Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Xiaodan Liang

SOON: Scenario Oriented Object Navigation with Graph-based Exploration


Mar 31, 2021
Fengda Zhu, Xiwen Liang, Yi Zhu, Xiaojun Chang, Xiaodan Liang


  Access Paper or Ask Questions

DAGN: Discourse-Aware Graph Network for Logical Reasoning


Mar 26, 2021
Yinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang

* Accepted by NAACL 2021 

  Access Paper or Ask Questions

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search


Mar 24, 2021
Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang

* Our searched hybrid CNN-transformer models achieve up to 82.2% accuracy on ImageNet, surpassing EfficientNet by 2.1% with comparable compute time 

  Access Paper or Ask Questions

Dynamic Slimmable Network


Mar 24, 2021
Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

* Accepted to CVPR 2021 as an Oral Presentation 

  Access Paper or Ask Questions

A Data-Centric Framework for Composable NLP Workflows


Mar 03, 2021
Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Xiaodan Liang, Teruko Mitamura, Eric P. Xing, Zhiting Hu

* 8 pages, 4 figures, EMNLP 2020 

  Access Paper or Ask Questions

SparseBERT: Rethinking the Importance Analysis in Self-attention


Feb 25, 2021
Han Shi, Jiahui Gao, Xiaozhe Ren, Hang Xu, Xiaodan Liang, Zhenguo Li, James T. Kwok


  Access Paper or Ask Questions

Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search


Feb 09, 2021
Peidong Liu, Gengwei Zhang, Bochao Wang, Hang Xu, Xiaodan Liang, Yong Jiang, Zhenguo Li

* Accepted by ICLR2021 Poster 

  Access Paper or Ask Questions

UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers


Feb 07, 2021
Siyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang

* 15 pages, 8 figures 

  Access Paper or Ask Questions

GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer


Feb 01, 2021
Yukai Shi, Sen Zhang, Chenxing Zhou, Xiaodan Liang, Xiaojun Yang, Liang Lin

* The first two authors share equal-authorship; Code:https://github.com/SenZHANG-GitHub/graph-text-style-transfer ; benchmark: https://github.com/ykshi/text-style-transfer-benchmark 

  Access Paper or Ask Questions

Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer


Jan 26, 2021
Liang Lin, Yiming Gao, Ke Gong, Meng Wang, Xiaodan Liang

* To appear in IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (T-PAMI) 2021. We propose a graph reasoning and transfer learning framework, which incorporates human knowledge and label taxonomy into the intermediate graph representation learning beyond local convolutions. arXiv admin note: substantial text overlap with arXiv:1904.04536 

  Access Paper or Ask Questions

Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition


Jan 09, 2021
Fuyu Wang, Xiaodan Liang, Lin Xu, Liang Lin

* To appear in IEEE Transactions on Cybernetics 2021. We attempt to resolve the challenging medical report composition task by i) enforcing the semantic consistency of medical terms to be incorporated into the final reports; and ii) encouraging the sentence generation for rare abnormal descriptions 

  Access Paper or Ask Questions

REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement


Jan 03, 2021
Yinya Huang, Meng Fang, Xunlin Zhan, Qingxing Cao, Xiaodan Liang, Liang Lin

* Accepted by AAAI 2021 

  Access Paper or Ask Questions

Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition


Dec 23, 2020
Yubei Xiao, Ke Gong, Pan Zhou, Guolin Zheng, Xiaodan Liang, Liang Lin

* accepted in AAAI2021 

  Access Paper or Ask Questions

Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation


Dec 22, 2020
Shuai Lin, Pan Zhou, Xiaodan Liang, Jianheng Tang, Ruihui Zhao, Ziliang Chen, Liang Lin

* Accepted by AAAI 2021 

  Access Paper or Ask Questions

Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding


Dec 14, 2020
Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, Liang Lin

* To appear in TNNLS 2021. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed dataset aims to cutoff the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning 

  Access Paper or Ask Questions

Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation


Dec 07, 2020
Gengwei Zhang, Yiming Gao, Hang Xu, Hao Zhang, Zhenguo Li, Xiaodan Liang

* Accepted by AAAI2021 

  Access Paper or Ask Questions

Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp


Nov 30, 2020
Junfan Lin, Zhongzhan Huang, Keze Wang, Xiaodan Liang, Weiwei Chen, Liang Lin


  Access Paper or Ask Questions

Towards Robust Medical Image Segmentation on Small-Scale Data with Incomplete Labels


Nov 28, 2020
Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Min Xu, Irina Voiculescu, Eric P. Xing


  Access Paper or Ask Questions

Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation


Oct 30, 2020
Yangxin Wu, Gengwei Zhang, Hang Xu, Xiaodan Liang, Liang Lin

* NeurIPS2020 

  Access Paper or Ask Questions

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables


Oct 24, 2020
Wangchunshu Zhou, Jinyi Hu, Hanlin Zhang, Xiaodan Liang, Maosong Sun, Chenyan Xiong, Jian Tang


  Access Paper or Ask Questions

Iterative Graph Self-Distillation


Oct 23, 2020
Hanlin Zhang, Shuai Lin, Weiyang Liu, Pan Zhou, Jian Tang, Xiaodan Liang, Eric P. Xing


  Access Paper or Ask Questions

MedDG: A Large-scale Medical Consultation Dataset for Building Medical Dialogue System


Oct 15, 2020
Wenge Liu, Jianheng Tang, Jinghui Qin, Lin Xu, Zhen Li, Xiaodan Liang

* Data and code are available at https://github.com/lwgkzl/MedDG 

  Access Paper or Ask Questions

Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems


Oct 14, 2020
Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin

* EMNLP2020 

  Access Paper or Ask Questions

GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems


Oct 08, 2020
Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, Xiaodan Liang

* Long paper; EMNLP2020 

  Access Paper or Ask Questions

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending


Jul 23, 2020
Hang Xu, Shaoju Wang, Xinyue Cai, Wei Zhang, Xiaodan Liang, Zhenguo Li

* Accepted by ECCV2020 

  Access Paper or Ask Questions

CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search


Jul 22, 2020
Xin Chen, Yawen Duan, Zewei Chen, Hang Xu, Zihao Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

* Published at ECCV2020 

  Access Paper or Ask Questions