Photo

I am a Senior Research Scientist at NVIDIA Research. I obtained my PhD from Georgia Institute of Technology in May 2025, advised by Dr. Yingyan (Celine) Lin. Before that, I obtained my Bachelor's degree with a dual major in Applied Physics and Computer Science from the School of The Gifted Young at the University of Science and Technology of China in 2019. I am a recipient of IBM PhD Fellowship and was selected as Machine Learning and Systems Rising Stars 2023.

My research focuses on developing efficient foundation models that bring frontier AI to everyday platforms. At NVIDIA, I led the development of Nemotron-Flash, Hymba, and Efficient-DLM. My research work has been featured as spotlight papers at ICLR (2025 & 2021 & 2021 & 2020), an oral paper at ECCV (2024), and an IEEE Micro Top Pick (2023). My CV can be found here (Updated: Mar. 2026).

   /      /      /   yonggan (dot) gatech [at] gmail (dot) com & yongganf [at] nvidia (dot) com


Research Interest



News



Selected Publications (see full publication list here; * indicates equal contribution)

Yonggan Fu*, Lexington Whalen*, Zhifan Ye, Xin Dong, Shizhe Diao, Jingyu Liu, Chengyue Wu, Hao Zhang, Enze Xie, Song Han, Maksim Khadkevich, Jan Kautz, Yingyan (Celine) Lin, Pavlo Molchanov
Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
arXiv Preprint [Tech Report]
Yonggan Fu*, Xin Dong*, Shizhe Diao, Matthijs Van keirsbilck, Hanrong Ye, Wonmin Byeon, Yashaswi Karnati, Lucas Liebenwein, Hannah Zhang, Nikolaus Binder, Maksim Khadkevich, Alexander Keller, Jan Kautz, Yingyan (Celine) Lin, Pavlo Molchanov
Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
NeurIPS 2025 [Paper] [Nemotron-Flash-1B][Nemotron-Flash-3B][Nemotron-Flash-3B-Instruct]
Integration into TensorRT-LLM
Shizhe Diao, Yu Yang, Yonggan Fu, Xin Dong, Dan Su, Markus Kliegl, Zijia Chen, Peter Belcak, Yoshi Suhara, Hongxu Yin, Mostofa Patwary, Yingyan (Celine) Lin, Jan Kautz, Pavlo Molchanov
CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
NeurIPS 2025 Datasets & Benchmarks Track [Paper] [Nemotron-ClimbMix][Nemotron-ClimbLab]
Spotlight Paper
Zhenbang Du*, Yonggan Fu*, Lifu Wang*, Jiayi Qian, Xiao Luo, Yingyan (Celine) Lin
Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
ICCV 2025 [Paper] [Code]
Yonggan Fu*, Xin Dong*, Shizhe Diao, Wonmin Byeon, Zijia Chen, Ameya Sunil Mahabaleshwarkar, Shih-Yang Liu, Matthijs Van Keirsbilck, Min-Hung Chen, Yoshi Suhara, Yingyan (Celine) Lin, Jan Kautz, Pavlo Molchanov
Hymba: A Hybrid-head Architecture for Small Language Models
ICLR 2025 [Paper] [Code] [Hymba-1.5B-Base][Hymba-1.5B-Instruct]
Spotlight Paper
Yonggan Fu, Zhongzhi Yu, Jiayi Qian, Junwei Li, Yongan Zhang, Dachuan Shi, Xiangchi Yuan, Roman Yakunin, Yingyan (Celine) Lin
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
NeurIPS 2024 [Paper] [Code] [Video] [Slide]
Yonggan Fu, Huaizhi Qu, Zhifan Ye, Chaojian Li, Kevin Zhao, Yingyan (Celine) Lin
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
ECCV 2024 [Paper] [Code] [Video] [Slide]
Oral Paper
Yonggan Fu*, Yongan Zhang*, Zhongzhi Yu*, Sixu Li, Zhifan Ye, Chaojian Li, Cheng Wan, Yingyan (Celine) Lin
GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models
ICCAD 2023 [Paper] [Slide], Covered by [The Next Platform] [Anastasi In Tech]
Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan (Celine) Lin
NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
ICML 2023 [Paper] [Code] [Video] [Slide]
In collaboration with Intel
Yonggan Fu, Yuecheng Li, Chenghui Li, Jason Saragih, Peizhao Zhang, Xiaoliang Dai, Yingyan (Celine) Lin
Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence
CVPR 2023 [Paper] [Video] [Slide]
In collaboration with Meta
Yonggan Fu*, Zhifan Ye*, Jiayi Yuan, Shunyao Zhang, Sixu Li, Haoran You, Yingyan (Celine) Lin
Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design
ISCA 2023 [Paper] [Video] [Slide]
2nd Place in the 33rd ACM SIGDA/IEEE CEDA University Demonstration at DAC 2023
Yonggan Fu, Yang Zhang, Kaizhi Qian, Zhifan Ye, Zhongzhi Yu, Cheng-I Lai, Yingyan (Celine) Lin
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
NeurIPS 2022 [Paper] [Code] [Video] [Slide]
In collaboration with MIT-IBM Watson AI Lab
Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan (Celine) Lin
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
ICML 2022 [Paper] [Code] [Video], Covered by [The Next Platform]
In collaboration with Meta
Yonggan Fu*, Shunyao Zhang*, Shang Wu*, Cheng Wan, Yingyan (Celine) Lin
Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
ICLR 2022 [Paper] [Code] [Video]
Yonggan Fu, Qixuan Yu, Yang Zhang, Shang Wu, Xu Ouyang, David Cox, Yingyan (Celine) Lin
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
NeurIPS 2021 [Paper] [Code] [Video]
In collaboration with MIT-IBM Watson AI Lab
Yonggan Fu, Yang Zhao, Qixuan Yu, Chaojian Li, Yingyan (Celine) Lin
2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency
MICRO 2021 [Paper] [Video]
Yonggan Fu, Yang Zhang, Yue Wang, Zhihan Lu, Vivek Boominathan, Ashok Veeraraghavan, Yingyan (Celine) Lin
SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCam
ICCV 2021 [Paper] [Code] [Video]
In collaboration with MIT-IBM Watson AI Lab
Yonggan Fu, Qixuan Yu, Meng Li, Vikas Chandra, Yingyan (Celine) Lin
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference
ICML 2021 [Paper] [Code] [Video]
In collaboration with Meta
Yonggan Fu, Yongan Zhang, Yang Zhang, David Cox, Yingyan (Celine) Lin
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
ICML 2021 [Paper] [Code] [Video]
In collaboration with MIT-IBM Watson AI Lab
Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan (Celine) Lin
CPT: Efficient Deep Neural Network Training via Cyclic Precision
ICLR 2021 [Paper] [Code] [Video]
Spotlight paper (top 6%), in collaboration with Meta
Yonggan Fu, Haoran You, Yang Zhao, Yue Wang, Chaojian Li, Kailash Gopalakrishnan, Zhangyang Wang, Yingyan (Celine) Lin
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
NeurIPS 2020 [Paper] [Code] [Video]
Yonggan Fu, Wuyang Chen, Haotao Wang, Haoran Li, Yingyan (Celine) Lin, Zhangyang Wang
AutoGan-Distiller: Searching to Compress Generative Adversarial Networks
ICML 2020 [Paper] [Code] [Video]


Education



Internship Experience



Selected Awards



Community Services



Invited Talks