Michihiro Yasunaga

How to Make LMs Strong Node Classifiers? EACL 2026 reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs EMNLP 2025 Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model ICLR 2025 AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning NeurIPS 2024 HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models NeurIPS 2024 Image2Struct: Benchmarking Structure Extraction for Vision-Language Models NeurIPS 2024 Large Language Models as Analogical Reasoners ICLR 2024 REPLUG: Retrieval-Augmented Black-Box Language Models NAACL 2024 STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases NeurIPS 2024 VHELM: A Holistic Evaluation of Vision Language Models NeurIPS 2024 Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models ACL 2023 Complex Reasoning in Natural Language ACL 2023 Holistic Evaluation of Text-to-Image Models NeurIPS 2023 Is ChatGPT a General-Purpose Natural Language Processing Task Solver? EMNLP 2023 Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts AAAI 2023 Retrieval-Augmented Multimodal Language Modeling ICML 2023 VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering ICCV 2023 Zero-shot causal learning NeurIPS 2023 Deep Bidirectional Language-Knowledge Graph Pretraining NeurIPS 2022 Extending the WILDS Benchmark for Unsupervised Adaptation ICLR 2022 GreaseLM: Graph REASoning Enhanced Language Models ICLR 2022 LinkBERT: Pretraining Language Models with Document Links ACL 2022 UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models EMNLP 2022 Break-It-Fix-It: Unsupervised Learning for Program Repair ICML 2021 LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs ICML 2021 LM-Critic: Language Models for Unsupervised Grammatical Error Correction EMNLP 2021 QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering NAACL 2021 WILDS: A Benchmark of in-the-Wild Distribution Shifts ICML 2021 Graph-based, Self-Supervised Program Repair from Diagnostic Feedback ICML 2020 CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases EMNLP 2019 ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks AAAI 2019 SParC: Cross-Domain Semantic Parsing in Context ACL 2019 TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts AAAI 2019 Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering ACL 2018 Robust Multilingual Part-of-Speech Tagging via Adversarial Training NAACL 2018 Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task EMNLP 2018 SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task EMNLP 2018 Graph-based Neural Multi-Document Summarization CoNLL 2017