Qijia He (何其佳)

Selected Research

LLM / VLM

DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision Qijia He, Zequn Li, Spencer Luo, Tianle Chen, Pradyumna Narayana, Zixian Ma, Ranjay Krishna, Lan Nie, Sugato Basu Preprint, 2026 [Paper] [Project Page] [Code]

DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents Tianle Chen, Pushkar Singh, Ketan Todi, Biswajit Paria, Qijia He, Wenqi Wang, Yuwen Tan, Jike Zhong, Sugato Basu, Deepti Ghadiyaram, Arjun Akula Preprint, 2026 [Paper]

Agent Capability Shapes the Value of Post-Training Data Jiayi Cheng, Yunshu Wu, Chenqian Le, Qijia He, Runhao Li, Michael Yue, Xupeng Chen, Michal Mankowski Preprint, 2026

Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence Chenqian Le, Jiayi Cheng, Qijia He, Runhao Li, Yinghao Li, Xupeng Chen Preprint, 2026 [Paper]

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Zhongzheng Ren, Dan Weld, Ranjay Krishna NeurIPS 2026 (Evaluations & Datasets Track) [Paper] [Project Page] [Code]

ARCHER: Adaptive Recovery Routing with Conformal-risk Calibration for Coding Agents Qijia He, Jiayi Cheng, Chenqian Le, Rui Wang, Xunmei Liu, Yixian Chen, Jie Mei, Zhihao Wang, Xupeng Chen, Yuhuan Chen, Tao Wang Efficient Reasoning @ COLM 2026 Spotlight [Paper] [Code]

Rethinking Human Preference Evaluation of LLM Rationales Ziang Li, Manasi Ganti, Zixian Ma, Helena Vasconcelos, Qijia He, Ranjay Krishna XLLM-Reason-Plan @ COLM 2025 Best Paper Award (Honorable Mention) [Paper]

Causal Inference

Dealing with positivity violations in mediation analysis via weighted controlled effects Qijia He, Bo Zhang arxiv, 2026 [Paper] [Code]

Role of placebo samples in observational studies Ting Ye, Qijia He, Shuxiao Chen, Bo Zhang Journal of Causal Inference, 2025 [Paper] [Supplement]

Generalizing the Intention-to-Treat Effect of an Active Control from Historical Placebo-Controlled Trials Qijia He, Fei Gao, Oliver Dukes, Sinead Delany-Moretlwe, Bo Zhang Journal of the American Statistical Association, 2024 [Paper] [Supplement]

Estimating individualized treatment rules by optimizing the adjusted probability of a longer survival Qijia He, Shixiao Zhang, Michael L LeBlanc, Yingqi Zhao Statistical Methods in Medical Research, 2024 [Paper] [Supplement]

Industry Experience

Google, New York, NY
Research on on-policy distillation in LLMs

TikTok, Bellevue, WA
Worked on agentic AI systems for e-commerce applications

Apple, Cupertino, CA
Worked on causal machine learning methods for ads marketplace

Teaching Experience

• STAT 311 Elements of Statistical Methods (Winter 2024, Autumn 2025)
• STAT 513 Statistical Inference (Winter 2026)
• STAT 435 Introduction to Statistical Machine Learning (Spring 2026)

Tutor in Mathematical analysis (Fall 2018)

Teaching Assistant in primary-school Olympiad Mathematics (2017-2018)

• Rated S (top 5% performance)