Research Log

Ph.D. student · Statistics and Data Science · Yonsei University

prof_pic.jpg

yjkim.stat@yonsei.ac.kr

Seoul, Republic of Korea

Ph.D. student in Statistics and Data Science at Yonsei University. I write paper reviews, survey posts, and notes on machine learning research — focusing on language model post-training, alignment, and reasoning.

For a full background, see my CV.

news

Feb 01, 2026 Started a research internship at Krafton.
Jul 15, 2025 Paper accepted at ICML 2025: Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective.
Mar 01, 2025 Paper published in Frontiers in Psychiatry: Aligning Large Language Models for Cognitive Behavioral Therapy: A Proof-of-Concept Study.
Jun 21, 2024 Paper accepted at ClinicalNLP 2024: ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification.
Feb 29, 2024 Finished research internship at Linq. Work contributed to arXiv:2412.03223.

latest posts

Aug 09, 2026 The Expressive Power of Transformers with Chain of Thought
Aug 07, 2026 Landscape of Thoughts — Visualizing Where LLM Reasoning Actually Goes
Jul 27, 2026 Magellan — Guided MCTS for Escaping the Gravity Wells of LLM Creativity

recent reports

Released May 18, 2026 Inference Architecture - May 18, 2026

exploration series

Agent Team Architecture 10 chapters · last updated Aug 07, 2026
  1. Ch. 1 Building an Agent Team with a Harness: Concepts and References May 06, 2026
  2. Ch. 2 When and How to Use Agents: A Practitioner's Frame May 18, 2026
  3. Ch. 3 Rules for an AI Research Agent Team: From Topic to Paper Draft May 18, 2026
  4. Ch. 4 Implicit Instruction: Teaching Agents Through Accumulated Experience May 25, 2026
  5. Ch. 5 CCTT — A Working Agent Team for Research Paper Writing May 28, 2026
  6. Ch. 6 Dynamic Workflows and Ultracode — Anthropic Ships the Orchestrator Pattern May 30, 2026
  7. Ch. 7 Two CCTT Workflows: Theory-Polish and Experiment-Polish for Research Papers Jun 06, 2026
  8. Ch. 8 Adversarial Feedback Loop 설계: 최근 연구가 말하는 것 Jul 06, 2026
  9. Ch. 9 Ultracode를 믿고 맡겨도 되는 순간 — Convergence를 Evaluation Signal로 만들기 Jul 29, 2026
  10. Ch. 10 Recipe for Research Team Management with Claude — 스스로 자라는 문헌 위키 Aug 07, 2026
Skills for Research Workflows 2 chapters · last updated May 18, 2026
  1. Ch. 1 Two Skills for Stress-Testing a Plan: grill-me and grill-with-docs May 18, 2026
  2. Ch. 2 A Packaged Skill for ML Paper Writing: Master-cai/Research-Paper-Writing-Skills May 18, 2026

explorations

Aug 20, 2026 에이전틱 시스템은 데이터를 어떻게 배치해야 하는가 — 온톨로지 문제
Aug 19, 2026 에이전트 메모리 아키텍처의 세 지층
Aug 07, 2026 Recipe for Research Team Management with Claude — 스스로 자라는 문헌 위키
Jul 29, 2026 Ultracode를 믿고 맡겨도 되는 순간 — Convergence를 Evaluation Signal로 만들기