Skip to content
View t1modo's full-sized avatar
😤
Life is like a GitHub repository - nothing will change if you don’t commit.
😤
Life is like a GitHub repository - nothing will change if you don’t commit.
9 followers · 10 following

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Organizations

@slaclab

Block or report t1modo

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
t1modo/README.md

Hello, I'm Timothy Do

📫 Email: tim.do.info@gmail.com

📄 Resume: View Here

💼 Portfolio: Visit Here

💫 About Me

Studying software engineering at San Jose State University, I've built experience in AI research, scientific computing, and immersive technologies. I've published on making language models recover when multi-turn conversations go wrong, and on efficient figurative language classification for Konkani, a low-resource language. Before that I spent a summer at SLAC National Accelerator Laboratory, building the analysis pipeline for an ultrafast electron diffraction experiment. Right now I'm an AI Fellow at Accenture through Break Through Tech's AI Studio, working on supply chain disruption prediction, and a Cal-Bridge Undergraduate Scholar preparing for graduate research.

🌐 Socials

LinkedIn LeetCode HackerRank HuggingFace Kaggle Google Scholar Semantic Scholar

📄 Publications

  • Title: ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models
    Authors: Haziq Mohammad Khalid, Athikash Jeyaganthan, Timothy Do, Yicheng Fu, Sean O'Brien, Vasu Sharma, Kevin Zhu
    Publication: arXiv:2510.14077
    In Proceedings of the Second Workshop on Uncertainty-Aware NLP @ EMNLP 2025 | Published Paper
    Accepted to First Workshop on Multi-Turn Interactions in Large Language Models @ NeurIPS 2025 | Research Poster
    Accepted to Reliable ML from Unreliable Data @ NeurIPS 2025 | Research Poster

  • Title: Timing of Ultrafast Electron and Laser Pulses with Narrowband Thz Interferometry for Ultrafast Electron Diffraction
    Authors: Stephen Weathersby, Timothy Khang Do, Valery Dolgashev, Cameron J. R. Duncan, Joel England, Patrick Kramer, Mohamed Othman, Dennis Palmer
    In Proceedings of 2025 North American Particle Accelerator Conference (NAPAC) | Publication: DOI:10.18429/JACoW-NAPAC2025-TUP099

  • Title: Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT
    Authors: Timothy Do, Pranav Saran, Harshita Poojary, Pranav Prabhu, Sean O'Brien, Vasu Sharma, Kevin Zhu
    Publication: arXiv:2506.02005
    Accepted to Student Research Workshop @ IJCNLP-AACL 2025 | Research Poster
    Accepted to 1st Workshop on Multilingual Data Quality Signals @ COLM 2025 | Research Poster

💻 Tech Stack:

Java JavaScript LaTeX Markdown Python Firebase Render Vercel Expo Flask JavaFX NPM Next JS NodeJS React React Native TailwindCSS MongoDB MySQL SQLite Matplotlib NumPy Pandas PyTorch scikit-learn Canva Framer GitHub Git Notion

github-snake

Pinned Loading

  1. haziq-exe/ERGO haziq-exe/ERGO Public

    Model-agnostic inference framework that helps LLMs recover from context degradation and maintain performance across multi-turn conversations. (UncertaiNLP @ EMNLP 25' & MTI-LLM @ NeurIPS 25')

    Python 6 1

  2. slaclab/MeV-UED_First_Othman_Beamtime_Data_Analysis slaclab/MeV-UED_First_Othman_Beamtime_Data_Analysis Public

    Data Analysis for 1st Othman Beamtime

    Jupyter Notebook

  3. Algoverse_KonkaniNLP Algoverse_KonkaniNLP Public

    A research project webpage presenting efficient figurative language classification methods for low-resource Konkani using attention head pruning techniques.

    HTML 1

  4. Citey Citey Public

    Web application that notifies researchers right when their previously published work gets cited

    Python

  5. Break-Through-Tech/Accenture-2A-predict-the-supply-chain-disruptions Break-Through-Tech/Accenture-2A-predict-the-supply-chain-disruptions Public template

    Build an AI system that can predict supply chain disruptions and recommend mitigation actions using operational and contextual data.

    Jupyter Notebook 2