Yutaka Matsuo

papers

6,589

total citations

papers (14)

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

NEURIPS 2021arXiv

citations

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

NEURIPS 2025arXiv

citations

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

ICLR 2025arXiv

citations

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence

ICML 2025arXiv

citations

Image Referenced Sketch Colorization Based on Animation Creation Workflow

CVPR 2025arXiv

citations

Langevin Autoencoders for Learning Deep Latent Variable Models

NEURIPS 2022arXiv

citations

GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields

ICCV 2025arXiv

citations

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

NEURIPS 2025arXiv

citations

DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views

NEURIPS 2023

citations

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization

NEURIPS 2021

citations

Yutaka Matsuo

papers (14)

Large Language Models are Zero-Shot Reasoners

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

CityNav: A Large-Scale Dataset for Real-World Aerial Navigation

Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence

Image Referenced Sketch Colorization Based on Animation Creation Workflow

Langevin Autoencoders for Learning Deep Latent Variable Models

GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization

papers (14)

Large Language Models are Zero-Shot Reasoners

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

CityNav: A Large-Scale Dataset for Real-World Aerial Navigation

Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence

Image Referenced Sketch Colorization Based on Animation Creation Workflow

Langevin Autoencoders for Learning Deep Latent Variable Models

GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization