Related papers: Defect-aware Hybrid Prompt Optimization via Progre…

An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model outputs. While recent Automatic Prompt Optimization (APO) methods…

Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects by establishing feature mapping between textual prompts and inspection images, demonstrating excellent research value in flexible industrial…

Prompt-based learning, with its capability to tackle zero-shot and few-shot NLP tasks, has gained much attention in community. The main idea is to bridge the gap between NLP downstream tasks and language modeling (LM), by mapping these…

Despite recent successes, LVLMs or Large Vision Language Models are prone to hallucinating details like objects and their properties or relations, limiting their real-world deployment. To address this and improve their robustness, we…

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…

Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image Pre-training (CLIP) have been shown to be susceptible to adversarial attacks, raising concerns about their deployment in safety-critical applications like…

An innovative few-shot anomaly detection approach is presented, leveraging the pre-trained CLIP model for medical data, and adapting it for both image-level anomaly classification (AC) and pixel-level anomaly segmentation (AS). A…

Recently, vision-language models (e.g. CLIP) have demonstrated remarkable performance in zero-shot anomaly detection (ZSAD). By leveraging auxiliary data during training, these models can directly perform cross-category anomaly detection on…

In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional…

Large pre-trained vision-language models like CLIP have transformed computer vision by aligning images and text in a shared feature space, enabling robust zero-shot transfer via prompting. Soft-prompting, such as Context Optimization…

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for…

Foundation models have shown strong performance in multi-object segmentation with visual prompts, yet histopathology images remain challenging due to high cellular density, heterogeneity, and the gap between pixel-level supervision and…

Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. However, existing methods that directly apply SAM through prompting often overlook the domain shift issue,…

Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string optimized through global edits, producing brittle…

Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of…

In recent years, soft prompt learning methods have been proposed to fine-tune large-scale vision-language pre-trained models for various downstream tasks. These methods typically combine learnable textual tokens with class tokens as input…

Large-scale vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization, but adapting them to downstream tasks typically requires costly labeled data. Existing unsupervised self-training methods rely on…

Zero-shot anomaly segmentation using pre-trained foundation models is a promising approach that enables effective algorithms without expensive, domain-specific training or fine-tuning. Ensuring that these methods work across various…

With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments.…

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language models (PLMs), vision pretrained models, and vision-language…