AFAA 2026 @ ICLR

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

Shoutout to our incredible organizing team for yet another successful workshop @prakhar_24 , @zeyu1tang , @adoubleva , @miriamrateike , @JamelleWD , @gfarnadi , @JessicaSchrouff , @sanmikoyejo

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

Takeaways from the panel

Thank you to our amazing roundtable leads @franavargas, @YatongChen, @andreas_h0wpt for great discussions!

Thank you to our amazing speakers @mark_riedl , @furongh, @isabela_alb

Now: panel with our amazing speakers

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

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

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

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

Next up, we three roundtable discussions: - Fairness via Interpretable Alignment led by @franavargas - Fairness under Strategic Interaction in Agentic Systems led by @YatongChen - Fairness in Preference Learning and Incentive Design led by @andreas_h0wpt

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

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

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

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

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