AIConfPaper
← Search

Yi-Lun Liao

7 accepted papers

2025

All-atom Diffusion Transformers: Unified generative modelling of molecules and materials

Chaitanya K. Joshi, Xiang Fu, Yi-Lun Liao, Vahe Gharakhanyan, Benjamin Kurt Miller, Anuroop Sriram +1
ICML 2025poster

Diffusion models are the standard toolkit for generative modelling of 3D atomic systems. However, for different types of atomic systems -- such as molecules and materials -- the generative processes are usually highly specific to the target system despite the underlying physics being the same. We in…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

Yi-Lun Liao, Brandon M Wood, Abhishek Das, Tess Smidt
ICLR 2024poster

Equivariant Transformers such as Equiformer have demonstrated the efficacy of applying Transformers to the domain of 3D atomistic systems. However, they are limited to small degrees of equivariant representations due to their computational complexity. In this paper, we investigate whether these arch…

Cited by 164Source ↗PDF ↗code ↗Scholar ↗
2022

On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis

Cheng-I Jeff Lai, Erica Cooper, Yang Zhang, Shiyu Chang, Kaizhi Qian, Yi-Lun Liao +5
ICASSP 2022accepted

Are end-to-end text-to-speech (TTS) models over-parametrized? To what extent can these models be pruned, and what happens to their synthesis capabilities? This work serves as a starting point to explore pruning both spectrogram prediction networks and vocoders. We thoroughly investigate the tradeoff…

Cited by 0Source ↗Scholar ↗
2021

NetAdaptV2: Efficient Neural Architecture Search With Fast Super-Network Training and Architecture Optimization

Tien-Ju Yang, Yi-Lun Liao, Vivienne Sze
CVPR 2021poster

Neural architecture search (NAS) typically consists of three main steps: training a super-network, training and evaluating sampled deep neural networks (DNNs), and training the discovered DNN. Most of the existing efforts speed up some steps at the cost of a significant slowdown of other steps or sa…

Cited by 33PDF ↗Scholar ↗
2021

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

Cheng-I Lai, Yang Zhang, Alexander H. Liu, Shiyu Chang, Yi-Lun Liao, Yung-Sung Chuang +4
NeurIPS 2021spotlight

Self-supervised speech representation learning (speech SSL) has demonstrated the benefit of scale in learning rich representations for Automatic Speech Recognition (ASR) with limited paired data, such as wav2vec 2.0. We investigate the existence of sparse subnetworks in pre-trained speech SSL models…

Cited by 80Source ↗PDF ↗Scholar ↗
2019

Learning Pose-aware 3D Reconstruction via 2D-3D Self-consistency

Yi-Lun Liao, Yao-Cheng Yang, Yuan-Fang Lin, Pin-Jung Chen, Chia-Wen Kuo, Wei-Chen Chiu +1
ICASSP 2019accepted

3D reconstruction, inferring 3D shape information from a single 2D image, has drawn attention from learning and vision communities. In this paper, we propose a framework for learning pose-aware 3D shape reconstruction. Our proposed model learns deep representation for recovering the 3D object, with…

Cited by 0Source ↗Scholar ↗