Authors · raw publication identity
Yusuke Iwasawa
全分野 · 掲載済みの全期間（2017–2026年）
データの修正を申請Googleログイン後に申請できます。内容を確認してから対応します。
対象会議のFull paperを全分野・掲載済み全期間でまとめています。1996～2025年の追加分には、氏名の一致・表記の正規化等に基づき同一人物と推定した対応を含みます。本人確認済みの対応や出版時所属の確認とは区別しています。表示する大学は著者ページの識別用で、過去論文の出版時所属や現在所属を示しません。追加分は大学ランキングやEdition別の件数に含みません。保存済みの1996～2025年の対象資料から確認できた範囲を追加しており、全業績の網羅を保証するものではありません。
著者ページの大学: 東京大学 · Top conference papers: 35
分野別内訳
分野別の本数はcross-listにより重なる場合があります。合計本数は同一論文を1本に数えます。
年別内訳
- 2026年 14
- 2025年 6
- 2024年 6
- 2023年 2
- 2022年 3
- 2021年 2
- 2020年 1
- 2017年 1
論文一覧（新しい年順）
- Understanding Emergent Misalignment via Feature Superposition Geometry
- CLIP-like Model as a Foundational Density Ratio Estimator
- MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation
- Towards High-resolution and Disentangled Reference-based Sketch Colorization
- E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
- C-Voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
- RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
- SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNING
- Emergent Analogical Reasoning in Transformers
- Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian Noise
- M2oE: Modular Mixture of Experts for Multi-Morphology Reinforcement Learning of Modular Robots
- PHASE: Compliance-Enabled Tactile Phase Retrieval for Few-Shot Insertion Learning
- PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models
- SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM
- Image Referenced Sketch Colorization Based on Animation Creation Workflow
- MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
- ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA
- Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
- Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
- Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
- Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?
- GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policy
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration0
- Self-Recovery Prompting: Promptable General Purpose Service Robot System with Foundation Models and Self-Recovery
- On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
- ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
- A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
- End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
- Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment
- Langevin Autoencoders for Learning Deep Latent Variable Models
- Large Language Models are Zero-Shot Reasoners
- Group Equivariant Conditional Neural Processes
- Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization
- Stabilizing Adversarial Invariance Induction from Divergence Minimization Perspective
著者の全期間ページへの追加分（出版時所属は示していません）
- Privacy Issues Regarding the Application of DNNs to Activity-Recognition using Wearables and Its Countermeasures by Use of Adversarial Training
著者の全期間ページへの追加分（出版時所属は示していません）