Elisa Nguyen

✨New preprint alert! Happy to share our latest research: "Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI" 📎arxiv.org/abs/2409.16978 Work with Johannes Bertram, @EKortukov, @jeanysong, @coallaoh 1/9

🚀 @ELLISInst_Tue will lead the AI development for Germany’s new open-source nationwide Adaptive Intelligent System (AIS) learning platform for schools – and we’re #hiring! We are part of a national consortium led by Assecor and @KImachtSchule, and mandated by the FWU. Join us to push the boundaries of #AI in education and build the core intelligence that will power adaptive learning for millions of teachers and pupils in real classrooms. We’re developing cutting-edge AI tutoring models, knowledge tracing, and recommendation systems to provide high-quality, personalised learning for all students—regardless of background. 🔹 Several full-time ML roles (2–3 years) 🔹 Top-tier AI research environment 🔹 From prototypes to production-ready solutions for national-scale impact 🔹 Open to on-site, hybrid & remote 👉 Apply now (quick & easy): forms.gle/XmLkwEDD45fY5c… (or via ais@tue.ellis.eu) We work closely with our amazing collaborators at Assecor, @KImachtSchule (@stes_io, @SchulzAuguste), Tübingen AI Center (@MatthiasBethge), the Hector Research Institute of Education Sciences and Psychology (Ulrich Trautwein), the Tübingen Center for Digital Education (Andreas Lachner) and the @IWMtue (@ucress). Let’s shape the future of AI-powered education together. 🔥 #AI #MachineLearning #EdTech #hiring #OpenSource #MLJobs

Very cool resource by @davidbau: NDIF. Hosted models larger than 50B dedicated to explainability research, both through web and API. See layer activation, run traces, change weights, all through NDIF. Neat! David said this really well: most interpability research is done on far from SoTA models, and this could solve that. docs.google.com/presentation/d…

Finally got the job ad—looking for 2 PhD students to start spring next year: gao-unit.com/join-us/ If comp neuro, ML, and AI4Neuro is your thing, or you just nerd out over brain recordings, apply! I'm at neurips. DM me here / on the app or email if you want to meet 🏖️🌮

I am on my way to #NeurIPS2025 in San Diego, crossing Greenland at the moment. I would love to meet anyone to just say hi or to discuss interesting ideas or to talk about positions and opportunities! Oh yes and I have a poster to present on Wed 11-14 about “rankability” in visual representations. But I wish to know more about what you have been up to. I want to know what everyone thinks as future paths for the community. Drop me a message and let’s schedule a chat/lunch etc!

Excited to present our work, Rethinking Approximate Gaussian Inference (AGI 🤯) in Classification, at #NeurIPS2025 in San Diego! Find out why you shouldn’t use softmax in (Gaussian) uncertainty quantification 😳 @ Exhibit Hall C,D,E, Poster #601 Thu 4 Dec 11 am - 2 pm.

Our paper on influence functions titled Better TDA via Better Inverse Hessian-Vector Products will be presented at #neurips25 San Diego on Friday from 4:30 PM - 7:30 PM in Exhibit hall C,D,E (Poster 3907) Work with my fantastic colleagues @_elinguyen, @Runshi_Yang , @juhan_bae, @SheilaMcIlraith, @RogerGrosse!

(I'm also graduating in fall/winter 2026, and interested to learn about both industry and academic opportunities!)

At NeurIPS SD to present this work led by @andrew_wang10! Come by poster 3907 Friday afternoon to learn more :) Please reach out if you want to chat about data attribution, human-centered XAI, social impacts of AI or anything else :)

@sarahcat21 Also up for a run! When and where? :)

Where can I find the betting pools on who will attend the most NeurIPS after parties?… Alas, I am no longer a contender. But hmu if you want to do a 7 AM run!

+++Startschuss für KI macht Schule Austria+++ Diesen Juli: KI macht Schule Austria gegründet! 🚀 Mit ersten Workshops in Wien, Salzburg und Innsbruck bringen wir KI-Bildung in Österreichs Schulen. 🏫🧑‍🏫 Mehr dazu: ki-macht-schule.at & sn.at/salzburg/polit…

@sanmikoyejo @SadhikaMalladi @coallaoh @baharanm After another very lively poster session, our final talk of the day from @coallaoh - who is talking about the interactions between ML, attribution, and humans!

@sanmikoyejo After some amazing contributed talks, we now have a panel moderated by @SadhikaMalladi - with @coallaoh @baharanm and Robert Geirhos!

@sanmikoyejo @SadhikaMalladi @coallaoh @baharanm Our second-last talk of the day - Robert Geirhos on “how do we make attribution easy?”

@sanmikoyejo @SadhikaMalladi @coallaoh @baharanm One great poster session (and lunch) later - @baharanm on data selection for large language models!

Next up, @sanmikoyejo on predicting downstream properties of language models!

Our first talk of the day @ ATTRIB 2024 (Rm 205-207): @SurbhiGoel_ on attributing model behavior using synthetic data!

Happening now!

Today, I'm giving a talk on Continual Foundation Model Learning at the Adaptive Foundation Models workshop @NeurIPSConf (adaptive-foundation-models.org) 🏠1 PM at Exhibit Hall A If you're interested in continual pretraining, flexible benchmarking, and more, please stop by!

I will be in ATTRIB workshop tomorrow (attrib-workshop.cc). Stop by if you’d like to chat with me and connect with other great researchers in this area.

Giving a talk tomorrow at #NeurIPS2024!