Profiles2020-2026
Kyunghyun Cho
New York University
21Papers
8Last author
49Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers21
- Forget Forgetting: Continual Learning in a World of Abundant MemoryAuthor 4 of 5ICLR 2026 · 9 citations
- Multi-Task Bayesian In-Context LearningAuthor 3 of 3ICML 2026
- Why Knowledge Distillation Works in Generative Models: A Minimal Working ExplanationAuthor 2 of 2NeurIPS 2025 · 9 citations
- Scaling Laws Are Unreliable for Downstream Tasks: A Reality CheckAuthor 3 of 3EMNLP Findings 2025 · 4 citations
- Test Time Scaling for Neural ProcessesAuthor 4 of 6NeurIPS 2025 · 1 citation
- Language Models as Causal Effect GeneratorsAuthor 2 of 2EMNLP 2025
- Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMsAuthor 3 of 8ICLR 2024 · 119 citations
- Preference Learning Algorithms Do Not Learn Preference RankingsAuthor 7 of 7NeurIPS 2024 · 60 citations
- On the Blind Spots of Model-Based Evaluation Metrics for Text GenerationAuthor 5 of 7ACL 2023 · 10 citations
- Translation between Molecules and Natural LanguageAuthor 5 of 6EMNLP 2022 · 112 citations
- Chemical-Reaction-Aware Molecule Representation LearningAuthor 4 of 7ICLR 2022 · 79 citations
- Translating Hanja Historical Documents to Contemporary Korean and EnglishAuthor 5 of 7EMNLP Findings 2022 · 3 citations
- DEEP: DEnoising Entity Pre-training for Neural Machine TranslationAuthor 3 of 4ACL 2022
- Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' RuleAuthor 2 of 3ICLR 2021 · 29 citations
- The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event PredictionAuthor 5 of 10EMNLP 2021 · 29 citations
- Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with SearchAuthor 2 of 2ACL 2021
- Asking and Answering Questions to Evaluate the Factual Consistency of SummariesAuthor 2 of 4ACL 2020 · 317 citations
- Mixout: Effective Regularization to Finetune Large-scale Pretrained Language ModelsAuthor 2 of 3ICLR 2020 · 233 citations
- Connecting the Dots: Event Graph Schema Induction with Path Language ModelingAuthor 4 of 8EMNLP 2020 · 71 citations
- Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine TranslationAuthor 3 of 3EMNLP 2020 · 20 citations
- Learning to Learn Morphological Inflection for Resource-Poor LanguagesAuthor 3 of 3AAAI 2020 · 9 citations
