Minsu Kim

Researcher, Google DeepMind

Joined

February 2020

Names

Minsu Kim (Preferred)

Emails

****@kaist.ac.kr (Confirmed)

****@ieee.org (Confirmed)

****@meta.com (Confirmed)

****@google.com (Confirmed)

Personal Links

Career & Education History

Researcher

Google DeepMind (google.com)

2025 – Present

Postdoc

Facebook (meta.com)

2024 – 2025

PhD student

Korea Advanced Institute of Science and Technology (kaist.ac.kr)

2019 – 2024

Undergrad student

Yonsei University (yonsei.ac.kr)

2013 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Yong Man Ro

2019 – 2024

Expertise

Deep Learning

Multimodal Processing

Audio-Visual Speech Processing

2019 – Present

Publications

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
Umberto Cappellazzo, Minsu Kim, Stavros Petridis, Daniele Falavigna, Alessio Brutti
- Interspeech
- Readers: Everyone
MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
Umberto Cappellazzo, Minsu Kim, Pingchuan Ma, Honglie Chen, Xubo Liu, Stavros Petridis, Maja Pantic
- NeurIPS 2025 poster
- Readers: Everyone
Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs
Umberto Cappellazzo, Minsu Kim, Stavros Petridis
- OpenReview Archive Direct Upload
- Readers: Everyone
Large Language Models are Strong Audio-Visual Speech Recognition Learners
Umberto Cappellazzo, Minsu Kim, Honglie Chen, Pingchuan Ma, Stavros Petridis, Daniele Falavigna, Alessio Brutti, Maja Pantic
- ICASSP 2025
- Readers: Everyone
Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation
Minsu Kim, Jeonghun Yeo, Se Jin Park, Hyeongseop Rha, Yong Man Ro
- MM2024 Poster
- Readers: Everyone
Multilingual Visual Speech Recognition with a Single Model using Visual Speech Unit
Minsu Kim, Jeonghun Yeo, Jeongsoo Choi, Se Jin Park, Yong Man Ro
- Submitted to ICLR 2024
- Readers: Everyone
Lip-to-Speech Synthesis in the Wild with Multi-task Learning
Minsu Kim, Joanna Hong, Yong Man Ro
- 2023 (modified: 24 Apr 2023)
- CoRR 2023
- Readers: Everyone
Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring
Joanna Hong, Minsu Kim, Jeongsoo Choi, Yong Man Ro
- 2023 (modified: 24 Apr 2023)
- CoRR 2023
- Readers: Everyone
Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition
Minsu Kim, Hyung-Il Kim, Yong Man Ro
- Published: 01 Jan 2023, Last Modified: 12 May 2023
- CoRR 2023
- Readers: Everyone
Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Video
Minsu Kim, Chae Won Kim, Yong Man Ro
- Published: 01 Jan 2023, Last Modified: 12 May 2023
- CoRR 2023
- Readers: Everyone

View all 32 publications