Youngwoo Shin

Ph.D. Candidate · Electrical Engineering, KAIST

I am a Ph.D. student at the Statistical Inference & Information Theory Laboratory (SIIT) at KAIST, advised by Prof. Junmo Kim.

I study how multimodal large language models represent and reason over time, and how to interpret the generation process to align better with intention.

I am currently looking for research internship opportunities. Feel free to reach out!

      Model Interpretability
      MLLMs
      Reasoning
      Generative Models
    

News

Sep 2026One paper has been accepted to NeurIPS 2026!

Mar 2026Started my Ph.D. at SIIT, KAIST.

Jan 2026One paper has been accepted to ICLR 2026!

Jul 2025One paper has been accepted to ACM Multimedia 2025!

Papers Under Review

Suppressing the Shortcut Hidden Behind the Gains of VideoLLM Fine-Tuning Youngwoo Shin, Jongsuk Kim†, Junmo Kim† Suppressing the shortcut that fine-tuning builds in VideoLLMs by intervening on the update through projection.

          Model InterpretabilityMLLMsReasoning
        

Publications

▼

Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs

Youngwoo Shin, Yusung Ro, Minseo Kim, Junmo Kim†

NeurIPS 2026

Reinforcing fading temporal signals in VideoLLMs at inference time, without additional training.

            Model InterpretabilityMLLMsReasoning
          

            arXivcode
          

SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation

Youngwoo Shin*, Jiwan Hur*, Junmo Kim†

ICLR 2026

Training-free guidance for visual autoregressive (VAR) models, derived from an information-theoretic view of next-scale generation.

            Model InterpretabilityGenerative Models
          

            arXivOpenReviewcode
          

B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding

Changho Choi*, Youngwoo Shin*, Gyojin Han, Dong-Jae Lee, Junmo Kim†

ACM Multimedia 2025

The first benchmark and baseline MLLM for spatio-temporal understanding of 4D LiDAR.

            MLLMs
          

            arXivcode
          

* equal contribution · † corresponding author

Education

2026 – present

KAIST — Ph.D. in Electrical Engineering Statistical Inference & Information Theory Laboratory (SIIT)

2024 – 2026

KAIST — M.S. in Electrical Engineering Statistical Inference & Information Theory Laboratory (SIIT)

2016 – 2023

KAIST — B.S. in Electrical Engineering

Industry Experience

2023 – 2024

LG CNS — Backend Engineer

2021 – 2023

Vitasoft — Computer Vision Researcher

Scholarships

2026 – 2028

Research Subsidies for Ph.D. National Research Foundation of Korea (NRF)
~600 selected among all STEM Ph.D. students nationwide · KRW 50M total

2024 – 2025

Research Subsidies for Master’s Students National Research Foundation of Korea (NRF)
~750 selected among all STEM master’s students nationwide · KRW 12M total

Teaching & Service

Spring, Fall 2025

EE202 Signals and Systems Teaching Assistant, School of Electrical Engineering, KAIST

Fall 2024
Spring, Fall 2025

EE215 EE Career Design Teaching Assistant, School of Electrical Engineering, KAIST

Fall 2024

EE205 Data Structures and Algorithms Teaching Assistant, School of Electrical Engineering, KAIST

Fall 2024
Spring, Fall 2025

Simultaneous Interpretation (Korean ↔ English) Official Interpreter, School of Electrical Engineering, KAIST

Skills & Languages

LanguagesPython, C, C++

FrameworksPyTorch, TensorFlow, ONNX, TensorRT

SpokenKorean (native), English (fluent)

Academic Services

ReviewerNeurIPS 2026, ICLR 2027