TT

Tri Ton

0009-0006-6820-4431

cs.LGcs.ROcs.AIcs.CV

On Valency

published · living versions

W_k2zhmf35·v1 · currentpublished

Progress-Guided Preference Generation for Aligning Generative Control Policies

with Tung M. Luu, Duc M. Nguyen, Xuan Thanh Nguyen, Nguyen Gia Binh +6

1 version

Preprints & journals

8 papers in the corpus · 2024–2026

Progress-Guided Preference Generation for Aligning Generative Control Policies2610.25692v1 · Tung M. Luu, Tri Ton, Duc M. Nguyen et al.2026 · 0 citationsarXivon Valency

SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation2609.20475v1 · Euiseok Han, Tri Ton, Hwanhee Kim et al.2026 · 0 citationsarXiv

Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning2606.10613v1 · Thanh Nguyen, Tri Ton, Hongbin Choe et al.2026 · 0 citationsICML 2026

Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning2602.19917v1 · Thanh Nguyen, Tung Luu, Tri Ton et al.2026 · 1 citationIEEE Access, vol. 12, pp. 100972-100982, 2024

ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On2503.20418v2 · Ji Woo Hong, Tri Ton, Trung X. Pham et al.2025 · 5 citationsarXiv

Zero-Shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation2408.08591v1 · Tri Ton, Ji Woo Hong, SooHwan Eom et al.2024 · 1 citationarXiv

On the Perturbed States for Transformed Input-robust Reinforcement Learning2408.00023v2 · Tung M. Luu, Haeyong Kang, Tri Ton et al.2024 · 0 citationsarXiv

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses2405.11206v1 · Thanh Nguyen, Tung M. Luu, Tri Ton et al.2024 · 4 citationsInternational Conference on Pattern Recognition and Artificial Intelligence (ICPRAI) 2024

Career total: 8 works. 8 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.