I will be at @neuripsconf.bsky.social in San Diego this week! Please reach out if you'd like to chat about interpretbaility, multiplicty, diversity and reliability in AI systems.
Two weeks left! Submit a 1-page overview for our AAAI “Perspectives from the Community” session alongside the workshop on the Rashomon Effect (Jan 27, 2026) ✨ Selected contributors will give 5–15 min talks.
Deadline Nov 30
➡️ forms.gle/h4Dj2MfVqYpa...
#AAAI26 #MLResearch #Uncertainty
🎉 Our paper "ElliCE: Efficient & Provably Robust Algorithmic Recourse via Rashomon Sets" is a Spotlight at #NeurIPS2025!
We provide a tool for fast, certifiably robust, and actionable recourse under model uncertainty.
📄 openreview.net/pdf?id=GNDgQ...
We’re extending the deadline by one week! 🔁
Now due October 22nd.
Alongside the main track, we welcome previously published and position papers!
#AAAIworkshop #modeluncertainty #uncertainty #modelmultiplicity
✔️ We show it achieves state-of-the-art accuracy on large expert-annotated EEG data, while also giving visual & channel-level explanations that neurologists prefer.
🧠 ProtoEEG-kNN is a model that detects interictal epileptiform discharges (IEDs) and explains its predictions by comparing an input EEG to training EEGs with similar morphology & spatial distribution.
🚀 Excited to share our new MICCAI ’25 paper “This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN”!
📍 Dennis will be presenting this today at #MICCAI2025 in Korea — if you’re around, stop by the poster!
🔗 papers.miccai.org/miccai-2025/...
💬 Our Perspectives from the Community session invites short talks on the Rashomon Effect, uncertainty & multiplicity, plus reflections on career paths, research directions & open problems.
📄 1-page overview due Nov 30 👉 forms.gle/h4Dj2MfVqYpa...
Organized alogside amazing team #ChudiZhong @haydeninplainsight.bsky.social #LucasMonteiroPaes #VarunBabbar
👉 The workshop features policy, applications, theory, and generative AI alongside the Rashomon Effect. 💡 We invite new research, position papers, and contributions from diverse perspectives.
🚀 Call for Papers!
Navigating Model Uncertainty & the Rashomon Effect (AAAI 2026, Singapore) welcomes work on model multiplicity in trustworthy AI.
📅 Submission Deadline: October 15, 2025
🔗 Call for papers: sites.google.com/view/rashomo...
✋ Volunteer to review: forms.gle/D8J1BWAfMbuN...
Biorxiv link: www.biorxiv.org/content/10.1...
New preprint! We identified distinct immune profiles in people with HIV on ART, linked to CD4:CD8 ratio (a key marker of immune recovery). Our work reveals potential new targets for therapies to improve immune function. Check out how a dimension reduction tool, PaCMAP, helped uncover these insights!
Reminder: The #FAccT2025 submission deadlines are roughly one month away! Abstracts are due January 15th and full papers on January 22nd. See the full CfP here: facctconference.org/2025/cfp
I am recruiting Ph.D. students this cycle to join my new lab at Rutgers CS! Please apply if you want to work with me on Trustworthy and Responsible ML topics.
📅 Deadline: January 1, 2025
🌐 Details: lesiasemenova.github.io
If you’re attending #NeurIPS2024, I’d be happy to chat!
Organizing alongside amazing @chhaviyadav.bsky.social #SurajSrinivas #ValentynBoreiko #BityaNeuhof
#MichalMoshkovitz #VinayakAbrol #DotanDiCastro #KamalikaChaudhuri
#NaveFrost #HimaLakkaraju
🌟 Excited about interpretability? Join us on Sunday, Dec 15, in East Ballroom A,B for the Interpretable AI Workshop at @neuripsconf.bsky.social!
🎙️ Keynotes: Cynthia Rudin, Rich Caruana, Jiaxin Zhang, Tong Wang, Neel Nanda
💡 Panel Discussion + Contributed Talks
☕ Poster Sessions & Coffee Breaks
Excited to share our work on model simplicity next week at @neuripsconf.bsky.social! If you’re attending NeurIPS and would like to chat, feel free to reach out — I’d love to connect!
I tried to find everyone who works in the area but I certainly missed some folks so please lmk...
go.bsky.app/BYkRryU
For those interested in ethical implications of AI, as well as work on Responsible and Trustworthy AI - here is a starter pack (non-exhaustive) to help find out more or connect with colleagues go.bsky.app/RnucJWZ
