Towards Open Domain Text-Driven Synthesis of Multi-person Motions.
Proceedings of the Computer Vision - ECCV 2024, 2024
OmniMotionGPT: Animal Motion Generation with Limited Data.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
EBM Life Cycle: MCMC Strategies for Synthesis, Defense, and Density Modeling.
CoRR, 2022
Learning Probabilistic Models from Generator Latent Spaces with Hat EBM.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Self-Joint Supervised Learning.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models.
Proceedings of the 9th International Conference on Learning Representations, 2021
Learning and Mapping Energy Functions of High-Dimensional Image Data.
PhD thesis, 2020
On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Divergence Triangle for Joint Training of Generator Model, Energy-Based Model, and Inferential Model.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model.
CoRR, 2018
Building a Telescope to Look Into High-Dimensional Image Spaces.
CoRR, 2018