AFAA 2026 @ ICLR

#AFAA2026 #ICLR2026 | @zeyu1tang @prakhar_24 @adoubleva @miriamrateike @jamelleWD @gfarnadi @JessicaSchrouff @sanmikoyejo

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

Takeaways from the panel

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

Now: panel with our amazing speakers

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

@furongh

[AFAA 2026 @ ICLR @afciworkshop]

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"

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

@isabela_alb

[AFAA 2026 @ ICLR @afciworkshop]

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"!

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

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

[AFAA 2026 @ ICLR @afciworkshop]

@mark_riedl

[AFAA 2026 @ ICLR @afciworkshop]

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