Xuan-Bach Le

works on

cross-axis ties 1 delta merging 1 few-shot learning 1 low-resource adaptation 1 multilingual models 1

From the 1 of 3 linked papers with an AI index.

collaborators

3 papers

cs.CL2026

NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and Reasoning

Thuong-Hieu Ngo, Hoang-Trung Nguyen, Huu-Dong Nguyen +5

This paper presents the methodologies and results of the NOWJ team's participation across all five tasks of the COLIEE 2026 competition. For Task 1 (Legal Case Retrieval), we propo…

cs.CL2026

DeltaMerge-LowRes: Composing Language and Task Deltas for Low-Resource Adaptation

Son Ha Xuan, Xuan-Bach Le, Phat T. Tran-Truong

The paper introduces DeltaMerge‑LowRes, a method that learns separate language and task parameter deltas and merges them in weight space using rules such as cross‑axis TIES, enabli…

cs.LG2024

Reinforcement Learning with LTL and $I ¨ $ -Regular Objectives via Optimality-Preserving Translation to Average Rewards

Xuan-Bach Le, Dominik Wagner, Leon Witzman +2

Linear temporal logic (LTL) and, more generally, $I ¨ $ -regular objectives are alternatives to the traditional discount sum and average reward objectives in reinforcement learning (R…

NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and Reasoning

DeltaMerge-LowRes: Composing Language and Task Deltas for Low-Resource Adaptation

Reinforcement Learning with LTL and I¨-Regular Objectives via Optimality-Preserving Translation to Average Rewards

Reinforcement Learning with LTL and $I ¨ $ -Regular Objectives via Optimality-Preserving Translation to Average Rewards