activity
20242026
collaborators

8 papers

cs.LG2026

Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning

Thanh Nguyen, Tri Ton, Hongbin Choe +2

Diffusion-based Q-learning has emerged as a powerful paradigm for offline reinforcement learning, but its reliance on multi-step denoising makes both training and inference computa…

cs.LG2026

One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning

Thanh Nguyen, Chang D. Yoo

Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step denoising for action…

cs.LG2026

Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning

Thanh Nguyen, Tung Luu, Tri Ton +2

Offline reinforcement learning (RL) has garnered significant interest due to its safe and easily scalable paradigm. However, training under this paradigm presents its own challenge…

cs.SD2025

TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis

Tri Ton, Ji Woo Hong, Chang D. Yoo

This paper introduces Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning (TARO), a novel framework for high-fidelity and temporally coherent video-to-audio sy…

cs.LG2025

Predictive Coding for Decision Transformer

Tung M. Luu, Donghoon Lee, Chang D. Yoo

Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decisio…

cs.SD2025

MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation

Trung X. Pham, Tri Ton, Chang D. Yoo

We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference speed. This framework in…