News
- Aug 2026Starting as a Student Researcher at Google DeepMind with Ankit Anand.
- Jul 2026I will be attending ICML 2026 in Seoul, Korea.
- Jun 2026automating-discovery is live...
- Jun 2026Learning the ARTS of Search for Automated Discovery is out on arXiv, with a project page from automating-discovery.
- Jun 2026Adversarial Training for Process Reward Models accepted to ICML 2026.
- Jun 2026Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable accepted to ICML 2026.
- Jun 2026Tournament Style RL: Stabilizing Policy Optimization on Non Verifiable Problems accepted to ICML 2026.
- Dec 2025I will be attending NeurIPS 2025 in San Diego.
- Jun 2025Our work on multi-agent negotiation under privacy constraints is on arXiv.
- Apr 2025I will be interning at Google DeepMind in Mountain View.
- Nov 2024I will be attending EMNLP 2024 in Miami.
- Sep 2024I joined UCSB as a PhD student, advised by Prof. William Wang.
- Apr 2024New paper on solving complex reasoning with a society of models.
- Feb 2024Presented our paper at AAAI 2024, Canada.
- Dec 2023Prompt-Propose-Verify accepted as an oral at the AAAI workshop AI for Digital Human.
- Dec 2023Presented my poster at EMNLP 2023, Singapore.
- Nov 2023Awarded a Microsoft Research Travel Grant and a Diversity and Inclusion Award for EMNLP 2023.
- Oct 2023UniPrompt accepted as a spotlight at the NeurIPS workshop R0-FoMo.
- Oct 2023DaSLaM accepted at EMNLP 2023 Main.
- Aug 2023Reviewing for EMNLP 2023.