2025
All-atom Diffusion Transformers: Unified generative modelling of molecules and materials.
CoRR, March, 2025

2024
Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields.
Trans. Mach. Learn. Res., 2024

Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields.
CoRR, 2024

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
Searching for Efficient Multi-Stage Vision Transformers.
CoRR, 2021

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

NetAdaptV2: Efficient Neural Architecture Search With Fast Super-Network Training and Architecture Optimization.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2019
Learning Pose-aware 3D Reconstruction via 2D-3D Self-consistency.
Proceedings of the IEEE International Conference on Acoustics, 2019

2018
3D Shape Reconstruction from a Single 2D Image via 2D-3D Self-Consistency.
CoRR, 2018

Three-Dimensional Dynamic Programming Accelerator for Multiple Sequence Alignment.
Proceedings of the 2018 IEEE Nordic Circuits and Systems Conference, 2018

Adaptively Banded Smith-Waterman Algorithm for Long Reads and Its Hardware Accelerator.
Proceedings of the 29th IEEE International Conference on Application-specific Systems, 2018