Trung-Hieu Tran

Hieu Tran, Zonghai Yao, Hong Yu

Reinforcement learning improves LLM reasoning, yet sparse delayed reward over long sequences makes token-level credit assignment the key bottleneck. We study the verifiable-reward setting, where the final answer is checkable and multiple responses can be drawn per prompt. Reasoning tasks in math and medical QA align with this setup, where only a few decision tokens significantly impact the outcome. PPO offers token-level advantages with a learned value model, but it is complex to train both the actor and critic models simultaneously, and it is not easily generalizable, as the token-level values from the critic model can make training prone to overfitting. GRPO is critic-free and supports verifiable rewards, but spreads a single sequence-level return across tokens and ignores branching. We introduce \textbf{Prefix-to-Tree (P2T)}, a simple procedure that converts a group of responses into a prefix tree and computes \emph{nonparametric} prefix values \(V(s)\) by aggregating descendant outcomes. Built on P2T, we propose \textbf{TEMPO} (\emph{\textbf{T}ree-\textbf{E}stimated \textbf{M}ean Prefix Value for \textbf{P}olicy \textbf{O}ptimization}), a critic-free algorithm that augments the group-relative outcome signal of GRPO with \emph{branch-gated} temporal-difference corrections derived from the tree. At non-branch tokens, the temporal-difference (TD) term is zero, so TEMPO reduces to GRPO; at branching tokens, it supplies precise token-level credit without a learned value network or extra judges/teachers. On Qwen3-1.7B/4B, TEMPO outperforms PPO and GRPO on in-distribution (MATH, MedQA) and out-of-distribution (GSM-HARD, AMC23, MedMCQA, MMLU-Medical) benchmarks, and reaches higher validation accuracy with roughly the same wall-clock time.

Trung-Hieu Tran, Jan Berberich, Sven Simon

Light field (LF) imaging, which captures both spatial and angular information of a scene, is undoubtedly beneficial to numerous applications. Although various techniques have been proposed for LF acquisition, achieving both angularly and spatially high-resolution LF remains a technology challenge. In this paper, a learning-based approach applied to 3D epipolar image (EPI) is proposed to reconstruct high-resolution LF. Through a 2-stage super-resolution framework, the proposed approach effectively addresses various LF super-resolution (SR) problems, i.e., spatial SR, angular SR, and angular-spatial SR. While the first stage provides flexible options to up-sample EPI volume to the desired resolution, the second stage, which consists of a novel EPI volume-based refinement network (EVRN), substantially enhances the quality of the high-resolution EPI volume. An extensive evaluation on 90 challenging synthetic and real-world light field scenes from 7 published datasets shows that the proposed approach outperforms state-of-the-art methods to a large extend for both spatial and angular super-resolution problem, i.e., an average peak signal to noise ratio improvement of more than 2.0 dB, 1.4 dB, and 3.14 dB in spatial SR $\times 2$, spatial SR $\times 4$, and angular SR respectively. The reconstructed 4D light field demonstrates a balanced performance distribution across all perspective images and presents superior visual quality compared to the previous works.

Trung-Hieu Tran, Long Phan, Truong-Son Nguyen et al.

This paper proposed several transformer-based approaches for Reliable Intelligence Identification on Vietnamese social network sites at VLSP 2020 evaluation campaign. We exploit both of monolingual and multilingual pre-trained models. Besides, we utilize the ensemble method to improve the robustness of different approaches. Our team achieved a score of 0.9378 at ROC-AUC metric in the private test set which is competitive to other participants.