Pracha Promthaw

Hi! I’m Pracha Promthaw, a MS Student in Computer Science at UC San Diego. Currently I’m fortunate to be working on research projects with Professor Julian McAuley and Professor Jingbo Shang, under the mentorship of Tianyang Liu and Zihan Wang.

Previously, I completed by Bachelor’s Degree at UMass Amherst, where I collaborated with Chris Samarinas as a PhD mentor, and was advised by Professor Hamed Zamani.

I see the future of AI as a partner to humans, not a replacement. My research explores ways to build reliable, practical tools for Human-AI collaboration, focusing on Human-AI alignment, LLM reasoning, and evaluation methods. I’m especially interested in applications as AI Agents, particularly in educational domain and broader societal impact.

Fun fact:

Outside of research, I enjoy drawing, singing, reading, and cooking (Here is my cooking diary). Right now, I’m studying both Japanese and French. (I’ll be sharing my drawing gallery on this site soon.)
At UMass Amherst, I performed in the Fringe Festival musical Fly By Night, playing the character Crable, one of my proudest performance on stage!

Extracurricular Club:

Thai Student Association (Senior Advisor)
UMass Machine Learning Club (Event Coordinator)
CS ForEach (Curriculum Team )

news

Apr 15, 2025	I got accepted to a Stanford’s Code In Place program as a Section Leader! A Program to teach Python to people from around the world!
Sep 28, 2024	Started my Master Degree at UC San Diego!
Apr 30, 2024	Our team get into the semi-final phase during the Alexa Prize Taskbot Challenge Competition!
Apr 19, 2023	My first medium blog got published! here :
Mar 27, 2023	I have been qualified into the final round of QTFT Optimization Hackathon!
Feb 17, 2023	Present a poster at the Undergraduate Research Volunteer session in topic "Continuous control of latent diffusion model through token embedding interpolation"
Dec 7, 2022	Got accepted into the Alexa Prize Project !

latest posts

Apr 20, 2023	Save your time with these numpy techniques
Apr 19, 2023	Numpy Blog

selected publications

Amazon

MarunaBot V2: Towards End-to-End Multi-Modal Task-Oriented Dialogue Systems

Chris Samarinas, Pracha Promthaw, Rohan Lekhwani, and 5 more authors

In Alexa Prize TaskBot Challenge Proceedings, 2023

Abs PDF

We introduce MarunaBot V2, an advanced Task-Oriented Dialogue System (TODS) primarily aimed at aiding users in cooking and Do-It-Yourself tasks. We utilized large language models (LLMs) for data generation and inference, and implemented hybrid methods for intent classification, retrieval, and question answering, striking a balance between efficiency and performance. A key feature of our system is its multi-modal capabilities. We have incorporated a multi-modal enrichment technique that uses a fine-tuned CLIP model to supplement recipe instructions with pertinent images, a custom Diffusion model for image enhancement and generation, and a method for multi-modal option matching. A unique aspect of our system is its user-centric development approach, facilitated by a custom tool for tracking user interactions and swiftly integrating feedback. Finally, we showcase the promising results of our end-to-end retrieval-augmented LLM taskbot, MarunaChef, and set a promising precedent for future task-oriented dialogue systems.
arxiv

Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models

Chris Samarinas, Pracha Promthaw, Atharva Nijasure, and 3 more authors

2024