b'Xiujun Li'

research

∙ 01/02/2021

VinVL: Making Visual Representations Matter in Vision-Language Models

This paper presents a detailed study of improving visual representations...

Pengchuan Zhang, et al. ∙

research

∙ 12/25/2020

Self-supervised Pre-training with Hard Examples Improves Visual Representations

Self-supervised pre-training (SSP) employs random image transformations ...

Chunyuan Li, et al. ∙

research

∙ 12/13/2020

MiniVLM: A Smaller and Faster Vision-Language Model

Recent vision-language (VL) studies have shown remarkable progress by le...

Jianfeng Wang, et al. ∙

research

∙ 04/13/2020

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

Large-scale pre-training methods of learning cross-modal representations...

Xiujun Li, et al. ∙

research

∙ 04/05/2020

Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space

When trained effectively, the Variational Autoencoder (VAE) can be both ...

Chunyuan Li, et al. ∙

research

∙ 03/02/2020

Multi-View Learning for Vision-and-Language Navigation

Learning to navigate in a visual environment following natural language ...

Qiaolin Xia, et al. ∙

research

∙ 02/27/2020

Few-shot Natural Language Generation for Task-Oriented Dialog

As a crucial component in task-oriented dialog systems, the Natural Lang...

Baolin Peng, et al. ∙

research

∙ 02/25/2020

Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training

Learning to navigate in a visual environment following natural-language ...

Weituo Hao, et al. ∙

research

∙ 09/05/2019

Robust Navigation with Language Pretraining and Stochastic Sampling

Core to the vision-and-language navigation (VLN) challenge is building r...

Xiujun Li, et al. ∙

research

∙ 06/02/2019

Budgeted Policy Learning for Task-Oriented Dialogue Systems

This paper presents a new approach that extends Deep Dyna-Q (DDQ) by inc...

Zhirui Zhang, et al. ∙

research

∙ 04/18/2019

ConvLab: Multi-Domain End-to-End Dialog System Platform

We present ConvLab, an open-source multi-domain end-to-end dialog system...

Sungjin Lee, et al. ∙

research

∙ 03/06/2019

Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation

We present FAST NAVIGATOR, a general framework for action decoding, whic...

Liyiming Ke, et al. ∙

research

∙ 11/19/2018

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

Training task-completion dialogue agents with reinforcement learning usu...

Yuexin Wu, et al. ∙

research

∙ 11/01/2018

A bird's-eye view on coherence, and a worm's-eye view on cohesion

Generating coherent and cohesive long-form texts is a challenging proble...

Woon Sang Cho, et al. ∙

research

∙ 09/16/2018

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Responses generated by neural conversational models tend to lack informa...

Yizhe Zhang, et al. ∙

research

∙ 08/28/2018

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to impro...

Shang-Yu Su, et al. ∙

research

∙ 08/21/2018

Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning

Given a text description, most existing semantic parsers synthesize a pr...

Ziyu Yao, et al. ∙

research

∙ 07/29/2018

Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems

This proposal introduces a Dialogue Challenge for building end-to-end ta...

Xiujun Li, et al. ∙

research

∙ 04/20/2018

Subgoal Discovery for Hierarchical Dialogue Policy Learning

Developing conversational agents to engage in complex dialogues is chall...

Da Tang, et al. ∙

research

∙ 01/18/2018

Integrating planning for task-completion dialogue policy learning

Training a task-completion dialogue agent with real users via reinforcem...

Baolin Peng, et al. ∙

research

∙ 11/15/2017

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems

We present a new algorithm that significantly improves the efficiency of...

Zachary Lipton, et al. ∙

research

∙ 10/31/2017

Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning

This paper presents a new method --- adversarial advantage actor-critic ...

Baolin Peng, et al. ∙

research

∙ 04/10/2017

Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning

Building a dialogue agent to fulfill complex tasks, such as travel plann...

Baolin Peng, et al. ∙

research

∙ 03/21/2017

Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems

Language understanding is a key component in a spoken dialogue system. I...

Xiujun Li, et al. ∙

research

∙ 03/03/2017

End-to-End Task-Completion Neural Dialogue Systems

One of the major drawbacks of modularized task-completion dialogue syste...

Xiujun Li, et al. ∙

research

∙ 12/17/2016

A User Simulator for Task-Completion Dialogues

Despite widespread interests in reinforcement-learning for task-oriented...

Xiujun Li, et al. ∙

research

∙ 12/03/2016

End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager

Natural language understanding and dialogue policy learning are both ess...

Xuesong Yang, et al. ∙

research

∙ 09/03/2016

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which help...

Bhuwan Dhingra, et al. ∙

research

∙ 09/10/2015

Recurrent Reinforcement Learning: A Hybrid Approach

Successful applications of reinforcement learning in real-world problems...

Xiujun Li, et al. ∙

Xiujun Li

Featured Co-authors