Selected work

Representative Papers

SADL: What to Ignore? A Benchmark for Subject-Aware Distractor Localization

Jun 29, 2026

Existing vision models lack subject-awareness, making it difficult to accurately identify and remove distractors in image editing without compromising scene semantic consistency. This work formalizes, for the first time, the task of Subject-Aware Distractor Localization (SADL) and introduces the first real-world benchmark for this task, comprising 1,800 cases with 14,617 annotated candidate objects. The authors propose a two-stage vision-language model (VLM) pipeline grounded in five inclusion factors and three contextual exclusion rules. Evaluation across seven VLMs reveals strong identification capabilities but exposes a systematic over-suppression bias during the exclusion phase. The SADL benchmark serves as a critical diagnostic tool for subject-conditioned reasoning in multimodal systems.

0 citationsRead paper

GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning

Apr 23, 2025

Vietnamese large language models suffer from pervasive code-mixing and factual inconsistency in structured logical reasoning—particularly in multi-step intermediate reasoning tasks. Method: We introduce GreenMind-Medium-14B-R1, built upon three key innovations: (1) the first Vietnamese synthetic Chain-of-Thought (CoT) dataset; (2) a dual reward mechanism comprising a character-level language bias detector for stylistic consistency and a Sentence-BERT–based factual consistency reward; and (3) reinforcement fine-tuning via Group Relative Policy Optimization (GRPO). Results: On the VLSP 2023 Vietnamese benchmark, GreenMind achieves significant improvements in linguistic coherence and reasoning accuracy. It also outperforms few-shot prompting baselines on the multilingual SeaExam evaluation suite, demonstrating strong cross-lingual generalization and robustness in logical reasoning. These results validate the efficacy of our dual-reward GRPO framework for enhancing both fidelity and fluency in Vietnamese LLMs.

0 citationsRead paper

Recent publications

Latest Papers

SADL: What to Ignore? A Benchmark for Subject-Aware Distractor Localization

Jun 29, 2026

Existing vision models lack subject-awareness, making it difficult to accurately identify and remove distractors in image editing without compromising scene semantic consistency. This work formalizes, for the first time, the task of Subject-Aware Distractor Localization (SADL) and introduces the first real-world benchmark for this task, comprising 1,800 cases with 14,617 annotated candidate objects. The authors propose a two-stage vision-language model (VLM) pipeline grounded in five inclusion factors and three contextual exclusion rules. Evaluation across seven VLMs reveals strong identification capabilities but exposes a systematic over-suppression bias during the exclusion phase. The SADL benchmark serves as a critical diagnostic tool for subject-conditioned reasoning in multimodal systems.

0 citationsRead paper

GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning

Apr 23, 2025

Vietnamese large language models suffer from pervasive code-mixing and factual inconsistency in structured logical reasoning—particularly in multi-step intermediate reasoning tasks. Method: We introduce GreenMind-Medium-14B-R1, built upon three key innovations: (1) the first Vietnamese synthetic Chain-of-Thought (CoT) dataset; (2) a dual reward mechanism comprising a character-level language bias detector for stylistic consistency and a Sentence-BERT–based factual consistency reward; and (3) reinforcement fine-tuning via Group Relative Policy Optimization (GRPO). Results: On the VLSP 2023 Vietnamese benchmark, GreenMind achieves significant improvements in linguistic coherence and reasoning accuracy. It also outperforms few-shot prompting baselines on the multilingual SeaExam evaluation suite, demonstrating strong cross-lingual generalization and robustness in logical reasoning. These results validate the efficacy of our dual-reward GRPO framework for enhancing both fidelity and fluency in Vietnamese LLMs.

0 citationsRead paper