Sajad Ebrahimi

We are going to see the need for emergency reviewers vanish very soon. And a while after that? Human reviewers might just be completely obsolete!

DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities Sajad Ebrahimi, Nima Jamali, Bardia Shirsalimian, Kelly McConvey, Wentao Zhang, … arxiv.org/abs/2606.04205 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙻𝙶 𝚌𝚜.𝚂𝙳]

A huge thanks to my amazing co-authors: @UnderdogGeek , @NegarEmpr , @StevenYuan666 , @Haolun_Wu0203 , @FattaneZ , and @ebrahim_bagheri for the incredible collaboration on this research. Check out our implementation on GitHub: github.com/sadjadeb/Diffu…

5/ 📈 Key benefits: ✅ Learns a more robust relevance estimation function by modeling the joint distribution over features + labels ✅ Matches inference cost of discriminative models ✅ Outperforms discriminative baselines on standard LTR datasets in our experiments.

Excited to announce that our paper “From Noise to Order: Learning to Rank via Denoising Diffusion” has been accepted to #ICTIR2026! 🎉📚 📄Paper: arxiv.org/pdf/2602.11453 💻 Code: github.com/sadjadeb/Diffu…

1/ 🎉PeeriScope from Reviewer.ly has been accepted @TheWebConf! How good is your review? Drop your review, or paste an OpenReview URL and it tells you how good the review is, across 13 dimensions. Try it now 👇 🔗 app.reviewer.ly/app/peeriscope 📜arxiv.org/html/2604.2407…

1/ Excited to share that PeerPrism from Reviewer.ly has been accepted at #SIGIR2026 A benchmark for reality of today’s peer review, where reviewers draft the reviews, LLMs refine it, and “was this written by AI?” is no longer a yes/no question. arxiv.org/abs/2604.14513

I’ve been dreaming of my first @ACMSIGIR since I became a student. Seems the universe has other plans: 📍 2024 (Washington DC) 🚫 Travel Ban 📍 2026 (Melbourne) 🚫 Travel Ban 📍 2027 (Silicon Valley) 🚫 Travel Ban It looks like I’ll have to wait until 2028😮‍💨. #SIGIR

Trending on Hacker News rn. slate.com/technology/201…

Thrilled to share that I successfully defended my M.A.Sc. thesis! Grateful to my supervisors(@FattaneZ and @ebrahim_bagheri) and committee for their support and insightful feedback. 🎓

Now the time for our second keynote speaker, Johanne Trippas @JTrippas, sharing her perspective on “Conversational Information Systems for a Proactive Future: Beyond Ten Blue Links” in our ProActLLM workshop. #proactllm @cikm2025

Earlier today, we had a very successful panel discussion on proactive conversational information seeking with active discussions from both panel members and audience. Thanks to the panel members for their support: @ppsunrise @NegarEmpr @ydeng_dandy @merrafelice @ChuanMg

I’ll be presenting our work “Conv2Title: A Conversation-to-Title Framework for Proactive Search in Conversations” at the Proactive LLMs Workshop (ProActLLM) today @cikm2025 at 11:00, and I’ll be on the panel discussion at 11:30. Details: proactllm.github.io #CIKM2025

#AI researcher @imsure318 helped organize today's Workshop on Proactive Conversational Information Seeking with Large Language Models (#ProActLLM) that's co-located with #CIKM2025 bloom.bg/43mOW6D #LLMs #GenAI #NLProc #InformationRetrieval #HCI #HumanComputerInteraction

I’ll be on the Panel Discussion at the Proactive LLMs workshop today at 11:30 @cikm2025 ! 🤖 We’ll be talking about when models should take initiative, how to ground their actions, and what the future of proactivity looks like. Details: proactllm.github.io #CIKM2025

The final program of the ProActLLM is up! 🎉 Check it out at proactllm.github.io Join us at #CIKM2025 (Friday, Nov 14th - Room 205B) for keynotes, talks, and a lively panel on proactive conversational info seeking with LLMs. #ProActLLM @cikm2025 @wangxieric @ShubhamC526

Today I’ll be presenting our paper "RottenReviews: Benchmarking Review Quality with Human and LLM-Based Judgments" at @cikm2025 , Room 209B, 4 PM session. Come by to chat and learn more! #CIKM2025