Ofra Amir retweeted
I am flying to @COLM_conf to present STATe-of-Thoughts (arxiv.org/pdf/2602.14265) along with @trsaenger , @GiladMorad12 , and @amir_feder .
We are presenting our poster on Thursday, October 8th, at the Imperial Ballroom #9 between 2 and 4 PM.
Github: github.com/zbambergerNLP/staโฆ
ื ืืกืืชื ืืืจืื ืื'ืืคืืื ืืืืฆืจ ืืืจืื ืขืืืจ ืืืื ืืืจืืงืื... ืืฉื.
Check out our new preprint introducing on STATe-of-thoughts, a new approach supporting diversity, controllability and interpretability in LLMs. Led by @ZacharyBamberg1 and @trsaenger
This Post is from a suspended account. Learn more
Our paper From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL was accepted to AAMAS 2026: arxiv.org/abs/2503.10509 (led by @saharad1)
We study how to explain reinforcement learning policies at a global level by summarizing agent behavior patterns
Ofra Amir retweeted
The Explainable AI workshop is underway at @IJCAIconf . Elisabeth Andrรฉ kicks it off with her keynote on counterfactuals, semi-factuals and alter-factuals, channelling Robert Webb from Peep Show
Ofra Amir retweeted
Sahar Admoni on the using LLMs to help with summarising reinforcement learning agent behaviour. Very promising results!
Ofra Amir retweeted
ืืฉืืืข ืืชืงืืื ืืืจืืข ืืคืชืืื ืฉื ืืืืช ืืืขื ืืงืืื ืืฆืื ืืืื ืืื, ืขื ืืจืฆืื ืืจืชืงืช ืฉื ืืืขื ืืืืจืืง @Liad_Mudrik.
ืจืืฆืื/ืืช ืืขืฉืืช ืชืืืจ ืืืืืื ืืืฉืื ืืืขื ืื ืชืื ืื ืขื ืืืขื ืืงืืื ืืฆืื? ืืืจืฉืื ืืขืืฆืืื!
dds.technion.ac.il/he/prograโฆ
@yoed_kenett @ofraam @roireichart
Ofra Amir retweeted
Applications for two postdocs in my lab at Uni of Queensland close next Wednesday (Australian time). We are pioneering new techniques in human-centered decision support. If you want to join the ride or know someone who may be suitable, details are below๐
I'm hiring! Two postdoctoral research fellows at @UQ_News (Brisbane, Australia), to pioneer human-centered decision support in collaboration with @UQMedicine.
Post 1๏ธโฃ Human factors, HCI, or psychology
Post 2๏ธโฃ Human-centered machine learning
Details: uqtmiller.github.io/recruitmโฆ
If youโre at AAAI, Yotam Amitai will be presenting our work (led by Yotam and Yael) on contrastive counterfactual explanations for reinforcement learning agents at the humans & AI session, today, 3:45pm. #AAAI24
arxiv.org/abs/2312.11118
Ofra Amir retweeted
ืืืจืฉืื ืืืื ืืื ื ืคืชืื, ืืืืชื ืื ืืืจืฉืื ืืืืืืจ ืืฉื ื ืฉื ืืืืช ืืืขื ืืงืืื ืืฆืื ืืชืืืจ ืืื ืืกืช ื ืชืื ืื ืืืืืข! ืืฆืืจืคื ืืืื ื ืืชืืืจ ืืจืชืง ืืืืืช ืืืืข ืืืื ืืกื ืืืฉืื ืืืขื ืื ืชืื ืื ืขื ืืืขื ืืงืืื ืืฆืื. ืืคืจืืื ื ืืกืคืื: dds.technion.ac.il/he/prograโฆโฆ
@yoed_kenett
@ofraam
@roireichart
Ofra Amir retweeted
We are seeking to hire a passionate and skilled Lead Software Developer for a new and exciting project on human-aware AI for cybersecurity. This is a full time position at BGU @bengurionu . More details at dropbox.com/scl/fi/gpquvaj53โฆ
Ofra Amir retweeted
What's going on with the AI ethics community and the Israel/Hamas war? An article at @VentureBeat by @sharongoldman dives into this painful twitter war. I was interviewed along with @yoavgo, @DanKotliar, @JulesPolonetsky, @TaliaRinger, and others >>
venturebeat.com/ai/ai-communโฆ
Ofra Amir retweeted
Important message from the presidents of Israeli universities. The shameful response of the top US universities seeing the brutal terror actions by Hamas as "one more event" is unforgiven. You're totally disoriented @Harvard @MIT @Stanford @nyuniversity #HamasisISIS
I'm recruiting PhD students through the ELLIS PhD program this year to work on explainable AI and human-AI interaction. The application deadline is Nov 15. Feel free to reach out if interested
The portal is open: Our #ELLISPhD Program is now accepting applications! Apply by November 15 to work with leading #AI labs across Europe and choose your advisors among 200 top #machinelearning researchers!
#JoinELLISforEurope #PhD #PhDProgram #ML ellis.eu/news/ellis-phd-progโฆ