About
Hi! I'm an incoming Assistant Professor of Computer Science & Engineering at The University of Texas at Arlington, where my group is supported by the RISE 100 initiative and a UT System STARs Award.
Before UTA, I was a Moore Foundation Postdoctoral Fellow hosted at UC San Diego and affiliated with CMU and MBZUAI, working with Eric Xing and Zhiting Hu; I received my PhD from The Ohio State University, working with Huan Sun and Yu Su.
My work has been supported by and recognized with the Gordon and Betty Moore Foundation Fellowship, OpenAI Research Grant, Rising Stars in Data Science, Best Paper Award at SoCal NLP, Amazon Alexa Prize Winner, and more. I have led collaborations with MIT-IBM Lab, Microsoft Research, NEC Labs, and academic institutions including CMU, MBZUAI, five UC campuses (Santa Barbara, Berkeley, Irvine, Merced, San Diego) and three national labs (Los Alamos, Lawrence Livermore, Lawrence Berkeley) through the UC-LEAP project.
Research Overview
I develop the algorithmic foundations of open-ended machine reasoning for discovery: AI systems that reason over structured knowledge, plan with learned world models, and remain accountable under human oversight. I unify these components through the LAW framework (Language, Agents, World Models) and stress-test the methods on frontier problems in scientific discovery (e.g., cancer genomics, single-cell biology, materials science, social simulation), where reliability, interpretability, and verifiability are treated as first principles rather than afterthoughts. My program advances both the core of AI and its principled translation to the sciences, engineering, and society.
My recent works explore:
- Deliberative Reasoning & World Models (EMNLP'23, COLM'24, ACL'23, EMNLP'24, ICLR'26)
- Autonomous Agents & Trustworthy Deployment (NeurIPS'25, ICLR'24, Amazon Alexa Prize, ICML'26)
- Compositional & Self-specializing Foundation Models (ICLR'23, ICLR'25, NeurIPS'23 Oral)
- Scientific FMs and AI Co-scientists for Discovery (Nature'26, Cancer Discovery'26, NeurIPS'25, UC-LEAP Grant)
News
Aug 2026
Two of two papers accepted to EMNLP 2026.
May 2026
Received the ICML 2026 Silver Reviewer Award.
Apr 2026
FIRE-Bench accepted to ICML 2026: the first benchmark for reliably evaluating research agents on full-cycle scientific (re-)discovery with verifiable evaluation.
Apr 2026
MutationProjector accepted to
Cancer Discovery (IF: 33.3): the first genomics foundation model of cancer mutations, enabling precise predictions of therapeutic response.
Apr 2026
De-Arena was accepted to ACL 2026: an LLM-arena framework for evaluating LLMs using collective intelligence.
Mar 2026
Invited talk at the
Stanford NLP Seminar on "Building AI that Reasons to Accelerate Real-world Discovery."
Jan 2026
Nabla Reasoner was accepted to ICLR 2026: LLM reasoning via test-time gradient descent in textual space.
Dec 2025
Honored to organize
LAW 2025 workshop (Bridging Language, Agent, and World Models) at NeurIPS 2025. Thanks to our amazing co-organizers, Ziqiao, Jessy, Melanie, Jianwen, Kelsey, Alane, Jacob, Tianmin, and Zhiting; and speakers, Sherry, Chelsea, François, Eric, Danijar, Philip, Stephen, Ying Nian, and Keyon. Check the recording of their talks
here.
Dec 2025
Presenting two papers at NeurIPS 2025: scPilot (first omics-native reasoning agents) and DeepPersona (generative engine for real-human personas).
Oct 2025
Received the Gordon and Betty Moore Foundation Fellowship for the Natural Sciences to support research on AI-driven scientific reasoning and discovery.
Sep 2025
scPilot accepted to NeurIPS 2025: omics-native reasoning for grounding LLMs in raw omics data.
Aug 2025
Attended
UC-LEAP Kick-off at
UCSB: exploring AI agents for Materials Science.
Jun 2025
Presented CellMaster at
DL4SCI 2025 at Berkeley.
Jan 2025
Self-MoE accepted to ICLR 2025: transforming monolithic LLMs into modular self-specialized experts.
Older news (2024 and earlier)
Oct 2024
Released
TxT360: first dataset to globally deduplicate 99 CommonCrawl snapshots.
Dataset
Sep 2024
DRPO accepted to EMNLP 2024: first tuning-free method for self-aligning LLMs with human preferences.
Feb 2024
Received OpenAI research grant to support agentic systems research.
Jan 2024
PromptAgent accepted to ICLR 2024: first principled framework for API-based prompt optimization.
Nov 2023
Received Top Reviewer Award at NeurIPS 2023.
Oct 2023
RAP accepted to EMNLP 2023 Main: augmenting LLM reasoning with world models and planning.
Sep 2023
ToolkenGPT accepted as
oral presentation at NeurIPS 2023: augmenting LLMs with efficient tool learning.
Feb 2023
Started postdoc at UCSD, collaborating with teams from CMU and MBZUAI on large language models research.
Nov 2022
Passed PhD defense: "Toward Knowledge-centric Natural Language Processing: Acquisition, Representation, Transfer, and Reasoning."
Mar 2022
Received 2022 Graduate Research Award from the CSE department.
Miscellaneous
Outside of research, you'll likely find me hiking, playing pickleball, or planning my next adventure in national parks. I'm a passionate sports fan, cheering for the Buckeyes, Dodgers, and Inter Miami.
Reading is also my main way of thinking outside of code and experiments. I enjoy essays, literary fiction, science fiction, and books on philosophy and ideas. Recently I've been reading 许知远的《伯克利的魔山》, The Complete Short Stories of Ernest Hemingway, and George Zarkadakis's In Our Own Image, among others.
