iiinova — where your digital self keeps evolving

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Shoutout to our incredible organizing team for yet another successful workshop @prakharg.bsky.social, @zeyutang.bsky.social, @adoubleva.bsky.social, Miriam Rateike, Jamelle Watson-Daniels, Golnoosh Farnadi, @jessicaschrouff.bsky.social, @sanmikoyejo.bsky.social

031

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Thank you to our amazing roundtable leads Francielle Vargas, Yatong Chen, Andreas Haupt for great discussions!

010

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Thank you to our amazing speakers @markriedl.bsky.social, Furong Huang, Isabela Albuquerque!

010

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

That’s a wrap for #AFAA2026!!! 🎉 Thank you to all the authors, attendees, roundtable leads and speakers for the great presentations and insightful discussions! 1/4

410

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Now: panel with our amazing speakers

010

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs

010

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations

000

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

For our afternoon spotlights, we have 3 talks by Seraphina Goldfarb-Tarrant (Cohere), Edie Pearman (Mila, McGill University), and Canyu Chen (Northwestern University)

210

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Back from lunch, we have our third and final invited talk of the day. Excited to have Professor Furong Huang from University of Maryland talk about "Rethinking Test-Time Thinking: From Token-Level Rewards to Robust Generative Agents"

110

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Next up, we three roundtable discussions: - Fairness via Interpretable Alignment led by Francielle Vargas - Fairness under Strategic Interaction in Agentic Systems led by Yatong Chen - Fairness in Preference Learning and Incentive Design led by Andreas Haupt

020

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Next up, we have our second invited talk by Isabela Albuquerque from Google DeepMind on "From Pixels to Actions: A Roadmap for Evaluating Safety in Multimodal Agents"!

110

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies

010

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

When AI Describes Race? Unveiling Racial Bias in Vision-Language Models in Brazilian People

110

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Moral Preferences of LLMs Under Directed Contextual Influence

100

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Now, for our morning spotlights, we have 3 talks by Phil Blandfort, Leodécio Braz da Silva Segundo, and Megan Smith

110

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

For our first invited talk of the day, we have Professor Mark Riedl @markriedl.bsky.social from Georgia Tech on "Reasoning, Alignment, and Explainability" #AFAA2026

151

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 26/04/2026

Excited for #AFAA2026 workshop at #ICLR2026 today 🎉 Join us for a full day of discussions on Fairness across alignment procedures and agentic systems! - 3 invited talks - 3 roundtables - 1 panel - 6 spotlights - 36 posters 📍Starting at 9am in Room 211, Riocentro Center

111

AFAA 2026 @ ICLR @afciworkshop.bsky.social · 22/04/2026

✈️ Happy #ICLR2026 week! ⏰ Join us on Sunday for the Algorithmic Fairness workshop #AFAA2026! We have an exciting program, with amazing talks/roundtables/papers and lots of time for discussions! 🔥 Schedule: afciworkshop.org/schedule 📆 April 26, 2026 📍 Room 211

020