PhD Student @michigan_AI | Vision + NLP | Advocate for Inclusive AI
Ann Arbor, MI
Joined January 2019
- Tweets287
- Following3.5K
- Followers511
- Likes8.3K
Pinned Tweet
🌎 A dataset says it covers Spanish. But whose Spanish?
Spanish is spoken across Spain and much of Latin America, from Mexico to Argentina and beyond. Yet an NLP dataset labeled simply “Spanish” may contain data representing only a small subset of those countries.
Joan Nwatu retweeted
Excited to present AtlasNLP, led by @_agirlyengineer, at Poster Session D today 11-12:30, Hall H! 🌍 A collaborative effort mapping geographic representation in NLP datasets and where gaps remain.
#EMNLP2026
Joan Nwatu retweeted
We’re excited to share that Prof. Michael Wellman & PhD candidate Joan Nwatu @_agirlyengineer are among the panelists of the upcoming @UMich MICDE Fall ’26 “State of AI & Future of Institutions” event!
🔗micde.umich.edu/news-events/…
And a huge shoutout to the incredible team behind this work: @tsedeniya_amare , @Longju_Bai, Bontu Fufa Balcha, Zayd Bashir, @AnganaBorah2, Zara Burzo, Yubin Choi, @NaihaoDeng, @SamikaGupta, @michelfaloughi, @GmailKwizera , @ziqiao_ma, Cynthia Yacel Fuertes Panizo, @EllieSeehorn
Team cont'd: Hui Shen, Jiayi Tang, Zesen Zhao, @boyuan__zheng , and @radamihalcea 🎉.
AtlasNLP was a truly collaborative effort, and I am incredibly grateful for the ideas, iterations, and teamwork that brought it together. I am so happy to finally be sharing it with the world!
Joan Nwatu retweeted
🔔 We are pleased to announce that our Trustworthy AI for GOOD (AI4GOOD) workshop at #NeurIPS2026 has formed a strategic partnership with @SpringerNature 🎉
Participants will have the opportunity to publish their work in an archival proceeding under the LNCS series (print and online) with no additional fees.
To maintain flexibility, all submissions remain non-archival by default; the Springer proceeding is entirely optional.
📢 The deadline has been extended to September 1st, 2026 (AoE)
More details and submission → trustworthy-ai-for-good.gith…
We are looking forward to your submissions!
@VectorInst @JinesisLab @EuroSafeAI @MPI_IS @UofTCompSci @TorontoSRI @CIFAR_News @ELLISInst_Tue @UMichCSE @michigan_AI @Harvard @ETH_en @CarnegieMellon @UniofOxford @NeurIPSConf @UofT
We are so excited to host the 2nd edition of the Trustworthy AI for Good (AI4GOOD) Workshop at #NeurIPS2026 in Paris, France 🇫🇷
We aim to bring together the AI safety, AI for social good, and AI policy/governance communities to connect what models can do as individual systems with what they do when deployed across populations.
For full details, welcome to visit our website at:
🔗 trustworthy-ai-for-good.gith…
📍December 12, 2026 · Paris 🇫🇷
We have an amazing lineup of speakers and plans. More details 🧵
Joan Nwatu retweeted
🌟 We’d love to welcome you as a reviewer for the 2nd Trustworthy AI4GOOD Workshop at #NeurIPS2026 in Paris! 🇫🇷
Following the success of our first edition at #ICML2026, this workshop will once again bring together researchers and practitioners working to ensure that advances in AI are not only powerful, but also trustworthy, responsible, and genuinely beneficial to society.
Each reviewer will be assigned no more than 3 papers through OpenReview, with no paper bidding or rebuttal phase.
🗓️ Review period: September 2026
⏰ Review deadline: September 22, 2026, AOE
Please make sure your OpenReview profile is up to date before registering.
Join us as a reviewer:
forms.gle/HpkPoE8HqMHH1geL9
We’d be delighted to have you help shape this year’s workshop! 🎉
#AI4GOOD #TrustworthyAI #NeurIPS #AISafety
Joan Nwatu retweeted
🎉 With the successful conclusion of our 1st Trustworthy AI4GOOD workshop at #ICML2026, we are delighted to share that its 2nd edition has been accepted for #NeurIPS2026 in Paris! 🎉🇫🇷
The workshop selection process was highly competitive: only 22% of 454 workshop proposals were accepted. We are grateful for the opportunity to bring the community together again! 🙌
Paris, here we come! 🇫🇷
ICML speakers: @Yoshua_Bengio, @OanaIgnatRo, @jzl86, @maksym_andr, Jenny Ni and @NamGoPro.
Panel: @MilindTambe_AI, @lrhammond, Gopal Sarma and @ARGleave.
Organizers: @TerryJCZhang, @ZhijingJin, @radamihalcea, @MilindTambe_AI, David Lie, @_agirlyengineer, @davidguzman1120, @ChanglingXavier, @Jerick1380, Prakhar Gupta, @vantru0ng, @EttoreGran, He (Shawn) Shuang, @ozzaney0101, Kexin Li and Wenjun Qiu.
Thank you for making our first edition unforgettable!🙏
Thank you for making AI4GOOD possible! 💙
trustworthy-ai-for-good.gith…
Joan Nwatu retweeted
Excited to share that our paper has been accepted to COLM 2026!
LLM safety isn’t only about the final prompt. Path matters.
We introduce ICD, a trajectory-based jailbreak strategy showing how small continuations can progressively weaken safety.
Paper: arxiv.org/abs/2604.25921
Joan Nwatu retweeted
Just arrived at ICML 2026 in Seoul! 🇰🇷
Come say hi, especially if you're interested in Equitable AI, Multimodal AI, AI for Social Good, or Mentorship. Coming from an ACL/NLP background, I'm excited to exchange ideas and learn from new perspectives.
On July 10th, I'll be sharing my work at the intersection of Multimodal AI and AI for Social Good, together with a broader vision for Equitable AI.
One idea that has shaped both my research and my own journey is:
**Talent is universal, opportunity is not.**
The truth is that today's AI often reflects existing inequalities.
Representation isn't just about fairness, though..
It's also about who feels seen, who feels capable, and who feels invited to shape the technology and the future.
When some voices are missing, our data becomes incomplete.
Incomplete data leads to biased AI.
Biased AI creates unequal opportunities, which means the same voices continue to be left out.
That's the cycle we need to break.
And I believe breaking that cycle is one of the greatest opportunities in AI research today.
Thank you to the organizers, Terry J. C. Zhang and Zhijing Jin!
Joan Nwatu retweeted
I'll be at #ACL2026 presenting this work, I'd love to connect and discuss research directions in human-centered NLP, societal impacts of AI, and safety risks of language models in mental health interactions. Lately, I’ve also been interested in how AI agents will impact the future of work and how we can center worker well being in human-AI collaboration.
Come check out our poster!
🗓 Mon, July 6 at 9am
📍 Poster Session D
📢 Can language models assist public health experts in uncovering new opportunities for prevention?
Excited to share our recent work: Supporting Intervention Design for Suicide Prevention with Language Model Assistants ✨
📄arxiv.org/abs/2508.18541
🔗dill-lab.github.io/intervent…
1/n
Joan Nwatu retweeted
📢 Excited for the launch of the new online course, Realizing #AI for Social Impact taught by @BondiElizabeth!
Discover how AI can drive positive social change while exploring the algorithmic, practical, & ethical challenges of developing responsible AI.
online.umich.edu/series/real…
Joan Nwatu retweeted
TODAY — Week 2 of the Grad School Series 2026 🎓
The Application Process starts at 5 pm WAT.
Register here if you haven't: briefen.me/grad-school-serie…
