Tri Ton

PhD student, Korea Advanced Institute of Science & Technology

Joined

October 2023

Names

Tri Ton (Preferred)

Emails

****@kaist.ac.kr (Confirmed)

Personal Links

Career & Education History

PhD student

Korea Advanced Institute of Science & Technology (kaist.ac.kr)

2022 – 2027

Advisors, Relations & Conflicts

PhD Advisor

2022 – 2027

Expertise

Computer Vision

2022 – 2027

Deep Learning

2022 – 2027

Publications

TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
Tri Ton, Ji Woo Hong, Chang D. Yoo
- International Conference on Computer Vision (ICCV)
- Readers: Everyone
Diffusion Negative Preference Optimization Made Simple
Joshua Tian Jin Tee, Hee Suk Yoon, Sunjae Yoon, Tri Ton, Chang D. Yoo
- ICLR 2026 Poster
- Readers: Everyone
MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation
Trung X. Pham, Tri Ton, Chang D. Yoo
- ICLR 2025 Poster
- Readers: Everyone
Zero-Shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation
Tri Ton, Ji Woo Hong, SooHwan Eom, Jun Yeop Shim, Junyeong Kim, Chang D. Yoo
- CVPR Workshops 2024
- Readers: Everyone
Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
Thanh Xuan Nguyen, Tung Minh Luu, Tri Ton, Chang D. Yoo
- CoRR 2024
- Readers: Everyone
Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning
Thanh Xuan Nguyen, Tung Minh Luu, Tri Ton, Sungwoong Kim, Chang D. Yoo
- IEEE Access 2024
- Readers: Everyone
On the Perturbed States for Transformed Input-robust Reinforcement Learning
Tung Minh Luu, Haeyong Kang, Tri Ton, Thanh Nguyen, Chang D. Yoo
- CoRR 2024
- Readers: Everyone

Co-Authors