Yi-Lin (Pascal) Tuan

my_pic.png

pascaltuan at gmail.com

I’m a researcher of machine learning algorithms, specializing in conversational AI, reinforcement learning, model interpretability. My research includes:

I received a PhD in Computer Science from the University of California Santa Barbara, where I worked with Professor William Yang Wang. I received a BS in Electrical Engineering from National Taiwan University, where I fortunately worked with professors Lin-shan Lee, Hung-yi Lee, and Yun-Nung Chen on language modeling, deep learning algorithms, and speech processing.

Education

PhD, Computer Science, University of California Santa Barbara 2019-2024
BS, Electrical Engineering, National Taiwan University 2013-2017

Experience

Graduate Student Researcher, University of California Santa Barbara 2019-2024
Research Intern, Meta GenAI 2023
Research Intern, Meta AI 2022
Applied Scientist Intern, Amazon Alexa AI 2021
Research Intern, Facebook AI 2020
Research Assitant, National Taiwan University 2017-2019

Research Papers

  1. A Gradient Analysis Framework for Rewarding Good and Penalizing Bad Examples in Language Models
    Yi-Lin Tuan, and William Yang Wang
    preprint, 2024
  2. Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
    Yi-Lin Tuan, Xilun Chen, Eric Michael Smith, Louis Martin, Soumya Batra, Asli Celikyilmaz, William Yang Wang, and Daniel M. Bikel
    preprint, 2024
  3. Dynamic Latent Separation for Deep Learning
    Yi-Lin TuanZih-Yun Chiu, and William Yang Wang
    preprint, 2024
  4. Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning
    In NeurIPS, 2023
  5. CausalDialogue: Modeling Utterance-level Causality in Conversations
    In ACL-Findings, 2023
  6. Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
    In EMNLP-Findings, 2022
  7. FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue
    In EMNLP, 2022
  8. Deep Learning–Based Perceptual Stimulus Encoder for Bionic Vision
    Lucas Relic, Bowen Zhang, Yi-Lin Tuan, and Michael Beyeler
    In Augmented Humans, 2022
  9. D-REX: Dialogue Relation Extraction with Explanations
    In NLP for Conversational AI workshop in ACL, 2022
  10. HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data
    Kai Nakamura, Sharon LevyYi-Lin TuanWenhu Chen, and William Yang Wang
    In ACL-Findings, 2022
  11. Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems
    In ACL-Findings, 2022
  12. Local explanation of dialogue response generation
    NeuIPS, 2021
  13. Quality Estimation without Human-labeled Data
    In EACL, 2021
  14. Parallelized reverse curriculum generation
    Zih-Yun ChiuYi-Lin TuanHung-yi Lee, and Li-Chen Fu
    preprint, 2021
  15. Knowledge injection into dialogue generation via language models
    Yi-Lin TuanWei Wei, and William Yang Wang
    preprint, 2020
  16. DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
    Yi-Lin TuanYun-Nung Chen, and Hung-Yi Lee
    In EMNLP, 2019
  17. Personalized Dialogue Response Generation Learned from Monologues.
    Feng-Guang Su*Aliyah R Hsu*Yi-Lin Tuan, and Hung-Yi Lee
    In Interspeech, 2019
  18. Proximal policy optimization and its dynamic version for sequence generation
    Yi-Lin Tuan*, Jinzhi Zhang*, Yujia Li, and Hung-yi Lee
    preprint, 2018
  19. Improving conditional sequence generative adversarial networks by stepwise evaluation
    Yi-Lin Tuan, and Hung-Yi Lee
    IEEE/ACM Transactions on Audio, Speech, and Language Processing (Journal), 2018
  20. Transcribing lyrics from commercial song audio: The first step towards singing content processing
    Che-Ping Tsai*Yi-Lin Tuan*, and Lin-shan Lee
    In ICASSP, 2018

miscs

I like to write songs, play the guitar, learn languages, and explore new things!