Yusuke Iwasawa

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise CoNLL 2026 ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making ACL 2026 CLIP-like Model as a Foundational Density Ratio Estimator CVPR 2026 Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts EACL 2026 Investigating the Multilingual Calibration Effects of Language Model Instruction Tuning EACL 2026 MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation CVPR 2026 One-shot Portrait Stylizaiton via Geometric Alignment WACV 2026 Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability UAI 2026 Revealing Redundant Syntax in Large Language Models through Multi-Hop Dependency Paths EACL 2026 Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models EACL 2026 Towards High-resolution and Disentangled Reference-based Sketch Colorization CVPR 2026 Understanding Emergent Misalignment via Feature Superposition Geometry ACL 2026 A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics IJCAI 2025 Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning ACL 2025 Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence ICML 2025 Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data IJCNLP 2025 Dynamic Injection of Entity Knowledge into Dense Retrievers EMNLP 2025 Image Referenced Sketch Colorization Based on Animation Creation Workflow CVPR 2025 Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar ACL 2025 Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge NAACL 2025 MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation EMNLP 2025 ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA EMNLP 2025 Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words ICLR 2025 Slender-Mamba: Fully Quantized Mamba in 1.58 Bits From Head to Toe COLING 2025 When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following EMNLP 2025 ADOPT: Modified Adam Can Converge with Any β_2 with the Optimal Rate NeurIPS 2024 Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks ACL 2024 On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons NAACL 2024 Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance? EMNLP 2024 A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation ICLR 2023 End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization ICML 2023 Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text EMNLP 2023 Langevin Autoencoders for Learning Deep Latent Variable Models NeurIPS 2022 Large Language Models are Zero-Shot Reasoners NeurIPS 2022 Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment IJCAI 2022 Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-Reinforcement Learning L4DC 2021 Group Equivariant Conditional Neural Processes ICLR 2021 Making Use of Latent Space in Language GANs for Generating Diverse Text without Pre-training EACL 2021 Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization NeurIPS 2021 Stabilizing Adversarial Invariance Induction from Divergence Minimization Perspective IJCAI 2020 Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder Interspeech 2018 Privacy Issues Regarding the Application of DNNs to Activity-Recognition using Wearables and Its Countermeasures by Use of Adversarial Training IJCAI 2017