News
All updates, newest first.
2026
- I joined Ai2 as a research intern (PhD) in Seattle, hosted by Dr. Bodhisattwa Majumder, Dr. Ashish Sabharwal and Dr. Peter Clark.
- We introduce ContextRL, a context-aware RL objective that rewards models for selecting the context that supports an answer, improving long-horizon agentic and multimodal reasoning by +2.2% and +1.8% over standard GRPO.
- I passed my general exam and am officially a PhD candidate! Huge thanks to my amazing advisor and committee: Karthik Narasimhan, Danqi Chen, and Zhuang Liu.
- Humanline has been accepted to ICLR 2026. See you in Rio!
2025
- Received the generous Tinker teaching grant to support our undergraduate Introduction to NLP course.
- Received the Tinker research grant ($5,000) to support our research on post-training algorithms.
- We introduce Humanline as a simple yet surprisingly effective design to close the online-offline alignment gap across multiple model families (Llama-3, Gemma-2) and model sizes (1.5B-27B) on both instruction-following and mathematical reasoning.
2024
- The Amazon Nova Family of Models have been released.
- Our work on LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints has been accepted by EMNLP 2024 and also NeurIPS System 2 Reasoning Workshop. See you in Miami!
- I started my PhD journey at Princeton University.
2023
- Our work on Aligning Dialogue Model Behavior with Guidelines has been accepted by EMNLP 2023.
- Our paper on Towards Credible Human Evaluation of Open-Domain Dialog Systems Using Interactive Setup has been accepted to AAAI2023 (oral and poster), NeurIPS HEGM (oral) and EMNLP GEM (oral).
- I presented work on interactive human evaluation of open-domain dialog systems at AAAI main conference 2023, NeurIPS Workshop on Human Evaluation of Generative Models 2022 and EMNLP Workshop on Generation, Evaluation & Metrics (GEM) 2022.
2022
- Our work on improving bot response contradiction detection has been accepted by SigDial 2022.