Compact medical vision-language models (VLMs) can answer clinical questions correctly without reliably using the image, relying instead on question wording or learned priors. Standard knowledge distillation copies a teacher's answer preference on the original image, but it leaves unchecked whether that preference is co...
Qi-Zhen Lan, Yi-Ling Ma, Rui-Qi Chen et al.· 0 citations
Semantics-Preserving Quantization (SPQ), which gives more calibration weight to concept-sensitive parameters, preserves residual features, and corrects the mean error in video memory, is proposed.
Xi Xiao, Yun-Bei Zhang, Lin Zhao et al.· 0 citations
Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-token pruning attractive but risky for medical images, where answers may depend on localized boundary and texture evidence. We study training free pre-decoding pruning an...
Meng-Chen Fan, Qi-Zhen Lan, Xi Xiao et al.· 0 citations
PFM is introduced, a general generative modeling framework that learns conditional velocity means and componentwise variances with a Gaussian posterior model and improves generation quality and provides endpoint-posterior readouts throughout generation.
Chen-Rui Ma, Xi Xiao, Lin Zhao et al.· 0 citations
Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as model size decreases. Knowledge distillation offers a natural way to bridge this gap, but existing methods primarily align output distributions or hidden representations dire...
ForGE is proposed, a unified framework for adapting frozen models through per-query routing over a joint action space that spans both support form and thinking depth and improves accuracy at 42-45% lower token cost on both main hosts.
Xi Xiao, Yun-Bei Zhang, Chen Liu et al.· 0 citations
Inspired by the Information Bottleneck principle, Prompted Information Bottlenecks (PIB) is introduced, a framework that regularizes layer-wise compression-sufficiency trade-offs and promotes a more coherent cross-layer information path.
Yuqi Li, Xi Xiao, Yun-Bei Zhang et al.· arXiv.org· 10 citations
This work injects two complementary semantic priors into Visual prompt tuning, a cascaded scheme that integrates both priors throughout ViT adaptation, and proposes a cascaded scheme that integrates both priors throughout ViT adaptation.
Xi Xiao, Xing-Jian Li, Cheng Han et al.· Trans. Mach. Learn. Res.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.