While Vision-Language Models (VLMs) demonstrate strong capabilities, they continue to suffer from a critical limitation: insufficient fine-grained visual perception, which fundamentally limits their multimodal understanding. We attribute this bottleneck to text-dominant optimization biases during pre-training, which en...
Zhe-Han Kan, Yu-Bo Zhu, Xing-Hua Jiang et al.· 0 citations
Despite remarkable advancements in multimodal large language models (MLLMs), their fine-grained visual understanding is constrained by a primary reliance on sparse textual supervision. Existing efforts to introduce visual supervision typically do so during post-training, when visual representations have already been la...
Zhe-Han Kan, Xing-Hua Jiang, Yu-Bo Zhu et al.· 0 citations
While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference. Existing token pruning methods primarily rely on diversity-based selection, discarding similar tokens to maxi...
Peng Ling, Yingda Yin, Lingting Zhu et al.· 0 citations
Video object removal must eliminate not only the target object but also its induced effects while maintaining high-fidelity and spatiotemporally coherent restoration. Existing methods mainly learn object-effect correspondences implicitly from predefined effect categories and fixed data distributions, limiting their gen...
Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning. However, current LVLM-based IAD methods still struggle to produce precise pixel-level anomaly maps from generated language judgm...
Shuimu Chen, Jing Jin, Nan Su et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
