🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Today (2/28), the #CIIRTalkSeries host Danqi Chen from Princeton NLP Group. The talk would be about "From RAG to Long-context Models: Benchmarks and Model Developments". You can watch it live on zoom. ciir.cs.umass.edu/node/792

Watch Danqi Chen's #CIIRTalk on long-context LLMs here: youtube.com/watch?v=qIo67i…

🚨New Breakthrough in Tip-of-the-Tongue (TOT) Retrieval Research! We address data limitations and offer a fresh evaluation method for the TOT complex queries. Curious how TREC TOT track test queries are created? Check out this thread🧵 and our paper📄: arxiv.org/abs/2502.17776

Andrew G. Barto and Richard S. Sutton have been awarded the prestigious 2024 ACM A.M. #TuringAward for developing a branch of artificial intelligence known as reinforcement learning. University of Alberta Manning College of Information & Computer Sciences #ManningCICS #ArtificialIntelligence #UMass bit.ly/3F6Poww

"Mathematical Information Retrieval: Search and Question Answering", the latest review article from FnTIR nowpublishers.com/article/Detail…

Glad to share our recent work on Dynamic and Parametric RAG in the CIIR Talk Series!🎉 We introduce our recent #TheWebConf2025 and #SIGIR2025 papers on how to inject retrieved docs into the attention layers and FFN layers of LLMs dynamically. Video here: youtu.be/z2dSY6IMFjQ?si…

I’m thrilled to share that two of my papers were accepted to SIGIR 2025: “Hypencoder: Hypernetworks for Information Retrieval” and “Scaling Sparse and Dense Retrieval in Decoder-Only LLMs” with Hansi Zeng Hamed Zamani

📢 New paper on scaling test-time compute for document re-ranking Do you want to know how to train compact 2-3B models that can reach the performance of 70B+ LLMs in reasoning-intensive ranking? 📄Check out the distillation + RL recipe in our paper: arxiv.org/abs/2504.03947

Anyone working on neural search/embedding/rerankers/deep research style things(from search angle) my team at SnowflakeDB is hiring aggressively. Send me a DM or email.

More news on Search-R1! Scale up to 32B+ model parameters, more retrieval models, etc. etc.

Research failures often come from chasing things that don’t matter long-term & it’s easy to fall into that trap individually, no matter how strong you are. That’s why joining flagship efforts can be great for researchers: the course-correcting power of group intelligence...

Some personal news: I'll join UMass Amherst CS as an assistant professor in fall 2026. Until then, I'll postdoc at Meta nyc. Reasoning will continue to be my main interest, with a focus on data-centric approaches🤩 If you're also interested, apply to me (phds & a postdoc)!

Happy to announce that 3 papers got accepted to ACL 2025! #NLProc #ACL2025NLP

[main] Personalized Generation In Large Model Era: A Survey Yiyan Xu, Jinghao Zhang, Alireza Salemi, Xinting Hu, Wenjie Wang, Fuli Feng, Hamed Zamani , Xiangnan He and Tat-Seng Chua arxiv.org/abs/2503.02614

[Findings] ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation Alireza Salemi, Julian Killingback Hamed Zamani arxiv.org/abs/2501.14956

[Findings] Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation Chris Samarinas , Alexander Krubner, Alireza Salemi, Youngwoo Kim and Hamed Zamani arxiv.org/abs/2501.03545

Glad to see a workshop on LLM Personalization at #EMNLP2025... An exciting research area and an interesting workshop program.

🇮🇹 We're presenting a tutorial on Retrieval-Enhanced Machine Learning (#REML) at #SIGIR2025! 🗓️Sunday July 13th | 9AM - 12:30PM 📌Donatello Floor 0 Details: retrieval-enhanced-ml.github.io/sigir-2025.html Fernando Diaz Andrew Drozdov Alireza Salemi Hamed Zamani SIGIR 2025