Skip to main content
Search

# Vision-language agent

2 related articles

Subscribe to updates
  1. arXiv

    One network no longer handles all three CT degradations: AgentCT, a vision-language agent, routes each scan to a specialist and leads PSNR across nine settings

    Low-dose, sparse-view and metal-artifact CT degradations have different physics, yet universal restoration models have processed all of them with one shared architecture. AgentCT uses a LoRA-adapted Qwen3-VL-4B controller to identify degradation type and severity, dispatch the image to an image-domain diffusion denoiser or a dual-domain specialist, and re-check the restored output. On nine degradation-severity settings of patient-disjoint Mayo 2020 abdominal CT, routing with ground-truth degradation labels gave an overall PSNR/SSIM of 46.18 dB/0.984, versus 44.93 dB/0.976 for AMIR and 44.29 dB/0.979 for TAMP.

    Zhihao Chen（First author）
    AgentCTVision-language agentQwen3-VLImage Restoration
  2. arXiv

    TSegAgent achieves zero-shot tooth segmentation and FDI identification by pairing SAM3 with geometric reasoning, reaching mIoU 93.37 and TIR=1 of 87.17% on Teeth3DS while generalizing to a private dataset

    The work proposes TSegAgent, which reformulates tooth instance segmentation and FDI labeling of intra-oral scanned 3D models as a zero-shot geometric reasoning problem: multi-view renderings with curvature heatmaps and the SAM3 text prompt "tooth" produce candidate masks, which are merged into face-level instance labels via IoU and containment relations, after which a geometry-aware vision-language agent performs non-tooth region identification, central incisor localization, full-arch classification, and error correction through multi-round conversation; it reports mIoU 93.37, TLA 96.40, TSA 96.76, TIR 97.46, and TIR=1 87.17 on Teeth3DS with 1200 3D tooth models, and mIoU 82.10, TLA 96.68, TSA 95.99, TIR 85.41, and TIR=1 51.

    University of SurreyShandong UniversityUniversity of Jinan
    Shaojie Zhuang（First author）Lu Yin（Corresponding author）Yuanfeng Zhou（Corresponding author）
    TSegAgentZero-shot tooth segmentationVision-language agentSAM3Teeth3DS dataset

You’re all caught up