Caiming Xiong

is this you? claim profile

∙ 0 followers
Microsoft ∙ Salesforce ∙ University at Buffalo

Director of Research, AI/ML at Salesforce

Featured Co-authors

Yoshua Bengio
345 publications
Bo Li
214 publications
Philip S. Yu
171 publications
Wei Chen
168 publications
Kyunghyun Cho
164 publications
Rui Zhang
163 publications
Jiashi Feng
158 publications
Yue Wang
121 publications
Stefano Ermon
111 publications
Richard Socher
109 publications
Devi Parikh
104 publications

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

Real world applications such as economics and policy making often involv...
02/23/2021 ∙ by Yu Bai, et al. ∙ 1 ∙ share

read it
Localized Calibration: Metrics and Recalibration

Probabilistic classifiers output confidence scores along with their pred...
02/22/2021 ∙ by Rachel Luo, et al. ∙ 1 ∙ share

read it
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification

Modern machine learning models with high accuracy are often miscalibrate...
02/15/2021 ∙ by Yu Bai, et al. ∙ 8 ∙ share

read it
Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models

In this work, we explore joint energy-based model (EBM) training during ...
01/18/2021 ∙ by Tianxing He, et al. ∙ 0 ∙ share

read it
Robustness Gym: Unifying the NLP Evaluation Landscape

Despite impressive performance on standard benchmarks, deep neural netwo...
01/13/2021 ∙ by Karan Goel, et al. ∙ 2 ∙ share

read it
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging

Influence functions approximate the 'influences' of training data-points...
12/31/2020 ∙ by Han Guo, et al. ∙ 9 ∙ share

read it
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization

The early phase of training has been shown to be important in two ways f...
12/28/2020 ∙ by Stanisław Jastrzębski, et al. ∙ 16 ∙ share

read it
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing

We present BRIDGE, a powerful sequential architecture for modeling depen...
12/23/2020 ∙ by Xi Victoria Lin, et al. ∙ 0 ∙ share

read it
CTRLsum: Towards Generic Controllable Text Summarization

Current summarization systems yield generic summaries that are disconnec...
12/08/2020 ∙ by Junxian He, et al. ∙ 0 ∙ share

read it
GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning

Disparate access to resources by different subpopulations is a prevalent...
12/07/2020 ∙ by Govardana Sachithanandam Ramachandran, et al. ∙ 0 ∙ share

read it
NaturalCC: A Toolkit to Naturalize the Source Code Corpus

We present NaturalCC, an efficient and extensible toolkit to bridge the ...
12/06/2020 ∙ by Yao Wan, et al. ∙ 0 ∙ share

read it
Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition

One crucial challenge of real-world multilingual speech recognition is t...
12/03/2020 ∙ by Genta Indra Winata, et al. ∙ 0 ∙ share

read it
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization

Semi-supervised learning has been an effective paradigm for leveraging u...
11/23/2020 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it
What's New? Summarizing Contributions in Scientific Literature

With thousands of academic articles shared on a daily basis, it has beco...
11/06/2020 ∙ by Hiroaki Hayashi, et al. ∙ 0 ∙ share

read it
Improving Limited Labeled Dialogue State Tracking with Self-Supervision

Existing dialogue state tracking (DST) models require plenty of labeled ...
10/26/2020 ∙ by Chien-Sheng Wu, et al. ∙ 0 ∙ share

read it
Probing Task-Oriented Dialogue Representation from Language Models

This paper investigates pre-trained language models to find out which mo...
10/26/2020 ∙ by Chien-Sheng Wu, et al. ∙ 0 ∙ share

read it
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference

Intent detection is one of the core components of goal-oriented dialog s...
10/25/2020 ∙ by Jian-Guo Zhang, et al. ∙ 10 ∙ share

read it
Unsupervised Paraphrase Generation via Dynamic Blocking

We propose Dynamic Blocking, a decoding algorithm which enables large-sc...
10/24/2020 ∙ by Tong Niu, et al. ∙ 5 ∙ share

read it
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers

Dialogue state trackers have made significant progress on benchmark data...
10/24/2020 ∙ by Shiyang Li, et al. ∙ 2 ∙ share

read it
Online Structured Meta-learning

Learning quickly is of great importance for machine intelligence deploye...
10/22/2020 ∙ by Huaxiu Yao, et al. ∙ 6 ∙ share

read it
Explaining and Improving Model Behavior with k Nearest Neighbor Representations

Interpretability techniques in NLP have mainly focused on understanding ...
10/18/2020 ∙ by Nazneen Fatema Rajani, et al. ∙ 0 ∙ share

read it
How Important is the Train-Validation Split in Meta-Learning?

Meta-learning aims to perform fast adaptation on a new task through lear...
10/12/2020 ∙ by Yu Bai, et al. ∙ 10 ∙ share

read it
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer f...
10/12/2020 ∙ by Pan Zhou, et al. ∙ 46 ∙ share

read it
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components

We propose Deep Autoencoding Predictive Components (DAPC) – a self-super...
10/07/2020 ∙ by Junwen Bai, et al. ∙ 0 ∙ share

read it
Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start

A standard way to address different NLP problems is by first constructin...
10/06/2020 ∙ by Wenpeng Yin, et al. ∙ 0 ∙ share

read it
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading

Document interpretation and dialog understanding are the two major chall...
10/05/2020 ∙ by Yifan Gao, et al. ∙ 6 ∙ share

read it
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing

We present GraPPa, an effective pre-training approach for table semantic...
09/29/2020 ∙ by Tao Yu, et al. ∙ 1 ∙ share

read it
Composed Variational Natural Language Generation for Few-shot Intents

In this paper, we focus on generating training examples for few-shot int...
09/21/2020 ∙ by Congying Xia, et al. ∙ 0 ∙ share

read it
MoPro: Webly Supervised Learning with Momentum Prototypes

We propose a webly-supervised representation learning method that does n...
09/17/2020 ∙ by Junnan Li, et al. ∙ 8 ∙ share

read it
Photon: A Robust Cross-Domain Text-to-SQL System

Natural language interfaces to databases (NLIDB) democratize end user ac...
07/30/2020 ∙ by Jichuan Zeng, et al. ∙ 13 ∙ share

read it
SummEval: Re-evaluating Summarization Evaluation

The scarcity of comprehensive up-to-date studies on evaluation metrics f...
07/24/2020 ∙ by Alexander R. Fabbri, et al. ∙ 0 ∙ share

read it
DART: Open-Domain Structured Data Record to Text Generation

We introduce DART, a large dataset for open-domain structured data recor...
07/06/2020 ∙ by Dragomir Radev, et al. ∙ 0 ∙ share

read it
Theory-Inspired Path-Regularized Differential Network Architecture Search

Despite its high search efficiency, differential architecture search (DA...
06/30/2020 ∙ by Pan Zhou, et al. ∙ 0 ∙ share

read it
BERTology Meets Biology: Interpreting Attention in Protein Language Models

Transformer architectures have proven to learn useful representations fo...
06/26/2020 ∙ by Jesse Vig, et al. ∙ 0 ∙ share

read it
Towards Understanding Hierarchical Learning: Benefits of Neural Representations

Deep neural networks can empirically perform efficient hierarchical lear...
06/24/2020 ∙ by Minshuo Chen, et al. ∙ 5 ∙ share

read it
A High-Quality Multilingual Dataset for Structured Documentation Translation

This paper presents a high-quality multilingual dataset for the document...
06/24/2020 ∙ by Kazuma Hashimoto, et al. ∙ 0 ∙ share

read it
WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos

Online action detection in untrimmed videos aims to identify an action a...
06/05/2020 ∙ by Mingfei Gao, et al. ∙ 0 ∙ share

read it
EMT: Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

The goal of conversational machine reading is to answer user questions g...
05/26/2020 ∙ by Yifan Gao, et al. ∙ 0 ∙ share

read it
Prototypical Contrastive Learning of Unsupervised Representations

This paper presents Prototypical Contrastive Learning (PCL), an unsuperv...
05/11/2020 ∙ by Junnan Li, et al. ∙ 10 ∙ share

read it
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation

Word embeddings derived from human-generated corpora inherit strong gend...
05/03/2020 ∙ by Tianlu Wang, et al. ∙ 0 ∙ share

read it
ESPRIT: Explaining Solutions to Physical Reasoning Tasks

Neural networks lack the ability to reason about qualitative physics and...
05/02/2020 ∙ by Nazneen Fatema Rajani, et al. ∙ 0 ∙ share

read it
VD-BERT: A Unified Vision and Dialog Transformer with BERT

Visual dialog is a challenging vision-language task, where a dialog agen...
04/28/2020 ∙ by Yue Wang, et al. ∙ 6 ∙ share

read it
ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues

The use of pre-trained language models has emerged as a promising direct...
04/15/2020 ∙ by Chien-Sheng Wu, et al. ∙ 0 ∙ share

read it
Towards Noise-resistant Object Detection with Noisy Annotations

Training deep object detectors requires significant amount of human-anno...
03/03/2020 ∙ by Junnan Li, et al. ∙ 2 ∙ share

read it
Differentially Private Deep Learning with Smooth Sensitivity

Ensuring the privacy of sensitive data used to train modern machine lear...
03/01/2020 ∙ by Lichao Sun, et al. ∙ 14 ∙ share

read it
Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT

There is an increasing amount of literature that claims the brittleness ...
02/27/2020 ∙ by Lichao Sun, et al. ∙ 0 ∙ share

read it
Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning

We introduce a parameterization method called Neural Bayes which allows ...
02/20/2020 ∙ by Devansh Arpit, et al. ∙ 36 ∙ share

read it
Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width

We propose Taylorized training as an initiative towards better understan...
02/10/2020 ∙ by Yu Bai, et al. ∙ 20 ∙ share

read it
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills

Acquiring abilities in the absence of a task-oriented reward function is...
02/10/2020 ∙ by Victor Campos, et al. ∙ 11 ∙ share

read it
Proposal Learning for Semi-Supervised Object Detection

In this paper, we focus on semi-supervised object detection to boost acc...
01/15/2020 ∙ by Peng Tang, et al. ∙ 11 ∙ share

read it