基础模型如Segment Anything Model 3（SAM3）能够实现灵活的文本引导医学图像分割，但其预测结果仍然对提示语的表述高度敏感。即使语义等价的描述也能产生不一致的掩码，限制了临床和病理工作流程中的可靠性。我们重新将提示敏感性视为一个组内一致性问题。语义相关的提示被组织成共享相同真实掩码的提示组，并引入一种提示组感知的训练框架，以实现鲁棒的文本引导核分割。该方法结合（i）利用分割损失作为隐含排序信号的质量引导组正则化，以及（ii）一种带有停止梯度策略的logit层面一致性约束，以在每组内对齐预测。该方法不需要架构修改，且保持推理不变。在多数据集核分割基准上的广泛实验显示，在文本提示下实现了稳定的提升，并在提示质量水平上显著减少了性能波动。在六个零样本跨数据集任务中，我们的方法平均将Dice值提高了2.16个百分点。这些结果展示了在计算病理学中的视觉-语言分割中改进的鲁棒性和泛化能力。
英文摘要：
Foundation models such as Segment Anything Model 3 (SAM3) enable flexible text-guided medical image segmentation, yet their predictions remain highly sensitive to prompt formulation. Even semantically equivalent descriptions can yield inconsistent masks, limiting reliability in clinical and pathology workflows. We reformulate prompt sensitivity as a group-wise consistency problem. Semantically related prompts are organized into \emph{prompt groups} sharing the same ground-truth mask, and a prompt group-aware training framework is introduced for robust text-guided nuclei segmentation. The approach combines (i) a quality-guided group regularization that leverages segmentation loss as an implicit ranking signal, and (ii) a logit-level consistency constraint with a stop-gradient strategy to align predictions within each group. The method requires no architectural modification and leaves inference unchanged. Extensive experiments on multi-dataset nuclei benchmarks show consistent gains under textual prompting and markedly reduced performance variance across prompt quality levels. On six zero-shot cross-dataset tasks, our method improves Dice by an average of 2.16 points. These results demonstrate improved robustness and generalization for vision-language segmentation in computational pathology.
MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM
College of Computer Science, Sichuan University（四川大学计算机学院）；West China Hospital, Sichuan University（四川大学华西医院）；Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究所）
Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes. Additionally, our novel RoI-based masked attention and RoI pruning techniques help leverage the zero-shot classification ability of the Vision Transformer-based CLIP, resulting in improved detection performance at minimal computational cost. Our experiments on the OV-COCO and OVLVIS datasets demonstrate that Prompt-OVD achieves an impressive 21.2 times faster inference speed…
Progressive Prompt-Guided Cross-Modal Reasoning for Referring Image Segmentation
School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；University of Electronic Science and Technology of China（电子科技大学）；Wuhan Vocational College of Software and Engineering（武汉软件工程职业学院）
AdaptFly: Prompt-Guided Adaptation of Foundation Models for Low-Altitude UAV Networks
Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（申明-明伍智能工程学院，华南理工大学）；Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education (Guilin University of Electronic Technology)（认知无线电与信息处理重点实验室，教育部（桂林电子科技大学））；School of Information and Communication, Guilin University of Electronic Technology（信息与通信学院，桂林电子科技大学）
We propose a novel approach for dynamic negative prompting in diffusion models that leverages Vision-Language Models (VLMs) to adaptively generate negative prompts during the denoising process. Unlike traditional Negative Prompting methods that use fixed negative prompts, our method generates intermediate image predictions at specific denoising steps and queries a VLM to produce contextually appropriate negative prompts. We evaluate our approach on various benchmark datasets and demonstrate the trade-offs between negative guidance strength and text-image alignment.
AWGUNET: Attention-Aided Wavelet Guided U-Net for Nuclei Segmentation in Histopathology Images
Jadavpur University（jadavpur大学）；Artificial Intelligence Research Institute, China University of Mining and Technology（中国矿业大学人工智能研究院）；Saint Petersburg Electrotechnical University "LETI"（圣彼得堡国立电工技术大学"LETI"）
Guided Prompt Evolution for Vision-Language Models Adaptation
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Sun Yat-sen University（中山大学）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning
School of Information and Communication Engineering, BUPT（北京邮电大学信息与通信工程学院）；Engineering Research Center for Information Network, Ministry of Education（教育部信息网络工程研究中心）
MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness
Department of AI Semiconductor Engineering, Hanyang University, Seoul, Korea（汉阳大学人工智能半导体工程系）；Department of Electronic Engineering, Hanyang University, Seoul, Korea（汉阳大学电子工程系）
Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；PCALab, VCIP, College of Computer Science, Nankai University（南开大学计算机学院PCALab, VCIP）
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；China Mobile Financial Technology Co., Ltd.（中移动金融科技有限公司）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人创新中心）；School of Computer Science and Engineering, the Faculty of Innovation Engineering, Macau University of Science and Technology（澳门科技大学创新工程学院计算机科学与工程学院）
The University of New South Wales（新南威尔士大学）；Australian National University（澳大利亚国立大学）；North South University（北南大学）；University of Technology Sydney（悉尼科技大学）；Commonwealth Scientific and Industrial Research Organisation（联邦科学与工业研究组织）
Zero-shot learning on 3D point cloud data is a related underexplored problem compared to its 2D image counterpart. 3D data brings new challenges for ZSL due to the unavailability of robust pre-trained feature extraction models. To address this problem, we propose a prompt-guided 3D scene generation and supervision method that augments 3D data to learn the network better, exploring the complex interplay of seen and unseen objects. First, we merge point clouds of two 3D models in certain ways described by a prompt. The prompt acts like the annotation describing each 3D scene. Later, we perform c…
Institute of Automation, CAS（中国科学院自动化研究所）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences(CAS)（中国科学院大学）
Prompt tuning is an effective way to adapt the pre-trained visual-language model (VLM) to the downstream task using task-related textual tokens. Representative CoOp-based work combines the learnable textual tokens with the class tokens to obtain specific textual knowledge. However, the specific textual knowledge is the worse generalization to the unseen classes because it forgets the essential general textual knowledge having a strong generalization ability. To tackle this issue, we introduce a novel Knowledge-guided Context Optimization (KgCoOp) to enhance the generalization ability of the le…
Prompt-Free Lightweight SAM Adaptation for Histopathology Nuclei Segmentation with Strong Cross-Dataset Generalization
School of Information and Communication Technology, Griffith University, QLD, Australia（信息与通信技术学院，格里菲斯大学，昆士兰，澳大利亚）；School of MDP -- Clinical Medicine, Griffith University, QLD, Australia（MDP临床医学学院，格里菲斯大学，昆士兰，澳大利亚）
Prompt-based Grouping Transformer for Nucleus Detection and Classification
Sun Yat-sen University（中山大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Guangdong University of Technology（广东工业大学）
UN-SAM: Universal Prompt-Free Segmentation for Generalized Nuclei Images
Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）；Chinese University of Hong Kong（香港中文大学）
Concept-Guided Prompt Learning for Generalization in Vision-Language Models
Harbin Institute of Technology（哈尔滨工业大学）；Southern University of Science and Technology（南方科技大学）；Carnegie Mellon University（卡内基梅隆大学）；Pengcheng Laboratory（鹏城实验室）
This study investigates unsupervised anomaly action recognition, which identifies video-level abnormal-human-behavior events in an unsupervised manner without abnormal samples, and simultaneously addresses three limitations in the conventional skeleton-based approaches: target domain-dependent DNN training, robustness against skeleton errors, and a lack of normal samples. We present a unified, user prompt-guided zero-shot learning framework using a target domain-independent skeleton feature extractor, which is pretrained on a large-scale action recognition dataset. Particularly, during the tra…
