avatar

Yueqian Lin

ECE PhD Student
yueqian.lin [AT] duke [DOT] edu


📅  Schedule a Meeting

About Me

I am Max Yueqian Lin. I am a PhD student in the CEI lab of the Department of Electrical and Computer Engineering at Duke University. I am fortunate to be advised by Prof. Yiran Chen and Prof. Hai “Helen” Li. I hold a Bachelor’s degree in Data Science from Duke Kunshan University and Duke University, where I graduated in May 2024 with summa cum laude honors, a signature work distinction, and served as the valedictorian. My undergraduate studies were guided by Prof. Ming Li and Prof. Kai Zhang.

My research interests are broadly in the area of multimodal large language models, with a focus on audio and vison understanding and generation.

Please contact me if you would like to collaborate.

linyueqian's Github chart

News

[more]

[/more]

Selected Publications

Note: * stands for equal contribution.

    Manuscripts & Drafts

  1. arXiv
    Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
    Yudong Liu, Jingwei Sun, Yueqian Lin, Jingyang Zhang, Ming Yin, Qinsi Wang, Jianyi Zhang, Hai Li, Yiran Chen
    arXiv preprint arXiv:2503.10742
    Paper

    2. Conference Papers

  2. ICME
    SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
    Yueqian Lin*, Yuzhe Fu*, Jingyang Zhang, Yudong Liu, Jianyi Zhang, Jingwei Sun, Hai Li, Yiran Chen
    IEEE International Conference on Multimedia and Expo, 2025.
    Paper Demo
  3. INTERSPEECH
    Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and KiSing-v2
    Jiatong Shi*, Yueqian Lin*, Xinyi Bai, Keyi Zhang, Yuning Wu, Yuxun Tang, Yifeng Yu, Qin Jin, Shinji Watanabe
    Interspeech, 2024.
    Paper Code Oral presentation
  4. ICLR
    SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion
    Yueqian Lin*, Jingyang Zhang*, Yiran Chen, Hai Li
    International Conference on Learning Representations, Tiny Papers Track, 2024.
    Paper Code
  5. IEEE ASRU
    BiSinger: Bilingual Singing Voice Synthesis
    Huali Zhou*, Yueqian Lin*, Yao Shi, Peng Sun, Ming Li
    IEEE Automatic Speech Recognition & Understanding, 2023.
    Paper Code Demo Presentation

    6. Journal Papers

  6. DMLR
    OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
    Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xuefeng Du, Yixuan Li, Ziwei Liu, Yiran Chen, Hai Li
    Journal of Data-centric Machine Learning Research
    Paper Code Leaderboard
More Publications

Projects

  1. SPIRAL: Testing Speech Large Language Models' ability to process long spoken inputs GitHub Repo stars
    SPIRAL consists of spoken lectures and conversations with corresponding transcripts, questions, and metadata. The dataset is specifically crafted to evaluate models' comprehension and information retrieval capabilities from extended audio content.
  2. lmms-finetune: Enabling the finetuning of the latest Large Multimodal Models GitHub Repo stars
    This project aims to provide a unified and flexible framework for finetuning large multimodal models (LMMs) across various types, including single image, multiple image, and video models.

Honors

Services

Reviewer

Teaching Assistant

Duke University

Duke Kunshan University


[expand]

More About me

You can find more about my life below.

Current

Join Duke ECE as a first-year PhD student.

spotify-github-profile

2024 Aug

✈️ Back to the US for my PhD study at Duke ECE. A new chapter of life is about to begin.

2024 May

🎓 Spoke on behalf of my class at Duke Kunshan University’s 2024 commencement in the theme of “the three begot ten thousand things” from the Tao Te Ching. See news coverage here.

2023 Dec

🖥️ Attended IEEE ASRU 2023 virtually. Listened many great talks. Presented our paper BiSinger: Bilingual Singing Voice Synthesis.

2023 Dec

🧰 Attended NCMMSC 2023 in Suzhou, China. Presented our paper EEG-Based Speech Envelope Decoding: Structured State Space and U-Net Model Integration.

2023 Oct

🇦🇺 Attended IEEE Vis 2023 in Melbourne, Australia. Presented our poster RTVis: Research Trend Visualization Toolkit.

2023 Oct

🎤 Perform in the DKU “Embrace Music” Charity Show. Our performance on The Song of Voice Parts is reposted by the renounced Rainbow Choir.

2023 Sep

✏️ My first first-author paper BiSinger: Bilingual Singing Voice Synthesis has been accepted by IEEE ASRU 2023. This is a remarkable milestone in my research career.

2023 Sep

🎶 Went to Beijing to attend JJ Lin’s concert.

2023 Jul

🕶️ Attended ChinaVis 2023 in Chongqing, China.

2023 Mar

🎶 Went to Hong Kong Central to attend JJ Lin’s concert.

JJ20 JJ20

🎤 As a member of DKU Chorus, I sang in the main city event of the “Earth Hour” in Kunshan, China in 2023. Oops, now I have become a bass.

Bass Bass

2022 Dec

🎓 End my exchange at Duke. Have the last round of quarantine in SH.

2022 Nov

🎿 Ski at Stowe, Vermont.

2022 Aug

✈️ Flied to US for exchange at Duke. Our flight (DL766) from LAX to RDU had an unexpected land in LAS due to losing the cabin pressure. It was a very scary experience.

2022 May

🧐 Summer Research at DKU. Gain a lot of foundational experience in deep learning and signal processing.

2022 Feb

💤 Participated in the Mathmatical Contest in Modeling (MCM/ICM) 2022. Slept less than 3 hours per day.

2021 Dec

🎿 Ski at Lake Songhua, Jilin.

2021 Aug

🙌 Joined DKU Chorus as a tenor.

2021 Jun

🚙 Officially became a licensed driver.

🔬 Strated to do research with Prof. Kai Zhang. He taught me a lot about how to be a good researcher.

2020 Sep

🪪 Started my journey as the third-ever class’s UG student in Duke Kunshan University.

2020 Jan

😷 Locked down in Wuhan due to the COVID-19 when I was preparing for the Gaokao.

2014 Sep

⚙️ Became the one in charge of IT equipment in my class.

2008

🐧 Got my first QQ account. Start to play games like Gold Miner.

2003

👶 I was born in Wuhan.

[/expand]

Use this template