activity
20242026
collaborators

7 papers

cs.LG2026

On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation

Andy Han, Kristina Fujimoto, Avidan Shah +5

Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promi…

cs.CL2026

DSC2025 -- ViHallu Challenge: Detecting Hallucination in Vietnamese LLMs

Anh Thi-Hoang Nguyen, Khanh Quoc Tran, Tin Van Huynh +3

The reliability of large language models (LLMs) in production environments remains significantly constrained by their propensity to generate hallucinations -- fluent, plausible-sou…

cs.CV2025

Towards Signboard-Oriented Visual Question Answering: ViSignVQA Dataset, Method and Benchmark

Hieu Minh Nguyen, Tam Le-Thanh Dang, Kiet Van Nguyen

Understanding signboard text in natural scenes is essential for real-world applications of Visual Question Answering (VQA), yet remains underexplored, particularly in low-resource…

cs.CL2025

VLSP 2025 MLQA-TSR Challenge: Vietnamese Multimodal Legal Question Answering on Traffic Sign Regulation

Son T. Luu, Trung Vo, Hiep Nguyen +5

This paper presents the VLSP 2025 MLQA-TSR - the multimodal legal question answering on traffic sign regulation shared task at VLSP 2025. VLSP 2025 MLQA-TSR comprises two subtasks:…

cs.CV2025

NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

Xin Li, Yeying Jin, Xin Jin +134

This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images. This challenge received a wide range of impressive solutions, which are devel…

cs.CL2024

ViFactCheck: A New Benchmark Dataset and Methods for Multi-domain News Fact-Checking in Vietnamese

Tran Thai Hoa, Tran Quang Duy, Khanh Quoc Tran +1

The rapid spread of information in the digital age highlights the critical need for effective fact-checking tools, particularly for languages with limited resources, such as Vietna…