← Authors

Kenji Kawaguchi

80 papers · 2013–2025 · 13 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (8) πŸ—ΊοΈ Taxonomy Completionist (13) 🧭 Keyword Pioneer 🌍 Conference Polyglot (13) πŸƒ Academic Marathon (12) 🐣 Hot Topic Early Bird 🏠 Conference Loyalist (20) πŸ”¬ Deep Specialist (10) πŸ† Keyword Champion (2) πŸ† Grand Slam πŸ‘‘ Triple Crown πŸ—ƒοΈ Keyword Collector (227) ⚑ Prolific Year (26) πŸš€ Conference Pioneer πŸ’Ž Century Club (80) πŸ”₯ Unstoppable (6) πŸ“ˆ Trend Setter ❓ The Questioner (4)

Conferences

ICML (20) NIPS (20) ICLR (14) ACL (6) AAAI (5) EMNLP (5) NAACL (3) AISTATS (2) COLING (1) CVPR (1) ECCV (1) IJCAI (1) UAI (1)

Top co-authors

Yiran Zhao (9) Seanie Lee (8) Yoshua Bengio (8) Sung Ju Hwang (8) Anirudh Goyal (7) Min-Yen Kan (7) Xiang Wang (6) Tat-Seng Chua (6) Zhiyuan Liu (6) Zhun Deng (6)

Keywords

large language model (12) representation learning (9) prompt engineering (5) graph neural network (5) generalization bound (4) gradient descent (4) neural network optimization (3) self-supervised learning (3) in-context learning (3) neural network (3) node classification (3) adversarial attack (3) prompt optimization (3) semi-supervised learning (3) text generation (2) catastrophic forgetting (2) deep learning (2) mutual information (2) continual learning (2) data augmentation (2)

Papers

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