Fangyu Liu

Orcid: 0000-0001-7038-3623

Affiliations:
  • University of Cambridge, Language Technology Lab, UK
  • University of Waterloo, ON, Canada
  • Beijing Normal University, Faculty of Geographical Science, China


According to our database1, Fangyu Liu authored at least 53 papers between 2017 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
LUQ: Long-text Uncertainty Quantification for LLMs.
CoRR, 2024

On-the-fly Denoising for Data Augmentation in Natural Language Understanding.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2024, 2024

2023
Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models.
CoRR, 2023

Compositional Zero-Shot Domain Transfer with Text-to-Text Models.
CoRR, 2023

Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding.
Proceedings of the International Conference on Machine Learning, 2023

POSQA: Probe the World Models of LLMs with Size Comparisons.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders.
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

WinoDict: Probing language models for in-context word acquisition.
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

On Reality and the Limits of Language Data: Aligning LLMs with Human Norms.
Proceedings of the 45th Annual Meeting of the Cognitive Science Society, 2023

MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

DePlot: One-shot visual language reasoning by plot-to-table translation.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022
Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems.
CoRR, 2022

On Reality and the Limits of Language Data.
CoRR, 2022

Language Models Can See: Plugging Visual Controls in Text Generation.
CoRR, 2022

Visual Spatial Reasoning.
CoRR, 2022

Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders.
CoRR, 2022

Modality-Balanced Embedding for Video Retrieval.
CoRR, 2022

Modality-Balanced Embedding for Video Retrieval.
Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022

TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colour.
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, 2022

How to tackle an emerging topic? Combining strong and weak labels for Covid news NER.
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, 2022

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages.
Proceedings of the International Conference on Machine Learning, 2022

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Sharpness-Aware Minimization with Dynamic Reweighting.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

Improving Bilingual Lexicon Induction with Cross-Encoder Reranking.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

Revisiting Parameter-Efficient Tuning: Are We Really There Yet?
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Prix-LM: Pretraining for Multilingual Knowledge Base Construction.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

Improving Word Translation via Two-Stage Contrastive Learning.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

Fine-Grained Controllable Text Generation Using Non-Residual Prompting.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

2021
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning.
CoRR, 2021

Fast, Effective and Self-Supervised: Transforming Masked LanguageModels into Universal Lexical and Sentence Encoders.
CoRR, 2021

DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2021

Self-Alignment Pretraining for Biomedical Entity Representations.
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021

Contrastive Out-of-Distribution Detection for Pretrained Transformers.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Visually Grounded Reasoning across Languages and Cultures.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models.
Proceedings of the 25th Conference on Computational Natural Language Learning, 2021

Integrating Transformers and Knowledge Graphs for Twitter Stance Detection.
Proceedings of the Seventh Workshop on Noisy User-generated Text, 2021

Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking.
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

Visual Pivoting for (Unsupervised) Entity Alignment.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Upgrading the Newsroom: An Automated Image Selection System for News Articles.
ACM Trans. Multim. Comput. Commun. Appl., 2020

Self-alignment Pre-training for Biomedical Entity Representations.
CoRR, 2020

COMETA: A Corpus for Medical Entity Linking in the Social Media.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020

HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
3D Depthwise Convolution: Reducing Model Parameters in 3D Vision Tasks.
Proceedings of the Advances in Artificial Intelligence, 2019

A Strong and Robust Baseline for Text-Image Matching.
Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019

2018
Joint Discriminative Dictionary and Classifier Learning for ALS Point Cloud Classification.
IEEE Trans. Geosci. Remote. Sens., 2018

Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model.
CoRR, 2018

A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases.
CoRR, 2018

Auto-classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model.
Proceedings of the Computer Vision - ACCV 2018 Workshops, 2018

2017
3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds.
Proceedings of the IEEE International Conference on Computer Vision, 2017


  Loading...