NewEvery arXiv paper, its researchers & institutions — mapped.
papers

Publications (211)

cs.CL2026

JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models

Junyu Liu, Zirui Li, Qian Niu +7

cs.CV2025

Image Referenced Sketch Colorization Based on Animation Creation Workflow

Dingkun Yan, Xinrui Wang, Zhuoru Li +4

hep-th2011

W(1+infinity) algebra as a symmetry behind AGT relation

Shoichi Kanno, Yutaka Matsuo, Shotaro Shiba

cs.AI2026

ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making

Yusuke Watanabe, Yohei Kobashi, Takeshi Kojima +3

cs.AI2025

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

Gouki Minegishi, Hiroki Furuta, Takeshi Kojima +2

hep-th2010

N=2 gauge theories and degenerate fields of Toda theory

Shoichi Kanno, Yutaka Matsuo, Shotaro Shiba +1

hep-th2008

M5 from M2

Pei-Ming Ho, Yutaka Matsuo

cs.LG2026

Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method

Chang Liu, Fei Suo, Yanzhou Jin +3

The paper introduces a temporally centered version of the Sketched Isotropic Gaussian Regularizer (SIGReg) that regularizes residuals instead of latent marginals, improving stabili…

#world models#multi-task learning#regularization#reinforcement learning
hep-th2002

Associativity Anomaly in String Field Theory

Itzhak Bars, Yutaka Matsuo

hep-th2016

Coherent states in quantum $\mathcal{W}_{1+\infty}$ algebra and qq-character for 5d Super Yang-Mills

Jean-Emile Bourgine, Masayuki Fukuda, Yutaka Matsuo +2

hep-th2015

Yangian associated with 2D $\mathcal{N}=1$ SCFT

Rui-Dong Zhu, Yutaka Matsuo

cs.AI2026

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima +2

cs.AI2025

When Object-Centric World Models Meet Policy Learning: From Pixels to Policies, and Where It Breaks

Stefano Ferraro, Akihiro Nakano, Masahiro Suzuki +1

cs.CL2026

Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models

Qi Cao, Takeshi Kojima, Andrew Gambardella +3

cs.CL2023

Large Language Models are Zero-Shot Reasoners

Takeshi Kojima, Shixiang Shane Gu, Machel Reid +2

cs.CV2026

Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting

Fumihiko Tsuchiya, Taiki Miyanishi, Shunsuke Yasuki +5

cs.CV2022

Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment

Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa

cs.AI2024

The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented Prompts

Wakana Haijima, Kou Nakakubo, Masahiro Suzuki +1

hep-th2009

Aspects of U-duality in BLG models with Lorentzian metric 3-algebras

Takayuki Kobo, Yutaka Matsuo, Shotaro Shiba

hep-th2006

Symmetry and Integrability of Non-Singlet Sectors in Matrix Quantum Mechanics

Yasuyuki Hatsuda, Yutaka Matsuo

cs.CV2025

WorldPack: Dynamic Frame Compression for Long-context Video World Modeling

Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki +2

cs.CV2026

JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation

Yue Xun, Junyu Liu, Qian Niu +10

cs.CL2025

Dynamic Injection of Entity Knowledge into Dense Retrievers

Ikuya Yamada, Ryokan Ri, Takeshi Kojima +2

stat.ML2016

Generative Adversarial Nets from a Density Ratio Estimation Perspective

Masatoshi Uehara, Issei Sato, Masahiro Suzuki +2

cs.AI2026

Visual Access Boundaries in Vision-Language Model Reasoning

Hiroto Osaka, Shohei Taniguchi, Gouki Minegishi +3

The paper investigates how chain-of-thought prompting works in vision-language models by introducing a visual access sweep that masks attention to image tokens, defining a visual a…

#chain-of-thought prompting#vision-language models#attention masking#visual access boundary
cs.LG2026

Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback

Hiroki Furuta, Heiga Zen, Dale Schuurmans +4

cs.AI2022

Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following

Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki +2

cs.LG2024

Geometric-Averaged Preference Optimization for Soft Preference Labels

Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu +4

cs.CL2023

Target-Aware Contextual Political Bias Detection in News

Iffat Maab, Edison Marrese-Taylor, Yutaka Matsuo

cs.CL2025

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation

Weihao Xuan, Rui Yang, Heli Qi +29

cs.LG2026

On Advantage Estimates for Max@K Policy Gradients

Shota Takashiro, Soichiro Nishimori, Paavo Parmas +6

hep-th2016

Nambu bracket and M-theory

Pei-Ming Ho, Yutaka Matsuo

cs.LG2026

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment

Jingyuan Feng, Andrew Gambardella, Gouki Minegishi +3

cs.LG2026

Looped Transformers with Source-Centered State Evolution

Bum Jun Kim, Kohei Hayashi, Shunsuke Kamiya +3

The paper introduces Source‑Centered State Evolution (SCSE), a method for looped Transformers that preserves input conditioning while keeping a fixed reference point, improving rec…

#looped transformers#recurrent depth#state evolution#anchor invariance
hep-th2001

Identity Projector and D-brane in String Field Theory

Yutaka Matsuo

cs.LG2021

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

Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima +2

hep-th1991

Classical W-symmetry and Grassmannian Manifold

Yutaka Matsuo

cs.CV2026

SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces

Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki +1

cs.RO2025

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Embodiment Collaboration, Abby O'Neill, Abdul Rehman +291

hep-th2004

Cardy states as idempotents of fusion ring in string field theory

Isao Kishimoto, Yutaka Matsuo

cs.CL2026

Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models

Xiaojie Gu, Sherry T. Tong, Aosong Feng +8

cs.CV2022

Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains

Xin Zhang, Shixiang Shane Gu, Yutaka Matsuo +1

cs.LG2020

Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization

Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo +2

hep-th2001

Exact Tachyon Condensation on Noncommutative Torus

Hiroshige Kajiura, Yutaka Matsuo, Tadashi Takayanagi

cs.CV2026

MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation

Yuta Oshima, Daiki Miyake, Kohsei Matsutani +4

physics.chem-ph2024

Low-Temperature Synthesis of Weakly Confined Carbyne inside Single-Walled Carbon Nanotubes

Bo-Wen Zhang, Xi-Yang Qiu, Yicheng Ma +16

cs.LG2026

Does "Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?

Ku Onoda, Paavo Parmas, Manato Yaguchi +1

cs.CL2018

IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations

Jorge A. Balazs, Edison Marrese-Taylor, Yutaka Matsuo

cs.CV2026

E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes

Koya Sakamoto, Taiki Miyanishi, Daichi Azuma +6

cs.AI2024

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

Jiaxian Guo, Bo Yang, Paul Yoo +3

hep-th2005

Boundary state in open string channel and open/closed string field theory

Hiroshi Isono, Yutaka Matsuo

cs.CV2025

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

Jungdae Lee, Taiki Miyanishi, Shuhei Kurita +4

cs.CL2017

EmoAtt at EmoInt-2017: Inner attention sentence embedding for Emotion Intensity

Edison Marrese-Taylor, Yutaka Matsuo

cs.RO2021

Tool as Embodiment for Recursive Manipulation

Yuki Noguchi, Tatsuya Matsushima, Yutaka Matsuo +1

cs.CL2025

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

Keno Harada, Lui Yoshida, Takeshi Kojima +2

cs.CL2025

When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following

Keno Harada, Yudai Yamazaki, Masachika Taniguchi +4

cs.CL2017

A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes

Pablo Loyola, Edison Marrese-Taylor, Yutaka Matsuo

cs.CV2024

Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases

Cristian Meo, Akihiro Nakano, Mircea Lică +7

hep-th2013

Extended Conformal Symmetry and Recursion Formulae for Nekrasov Partition Function

Shoichi Kanno, Yutaka Matsuo, Hong Zhang

cs.LG2024

A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees

Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato +6

cs.LG2026

OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation

Paavo Parmas, Yongmin Kim, Kohsei Matsutani +5

cs.RO2023

TRAIL Team Description Paper for RoboCup@Home 2023

Chikaha Tsuji, Dai Komukai, Mimo Shirasaka +13

cs.RO2025

A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics

Takeshi Kojima, Yaonan Zhu, Yusuke Iwasawa +8

cs.CL2025

MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering

Feiyang Li, Yingjian Chen, Haoran Liu +10

cs.LG2022

A survey of multimodal deep generative models

Masahiro Suzuki, Yutaka Matsuo

cs.RO2025

Leave No Observation Behind: Real-time Correction for VLA Action Chunks

Kohei Sendai, Maxime Alvarez, Tatsuya Matsushima +2

cs.LG2023

Pixyz: a Python library for developing deep generative models

Masahiro Suzuki, Takaaki Kaneko, Yutaka Matsuo

cs.LG2023

Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang +12

hep-th2012

Analysis of correlation functions in Toda theory and AGT-W relation for SU(3) quiver

Shoichi Kanno, Yutaka Matsuo, Shotaro Shiba

hep-th1992

Classical A_n--W-Geometry

Jean-Loup Gervais, Yutaka Matsuo

hep-th2003

Computing in String Field Theory Using the Moyal Star Product

Itzhak Bars, Yutaka Matsuo

cs.CL2025

Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning

Shota Takashiro, Takeshi Kojima, Andrew Gambardella +3

cs.CL2025

Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?

Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella +3

cs.CL2020

Character-level Japanese Text Generation with Attention Mechanism for Chest Radiography Diagnosis

Kenya Sakka, Kotaro Nakayama, Nisei Kimura +6

cs.IR2016

Understanding Rating Behaviour and Predicting Ratings by Identifying Representative Users

Rahul Kamath, Masanao Ochi, Yutaka Matsuo

cs.AI2026

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs

Kohsei Matsutani, Shota Takashiro, Gouki Minegishi +3

cs.CL2024

On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons

Takeshi Kojima, Itsuki Okimura, Yusuke Iwasawa +2

hep-th2003

Boundary states as exact solutions of (vacuum) closed string field theory

Isao Kishimoto, Yutaka Matsuo, Eitoku Watanabe

hep-th1993

Light-Cone Parametrizations for KÄhler Manifolds

Jean-Loup Gervais, Yutaka Matsuo

cs.CL2019

Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder

Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

hep-th2017

(p,q)-webs of DIM representations, 5d N=1 instanton partition functions and qq-characters

Jean-Emile Bourgine, Masayuki Fukuda, Koichi Harada +2

cs.AI2025

AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots

Xinjie Zhao, Moritz Blum, Fan Gao +10

stat.ML2016

Joint Multimodal Learning with Deep Generative Models

Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo

hep-th2015

SH$^c$ Realization of Minimal Model CFT: Triality, Poset and Burge Condition

Masayuki Fukuda, Satoshi Nakamura, Yutaka Matsuo +1

cs.LG2021

Wheelchair Behavior Recognition for Visualizing Sidewalk Accessibility by Deep Neural Networks

Takumi Watanabe, Hiroki Takahashi, Goh Sato +3

hep-th2014

Aspects of Effective Theory for Multiple M5-Branes Compactified On Circle

Pei-Ming Ho, Yutaka Matsuo

cs.CL2019

An Edit-centric Approach for Wikipedia Article Quality Assessment

Edison Marrese-Taylor, Pablo Loyola, Yutaka Matsuo

hep-th2012

Inner products of Bethe states as partial domain wall partition functions

Ivan Kostov, Yutaka Matsuo

cs.LG2025

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks

Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

cs.LG2026

Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form

Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai +6

cs.LG2026

C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions

Kenji Kubo, Shunsuke Kamiya, Masanori Koyama +3

cs.CV2023

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

Paul Yoo, Jiaxian Guo, Yutaka Matsuo +1

hep-th2017

Reflection states in Ding-Iohara-Miki algebra and brane-web for D-type quiver

Jean-Emile Bourgine, Masayuki Fukuda, Yutaka Matsuo +1

cs.RO2026

NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation

Daichi Azuma, Taiki Miyanishi, Koya Sakamoto +6

cs.AI2026

Emergent Analogical Reasoning in Transformers

Gouki Minegishi, Jingyuan Feng, Hiroki Furuta +3

cs.LG2022

Generalized Decision Transformer for Offline Hindsight Information Matching

Hiroki Furuta, Yutaka Matsuo, Shixiang Shane Gu

cs.CL2018

Learning to Automatically Generate Fill-In-The-Blank Quizzes

Edison Marrese-Taylor, Ai Nakajima, Yutaka Matsuo +1

hep-th2009

Lorentzian Lie (3-)algebra and toroidal compactification of M/string theory

Pei-Ming Ho, Yutaka Matsuo, Shotaro Shiba

hep-th2004

A universal nonlinear relation among boundary states in closed string field theory

Isao Kishimoto, Yutaka Matsuo, Eitoku Watanabe

cs.CV2025

ColorizeDiffusion v2: Enhancing Reference-based Sketch Colorization Through Separating Utilities

Dingkun Yan, Xinrui Wang, Yusuke Iwasawa +3