This work proposes a training-free, hierarchical token pruning framework that utilizes query guidance prior to executing any LLM blocks, and demonstrates that this plug-and-play framework retains 98.0% and 94.8% of unpruned performance at 25% and 10% vision token retention, respectively.
Luther Wei, Ling Zou, Kang-Yang Huang et al.· 0 citations
Look Before You Judge, a training-free framework that formulates explainable deepfake detection as a sequential evidence acquisition process, and improves detection accuracy by up to 12.8%, reduces CHAIR by up to 33.4% and hallucination rate by up to 21.3%, and outperforms representative training-free decoding and atte...
Chia-Ling Chen, Yu-Ting Ta, Jian-Yu Jiang-Lin et al.· 0 citations
This work proposes a geometry-aware composite metric that jointly leverages Euclidean distance and cosine similarity to capture token diversity from complementary perspectives and uses these two metrics to estimate the redundancy level of each attention head, allowing adaptive weighting between diversity and importance...
Chin-Ting Hsu, Yu-Syuan Xu, Ling Zou et al.· 0 citations
Humans can infer hidden physical processes from sparse observations, yet current evaluation protocols for Vision Language Models fail to assess whether such physical reasoning is genuinely captured. To address this gap, we introduce Retrospective Physical Process Reasoning, a new evaluation paradigm to reason backward...