b'Shiyu Chang'

research

∙ 08/19/2023

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Sparsely-gated Mixture of Expert (MoE), an emerging deep model architect...

0 Yihua Zhang, et al. ∙

research

∙ 04/12/2023

Improving Diffusion Models for Scene Text Editing with Dual Encoders

Scene text editing is a challenging task that involves modifying or inse...

0 Jiabao Ji, et al. ∙

research

∙ 03/09/2023

Users are the North Star for AI Transparency

Despite widespread calls for transparent artificial intelligence systems...

0 Alex Mei, et al. ∙

research

∙ 11/21/2022

CLAWSAT: Towards Both Robust and Accurate Code Models

We integrate contrastive learning (CL) with adversarial learning to co-o...

5 Jinghan Jia, et al. ∙

research

∙ 10/16/2022

Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices

In this paper, we propose a data-model-hardware tri-design framework for...

2 Yimeng Zhang, et al. ∙

research

∙ 06/15/2022

Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning

Class-incremental learning (CIL) suffers from the notorious dilemma betw...

9 Tianlong Chen, et al. ∙

research

∙ 06/15/2022

Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

Certifiable robustness is a highly desirable property for adopting deep ...

4 Tianlong Chen, et al. ∙

research

∙ 05/24/2022

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

Trojan attacks threaten deep neural networks (DNNs) by poisoning them to...

4 Tianlong Chen, et al. ∙

research

∙ 04/15/2022

Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection

Lifelong event detection aims to incrementally update a model with new e...

0 Minqian Liu, et al. ∙

research

∙ 03/27/2022

How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective

The lack of adversarial robustness has been recognized as an important i...

2 Yimeng Zhang, et al. ∙

research

∙ 03/12/2022

Optimizer Amalgamation

Selecting an appropriate optimizer for a given problem is of major inter...

11 Tianshu Huang, et al. ∙

research

∙ 12/23/2021

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

Adversarial training (AT) has become a widely recognized defense mechani...

11 Yihua Zhang, et al. ∙

research

∙ 10/26/2021

Understanding Interlocking Dynamics of Cooperative Rationalization

Selective rationalization explains the prediction of complex neural netw...

0 Mo Yu, et al. ∙

research

∙ 10/14/2021

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding

Event extraction is typically modeled as a multi-class classification pr...

0 Sijia Wang, et al. ∙

research

∙ 10/04/2021

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

Are end-to-end text-to-speech (TTS) models over-parametrized? To what ex...

1 Cheng-I Jeff Lai, et al. ∙

research

∙ 06/16/2021

Global Rhythm Style Transfer Without Text Transcriptions

Prosody plays an important role in characterizing the style of a speaker...

6 Kaizhi Qian, et al. ∙

research

∙ 06/15/2021

Learning Stable Classifiers by Transferring Unstable Features

We study transfer learning in the presence of spurious correlations. We ...

7 Yujia Bao, et al. ∙

research

∙ 06/10/2021

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

Recent work on speech self-supervised learning (speech SSL) demonstrated...

4 Cheng-I Jeff Lai, et al. ∙

research

∙ 05/26/2021

Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers

We propose Predict then Interpolate (PI), a simple algorithm for learnin...

5 Yujia Bao, et al. ∙

research

∙ 03/22/2021

Complementary Evidence Identification in Open-Domain Question Answering

This paper proposes a new problem of complementary evidence identificati...

4 Xiangyang Mou, et al. ∙

research

∙ 03/18/2021

Generating Adversarial Computer Programs using Optimized Obfuscations

Machine learning (ML) models that learn and predict properties of comput...

12 Shashank Srikant, et al. ∙

research

∙ 02/14/2021

TransGAN: Two Transformers Can Make One Strong GAN

The recent explosive interest on transformers has suggested their potent...

0 Yifan Jiang, et al. ∙

research

∙ 12/22/2020

Self-Progressing Robust Training

Enhancing model robustness under new and even adversarial environments i...

9 Minhao Cheng, et al. ∙

research

∙ 12/12/2020

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

The computer vision world has been re-gaining enthusiasm in various pre-...

9 Tianlong Chen, et al. ∙

research

∙ 10/18/2020

Training Stronger Baselines for Learning to Optimize

Learning to optimize (L2O) has gained increasing attention since classic...

8 Tianlong Chen, et al. ∙

research

∙ 10/05/2020

Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning

Interactive Fiction (IF) games with real human-written natural language ...

4 Xiaoxiao Guo, et al. ∙

research

∙ 09/02/2020

Lifelong Object Detection

Recent advances in object detection have benefited significantly from ra...

3 Wang Zhou, et al. ∙

research

∙ 07/23/2020

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

In natural language processing (NLP), enormous pre-trained models like B...

7 Tianlong Chen, et al. ∙

research

∙ 06/26/2020

Proper Network Interpretability Helps Adversarial Robustness in Classification

Recent works have empirically shown that there exist adversarial example...

11 Akhilan Boopathy, et al. ∙

research

∙ 06/25/2020

Can 3D Adversarial Logos Cloak Humans?

With the trend of adversarial attacks, researchers attempt to fool train...

5 Tianlong Chen, et al. ∙

research

∙ 04/23/2020

Unsupervised Speech Decomposition via Triple Information Bottleneck

Speech information can be roughly decomposed into four components: langu...

0 Kaizhi Qian, et al. ∙

research

∙ 04/06/2020

Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games

We propose the new problem of learning to recover reasoning chains from ...

0 Yufei Feng, et al. ∙

research

∙ 03/28/2020

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

Pretrained models from self-supervision are prevalently used in fine-tun...

11 Tianlong Chen, et al. ∙

research

∙ 03/22/2020

Invariant Rationalization

Selective rationalization improves neural network interpretability by id...

5 Shiyu Chang, et al. ∙

research

∙ 10/29/2019

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

Selective rationalization has become a common mechanism to ensure that p...

0 Mo Yu, et al. ∙

research

∙ 10/28/2019

A Game Theoretic Approach to Class-wise Selective Rationalization

Selection of input features such as relevant pieces of text has become a...

13 Shiyu Chang, et al. ∙

research

∙ 10/01/2019

An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack

There are two major paradigms of white-box adversarial attacks that atte...

11 Yang Zhang, et al. ∙

research

∙ 09/17/2019

Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering

A key challenge of multi-hop question answering (QA) in the open-domain ...

0 Wenhan Xiong, et al. ∙

research

∙ 08/16/2019

Few-shot Text Classification with Distributional Signatures

In this paper, we explore meta-learning for few-shot text classification...

0 Yujia Bao, et al. ∙

research

∙ 08/13/2019

Meta Reasoning over Knowledge Graphs

The ability to reason over learned knowledge is an innate ability for hu...

0 Hong Wang, et al. ∙

research

∙ 08/11/2019

AutoGAN: Neural Architecture Search for Generative Adversarial Networks

Neural architecture search (NAS) has witnessed prevailing success in ima...

10 Xinyu Gong, et al. ∙

research

∙ 07/14/2019

TWEETQA: A Social Media Focused Question Answering Dataset

With social media becoming increasingly pop-ular on which lots of news a...

0 Wenhan Xiong, et al. ∙

research

∙ 06/12/2019

A Stratified Approach to Robustness for Randomly Smoothed Classifiers

Strong theoretical guarantees of robustness can be given for ensembles o...

1 Guang-He Lee, et al. ∙

research

∙ 06/11/2019

Self-Supervised Learning for Contextualized Extractive Summarization

Existing models for extractive summarization are usually trained from sc...

0 Hong Wang, et al. ∙

research

∙ 06/11/2019

Coupled Variational Recurrent Collaborative Filtering

We focus on the problem of streaming recommender system and explore nove...

0 Qingquan Song, et al. ∙

research

∙ 05/17/2019

Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader

We propose a new end-to-end question answering model, which learns to ag...

5 Wenhan Xiong, et al. ∙

research

∙ 05/16/2019

Additive Adversarial Learning for Unbiased Authentication

Authentication is a task aiming to confirm the truth between data instan...

6 Jian Liang, et al. ∙

research

∙ 05/15/2019

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets

Natural Language Sentence Matching (NLSM) has gained substantial attenti...

6 Guanhua Zhang, et al. ∙

research

∙ 05/14/2019

Zero-Shot Voice Style Transfer with Only Autoencoder Loss

Non-parallel many-to-many voice conversion, as well as zero-shot voice c...

5 Kaizhi Qian, et al. ∙

research

∙ 05/14/2019

AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

Non-parallel many-to-many voice conversion, as well as zero-shot voice c...

0 Kaizhi Qian, et al. ∙

Shiyu Chang

Featured Co-authors