b'Xiujun Li'

VinVL: Making Visual Representations Matter in Vision-Language Models

This paper presents a detailed study of improving visual representations...
01/02/2021 ∙ by Pengchuan Zhang, et al. ∙ 10 ∙ share

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

Self-supervised pre-training (SSP) employs random image transformations ...
12/25/2020 ∙ by Chunyuan Li, et al. ∙ 0 ∙ share

read it
MiniVLM: A Smaller and Faster Vision-Language Model

Recent vision-language (VL) studies have shown remarkable progress by le...
12/13/2020 ∙ by Jianfeng Wang, et al. ∙ 0 ∙ share

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

Large-scale pre-training methods of learning cross-modal representations...
04/13/2020 ∙ by Xiujun Li, et al. ∙ 7 ∙ share

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

When trained effectively, the Variational Autoencoder (VAE) can be both ...
04/05/2020 ∙ by Chunyuan Li, et al. ∙ 1 ∙ share

read it
Multi-View Learning for Vision-and-Language Navigation

Learning to navigate in a visual environment following natural language ...
03/02/2020 ∙ by Qiaolin Xia, et al. ∙ 7 ∙ share

read it
Few-shot Natural Language Generation for Task-Oriented Dialog

As a crucial component in task-oriented dialog systems, the Natural Lang...
02/27/2020 ∙ by Baolin Peng, et al. ∙ 0 ∙ share

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

Learning to navigate in a visual environment following natural-language ...
02/25/2020 ∙ by Weituo Hao, et al. ∙ 1 ∙ share

read it
Robust Navigation with Language Pretraining and Stochastic Sampling

Core to the vision-and-language navigation (VLN) challenge is building r...
09/05/2019 ∙ by Xiujun Li, et al. ∙ 5 ∙ share

read it
Budgeted Policy Learning for Task-Oriented Dialogue Systems

This paper presents a new approach that extends Deep Dyna-Q (DDQ) by inc...
06/02/2019 ∙ by Zhirui Zhang, et al. ∙ 2 ∙ share

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

We present ConvLab, an open-source multi-domain end-to-end dialog system...
04/18/2019 ∙ by Sungjin Lee, et al. ∙ 6 ∙ share

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

We present FAST NAVIGATOR, a general framework for action decoding, whic...
03/06/2019 ∙ by Liyiming Ke, et al. ∙ 6 ∙ share

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

Training task-completion dialogue agents with reinforcement learning usu...
11/19/2018 ∙ by Yuexin Wu, et al. ∙ 0 ∙ share

read it
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...
11/01/2018 ∙ by Woon Sang Cho, et al. ∙ 0 ∙ share

read it
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Responses generated by neural conversational models tend to lack informa...
09/16/2018 ∙ by Yizhe Zhang, et al. ∙ 0 ∙ share

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

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to impro...
08/28/2018 ∙ by Shang-Yu Su, et al. ∙ 0 ∙ share

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

Given a text description, most existing semantic parsers synthesize a pr...
08/21/2018 ∙ by Ziyu Yao, et al. ∙ 0 ∙ share

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

This proposal introduces a Dialogue Challenge for building end-to-end ta...
07/29/2018 ∙ by Xiujun Li, et al. ∙ 0 ∙ share

read it
Subgoal Discovery for Hierarchical Dialogue Policy Learning

Developing conversational agents to engage in complex dialogues is chall...
04/20/2018 ∙ by Da Tang, et al. ∙ 0 ∙ share

read it
Integrating planning for task-completion dialogue policy learning

Training a task-completion dialogue agent with real users via reinforcem...
01/18/2018 ∙ by Baolin Peng, et al. ∙ 0 ∙ share

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

We present a new algorithm that significantly improves the efficiency of...
11/15/2017 ∙ by Zachary Lipton, et al. ∙ 0 ∙ share

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

This paper presents a new method --- adversarial advantage actor-critic ...
10/31/2017 ∙ by Baolin Peng, et al. ∙ 0 ∙ share

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

Building a dialogue agent to fulfill complex tasks, such as travel plann...
04/10/2017 ∙ by Baolin Peng, et al. ∙ 0 ∙ share

read it
Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems

Language understanding is a key component in a spoken dialogue system. I...
03/21/2017 ∙ by Xiujun Li, et al. ∙ 0 ∙ share

read it
End-to-End Task-Completion Neural Dialogue Systems

One of the major drawbacks of modularized task-completion dialogue syste...
03/03/2017 ∙ by Xiujun Li, et al. ∙ 0 ∙ share

read it
A User Simulator for Task-Completion Dialogues

Despite widespread interests in reinforcement-learning for task-oriented...
12/17/2016 ∙ by Xiujun Li, et al. ∙ 0 ∙ share

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

Natural language understanding and dialogue policy learning are both ess...
12/03/2016 ∙ by Xuesong Yang, et al. ∙ 0 ∙ share

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

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which help...
09/03/2016 ∙ by Bhuwan Dhingra, et al. ∙ 0 ∙ share

read it
Recurrent Reinforcement Learning: A Hybrid Approach

Successful applications of reinforcement learning in real-world problems...
09/10/2015 ∙ by Xiujun Li, et al. ∙ 0 ∙ share

read it

Xiujun Li

Featured Co-authors