Research

My long-term goal is to build AI systems that remain faithful and useful under uncertainty: systems that can detect unsupported claims, localize what should be changed, allocate computation to uncertain parts of a reasoning trace, and act safely in long-horizon environments. I approach this through a bridge between diffusion-based generation/editing and agent evaluation/training.

In diffusion language modeling, I study how non-autoregressive models can use their ability to infill and revise arbitrary spans for faithful summarization, reasoning templates, and efficient inference. In agents, I study how realistic environments, verifiers, and harnesses can make training and evaluation match the way agents are actually deployed.

News

• Aug 2026: Detect, Remask, Repair was accepted to EMNLP 2026 Main Conference!
• Jul 2026: OpenForgeRL is on arXiv, and the code has been released.
• Jul 2026: Rethinking Reasoning with MDLMs was accepted to COLM 2026!
• Jun 2026: Continuing at Columbia CS as a Research Staff Associate in Prof. McKeown's group on faithful summarization.
• Jun 2026: OSWorld 2.0 is on arXiv with the project website released.
• 2024: Our question rewriting work was accepted to EMNLP 2024!

Selected Papers & Projects

	Detect, Remask, Repair: Diffusion Editing for Faithful Summarization of Evolving Contexts Hao Zou, Zachary Horvitz, Chandhru Karthick, Zhou Yu, Kathleen McKeown EMNLP 2026 Main Conference arXiv / bibtex A diffusion-based framework for localized faithfulness repair: detect unsupported spans in an existing summary, remask them, and repair only the unreliable content instead of fully regenerating the summary.
	OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks Large collaborative project Under review, NeurIPS 2026 project page / arXiv / pdf A benchmark of 108 long-horizon computer-use workflows and 31 self-hosted websites for evaluating realistic GUI agents, including streaming interaction, dynamic environments, cross-source reasoning, implicit-state inference, multimodal editing, and safety-oriented checks.
	OpenForgeRL: Train Harness-native Agents in Any Environment Xiao Yu, Baolin Peng, Ruize Xu, Hao Zou, Qianhui Wu, Hao Cheng, Wenlin Yao, Nikhil Singh, Zhou Yu, Jianfeng Gao arXiv, 2026 arXiv / pdf / code An open-source framework for training harness-native agents end-to-end across diverse environments, using a lightweight proxy and Kubernetes-based rollout orchestration to connect real inference harnesses with scalable SFT/RL training.
	Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond Zachary Horvitz, Raghav Singhal, Hao Zou, Carles Domingo-Enrich, Zhou Yu, Rajesh Ranganath, Kathleen McKeown COLM 2026 arXiv / bibtex Studies how masked diffusion language models use inference-time compute, including reasoning-as-infilling, answer-conditioned posterior sampling, uncertainty-aware early exit, and reasoning validation.
	You Make me Feel like a Natural Question: Training QA Systems on Transformed Trivia Questions Tasnim Kabir, Yoo Yeon Sung, Saptarashmi Bandyopadhyay, Hao Zou, Abhranil Chandra, Jordan Boyd-Graber EMNLP 2024 paper / bibtex Transforms trivia-style questions into more natural information-seeking questions to improve retrieval alignment and cross-domain question answering.
	A Survey of Diffusion Models in Natural Language Processing Hao Zou, Zae Myung Kim, Dongyeop Kang arXiv, 2023 arXiv / bibtex Surveys diffusion formulations for NLP, including non-autoregressive generation, text editing, token-level control, robustness, and scaling directions for diffusion language models.
	Debiasing Language Models for In-Context Learning Using a Causal Inference-Inspired Method Hao Zou, Karin de Langis, Dongyeop Kang, Yohan Jo Manuscript, 2023 bibtex Uses intervention-inspired estimates of the causal effect of input text to reduce spurious prompt-label bias in in-context learning.

Experience