Kenji Kawaguchi

STDE++: Polynomial-Time Amortization for Linear Differential Operators JMLR 2026 AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging NAACL 2025 Aligning Large Language Models with Human Opinions through Persona Selection and Value–Belief–Norm Reasoning COLING 2025 Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines ACL 2025 Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data NAACL 2025 Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning ICLR 2025 LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs NAACL 2025 Minimalist Concept Erasure in Generative Models ICML 2025 NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation ICLR 2025 Pruning General Large Language Models into Customized Expert Models ACL 2025 Single Character Perturbations Break LLM Alignment AAAI 2025 Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron ICLR 2025 Unnatural Languages Are Not Bugs but Features for LLMs ICML 2025 What Makes a Good Natural Language Prompt? ACL 2025 Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling NeurIPS 2024 Deep Regression Representation Learning with Topology ICML 2024 Drug Discovery with Dynamic Goal-aware Fragments ICML 2024 Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models ECCV 2024 Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers ICML 2024 How do Large Language Models Handle Multilingualism? NeurIPS 2024 Investigating Layer Importance in Large Language Models EMNLP 2024 Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization NeurIPS 2024 Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models EMNLP 2024 PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer ICML 2024 Prompt Optimization via Adversarial In-Context Learning ACL 2024 ProtT3: Protein-to-Text Generation for Text-based Protein Understanding ACL 2024 ReactXT: Understanding Molecular “Reaction-ship” via Reaction-Contextualized Molecule-Text Pretraining ACL 2024 Reasoning Robustness of LLMs to Adversarial Typographical Errors EMNLP 2024 Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion ICML 2024 Scalable and Effective Implicit Graph Neural Networks on Large Graphs ICLR 2024 Self-Supervised Dataset Distillation for Transfer Learning ICLR 2024 Simple Hierarchical Planning with Diffusion ICLR 2024 Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators NeurIPS 2024 The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline ICML 2024 The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling ICML 2024 Towards 3D Molecule-Text Interpretation in Language Models ICLR 2024 Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding AAAI 2024 Towards Robust Out-of-Distribution Generalization Bounds via Sharpness ICLR 2024 Unsupervised Concept Discovery Mitigates Spurious Correlations ICML 2024 VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models CVPR 2024 Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization for Heterogeneous Representational Coarseness AAAI 2023 An Information Theory Perspective on Variance-Invariance-Covariance Regularization NeurIPS 2023 Automatic Model Selection with Large Language Models for Reasoning EMNLP 2023 Auxiliary Learning as an Asymmetric Bargaining Game ICML 2023 D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory ICLR 2023 Discrete Key-Value Bottleneck ICML 2023 GFlowOut: Dropout with Generative Flow Networks ICML 2023 How Does Information Bottleneck Help Deep Learning? ICML 2023 Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks NeurIPS 2023 MixupE: Understanding and improving Mixup from directional derivative perspective UAI 2023 MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter EMNLP 2023 PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification NeurIPS 2023 Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules NeurIPS 2023 Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation ICML 2023 Self-Distillation for Further Pre-training of Transformers ICLR 2023 Self-Evaluation Guided Beam Search for Reasoning NeurIPS 2023 Self-Supervised Set Representation Learning for Unsupervised Meta-Learning ICLR 2023 Simplicial Embeddings in Self-Supervised Learning and Downstream Classification ICLR 2023 Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning NeurIPS 2022 MGNNI: Multiscale Graph Neural Networks with Implicit Layers NeurIPS 2022 Multi-Task Learning as a Bargaining Game ICML 2022 Robustness Implies Generalization via Data-Dependent Generalization Bounds ICML 2022 Set-based Meta-Interpolation for Few-Task Meta-Learning NeurIPS 2022 When and How Mixup Improves Calibration ICML 2022 Adversarial Training Helps Transfer Learning via Better Representations NeurIPS 2021 A Recipe for Global Convergence Guarantee in Deep Neural Networks AAAI 2021 Discrete-Valued Neural Communication NeurIPS 2021 EIGNN: Efficient Infinite-Depth Graph Neural Networks NeurIPS 2021 GraphMix: Improved Training of GNNs for Semi-Supervised Learning AAAI 2021 How Does Mixup Help With Robustness and Generalization? ICLR 2021 Noether Networks: meta-learning useful conserved quantities NeurIPS 2021 On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers ICLR 2021 Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth ICML 2021 Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time NeurIPS 2021 Towards Domain-Agnostic Contrastive Learning ICML 2021 Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization NeurIPS 2021 Elimination of All Bad Local Minima in Deep Learning AISTATS 2020 Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization AISTATS 2020 Deep Learning without Poor Local Minima NeurIPS 2016 Bayesian Optimization with Exponential Convergence NeurIPS 2015 Prior-Free Exploration Bonus for and beyond Near Bayes-Optimal Behavior IJCAI 2013