Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Zhaojie JuSuggested from co-authorship
- Thomas S. HuangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works178 from public data
- Conformer: Convolution-augmented Transformer for Speech Recognition4,403
This work proposes the convolution-augmented transformer for speech recognition, named Conformer, which significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies.
- Generative Image Inpainting with Contextual Attention2,597
This work proposes a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.
- Free-Form Image Inpainting With Gated Convolution2,102
The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers.
- 1,955
- Universally Slimmable Networks and Improved Training Techniques473
This work proposes a systematic approach to train universally slimmable networks (US-Nets), extending slimmables to execute at arbitrary width, and generalizing to networks both with and without batch normalization layers, and opens up the possibility to directly evaluate FLOPs-Accuracy spectrum of network architectures.
- Foreground-Aware Image Inpainting402
This work proposes a foreground-aware image inpainting system that explicitly disentangles structure inference and content completion, and shows that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inPainting.
- 360
- BigNAS: Scaling up Neural Architecture Search with Big Single-Stage Models344
The proposed BigNAS, an approach that challenges the conventional wisdom that post-processing of the weights is necessary to get good prediction accuracies, is proposed, able to train a single set of shared weights on ImageNet and use these weights to obtain child models whose sizes range from 200 to 1000 MFLOPs.
- 327
- ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context306
This paper proposes a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy and demonstrates that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate of 2.1%/4.6%.
- 301
- Combined scaling for zero-shot transfer learning251
A theoretical framework is developed which shows that larger contrastive batch sizes lead to smaller generalization gaps for image-text models such as BASIC, and sheds light on the benefits of large contrastivebatch sizes.
- Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications235
An overview of GANs with a special focus on algorithms and applications for visual synthesis is provided and several important techniques to stabilize GAN training are covered, which has a reputation for being notoriously difficult.
- 217
- BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition212
It is found that the combination of pre-training, self-training and scaling up model size greatly increases data efficiency, even for extremely large tasks with tens of thousands of hours of labeled data.
- Engineered monoculture and co-culture of methylotrophic yeast for de novo production of monacolin J and lovastatin from methanol161
This study provides an alternative method for production of monacolin J and lovastatin and reveals the potential of a methylotrophic yeast to produce complicated pharmaceuticals from methanol.
- Pyramid Attention Network for Image Restoration142
A novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid, and is designed to be able to borrow clean signals from their “clean” correspondences at the coarser levels.
- A Better and Faster end-to-end Model for Streaming ASR136
The Conformer RNN-T with Cascaded Encoders offers a better quality and latency tradeoff for streaming ASR.
- 121
- 115
- FastEmit: Low-Latency Streaming ASR with Sequence-Level Emission Regularization108
This work proposes a sequence-level emission regularization method, named FastEmit, that applies latency regularization directly on per-sequence probability in training transducer models, and does not require any alignment.
- 90
- Cascaded Encoders for Unifying Streaming and Non-Streaming ASR89
This work presents cascaded encoders for building a single E2E ASR model that can operate in both streaming and non-streaming mode simultaneously, and shows that the proposed approach outperforms existing E 2E two-pass models, especially on long-form speech.
- 83
- Organic Compound Synthetic Accessibility Prediction Based on the Graph Attention Mechanism73
This study proposed a data-driven interpretable prediction framework called GASA (Graph Attention-based assessment of Synthetic Accessibility) to evaluate the synthetic accessibility of small molecules by distinguishing compounds to be easy- (ES) or hard-to-synthesize (HS).
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.