Senior Researcher / Industrial AI Research

Yuuki Tachioka, Ph.D.

I am a senior industrial AI researcher working on knowledge- and constraint-aware AI systems. My recent work includes diagnosing LLM behavior via information spectrum analysis, efficient knowledge-augmented recommendation with lightweight LLMs, retrieval-augmented generation, multimodal document understanding, and physics-constrained generative modeling.

LLM analysis Information spectrum theory Recommender systems RAG Document & table understanding 6G / Wireless propagation Speech & acoustics

Research Themes

Research themes

Humans communicate and share knowledge through speech, writing, figures, tables, spaces, media, and artificial intelligence. My research aims to understand the structures behind communication and knowledge transfer, and to develop practical intelligent information processing technologies.

1. LLM analysis and knowledge-/constraint-aware AI systems

I analyze large language model behavior using information-theoretic approaches, including information spectrum theory, and study how side information, external knowledge, and constraints affect generation behavior.

2. Recommendation, RAG, and knowledge-graph-based information access

I study knowledge-augmented recommendation with lightweight LLMs, retrieval-augmented generation, and information access methods that incorporate user knowledge, venue knowledge, and structured knowledge.

3. Multimodal document understanding and structured knowledge extraction

I work on understanding visually rich documents that include text, tables, figures, and layouts, including text-table relatedness, joint triple extraction, and table cell entity annotation.

4. Wireless propagation and physics-constrained generative modeling for the 6G era

I study path loss map estimation, radio propagation modeling, wave simulation verification, and physics-constrained generative modeling using vision transformers and diffusion models.

5. Earlier work on acoustics, speech, dialogue, and quantitative linguistics

My earlier research includes room acoustic analysis, robust speech recognition under noise and reverberation, speech enhancement, spoken dialogue systems, and quantitative analysis of classical Japanese literature.

Selected Recent Publications

Selected recent publications

A short list of recent representative work. Please see the full publication list or CV for all papers.

  1. ACL 2026 Diagnosing LLMs via Information Spectrum Analysis: Tail Behavior and the Effects of Side Information. Y. Tachioka.
  2. SemEval 2026 @ ACL Per-Option Surprisal and Multi-Stage Gating for Precision-Oriented Causal Reasoning. Y. Terao and Y. Tachioka.
  3. RecSys 2025 Workshop KP4POI: Efficient POI Recommendation on Large-Scale Datasets via Knowledge Prompting of Venues and Users. Y. Tachioka.
  4. RecSys 2024 LBR User Knowledge Prompt for Sequential Recommendation. Y. Tachioka.
  5. NLDB 2025 Fusion-in-LLM: A Parallel Approach to Improve Retrieval-Augmented Generation for Quiz-Based Question Answering. Y. Tachioka.
  6. ESWC 2026 Challenge Typed Candidate Generation and Neural Verification for Joint Triple Extraction from Texts and Tables. Y. Tachioka.
  7. IEEE VTC 2026-Spring Training-Free Constraint-Guided Diffusion for One-Shot Path Loss Map Estimation. Y. Tachioka.
  8. EUSIPCO 2025 Enhancing Pathloss Estimation with Vision Transformers and Direct Wave Power Integration. Y. Tachioka.

Profile

Professional experience

Apr. 2022–present

Denso IT Laboratory, Senior Researcher

Apr. 2018–Mar. 2022

Denso IT Laboratory, Researcher

May 2017–Mar. 2018

Denso IT Laboratory, Associate Researcher

Apr. 2008–Apr. 2017

Mitsubishi Electric Corporation, Information Technology R&D Center, Researcher

Nov. 2012–Feb. 2013

Mitsubishi Electric Research Laboratories, Visitor

Education

Education

Apr. 2017–Mar. 2018

Ph.D. in Engineering, Tokyo Institute of Technology

Apr. 2011–Mar. 2014

B.A. in Japanese Language and Literature, Nihon University

Apr. 2006–Mar. 2008

M.Env., Graduate School of Frontier Sciences, The University of Tokyo

Apr. 2002–Mar. 2006

B.Eng., Department of Architecture, The University of Tokyo

Awards

Awards and honors

  • IEEE GCCE 2022 Excellent Paper Award (Gold Prize)
  • IPSJ Yamashita SIG Research Award, 2021
  • ISPACS 2018 Best Paper Award
  • 35th Awaya Prize, Acoustical Society of Japan, 2014
  • 19th Excellent Master’s Thesis Prize, Architectural Institute of Japan, 2008

Service

Academic activities

  • Information Processing Society of Japan, Senior Member
  • Reviewer: IEEE/ACM TASLP, Speech Communication, EURASIP Journal
  • Reviewer: ICASSP, ASRU, SLT, INTERSPEECH, SIGIR, APSIPA, SCIS&ISIS, NeurIPS
  • APSIPA Chair (2016), Area Chair (2023)