Sayash Kapoor

5 papers · 2018–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 👥 Mega-Team · Squad

Venues

ICML (4) IJCAI (1)

Top co-authors

Arvind Narayanan (3) Shayne Longpre (3) Percy Liang (3) Peter Henderson (3) Rishi Bommasani (3) Kevin Klyman (3) Rumman Chowdhury (2) Seth Lazar (2) Borhane Blili-Hamelin (2) Yacine Jernite (2)

Research topics

Artificial Intelligence (4) Core AI (4) Computer Science (1) Interdisciplinary (1) Machine Learning (1) Application Areas (1) Applications (1) Social (1)

Keywords

safe harbor (2) red teaming (1) societal impact (1) filter bubble (1) ai evaluation (1) news personalization (1) constrained bandit (1) balanced news (1) content polarization (1) jailbreak (1) account suspensions (1) legal reprisal (1) coordination (1) agent advocates (1) choice (1) individual autonomy (1) platform agents (1) surveillance (1) user-controlled agents (1) accountability (1)

Papers

Position: Build Agent Advocates, Not Platform Agents ICML 2025 Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI ICML 2025 Position: A Safe Harbor for AI Evaluation and Red Teaming ICML 2024 Position: On the Societal Impact of Open Foundation Models ICML 2024 Balanced News Using Constrained Bandit-based Personalization IJCAI 2018