Kyunghyun Cho

The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models NAACL 2025 Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check EMNLP 2025 Shared Heritage, Distinct Writing: Rethinking Resource Selection for East Asian Historical Documents IJCNLP 2025 Following Length Constraints in Instructions EMNLP 2025 Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks ICML 2025 Semiparametric conformal prediction AISTATS 2025 Language Models as Causal Effect Generators EMNLP 2025 Shared Heritage, Distinct Writing: Rethinking Resource Selection for East Asian Historical Documents AACL 2025 $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs ICLR 2025 Aioli: A Unified Optimization Framework for Language Model Data Mixing ICLR 2025 Concept Bottleneck Language Models For Protein Design ICLR 2025 Predicting the Year of Total Knee Replacement: A Transformer-Based Multimodal Approach MIDL 2025 System-Level Natural Language Feedback EACL 2024 Generalization Measures for Zero-Shot Cross-Lingual Transfer EMNLP 2024 Concept Bottleneck Generative Models ICLR 2024 Protein Discovery with Discrete Walk-Jump Sampling ICLR 2024 Non-convolutional graph neural networks. NIPS 2024 Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient NIPS 2024 Preference Learning Algorithms Do Not Learn Preference Rankings NIPS 2024 Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning NIPS 2024 Iterative Reasoning Preference Optimization NIPS 2024 Multiple Physics Pretraining for Spatiotemporal Surrogate Models NIPS 2024 Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs ICLR 2024 Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning ICML 2024 Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization ICML 2024 Show Your Work with Confidence: Confidence Bands for Tuning Curves NAACL 2024 First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models NAACL 2024 BOtied: Multi-objective Bayesian optimization with tied multivariate ranks ICML 2024 Self-Rewarding Language Models ICML 2024 Leveraging Implicit Feedback from Deployment Data in Dialogue EACL 2024 Intriguing Effect of the Correlation Prior on ICD-9 Code Assignment ACL 2023 Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section ACL 2023 On the Blind Spots of Model-Based Evaluation Metrics for Text Generation ACL 2023 A Non-monotonic Self-terminating Language Model ICLR 2023 AbDiffuser: full-atom generation of in-vitro functioning antibodies NIPS 2023 Towards Understanding and Improving GFlowNet Training ICML 2023 Protein Design with Guided Discrete Diffusion NIPS 2023 On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis MIDL 2023 Linear Connectivity Reveals Generalization Strategies ICLR 2023 Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling CLEAR 2023 Improving Joint Speech-Text Representations Without Alignment INTERSPEECH 2023 Translation between Molecules and Natural Language EMNLP 2022 Chemical-Reaction-Aware Molecule Representation Learning ICLR 2022 Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling AACL 2022 Towards Disentangled Speech Representations INTERSPEECH 2022 Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling IJCNLP 2022 HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea NAACL 2022 DEEP: DEnoising Entity Pre-training for Neural Machine Translation ACL 2022 On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model NAACL 2022 Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks ICML 2022 Generative multitask learning mitigates target-causing confounding NIPS 2022 Translating Hanja Historical Documents to Contemporary Korean and English EMNLP 2022 Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement EMNLP 2021 VisualSem: a high-quality knowledge graph for vision and language EMNLP 2021 Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule ICLR 2021 Rissanen Data Analysis: Examining Dataset Characteristics via Description Length ICML 2021 Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021 MLE-Guided Parameter Search for Task Loss Minimization in Neural Sequence Modeling AAAI 2021 Comparing Test Sets with Item Response Theory ACL 2021 AdapterFusion: Non-Destructive Task Composition for Transfer Learning EACL 2021 Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models EACL 2021 The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction EMNLP 2021 Comparing Test Sets with Item Response Theory IJCNLP 2021 True Few-Shot Learning with Language Models NIPS 2021 Mode recovery in neural autoregressive sequence modeling ACL 2021 Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search ACL 2021 Mode recovery in neural autoregressive sequence modeling IJCNLP 2021 Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search IJCNLP 2021 SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness EMNLP 2020 Consistency of a Recurrent Language Model With Respect to Incomplete Decoding EMNLP 2020 Unsupervised Question Decomposition for Question Answering EMNLP 2020 AdapterHub: A Framework for Adapting Transformers EMNLP 2020 Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset EMNLP 2020 On the Discrepancy between Density Estimation and Sequence Generation EMNLP 2020 Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation EMNLP 2020 Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning COLING 2020 Compositionality and Capacity in Emergent Languages ACL 2020 Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset ACL 2020 Asking and Answering Questions to Evaluate the Factual Consistency of Summaries ACL 2020 Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training ACL 2020 A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks JMLR 2020 Improving the Ability of Deep Neural Networks to Use Information from Multiple Views in Breast Cancer Screening MIDL 2020 A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation AACL 2020 Neural Machine Translation with Byte-Level Subwords AAAI 2020 Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior AAAI 2020 Learning to Learn Morphological Inflection for Resource-Poor Languages AAAI 2020 Neural Text Generation With Unlikelihood Training ICLR 2020 Dynamics-Aware Embeddings ICLR 2020 Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models ICLR 2020 Connecting the Dots: Event Graph Schema Induction with Path Language Modeling EMNLP 2020 Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation EMNLP 2020 Neural Unsupervised Parsing Beyond English EMNLP 2019 Can Unconditional Language Models Recover Arbitrary Sentences? NIPS 2019 Classifier-Agnostic Saliency Map Extraction AAAI 2019 Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations ACL 2019 Generating Diverse Translations with Sentence Codes ACL 2019 Dialogue Natural Language Inference ACL 2019 Non-Monotonic Sequential Text Generation ACL 2019 Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples CVPR 2019 Finding Generalizable Evidence by Learning to Convince Q&A Models EMNLP 2019 Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set EMNLP 2019 Emergent Linguistic Phenomena in Multi-Agent Communication Games EMNLP 2019 Countering Language Drift via Visual Grounding EMNLP 2019 DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder ICLR 2019 Non-Monotonic Sequential Text Generation ICML 2019 Finding Generalizable Evidence by Learning to Convince Q&A Models IJCNLP 2019 Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set IJCNLP 2019 Emergent Linguistic Phenomena in Multi-Agent Communication Games IJCNLP 2019 Countering Language Drift via Visual Grounding IJCNLP 2019 BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model NAACL 2019 Jump to better conclusions: SCAN both left and right EMNLP 2018 Code-Switched Named Entity Recognition with Embedding Attention ACL 2018 Zero-Shot Transfer Learning for Event Extraction ACL 2018 The NYU System for the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection CONLL 2018 Dynamic Meta-Embeddings for Improved Sentence Representations EMNLP 2018 Emergent Communication in a Multi-Modal, Multi-Step Referential Game ICLR 2018 Unsupervised Neural Machine Translation ICLR 2018 Emergent Translation in Multi-Agent Communication ICLR 2018 Grammar Induction with Neural Language Models: An Unusual Replication EMNLP 2018 Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement EMNLP 2018 A Stable and Effective Learning Strategy for Trainable Greedy Decoding EMNLP 2018 Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding EMNLP 2018 Conditional Word Embedding and Hypothesis Testing via Bayes-by-Backprop EMNLP 2018 Meta-Learning for Low-Resource Neural Machine Translation EMNLP 2018 Boundary Seeking GANs ICLR 2018 Loss Functions for Multiset Prediction NIPS 2018 Training a Ranking Function for Open-Domain Question Answering NAACL 2018 Nematus: a Toolkit for Neural Machine Translation EACL 2017 Saliency-based Sequential Image Attention with Multiset Prediction NIPS 2017 Trainable Greedy Decoding for Neural Machine Translation EMNLP 2017 Task-Oriented Query Reformulation with Reinforcement Learning EMNLP 2017 Learning to Translate in Real-time with Neural Machine Translation EACL 2017 Learning to Parse and Translate Improves Neural Machine Translation ACL 2017 Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism NAACL 2016 Learning Distributed Representations of Sentences from Unlabelled Data NAACL 2016 Zero-Resource Translation with Multi-Lingual Neural Machine Translation EMNLP 2016 Iterative Refinement of the Approximate Posterior for Directed Belief Networks NIPS 2016 End-to-End Goal-Driven Web Navigation NIPS 2016 Gated Word-Character Recurrent Language Model EMNLP 2016 Neural Machine Translation ACL 2016 A Character-level Decoder without Explicit Segmentation for Neural Machine Translation ACL 2016 Larger-Context Language Modelling with Recurrent Neural Network ACL 2016 A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation COLING 2016 Joint Event Extraction via Recurrent Neural Networks NAACL 2016 Describing Videos by Exploiting Temporal Structure ICCV 2015 On Using Very Large Target Vocabulary for Neural Machine Translation IJCNLP 2015 On Using Very Large Target Vocabulary for Neural Machine Translation ACL 2015 Gated Feedback Recurrent Neural Networks ICML 2015 Show, Attend and Tell: Neural Image Caption Generation with Visual Attention ICML 2015 Attention-Based Models for Speech Recognition NIPS 2015 On the Number of Linear Regions of Deep Neural Networks NIPS 2014 Iterative Neural Autoregressive Distribution Estimator NADE-k NIPS 2014 Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation EMNLP 2014 Identifying and attacking the saddle point problem in high-dimensional non-convex optimization NIPS 2014 Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images ICML 2013