←
Faegheh Hasibi652 posts
Faegheh Hasibi avatar

Faegheh Hasibi

@fhasibi

Assistant Professor of Information Retrieval at Radboud University Mastodon account: @fhasibi@idf.social

◷ Joined January 2010▧ 36 Photos and videos
Krisztian Balog avatar
⟳ Faegheh Hasibi retweeted
Krisztian Balog@krisztianbalog·4 Jun 2024

Happy to share the revised and extended version of our book "User Simulation for Evaluating Information Access Systems" w/ ChengXiang Zhai arxiv.org/abs/2306.08550 (to appear in print at #sigir2024)

Thomas Kipf avatar
⟳ Faegheh Hasibi retweeted
Thomas Kipf@tkipf·17 Jan 2024

Very impressive result by @thtrieu_ et al @GoogleDeepMind. It takes an incredible amount of ambition and long-term commitment to land a project like this. I highly recommend watching @thtrieu_'s explainer video about AlphaGeometry: youtube.com/watch?v=TuZhU1Ci…

Introducing AlphaGeometry: an AI system that solves Olympiad geometry problems at a level approaching a human gold-medalist. 📐 It was trained solely on synthetic data and marks a breakthrough for AI in mathematical reasoning. 🧵 dpmd.ai/alphageometry

Harrie Oosterhuis avatar
⟳ Faegheh Hasibi retweeted
Harrie Oosterhuis@HarrieOos·13 Dec 2023

I am looking for a PhD candidate to work on machine learning for search systems! 👩‍🎓👨‍🎓 We offer a fully funded position, freedom in your research direction, great working environment and very friendly colleagues. You can apply here: ru.nl/en/working-at/job-oppo… RT is appreciated! 😄

Post attachment
Faegheh Hasibi avatar
Faegheh Hasibi@fhasibi·24 Jul 2023

Exited to share our group presence at #SIGIR2023. Also we five vacancies at all levels of assistant/associate/full prof (f/m) at our institute lnkd.in/e-g4sCC9 Come and talk to us online or in-person. #vacancy

We are excited to be at #SIGIR2023 next week! 🌞🇹🇼🏙️ Our group has six presentations this year, see the overview below. Come talk to us if you want to know more about our research, group or university and job openings! 😄

Post attachment
Amirkeivan Mohtashami avatar
⟳ Faegheh Hasibi retweeted
Amirkeivan Mohtashami@akmohtashami_a·28 May 2023

Introducing Landmark Attention! Our method allows #transformers to handle any inference context length, regardless of their training context length. This enables #LLAMA7B to process contexts with 32k+ tokens—just like #GPT4. Read our paper: arxiv.org/abs/2305.16300 🧵👇(1/3)