Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded in the visual evidence underlying the prediction. A model may describe plausible artifacts inferred from language priors rather than from image evidence. Existing groun...
Chia-Ling Chen, Yu-Ting Ta, Jian-Yu Jiang-Lin et al.· 0 citations
The growing scale of academic peer review has motivated the use of Large Language Models (LLMs) as review assistants, yet LLMs can generate fluent but unsupported claims that undermine review reliability. Existing hallucination benchmarks are not designed for peer review, where verification requires grounding claims in...
Tzu-Ling Lin, Dong-Ting Yao, Teng-Fang Hsiao et al.· 0 citations
This article introduces Uncertainty-Guided Adaptive Knowledge Distillation (UGAKD), a novel framework designed to enhance UDA while simultaneously reducing model size through targeted knowledge distillation and proposing a two-stage, difficulty-aware training scheme to facilitate learning.
Wei-Lun Tseng, Yi-Lun Wu, Yung-Hui Li et al.· ACM Transactions on Intellig...· 0 citations
RADIANCE is proposed, a training-free framework that treats inference as a closed-loop feedback process that consistently enhances compositional alignment and perceptual quality over state-of-the-art baselines.
