Dongkuan (DK) Xu
I am an Assistant Professor of Computer Science at NC State University, where I lead the Generative Intelligent Computing (GIC) Lab. My research focuses on machine learning, natural language processing, and computer vision, with an emphasis on efficient and reliable AI systems. I have received several awards, including the Microsoft Accelerating Foundation Models Research Award 2024, the NCSU Carla Savage Award 2024, the Best Paper Award Runner-Up at IEEE IPCCC 2024, and the Best Paper Award at ICCCN 2023. I hold my Ph.D. from Penn State, M.S. from the University of Chinese Academy of Sciences, and B.E. from Renmin University of China.
I am also involved in MARINA, a research initiative at the intersection of AI and ocean sciences, focusing on advancing ocean modeling, environmental monitoring, and AI-driven scientific discovery. As part of my broader work on AI systems, I have contributed to the development of Synthora and Gentopia. Synthora is an extensible AI platform designed to enhance the computational efficiency of LLM-driven applications through full-stack software-system hardware optimization. Gentopia is a lightweight framework for LLM-driven autonomous agents, providing essential components for building, testing, and evaluating AI agent applications.
Outside of work, I am a fan of American football (Nittany Lions, Eagles, Cowboys) and enjoy working out and playing soccer.
Email  / 
CV (Nov 2024)  / 
Twitter  / 
Google Scholar  / 
LinkedIn   
📣 Seeking 1-2 PhD students, encouraging candidates from underrepresented groups. Interested applicants should email "PhD Fall 2025" with their CV.
|
|
News
- 03/2025: MerryQuery won the AAAI-2025 Best Demonstration Award (award link). Congrats Team.
- 03/2025: Our 2nd workshop on deep learning-hardware co-design for GenAI acceleration was accepted at DAC'25
- 02/2025: MARINA has been launched, a research initiative combining AI and ocean sciences
- 02/2025: The I/O Navigator Demo v1 [link], developed with UDel, OSU, LBNL and NCSU, is now available.
- 02/2025: Our paper Adaptix, adaptive draft-verification for efficient LLM decoding, was selected for an Oral at AAAI'25
- 01/2025: Our paper IOAgent, LLM-powered I/O performance diagnosis for HPC storage, was accepted to IPDPS'25
- 01/2025: Precious's (undergraduate) work on LLM bias evaluation was accepted at NCUR'25
- 01/2025: Gave a talk at ABB Research Center, US: Advancing Real-World Edge Intelligence
- 12/2024: Preprint of Exploring LLM Agents for Multi-Modality Enhanced Causal Discovery is on arXiv
- 12/2024: Selected for the AAAI New Faculty Highlights 2025
- 12/2024: Honored to be awarded a grant from the NC State Data Science and AI Academy as a Co-PI to support research on developing responsible LLM agents for enhancing access to large environmental datasets [link]
- 12/2024: Our work on adaptive accelerated LLM decoding was accepted to AAAI'25
- 12/2024: Our tutorial, Resource-Efficient Learning for the Web, has been accepted by TheWebConf'25
- 11/2024: Our paper on network-oriented LLMs won Best Paper Award Runner-Up at IPCCC'24
- 11/2024: MerryQuery was accepted to AAAI'25 (Demo Track)
- 11/2024: Precious had her research accepted by the AAAI'25 Undergraduate Consortium
- 11/2024: Talks at Purdue ECE-570 and NCSU DSC-595: Building Reliable Cost-Effective Sparse Models
- 11/2024: Our GenAI@Edge Symposium was accepted at the AAAI 2025 Spring Symposium Series
- 11/2024: Our workshop, RelWeb [link], was accepted at TheWebConf'25
- 09/2024: Paper on black-box LLM-generated text detection was accepted to NeurIPS'24
- 09/2024: Precious received the Federal Work-Study Award ($1,000)
- 09/2024: Will attend the 2024 Oak Ridge Lab’s Core Universities AI Workshop. See you in Raleigh
- 09/2024: Gave a talk at ABB Research Center, US: Agentic LLM Diagnostic Chatbot for SAP Manufacturing
- 08/2024: Precious received COE REU Award ($3,000)
- 08/2024: A paper on integrating LLMs with network simulators for script-free simulations was accepted to IPCCC'24
- 08/2024: Honored to be awarded a grant from the NSF CyberTraining program as a Co-PI to support AI-driven, cross-disciplinary training for sustainable environmental science research [link]
- 08/2024: Will attend the NSF CSSI/CyberTraining/SCIPE PI Meeting 2024. See you in Charlotte
- 07/2024: Will attend the NSF Workshop on Sustainable Computing 2024. See you at Purdue
- 07/2024: The research paper of our workshops on Integrating ChatGPT into K-12 Classrooms was accepted to FIE'24
- 07/2024: Keynote speakers for RelKD workshop at KDD'24 were announced: Derek Cheng (Google DeepMind), Hanghang Tong (UIUC), Jing Gao (Purdue)
- 07/2024: A paper on algorithm-hardware co-design for real-time vision Transformer was accepted to CODES+ISSS'24
- 07/2024: A paper on accelerating diffusion generative models via adaptive computation was accepted to ECCV'24
- 06/2024: Honored to be awarded a grant from the NSF HEGS program as a Co-PI to support research on multimodal data analysis of neighborhood dynamics [link]
- 06/2024: Received additional funding from the Microsoft Accelerating Foundation Models Research
- 06/2024: Successfully concluded our 3rd workshop on integrating Large Language Models into K-12 classrooms [News]
- 06/2024: Our research work on black-box LLM detection is available [link]
- 06/2024: Our research work on scaling LLM with massive tools is available [link]
- 05/2024: Keynote speakers for DCgAA workshop at DAC'24 were announced: Andreas Andreou (JHU), Farinaz Koushanfar (UCSD), Massoud Pedram (USC), Vijay Janapa Reddi (Harvard), Zhibin Xiao (CASPA). See u in San Francisco!
- 05/2024: A paper on digital twin-assisted reliable edge caching for wireless networks was accepted to IEEE JSAC (IF=16.4)
- 04/2024: Will mentor Wake STEM Early College High School students in GCSP-REU Summer Program 2024
- 04/2024: A paper on big model alignment was accepted to IJCAI'24 Survey Track
- 04/2024: A paper on LLM-powered code comprehension was accepted to IJCAI'24
- 04/2024: A paper on diffusion model-augmented wireless networks was accepted to IFIP/IEEE Networking'24
- 04/2024: Invited to serve on the NSF Core Program panel
- 03/2024: The 2nd Workshop on Resource-Efficient Learning for Knowledge Discovery was accepted to KDD'24
- 03/2024: Gave a talk at NCSU Forest Carbon Solutions Initiative: Foundation Models for Geospatial Analytics
- 03/2024: Gave a talk at Fo Guang Shan Buddhist Temple [link]: Impact of AI on Our Lives and Beyond [News, in Chinese]
- 03/2024: A paper on reliable sparse training was accepted to Transactions on Machine Learning Research
- 03/2024: Received the The Carla Savage Award [News]
- 02/2024: A paper on explaining predictions made by graph neural networks was accepted to IEEE PAMI (IF=23.6)
- 02/2024: Workshop on Deep Learning-Hardware Co-Design for Generative AI Acceleration was accepted to DAC'24
- 02/2024: Our DDCV workshop@CVPR'24 is looking for submissions. We will offer 3 free registration for students!
- 02/2024: Received a Gift Fund from Microsoft
- 01/2024: Awarded the Microsoft Accelerating Foundation Models Research Award [News]
- 01/2024: Our proposal of The 1st Workshop on Dataset Distillation for Computer Vision was accepted to CVPR'24
- 12/2023: Gave a talk at STARS AI Scholars Program: How LLMs Work and Cutting-Edge Research on Generative AI
- 12/2023: A paper on large language model education was accepted to AAAI/EAAI'24
- 12/2023: A paper on neural architecture search for Spiking Transformers was accepted to ICASSP'24
- 11/2023: Our work, AGENT [link], was accepted to CPAL'24 as Oral Paper
- 10/2023: Gentopia was accepted to EMNLP'23 (System Demo)
- 10/2023: Two papers (Robust LLM Pruning + Controllable Randomized Pruning) were accepted to EMNLP'23
- 10/2023: A paper on code generation in domain-changing environments was accepted to EMNLP'23 Pan-DL Workshop
- 09/2023: A paper on personalized federated learning was accepted to NeurIPS'23
- 09/2023: My mentored undergraduate, Zihan, received COE REU Award ($3,000). Congrats Zihan.
- 09/2023: Gave a talk at Microsoft Research Asia: Sculpting the Future of Collective Growth in Collaborative AI
- 09/2023: Invited to serve as an Area Chair for LREC-COLING'24
- 08/2023: Invited to serve on the NSF CAREER panel
- 08/2023: Gave a talk at CoreNet Global: ChatGPT in Corporate Real Estate - Unlocking the Potential [link]
- 08/2023: Released a paper providing more details about Gentopia.AI
- 08/2023: Launched Gentopia.AI. Check out our teams from NCSU, GMU, CMU, UMich, etc.
- 07/2023: Honored to receive the Best Paper Award at ICCCN'23
- 07/2023: A paper was accepted to ICCV'23
- 07/2023: A paper was accepted to CDC'23
- 07/2023: Our ChatGPT Education Workshops [link] are available (co-organized with Tiffany)
- 06/2023: Feel free to check out our ALM work, ReWOO (GitHub) (中文解读 1, 2, 3)
- 06/2023: Invited to serve as a Senior PC member of AAAI'24.
- 05/2023: A paper was accepted to KDD'23
- 05/2023: A paper was accepted to ACL'23
- 04/2023: Our work, E-App, was accepted to ICCCN'23. See u in Honolulu
- 04/2023: A paper was accepted to ICAIBD'23. Congrats to our undergrad, Zihan
- 03/2023: Our work, Acc.DD (paper), was selected as a Highlight (2.5%) of CVPR'23
- 03/2023: Will co-chair RelKD'23: Resource-Efficient Learning for Knowledge Discovery Workshop @KDD'23.
- 02/2023: Two papers on accelerating data/model learning were accepted to CVPR'23. Stay tuned ;-)
- 02/2023: Two papers on dynamic training were accepted to DAC'23.
- 01/2023: Our work, Calibrated Rigged Lottery, was accepted to ICLR'23.
- 01/2023: Our work, Efficient Informed Proposals for Discrete Distributions, was accepted to AISTATS'23.
- 01/2023: Invited to give a talk at Rutgers EFficient AI (REFAI) Seminar on Feb 16, 2023.
- 12/2022: Invited to serve as a journal reviewer for TPAMI and Communications of the ACM.
- 11/2022: Invited to serve as the PC Chair for MLNLP 2022.
- 11/2022: Two papers were accepted to AAAI'23. See you in DC in February
- 10/2022: Invited to serve as a TPC member for ISQED'23.
- 09/2022: Will chair The First Workshop on DeepLearning-Hardware Co-Design for AI Acceleration with AAAI'23
- 09/2022: Our work, AutoDistil (paper), was accepted to NeurIPS'22.
- 09/2022: Invited to give a talk at the CIS Department of the University of Macau.
|
Research
My research focuses on scalable, efficient, and reliable learning for AI systems, particularly in the context of large language models (LLMs), diffusion models, and other generative AI models. I explore methods that enhance inference-time performance, shift computational efficiency curves, and ensure robust and reliable learning across diverse applications.
Test-Time Scaling & Adaptation. I study test-time scaling laws to dynamically enhance AI performance at inference and testing stages. My work explores adaptive inference strategies, while also leveraging test-time training techniques to generate and utilize high-quality data. Additionally, I focus on optimizing reasoning workflows to improve model accuracy through self-refinement mechanisms.
Shifting the Computational Curve. To optimize the efficiency-performance tradeoff in AI systems, my research focuses on accelerating models and enabling dynamic computation. This includes model compression and distillation techniques, as well as conditional computation methods. I also explore system-algorithm co-design for large model inference and training, along with hardware-algorithm co-design to develop energy-efficient neural network architectures and optimize AI-accelerator collaboration.
Reliable Learning & Robust Generalization. Beyond efficiency, I focus on trustworthy AI by ensuring robustness, uncertainty quantification, and adaptive learning. My research includes uncertainty-aware AI techniques that enable models to recognize and communicate prediction uncertainty, improving their reliability in deployment. Furthermore, I investigate adaptive learning strategies that allow AI systems to refine their knowledge efficiently from new data with minimal supervision.
Applications. My research contributes to real-world challenges in Education, Agriculture, Networking, Sustainability, Climate, Transportation, Healthcare.
|
★ Representative work: Adaptix
MISSION: To revolutionize LLM decoding with adaptive, compute-optimal strategies and test-time learning
✅ Fine-Tuning-Free Efficiency: Achieve 2.5x speedup without the need for fine-tuning
✅ Dynamic Adaptability: Align token predictions with evolving output distributions in real time
Project Website [link] / AAAI'25 Oral Paper Award
|
★ Representative platform: Gentopia
MISSION: To build artificial general intelligence through collective growth of generative intelligent agents
⭐ Demo I (Create Agents), ⭐ Demo II (Customize and Interact with Agents), ⭐ Demo III (Evaluate Agents)
Project Website [link] / Full Documentation [link] / EMNLP'23 (System Demo Track)
|
★ Representative application: MerryQuery
MISSION: To reshape next-generation education through trustworthy generative AI technologies
✅ Innovations: ① Trust & Transparency, ② Dynamic & Controllable, ③ Multimodal & Multifunctional
Project Website [link] / Video Demo [link] / AAAI'25 (Best Demonstration Award)
|
*Last updated on 03/17/2025*
|
|