Nan Jiang (姜楠)

Assistant Professor
Department of Computer Science, University of Texas - El Paso

Previously: PhD, Department of Computer Science, Purdue University

Research Interests: Diffusion Language Model; Neuro-symbolic AI for scientific discovery.

Contacts: Email / CV / Google Scholar



About Me

Hiring: I'm looking for self-motivated students who are passionate about Efficient dLLM, and AI4Science. If you are interested in working with me, please apply for the UTEP@CS PhD program.

My name is Nan Jiang (姜楠). I earned my Ph.D. degree in Computer Science from Purdue University, where I was advised by Dr. Yexiang Xue. My PhD research focuses on Integrating Automated Reasoning with Machine Learning for Structured Prediction and Scientific Discovery.

Research Highlights

Efficient Inference for Diffusion Language Models

  • Goal: Reduce the inference cost of diffusion-based LLMs for language generation.
  • Strategies: (1) Reduce the number of diffusion iterations via distillation; (2) Develop a sparse attention mechanism for long-sequence generation.

Neuro-Symbolic AI for Scientific Discovery

  • Goal: Accelerate the discovery of physical knowledge from experimental data (see the Genesis Mission).
  • Strategies: (1) Design control-variable experiments; (2) Perform active data querying guided by phase portraits; (3) Learn a symbolic-equivalence–aware objective.

People

  • Alondra Banquier Bujanda (CS@UTEP, Fall 2025)

Publications

2026

  1. Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct.
    Haoyang Zheng, Xinyang Liu, Cindy Xiangrui Kong, Nan Jiang, Zheyuan Hu, Weijian Luo, Wei Deng, Guang Lin
    Arxiv.
    website / code

  2. DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
    Ziyi Wang, Siva Rajesh Kasa, Ankith M S, SANTHOSH KUMAR KASA, Jiaru Zou, Nan Jiang, Sumit Negi, Ruqi Zhang, Qifan Song.
    NeurIPS 2025 Efficient Reasoning workshop.

  3. EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph
    Nan Jiang, Ziyi Wang, Yexiang Xue.
    Arxiv.
    website / code

  4. SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions.
    Ziyi Wang, Nan Jiang, Guang Lin, Qifan Song.
    Arxiv.
    website / code

2025

  1. An Exact Solver for Satisfiability Modulo Counting with Probabilistic Circuits.
    Jinzhao Li*, Nan Jiang*, Yexiang Xue.
    ICML 2025.
    poster / code

  2. Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching.
    Nan Jiang, Md Nasim, Yexiang Xue.
    AAAI 2025.
    poster / code

  3. PhD Thesis: Integrating Automated Reasoning with Machine Learning for Structured Prediction and Scientific Discovery.
    thesis defense slides / thesis video at Youtube / video at Bilibili

  4. Expediting Symbolic Regression for Science Using Scientific Approaches.
    Md Nasim, Nan Jiang, Yexiang Xue.
    Book Chapter at Computational Approaches to Scientific Discovery (Springer) 2025.

2024

  1. A Tighter Convergence Proof of Reverse Experience Replay.
    Nan Jiang, Jinzhao Li, Yexiang Xue.
    The first Reinforcement Learning Conference (RLC) 2024.
    poster slides code

  2. Vertical Symbolic Regression via Deep Policy Gradient,
    Nan Jiang, Md Nasim, Yexiang Xue.
    IJCAI 2024.
    poster / slides / code

  3. Solving Satisfiability Modulo Counting for Symbolic and Statistical AI Integration with Provable Guarantees,
    Jinzhao Li, Nan Jiang and Yexiang Xue.
    AAAI 2024.
    poster / code

  4. Racing Control Variable Genetic Programming for Symbolic Regression.
    Nan Jiang, Yexiang Xue.
    AAAI 2024.
    poster / slides / video / code

2023

  1. Symbolic Regression via Control Variable Genetic Programming.
    Nan Jiang, Yexiang Xue.
    ECML-PKDD 2023.
    poster / slides / code

  2. Learning Markov Random Fields for Combinatorial Structures via Sampling through Lovász Local Lemma.
    Nan Jiang*, Yi Gu*, Yexiang Xue.
    AAAI 2023.
    Arxiv / poster / slides / code / (CPML@AAAI2025)

2022

  1. Constraint Reasoning Embedded Structured Prediction.
    Nan Jiang, Maosen Zhang, Willem-Jan van Hoeve, Yexiang Xue.
    JMLR 2022.
    video / poster / code

  2. Massive Text Normalization via an Efficient Randomized Algorithm.
    Nan Jiang, Chen Luo, Vihan Lakshman, Yesh Dattatreya, Yexiang Xue.
    TheWebConf 2022.
    slides / video / code

2021

  1. PALM: Probabilistic Area Loss Minimization for Protein Sequence Alignment.
    Fan Ding*, Nan Jiang*, Jianzhu Ma, Jian Peng, Jinbo Xu, and Yexiang Xue.
    UAI 2021.
    video / poster / slides / code

2020

  1. Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach.
    Maosen Zhang, Nan Jiang, Lei Li, and Yexiang Xue.
    Finding in EMNLP 2020.
    poster / video / code

  2. A dual channel class hierarchy-based recurrent language modeling.
    Libin Shi, Wenge Rong, Shijie Zhou, Nan Jiang, Zhang Xiong.
    Neurocomputing 2020.

Older Papers

  1. LSDSCC: A Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics.
    Zhen Xu, Nan Jiang and et. al.
    NAACL-HLT 2018.

  2. Exploration of Tree-based Hierarchical Softmax for Recurrent Language Models.
    Nan Jiang, Wenge Rong, Min Gao, Yikang Shen, Zhang Xiong.
    IJCAI 2017.
    code

  3. Biological Event Trigger Identification with Noise Contrastive Estimation.
    Nan Jiang, Wenge Rong, Yifan Nie, Yikang Shen, and Zhang Xiong.
    IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2017.
    code

  4. An Empirical Analysis of Different Sparse Penalties for Autoencoder in Unsupervised Feature Learning.
    Nan Jiang, Wenge Rong, Baolin Peng, Yifan Nie, Zhang Xiong.
    IJCNN, 2015.
    code

Teaching

  1. Seminar Course: Artificial Intelligence for Scientific Discovery (Fall 2025)

Update

Nov 25: Got 3000 hours of H100/A100 GPU computing from TACC.