datasets for Grounded Language Understanding” accepted at the InterNLP workshop at NeurIPS 2022.

Joined Google Brain as a Student Researcher Intern.

Launched the IGLU competition for NeurIPS 2022 in two RL and NLP tasks.

Finished my internship at Spotify Research.

Two papers accepted at CIKM 2022: Early Stage Sparse Retrieval with Entity Linking and Unsupervised Question Clarity Prediction through Retrieved Item Coherency.

Gave a tutorial on Gender Bias in Information Retrieval Systems at SIGIR 2022.

Attended SIGIR 2022 in Madrid — could not be more fun in person after two years!

Attended WebSci 2022 in Barcelona.

“A Light-Weight Strategy for Restraining Gender Biases in Neural Rankers” received the Best Paper Award at ECIR 2022.

Started an internship at Spotify on podcasts' offline evaluation.

Visiting my family in Iran for the holidays :)

“A Light-Weight Strategy for Restraining Gender Biases in Neural Rankers” accepted at ECIR 2022.

Four papers accepted at CIKM 2021: BERT-QPP, Predicting Efficiency / Effectiveness Trade-offs, MS MARCO Chameleons, and Matches Made in Heaven.

Finished my internship at Spotify Research.

Started an internship at Microsoft Research.