Schedule

09:00 AM-10:15 AM: Poster Session I

• Designing AI for Meta-Expertise in Regulatory Drafting (Dan Bateyko)

• Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality & Uncertainty (Valia Efthymiou, Chara Podimata, Diptangshu Sen, Juba Ziani) [paper]

• Centralization vs Decentralization in Hiring and Admissions (Benjamin Fish, Diptangshu Sen, Juba Ziani) [paper]

• Fairness in Strategic Learning: Understanding disparate effects of partial information (Srikanth Avasarala, Serena Wang, Juba Ziani) [paper]

• Online Learning for Dynamic Service Mode Control (Wenqian Xing, Yue Hu, Anand Kalvit, Vahid Sarhangian) [paper]

• Interpretable, Explorable, and Controllable Recommendation with SAE Concepts (Kenny Peng, Erica Chiang, Sophie Greenwood, Jon Kleinberg, Nikhil Garg)

• Human-AI Collaboration with Misaligned Preferences (Jiaxin Song, Parnian Shahkar, Kate Donahue, Bhaskar Ray Chaudhury)

10:45 AM-12:00 PM: Poster Session II

• User Altruism in Recommendation Systems (Ekaterina Fedorova, Madeline Kitch, Chara Podimata) [paper]

• Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents (Shayan Kiyani, George Pappas, Aaron Roth, Hamed Hassani) [paper]

• The Impact of Precision of Algorithmic Advice on Human Sequential Decision-Making (Philippe Blaettchen, Wichinpong Park Sinchaisri)

• Learning on the Go: How Gig Workers Learn with Algorithmic Recommendations (Shunan Jiang, Wichinpong Park Sinchaisri)

• Aligning Rational Superintelligences through Debate: A Game-Theoretic Framework (Thanawat Sornwanee)

• Strategic Selection and Manipulation in Imperfect Risk Models (Jivat Neet Kaur, Divya Shanmugam, Emma Pierson, Michael I. Jordan, Serena Wang, Ahmed Alaa)

• Direct Alignment with Heterogeneous Preferences (Ali Shirali, Arash Nasr-Esfahany, Abdullah Alomar, Parsa Mirtaheri, Rediet Abebe, Ariel Procaccia) [paper]

• Tokenized Bandit for LLM Decoding and Alignment (Suho Shin, Chenghao Yang, Haifeng Xu, Mohammad T. Hajiaghayi) [paper]

• Deliberation Markets: Incentivizing Human-AI Collective Reasoning in Natural Language (Siddarth Srinivasan, Ezra Karger, Michiel Bakker, Yiling Chen) [paper]

Accepted posters whose authors can't attend:

• MultiScale Contextual Bandits for Long Term Objectives (Richa Rastogi, Yuta Saito, Thorsten Joachims) [paper]

• CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models (Son The Nguyen, Niranjan Uma Naresh, Theja Tulabandhula) [paper]

• Topic Labeling Using Large Language Models (Olga Bogachek)

• Relying on the Metrics of Evaluated Agents (Serena Wang, Michael I. Jordan, Katrina Ligett, R. Preston McAfee) [paper] [poster]