2026

Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives

Hua (Edward) XU*, Dongxin Li*, Gwen Yidou-Weng, Guy Van den Broeck, Wei Wang, Anji Liu (* equal contribution)

ICLR 2027 submission 2026 arXiv preprint

Summary COFFEE uses a target-free carrier and a compiled finite-state objective model to guide discrete diffusion with sequence-level preferences without retraining the backbone.

My role Co-first author and project lead; formulated the method, implemented the framework, designed evaluations across symbolic, language, and biological tasks, and led the manuscript.

RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models

Yang Yang*, Hua XU*, Zhangyi Hu*, Yutao Yue† (* equal contribution, † corresponding author)

43rd International Conference on Machine Learning (ICML) 2026 Accepted

Summary This work constructs explainable rules for scientific discovery using LLMs. Specifically, we develop a unified framework integrating LLMs with probabilistic modeling through four stages: rule generation via LLM, weight learning through logistic regression, iterative refinement, and evaluation, achieving higher rule quality and better rule combination effects.

My role Equal-contribution author; contributed evaluation-experiment design, data analysis, and manuscript writing.

A Very Big Video Reasoning Suite

Maijunxian Wang, Ruisi Wang, Juyi Lin, ..., Hua XU, ..., Hokin Deng† († corresponding author)

43rd International Conference on Machine Learning (ICML) 2026 Accepted

Summary A GrowAI project introducing the Very Big Video Reasoning (VBVR) suite, a large-scale dataset and benchmark for evaluating video models' spatiotemporal reasoning, generalization, and verifiable task-solving abilities.

My role GrowAI contributor and large-team co-author; helped frame cognitive-evaluation tasks for testing video generative models' reasoning abilities.

Building Interpretable, Trustworthy Systems for Neural Signal Decoding

Hua XU

AAAI 2026 Undergraduate Consortium 2026 Accepted proposal

Summary Single-author Undergraduate Consortium research proposal on developing interpretable and trustworthy neural signal decoding systems.

My role Single-author undergraduate consortium proposal; formulated the problem framing and research agenda for interpretable, trustworthy neural signal decoding.

2025

IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction

Zhangyi Hu*, Jiemin Wu*, Hua XU*, Mingqian Liao, Ninghui Feng, Bo Gao, Songning Lai, Yutao Yue† (* equal contribution, † corresponding author)

42nd International Conference on Machine Learning (ICML) 2025 Accepted

Summary Leveraging visual pretrained masked autoencoders to address irregular multivariate time series prediction challenges by converting sparse data into time × channel image-like patches, capturing cross-channel interactions with superior accuracy and strong few-shot performance.

My role Equal-contribution core contributor; helped design and run experiments, write the paper, and participate in the rebuttal process.

vNeck: Electrical Muscle Stimulation Around the Neck for Eyes-Free Target Acquisition in Virtual Reality

Yuchao ZHUO, Hua XU, Yucheng Liu, Duotun Wang, Jianhao Chen, Jiawei Li, Chutian Jiang, Tristan Camille Braud, Mingming Fan† († corresponding author)

International Conference on Human-Engaged Computing (ICHEC) 2025 Accepted Best Paper

Summary An innovative VR interaction system using electrical muscle stimulation around the neck for eyes-free target acquisition in virtual reality environments.

My role Responsible for the user study and data processing.