103 citations · 515 across the 26 of their papers we have counts for
26 papers
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
Ansong Ni, Pengcheng Yin, Yilun Zhao +11
Recently, large language models (LLMs), especially those that are pretrained on code, have demonstrated strong capabilities in generating programs from natural language inputs in a…
XGen-7B Technical Report
Erik Nijkamp, Tian Xie, Hiroaki Hayashi +22
Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LL…
EqGAN: Feature Equalization Fusion for Few-shot Image Generation
Yingbo Zhou, Zhihao Yue, Yutong Ye +3
Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity. T…
CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning
Pengyu Zhang, Yingbo Zhou, Ming Hu +2
Federated learning (FL) has been proposed to enable distributed learning on Artificial Intelligence Internet of Things (AIoT) devices with guarantees of high-level data privacy. Si…
Online Structured Meta-learning
Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi +3
Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has s…
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
Shiyang Li, Semih Yavuz, Kazuma Hashimoto +6
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations…
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
Junwen Bai, Weiran Wang, Yingbo Zhou +1
We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations…
WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos
Mingfei Gao, Yingbo Zhou, Ran Xu +2
Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications. Previous methods rely on tedious ann…
Fast and Robust Unsupervised Contextual Biasing for Speech Recognition
Young Mo Kang, Yingbo Zhou
Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area th…
An investigation of phone-based subword units for end-to-end speech recognition
Weiran Wang, Guangsen Wang, Aadyot Bhatnagar +3
Phones and their context-dependent variants have been the standard modeling units for conventional speech recognition systems, while characters and subwords have demonstrated their…
Differentially Private Deep Learning with Smooth Sensitivity
Lichao Sun, Yingbo Zhou, Philip S. Yu +1
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is th…
Private Deep Learning with Teacher Ensembles
Lichao Sun, Yingbo Zhou, Ji Wang +4
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information. Most pri…
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
Xilai Li, Yingbo Zhou, Tianfu Wu +2
Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. Despite recent…
Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation
Ehsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong +1
Training a model to perform a task typically requires a large amount of data from the domains in which the task will be applied. However, it is often the case that data are abundan…
End-to-End Dense Video Captioning with Masked Transformer
Luowei Zhou, Yingbo Zhou, Jason J. Corso +2
Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods…
A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
Ehsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong +1
Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-con…
Improved Regularization Techniques for End-to-End Speech Recognition
Yingbo Zhou, Caiming Xiong, Richard Socher
Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving e…
Improving End-to-End Speech Recognition with Policy Learning
Yingbo Zhou, Caiming Xiong, Richard Socher
Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between th…
Spelling Correction as a Foreign Language
Yingbo Zhou, Utkarsh Porwal, Roberto Konow
In this paper, we reformulated the spell correction problem as a machine translation task under the encoder-decoder framework. This reformulation enabled us to use a single model f…
On Optimality Conditions for Auto-Encoder Signal Recovery
Devansh Arpit, Yingbo Zhou, Hung Q. Ngo +2
Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sp…
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
Devansh Arpit, Yingbo Zhou, Bhargava U. Kota +1
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has cer…
Maximum Entropy Binary Encoding for Face Template Protection
Rohit Kumar Pandey, Yingbo Zhou, Bhargava Urala Kota +1
In this paper we present a framework for secure identification using deep neural networks, and apply it to the task of template protection for face authentication. We use deep conv…
Deep Secure Encoding: An Application to Face Recognition
Rohit Pandey, Yingbo Zhou, Venu Govindaraju
In this paper we present Deep Secure Encoding: a framework for secure classification using deep neural networks, and apply it to the task of biometric template protection for faces…
Why Regularized Auto-Encoders learn Sparse Representation?
Devansh Arpit, Yingbo Zhou, Hung Ngo +1
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solutio…