Wayne Wu

 

Ting-Wei Wu

Gatech ML PhD

UC Berkeley BioE MEng

National Taiwan University EE MS/BS


Conversational AI & Computer Vision

     

Latest News

  • [08/2023]: Join Amazon Alexa AI as an Applied Scientist!!
  • [06/2023]: Our paper: XDFusion has received the ACL Outstanding Paper Award!! (list)
  • [06/2023]: Passed ML Defense. Officially graduated from ML PhD program!! (thesis)
  • [05/2023]: Our paper: XDFusion has been accepted to ACL 2023 (main conference Oral Presentation)!!
  • [02/2023]: Our paper: CoFunDST has been accepted to ICASSP 2023!!
  • [01/2023]: Our paper: CKA-NLU has been published in EACL 2023 (Findings)!!

  • [08/2022]: Worked at Meta Reality Lab FAST AI Team as a Research Scientist Intern for cross-lingual dialogue system.
  • [08/2022]: Our paper to improve interpretability in retinal image captioning has been published in WACV 2023!!
  • [06/2022]: Our paper: Context Contrastive Clustering has been published in Interspeech 2022!!
  • [06/2022]: Our paper: ASR with LTR has been published in Interspeech 2022!!
  • [05/2022]: Worked at Amazon Alexa AI NLU Dynamic Routing Team as a Applied Scientist Intern.
  • [04/2022]: Passed ML Proposal Exam. Officially admitted to candidacy in ML PhD program!
  • [01/2022]: Our paper: KABEM has been published in ICASSP 2022!!
  • [10/2021]: Our paper: TransFuser has been published in WACV 2022!!
  • [08/2021]: Our paper: LABAN has been published in EMNLP 2021 (main conference)!!
  • [06/2021]: Our paper: CaBERT-SLU has been published in Interspeech 2021!!
  • [06/2021]: Our paper: ADST has been published in Interspeech 2021!!
  • [05/2021]: Worked at Amazon Alexa Speech Team as a Applied Scientist Intern.
  • [05/2021]: Our paper has been published in ICIP 2021!!
  • [04/2021]: Our paper has been published in ICMR 2021!!
  • [03/2021]: Passed ML Qualifying Exam.
  • [01/2021]: Our paper: DeepOpht has been published in WACV 2021!!

  • [05/2020]: Worked at VMware as a ML Research Intern for causality extraction in NLP.
  • [08/2019]: Joined Georgia Tech as a Machine Learning PhD student.
  • [05/2018]: Graduated from UC Berkeley BioE MEng!

About Me

Research

My research interests lie in the field of conversational AI and dialog systems. Particularly for low-resource, cross-lingual, multi-modal NLP and Speech Processing. While in National Taiwan University and UC Berkeley, I focused on BioMEMS applications in single cell analysis and cell-based data analysis.

Projects

I mainly focus on exploring deep learning technqiues to improve model's naturalness and robustness in spoken language understanding, task-oriented dialogs, speech recognition and multi-modal conversational QA, etc. I am also happy to work in Meta Reality Labs, Amazon Alexa Speech, Alexa Intelligent Decisions, and VMware.

Life

I also serve as program review committee in WACV, ECCV, EMNLP, AAAI, CVPR, ACL, Interspeech, etc. I enjoy playing sports especially basketball and badminton, guitar and drums outside academics. I am also have several leadership and extracurricular activity experiences in volunteering.
·

SKILLS

Machine Learning

Deep Learning

Natural Language Processing

Reinforcement Learning

Data Science (Statistics)

Language & Tools

Python, C++

Pytorch, Tensorflow, Keras

Huggingface, Pytext, Fairseq

Pyspark, Sklearn, Docker

Medical Electronics

MATLAB

Verilog

SPICE

AutoCAD, 3dsMax

Research

BioMEMS RNA-Seq
Device

UC Berkeley Capstone Project:
Single cell sequencing device using droplet-based microfluidics.

Speech &
Language Processing

Georgia Tech PhD research:
Spoken language understanding, low-resource conversational AI, image captioning.

Impedance-based Flow Cytometry

National Taiwan University Master Thesis:
Particle-analyzing devices fabricated with soft-lithography with machine learning analysis.

Check some of my latest research work.

Please feel free to click on the following icons.

XDFusion

Cross-lingual adaptive response generation

ACL Outstanding Paper Award (Oral Presentation) [Meta Reality Labs] Adopt mSeq2seqs for cross-lingual transfer in low-resource language generation.

Read More

LABAN

Multi-intent Zero-shot Detection

Enabled zero-shot intent detection with linear approximation of a user utterance using label BERT embeddings.

Read More

Intent Clustering

Contrastive Context Clustering for intent induction

An unsupervised approach to induce dialog intents with a new contrastive learning-based clustering method.

Read More

CKA-NLU

Context and Knowledge augmented SLU network. Published in Interspeech '21, ICASSP '22, EACL '23.

Enabled context and commonsense knowledge awareness for multi-intent and slot filling detection.

Read More

ASR with LTR

Learning to rank in ASR second pass rescoring

Enabled zero-shot intent detection with linear approximation of a user utterance using label BERT embeddings.

Read More

Skill Routing Robustness

Heterogeneous data augmentation in skill routing

[Amazon Alexa NLU] Adopt generative language models for heterogeneous data augmentation to improve skill routing model robustness in tail domains.

Read More

Deep EyeNet

Retinal image report generation

Generate medical descriptions for retinal images with keyword reinforced. This is a collaborative project with published papers. See more in the following link in github pages.

Read More

Stack Boxer

Interactive Chatroom with AI chatbot

Play Now!!

A fancy chatroom for you to chat with a deep minded chatbot both in english and chinese.
Three chatbots: StackBot, MovieBot, ChickBot!!

Read More

Make Hatsune & Naruto Image

Comic image generation

Simulated the style drawing of Naruto figures to construct new naruto characters completely by artificial intelligence with deep convolutional generative adversarial networks (GAN).

Read More

Malaria Image Prediction

Classify and diagnose disease possiblity of a malaria cell dataset with modified resnet50 structure implemented with pytorch, achieving testing accuracy around 85%.

Read More

Compose Chinese Lyrics

Trained machine to generate Chinese lyrics based on dataset of composed songs from four popular singers scraped from internet in Taiwan by pytorch with self-defined input words.

Read More

Describe an image (Contest)

Describe a general image with 1-2 sentences by using datasets from Google's Conceptual Captions Competition. Extract and train with ~50000 images to get decent results.

Read More

My experiences and how I build my life style.

Please feel free to click on the following icons to explore more my personal life
Extracurricular and volunteering activities

My Albums

Here is my personal life experiences! Click below to find more!

I live in the amazing Formosa: Taiwan

Album for my fantastic life

  • All
  • Family
  • Activities
  • Graduation
  • Trips

Berkeley Graduation

Berkeley Graduation

Berkeley Graduation

Berkeley Graduation

Berkeley Graduation

Berkeley Graduation

Streets Lab Graduation

Google Trip

Graduation Ceremony

Volunteering

IMCS 2016

Family Trip

Club Union

EE Camp 2015

EE Camp 2015

EE Camp 2015

Nepal Volunteering

Nepal Volunteering

Nepal Volunteering

Nepal Volunteering

YWCA Volunteering

Spain Trip

Spain Trip

Birthday Celebration

Bali Graduation Trip

Graduation Photo

Graduation Photo

Graduation Photo

Graduation Reception

Club Graduation

Birthday

Graduation Photo

Australia Youth Camp

Spanish Class

Aerobic Class

Drama Presentation

Clubbing Vacation

Japan Trip

Contact Me

 

Your message has been sent. Thank you!