publications

2026

1. ICLR

   

   Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment

   Bac Nguyen, Yuhta Takida, Naoki Murata, Chieh-Hsin Lai, Toshimitsu Uesaka, Stefano Ermon, and Yuki Mitsufuji

   In The International Conference on Learning Representations, 2026

   arXiv Bib HTML Code

   @inproceedings{nguyen2026coda,
     title = {Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment},
     author = {Nguyen, Bac and Takida, Yuhta and Murata, Naoki and Lai, Chieh-Hsin and Uesaka, Toshimitsu and Ermon, Stefano and Mitsufuji, Yuki},
     year = {2026},
     booktitle = {The International Conference on Learning Representations}
   }

2. ICLR

   

   SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator

   Yuhta Takida, Satoshi Hayakawa, Takashi Shibuya, Masaaki Imaizumi, Naoki Murata, Bac Nguyen, Toshimitsu Uesaka, Chieh-Hsin Lai, and Yuki Mitsufuji

   In The International Conference on Learning Representations, 2026

   arXiv Bib HTML Code

   @inproceedings{takida2026sona,
     title = {SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator},
     author = {Takida, Yuhta and Hayakawa, Satoshi and Shibuya, Takashi and Imaizumi, Masaaki and Murata, Naoki and Nguyen, Bac and Uesaka, Toshimitsu and Lai, Chieh-Hsin and Mitsufuji, Yuki},
     year = {2026},
     booktitle = {The International Conference on Learning Representations}
   }

2025

1. IJCNN

   

   Improving vector-quantized image modeling with latent consistency-matching diffusion

   Bac Nguyen, Chieh-Hsin Lai, Yuta Takida, Naoki Murata, Toshimitsu Uesaka, Stefano Ermon, and Yuki Mitsufuji

   In International Joint Conference on Neural Networks, 2025

   Best Industry Paper arXiv Bib HTML

   Best Industry Paper Award

   @inproceedings{nguyen2025improving,
     title = {Improving vector-quantized image modeling with latent consistency-matching diffusion},
     author = {Nguyen, Bac and Lai, Chieh-Hsin and Takida, Yuta and Murata, Naoki and Uesaka, Toshimitsu and Ermon, Stefano and Mitsufuji, Yuki},
     booktitle = {International Joint Conference on Neural Networks},
     pages = {1--8},
     year = {2025},
     organization = {IEEE},
   }

2. TMLR

   

   G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving

   Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, and Yuki Mitsufuji

   Transactions on Machine Learning Research, 2025

   arXiv Bib HTML Code

   @article{murata2025gd,
     title = {G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving},
     author = {Murata, Naoki and Lai, Chieh-Hsin and Takida, Yuhta and Uesaka, Toshimitsu and Nguyen, Bac and Ermon, Stefano and Mitsufuji, Yuki},
     journal = {Transactions on Machine Learning Research},
     issn = {2835-8856},
     year = {2025},
   }

2024

1. ECCV

   

   SAFT: Towards out-of-distribution generalization in fine-tuning

   Bac Nguyen, Stefan Uhlich, Fabien Cardinaux, Lukas Mauch, Marzieh Edraki, and Aaron Courville

   In European Conference on Computer Vision, 2024

   arXiv Bib HTML

   @inproceedings{nguyen2024saft,
     title = {SAFT: Towards out-of-distribution generalization in fine-tuning},
     author = {Nguyen, Bac and Uhlich, Stefan and Cardinaux, Fabien and Mauch, Lukas and Edraki, Marzieh and Courville, Aaron},
     booktitle = {European Conference on Computer Vision},
     pages = {138--154},
     year = {2024},
     organization = {Springer},
   }

2. ECCV

   

   Sparo: Selective attention for robust and compositional transformer encodings for vision

   Ankit Vani, Bac Nguyen, Samuel Lavoie, Ranjay Krishna, and Aaron Courville

   In European Conference on Computer Vision, 2024

   arXiv Bib HTML Code

   @inproceedings{vani2024sparo,
     title = {Sparo: Selective attention for robust and compositional transformer encodings for vision},
     author = {Vani, Ankit and Nguyen, Bac and Lavoie, Samuel and Krishna, Ranjay and Courville, Aaron},
     booktitle = {European Conference on Computer Vision},
     pages = {233--251},
     year = {2024},
     organization = {Springer},
   }

3. ICASSP

   

   Skill: Similarity-aware knowledge distillation for speech self-supervised learning

   Luca Zampierin, Ghouthi Boukli Hacene, Bac Nguyen, and Mirco Ravanelli

   In International Conference on Acoustics, Speech, and Signal Processing Workshops, 2024

   arXiv Bib HTML

   @inproceedings{zampierin2024skill,
     title = {Skill: Similarity-aware knowledge distillation for speech self-supervised learning},
     author = {Zampierin, Luca and Hacene, Ghouthi Boukli and Nguyen, Bac and Ravanelli, Mirco},
     booktitle = {International Conference on Acoustics, Speech, and Signal Processing Workshops},
     pages = {675--679},
     year = {2024},
     organization = {IEEE},
   }

2023

1. Interspeech

   

   Towards Robust FastSpeech 2 by Modelling Residual Multimodality

   Fabian Kögel, Bac Nguyen, and Fabien Cardinaux

   In Annual Conference of the International Speech Communication Association, 2023

   arXiv Bib HTML Code Website

   @inproceedings{kogel2023towards,
     title = {Towards Robust FastSpeech 2 by Modelling Residual Multimodality},
     author = {K{\"o}gel, Fabian and Nguyen, Bac and Cardinaux, Fabien},
     booktitle = {Annual Conference of the International Speech Communication Association},
     pages = {4309--4313},
     year = {2023},
   }

2. ICASSP

   

   Improving self-supervised learning for audio representations by feature diversity and decorrelation

   Bac Nguyen, Stefan Uhlich, and Fabien Cardinaux

   In International Conference on Acoustics, Speech, and Signal Processing, 2023

   arXiv Bib HTML

   @inproceedings{nguyen2023improving,
     title = {Improving self-supervised learning for audio representations by feature diversity and decorrelation},
     author = {Nguyen, Bac and Uhlich, Stefan and Cardinaux, Fabien},
     booktitle = {International Conference on Acoustics, Speech, and Signal Processing},
     pages = {1--5},
     year = {2023},
     organization = {IEEE},
   }

3. ICASSP

   

   AutoTTS: End-to-end text-to-speech synthesis through differentiable duration modeling

   Bac Nguyen, Fabien Cardinaux, and Stefan Uhlich

   In International Conference on Acoustics, Speech and Signal Processing, 2023

   arXiv Bib HTML Website

   @inproceedings{nguyen2023autotts,
     title = {AutoTTS: End-to-end text-to-speech synthesis through differentiable duration modeling},
     author = {Nguyen, Bac and Cardinaux, Fabien and Uhlich, Stefan},
     booktitle = {International Conference on Acoustics, Speech and Signal Processing},
     pages = {1--5},
     year = {2023},
     organization = {IEEE},
   }

2022

1. ICML Workshop

   Efficient Training of Deep Equilibrium Models

   Bac Nguyen^* and Lukas Mauch^*

   In Hardware Aware Efficient Training ICML Workshop, 2022

   arXiv Bib HTML

   @inproceedings{nguyen2023efficient,
     title = {Efficient Training of Deep Equilibrium Models},
     author = {Nguyen, Bac and Mauch, Lukas},
     booktitle = {Hardware Aware Efficient Training ICML Workshop},
     year = {2022},
   }

2. ICASSP

   

   NVC-Net: End-to-end adversarial voice conversion

   Bac Nguyen and Fabien Cardinaux

   In International Conference on Acoustics, Speech and Signal Processing, 2022

   arXiv Bib HTML Website

   @inproceedings{nguyen2022nvc,
     title = {NVC-Net: End-to-end adversarial voice conversion},
     author = {Nguyen, Bac and Cardinaux, Fabien},
     booktitle = {International Conference on Acoustics, Speech and Signal Processing},
     pages = {7012--7016},
     year = {2022},
     organization = {IEEE},
   }

2020

1. Neurocomputing

   

   Improved deep embedding learning based on stochastic symmetric triplet loss and local sampling

   Bac Nguyen and Bernard De Baets

   Neurocomputing, 2020

   Bib HTML Code

   @article{nguyen2020improved,
     title = {Improved deep embedding learning based on stochastic symmetric triplet loss and local sampling},
     author = {Nguyen, Bac and De Baets, Bernard},
     journal = {Neurocomputing},
     volume = {402},
     pages = {209--219},
     year = {2020},
     publisher = {Elsevier},
   }

2019

1. IEEE TNNLS

   

   Kernel-based distance metric learning for supervised k-means clustering

   Bac Nguyen and Bernard De Baets

   IEEE Transactions on Neural Networks and Learning Systems, 2019

   Bib HTML

   @article{nguyen2019kernel,
     title = {Kernel-based distance metric learning for supervised $k$-means clustering},
     author = {Nguyen, Bac and De Baets, Bernard},
     journal = {IEEE Transactions on Neural Networks and Learning Systems},
     volume = {30},
     number = {10},
     pages = {3084--3095},
     year = {2019},
     publisher = {IEEE},
   }

2. IS

   

   An efficient method for clustered multi-metric learning

   Bac Nguyen, Francesc J Ferri, Carlos Morell, and Bernard De Baets

   Information Sciences, 2019

   Bib HTML Code

   @article{nguyen2019efficient,
     title = {An efficient method for clustered multi-metric learning},
     author = {Nguyen, Bac and Ferri, Francesc J and Morell, Carlos and De Baets, Bernard},
     journal = {Information Sciences},
     volume = {471},
     pages = {149--163},
     year = {2019},
     publisher = {Elsevier},
   }

3. PhD

   

   Supervised distance metric learning for pattern recognition

   Bac Nguyen

   Ghent University, 2019

   Bib HTML PDF

   @phdthesis{nguyen2019supervised,
     title = {Supervised distance metric learning for pattern recognition},
     author = {Nguyen, Bac},
     year = {2019},
     school = {Ghent University},
   }

2018

1. IEEE TIP

   

   Kernel distance metric learning using pairwise constraints for person re-identification

   Bac Nguyen and Bernard De Baets

   IEEE Transactions on Image Processing, 2018

   Bib HTML Code

   @article{nguyen2018kernel,
     title = {Kernel distance metric learning using pairwise constraints for person re-identification},
     author = {Nguyen, Bac and De Baets, Bernard},
     journal = {IEEE Transactions on Image Processing},
     volume = {28},
     number = {2},
     pages = {589--600},
     year = {2018},
     publisher = {IEEE},
   }

2. IEEE TCYB

   

   Scalable large-margin distance metric learning using stochastic gradient descent

   Bac Nguyen, Carlos Morell, and Bernard De Baets

   IEEE Transactions on Cybernetics, 2018

   Bib HTML Code

   @article{nguyen2018scalable,
     title = {Scalable large-margin distance metric learning using stochastic gradient descent},
     author = {Nguyen, Bac and Morell, Carlos and De Baets, Bernard},
     journal = {IEEE Transactions on Cybernetics},
     volume = {50},
     number = {3},
     pages = {1072--1083},
     year = {2018},
     publisher = {IEEE},
   }

3. PR

   

   An approach to supervised distance metric learning based on difference of convex functions programming

   Bac Nguyen and Bernard De Baets

   Pattern Recognition, 2018

   Bib HTML Code

   @article{nguyen2018approach,
     title = {An approach to supervised distance metric learning based on difference of convex functions programming},
     author = {Nguyen, Bac and De Baets, Bernard},
     journal = {Pattern Recognition},
     volume = {81},
     pages = {562--574},
     year = {2018},
     publisher = {Elsevier},
   }

4. KBS

   

   Distance metric learning for ordinal classification based on triplet constraints

   Bac Nguyen, Carlos Morell, and Bernard De Baets

   Knowledge-Based Systems, 2018

   Bib HTML Code

   @article{nguyen2018distance,
     title = {Distance metric learning for ordinal classification based on triplet constraints},
     author = {Nguyen, Bac and Morell, Carlos and De Baets, Bernard},
     journal = {Knowledge-Based Systems},
     volume = {142},
     pages = {17--28},
     year = {2018},
     publisher = {Elsevier},
   }

2017

1. PR

   

   Supervised distance metric learning through maximization of the Jeffrey divergence

   Bac Nguyen, Carlos Morell, and Bernard De Baets

   Pattern Recognition, 2017

   Bib HTML Code

   @article{nguyen2017supervised,
     title = {Supervised distance metric learning through maximization of the Jeffrey divergence},
     author = {Nguyen, Bac and Morell, Carlos and De Baets, Bernard},
     journal = {Pattern Recognition},
     volume = {64},
     pages = {215--225},
     year = {2017},
     publisher = {Elsevier},
   }

2. PRL

   

   Distance metric learning with the universum

   Bac Nguyen, Carlos Morell, and Bernard De Baets

   Pattern Recognition Letters, 2017

   Bib HTML Code

   @article{nguyen2017distance,
     title = {Distance metric learning with the universum},
     author = {Nguyen, Bac and Morell, Carlos and De Baets, Bernard},
     journal = {Pattern Recognition Letters},
     volume = {100},
     pages = {37--43},
     year = {2017},
     publisher = {Elsevier},
   }

2016

1. Neurocomputing

   

   Large-scale distance metric learning for k-nearest neighbors regression

   Bac Nguyen, Carlos Morell, and Bernard De Baets

   Neurocomputing, 2016

   Bib HTML

   @article{nguyen2016large,
     title = {Large-scale distance metric learning for $k$-nearest neighbors regression},
     author = {Nguyen, Bac and Morell, Carlos and De Baets, Bernard},
     journal = {Neurocomputing},
     volume = {214},
     pages = {805--814},
     year = {2016},
     publisher = {Elsevier},
   }