Authors · raw publication identity
Yutaka Matsuo
2022–2026 LIVE
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。
対象会議の検証済み掲載データを、全分野・選択したEditionでまとめています。過去の論文は出版・論文種別・著者との対応を確認できたものから追加しており、全発表論文の網羅を保証するものではありません。著者ページだけへの追加分は大学ランキングの件数に含みません。著者ページは、公開時の所属大学IDと論文上の著者名の完全一致を基に作成しています。本人の業績一覧などで同一人物の論文と個別に確認できた場合は、所属が異なる論文も追加します。氏名だけの自動名寄せは行いません。表示する大学はこのページの識別用で、掲載した全論文の出版時所属や現在所属を示すものではありません。研究者の総合順位を表すものでもありません。
著者ページの大学: 東京大学 · Top conference papers: 44
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。
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
- Does “Do Differentiable Simulators Give Better Policy Gradients?” Give Better Policy Gradients?
- Quantization-Aware Diffusion Models For Maximum Likelihood Training
- 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
- Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
- Emergent Analogical Reasoning in Transformers
- Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian Noise
- 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
- CityNav: A Large-Scale Dataset for Real-World Aerial Navigation
- GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields
- Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
- Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
- Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
- Language Models can Categorize System Inputs for Performance Analysis
- Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
- Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
- 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?
- A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
- Multimodal Web Navigation with Instruction-Finetuned Foundation Models
- 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
- Media Bias Detection Across Families of Language Models
- 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
- Geometric-Averaged Preference Optimization for Soft Preference Labels
- A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
- Interaction-Based Disentanglement of Entities for Object-Centric World Models
- End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
- Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
- DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views
- Generalized Decision Transformer for Offline Hindsight Information Matching
- 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