Fangyu Liu

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation ICLR 2025 Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs NAACL 2024 Faithful Chart Summarization with ChaTS-Pi ACL 2024 LUQ: Long-text Uncertainty Quantification for LLMs EMNLP 2024 On-the-fly Denoising for Data Augmentation in Natural Language Understanding EACL 2024 Plot Twist: Multimodal Models Don’t Comprehend Simple Chart Details EMNLP 2024 ReMI: A Dataset for Reasoning with Multiple Images NeurIPS 2024 Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems COLING 2024 DePlot: One-shot visual language reasoning by plot-to-table translation ACL 2023 MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering ACL 2023 Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding ICML 2023 POSQA: Probe the World Models of LLMs with Size Comparisons EMNLP 2023 Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders EACL 2023 WinoDict: Probing language models for in-context word acquisition EACL 2023 Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colour AACL 2022 Fine-Grained Controllable Text Generation Using Non-Residual Prompting ACL 2022 How to tackle an emerging topic? Combining strong and weak labels for Covid news NER AACL 2022 IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages ICML 2022 Improving Bilingual Lexicon Induction with Cross-Encoder Reranking EMNLP 2022 Improving Word Translation via Two-Stage Contrastive Learning ACL 2022 Prix-LM: Pretraining for Multilingual Knowledge Base Construction ACL 2022 Revisiting Parameter-Efficient Tuning: Are We Really There Yet? EMNLP 2022 Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models ACL 2022 Sharpness-Aware Minimization with Dynamic Reweighting EMNLP 2022 TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning NAACL 2022 Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations ICLR 2022 TweetNLP: Cutting-Edge Natural Language Processing for Social Media EMNLP 2022 Contrastive Out-of-Distribution Detection for Pretrained Transformers EMNLP 2021 DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation WACV 2021 Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders EMNLP 2021 Integrating Transformers and Knowledge Graphs for Twitter Stance Detection EMNLP 2021 Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ACL 2021 MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models CoNLL 2021 Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT EMNLP 2021 Self-Alignment Pretraining for Biomedical Entity Representations NAACL 2021 Visually Grounded Reasoning across Languages and Cultures EMNLP 2021 Visual Pivoting for (Unsupervised) Entity Alignment AAAI 2021 COMETA: A Corpus for Medical Entity Linking in the Social Media EMNLP 2020 HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs AAAI 2020 A Strong and Robust Baseline for Text-Image Matching ACL 2019 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds ICCV 2017