5 papers
Hierarchical and Query-Aware Visual Token Pruning for High-Resolution LVLMs
Luther Wei, Ling Zou, Kang-Yang Huang +2
High-resolution Large Vision-Language Models (LVLMs) preserve critical, fine-grained visual details by encoding a global thumbnail alongside multiple local crops. However, the resu…
Look Before You Judge: Training-Free Region Mining for Grounded and Explainable Deepfake Detection
Chia-Ling Chen, Yu-Ting Ta, Jian-Yu Jiang-Lin +8
Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded in the visual evidence under…
ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics
Chin Ting Hsu, Yu-Syuan Xu, Ling Zou +2
Although multimodal Large Language Models (MLLMs) excel in diverse tasks, their scalability remains limited by the memory and computational overhead of KV cache storage. Recent KV…
RetroHolmes: When Semantic Plausibility Fails Retrospective Physical Process Reasoning
Ruoxuan Zhang, Qiyun Zheng, Siyu Wu +13
Vision-Language Models (VLMs) are widely used for visual understanding, yet current evaluation protocols fail to assess whether these capabilities are grounded in physical reasonin…
TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection
Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Zou +11
Advances in generative modeling have made it increasingly easy to fabricate realistic portrayals of individuals, creating serious risks for security, communication, and public trus…