Yan-Bo Lin
Computer vision · Multimodal learning

Yan-Bo Lin

I am a Senior Research Scientist at Bosch, working on multimodal senior data. Before joining Bosch, I completed my Ph.D. in Computer Science at UNC Chapel Hill, advised by Gedas Bertasius. My work spans efficient audio-video understanding, multimodal reasoning with LLMs, and video, audio, and music generation and editing.

Before coming to the U.S., I worked with Yen-Yu Lin, Ming-Hsuan Yang, and Yu-Chiang Frank Wang.

EMAILyblin [🅰️t🥳] cs.unc.edu
Portrait of Yan-Bo Lin

Selected Publications

View all papers on Google Scholar ↗
V2M-Zero paper preview

V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation

Yan-Bo Lin, Jonah Casebeer, Long Mai, Aniruddha Mahapatra, Gedas Bertasius, Nicholas J. Bryan

Conference on Neural Information Processing Systems (NeurIPS) · 2026

PaperProject
SiLVR paper preview

SiLVR: A Simple Language-based Video Reasoning Framework

Ce Zhang, Yan-Bo Lin, Ziyang Wang, Mohit Bansal, Gedas Bertasius

Transactions on Machine Learning Research (TMLR) · 2026

PaperProject
AvED paper preview

Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising

Yan-Bo Lin, Kevin Lin, Zhenyuan Yang, Linjie Li, Jianfeng Wang, Chung-Ching Lin, Xiaofei Wang, Gedas Bertasius, Lijuan Wang

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · 2026 Oral

PaperProjectCodeBibTeX
VMAs paper preview

VMAs: Video-to-Music Generation via Semantic Alignment in Web Music Videos

Yan-Bo Lin, Yu Tian, Linjie Yang, Gedas Bertasius, Heng Wang

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · 2025 Oral

PaperProject
Siamese Vision Transformers paper preview

Siamese Vision Transformers are Scalable Audio-visual Learners

Yan-Bo Lin, Gedas Bertasius

European Conference on Computer Vision (ECCV) · 2024

PaperCodeBibTeX
LAVISH paper preview

Vision Transformers are Parameter-Efficient Audio-Visual Learners

Yan-Bo Lin, Yi-Lin Sung, Jie Lei, Mohit Bansal, Gedas Bertasius

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2023

PaperProjectCodeBibTeX
ECLIPSE paper preview

ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound

Yan-Bo Lin, Jie Lei, Mohit Bansal, Gedas Bertasius

European Conference on Computer Vision (ECCV) · 2022 Oral

PaperProjectCodeDemoBibTeX
Audio-visual video parsing paper preview

Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing

Yan-Bo Lin, Hung-Yu Tseng, Hsin-Ying Lee, Yen-Yu Lin, Ming-Hsuan Yang

Conference on Neural Information Processing Systems (NeurIPS) · 2021

PaperCodeBibTeX
Spatial audio generation paper preview

Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation

Yan-Bo Lin, Yu-Chiang Frank Wang

AAAI Conference on Artificial Intelligence (AAAI) · 2021

PaperDemoBibTeX
Audiovisual Transformer paper preview

Audiovisual Transformer with Instance Attention for Audio-Visual Event Localization

Yan-Bo Lin, Yu-Chiang Frank Wang

Asian Conference on Computer Vision (ACCV) · 2020

PaperDemoSpotlightBibTeX

Experience

  1. Bosch

    Senior Research Scientist

  2. Adobe

    Research Intern

  3. Microsoft

    Research Intern

  4. ByteDance

    Research Intern

Education

  1. University of North Carolina at Chapel Hill

    Ph.D. in Computer Science

    Chapel Hill, NC, USA

    2021–2026

  2. National Taiwan University

    M.S. in Communication Engineering

    Taipei, Taiwan

    2017–2019

  3. National Central University

    B.S. in Computer Science

    Taoyuan, Taiwan

    2013–2017

Professional Activities

  • Program CommitteeTransformers for Vision (T4V) workshop at CVPR · 2022–2026WorldModelBench workshop at CVPR · 2025
  • ReviewerAAAI · ECCV · CVPR · ICCV · NeurIPS · ICML · TPAMI

Selected Honors

  • 1st Place Winner at CVPR 2025 MMLU Challenge
  • WACV Doctoral Consortium travel grant
  • TAAI Master's Thesis Honorable Mention Award
  • IPPR Master's Thesis Honorable Mention Award
  • Excellent Student Scholarship
  • National Science Council fellowship for excellent students
  • Undergraduate Research Project, First Prize
  • ASE International Conference on Social Informatics Best Paper Award
  • 2014–16Dean's Award · Fall 2014, Spring 2015, Fall 2016

Visitors