Tensor Product Attention Is All You Need, NeurIPS 2025 Spotlight
Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment, ICML 2025
Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts, ACL 2025 Findings
Augmenting Math Word Problems via Iterative Question Composing, AAAI 2025
Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks, ICLR 2025 Spotlight
Cumulative Reasoning with Large Language Models, Transactions on Machine Learning Research (TMLR)
SEAL: Simultaneous Label Hierarchy Exploration and Learning, TMLR
Information Flow in Self-Supervised Learning, ICML 2024
Matrix Information Theory for Self-Supervised Learning, ICML
Background
PhD student at Princeton University, focusing on building scalable and capable large language models (LLMs)
Research interests include improving LLM reasoning, developing new attention mechanisms and model architectures, and aligning model behavior with human preferences via general preference models
Former visiting researcher at UCLA AGI Lab
Top Seed researcher with the Seed LLM (Foundation Model) Team, working on LLM pretraining and scaling
Currently seeking Summer 2026 internship or residency opportunities at industry AI labs