Thanh-Long V. Le

Thanh-Long V. Le

Hey there! Glad to have you here. Call me Long for short 😆. My full name in Vietnamese is Lê Viết Thanh Long.

I am a M.S. student at KAIST AI, advised by Prof. Eunho Yang and working closely with Dr. Viet Lai from Adobe Research. Previously, I received my B.S. degree in Computer Science at KAIST, advised by Prof. Sung-Ju Lee.

My research centers on large language models (LLMs), with an emphasis on improving their reasoning abilities through reinforcement learning and other post-training techniques. Recently, I have also begun exploring generative modeling, with a current focus on applying reinforcement learning to diffusion and flow models.

Outside of research, I’m deeply passionate about cinema and photography. If you ever find yourself in Seoul, feel free to shoot me an email—we could grab a coffee and yap about AI and movies, or head out for some spontaneous photo-taking!

News


Dec. 2025        🎉 I'll be joining Adobe Research as a Research Scientist Intern in Summer 2026. See you in Silicon Valley, USA!
Apr. 2025        🎉 One paper has been accepted to DIS 2025.
Feb. 2025        🏫 I started my M.S. in MLILAB at KAIST AI.
Sep. 2024        🎉 One paper has been accepted to NeurIPS 2024. This is my first publication at a top-tier conference.
Feb. 2024        🎓 I graduated from KAIST with a bachelor's degree in Computer Science.
Jun. 2023        🏫 I joined KAIST NMSL as a research intern.

Publications


No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Thanh-Long V. Le, Myeongho Jeon, Kim Vu, Viet Lai, Eunho Yang
In Submission
Paper Website

Design Opportunities for Explainable AI Paraphrasing Tools: A User Study with Non-native English Speakers
Yewon Kim, Thanh-Long V. Le, Donghwi Kim, Mina Lee, Sung-Ju Lee
Equal senior role
DIS 2025
Paper

(FL)2: Overcoming Few Labels in Federated Semi-Supervised Learning
Seungjoo Lee, Thanh-Long V. Le, Jaemin Shin, Sung-Ju Lee
NeurIPS 2024
Paper Website Code

Honors


Magna Cum Laude
Graduated with GPA 3.98/4.30, ranked top 10 in School of Computing, KAIST (2024).

KAIST–Qualcomm Innovation Award
Recognized as one of the top-performing teams in the KAIST–Qualcomm AI Hackathon (2023).

Dean’s List
Awarded to the top 3% of 2,900+ students in the College of Engineering, KAIST (2020).

KAIST International Undergraduate Scholarship
Full tuition and living support for the entire B.S. program (2019–2024).

Vietnam Mathematical Olympiad
Silver Medalist, VMO (2018).