Related papers: GRIT: Graph-Regularized Logit Refinement for Zero-…

Semantic segmentation is a fundamental task in medical image analysis and autonomous driving and has a problem with the high cost of annotating the labels required in training. To address this problem, semantic segmentation methods based on…

While vision-language models like CLIP have advanced zero-shot surgical phase recognition, they struggle with fine-grained surgical activities, especially action triplets. This limitation arises because current CLIP formulations rely on…

The identification of essential genes/proteins is a critical step towards a better understanding of human biology and pathology. Computational approaches helped to mitigate experimental constraints by exploring machine learning (ML) methods…

Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many…

Few-shot learning (FSL), purposing to resolve the problem of data-scarce, has attracted considerable attention in recent years. A popular FSL framework contains two phases: (i) the pre-train phase employs the base data to train a CNN-based…

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a…

Large language models (LLMs), including zero-shot and few-shot paradigms, have shown promising capabilities in clinical text generation. However, real-world applications face two key challenges: (1) patient data is highly unstructured,…

Automated single-cell annotation is difficult when the most abundant genes are not the most discriminative ones, or when a target state is poorly covered by a fixed reference atlas. GPTCelltype-style one-shot prompting allows large language…

We introduce a novel gene regulatory network (GRN) inference method that integrates optimal transport (OT) with a deep-learning structural inference model. Advances in next-generation sequencing enable detailed yet destructive gene…

Contrastive Language-Image Pretraining (CLIP) has shown impressive zero-shot performance on image classification. However, state-of-the-art methods often rely on fine-tuning techniques like prompt learning and adapter-based tuning to…

Traditional verification methods in chip design are highly time-consuming and computationally demanding, especially for large scale circuits. Graph neural networks (GNNs) have gained popularity as a potential solution to improve…

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge…

Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders are typically…

Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data has proven effective in improving performance, these methods…

The task of annotating data into concise summaries poses a significant challenge across various domains, frequently requiring the allocation of significant time and specialized knowledge by human experts. Despite existing efforts to use…

Large language models (LLMs) have advanced information extraction (IE) by enabling zero-shot and few-shot named entity recognition (NER), yet their generative outputs still show persistent and systematic errors. Despite progress through…

This paper presents a novel method that leverages a visual-language model, CLIP, as a data source for zero-shot anomaly detection. Tremendous efforts have been put towards developing anomaly detectors due to their potential industrial…

Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become too expensive. Zero-shot learning requires an annotated set…

Parameter-efficient fine-tuning (PEFT) is the default way to adapt LLMs, but widely used LoRA and QLoRA are largely geometry-agnostic: they optimize in fixed, randomly oriented low-rank subspaces with first-order descent, mostly ignoring…

Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation.…