相关论文: Encapsulating Knowledge in One Prompt

While transfer learning is an effective strategy, it often overlooks the opportunity to leverage knowledge from numerous available models online. Addressing this multi-source transfer learning problem is a promising path to boost…

Knowledge transfer among multiple networks using their outputs or intermediate activations have evolved through extensive manual design from a simple teacher-student approach (knowledge distillation) to a bidirectional cohort one (deep…

Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with the emergence of deep models pre-trained from different…

Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model architecture amount, and the private/inaccessible data, it is not very efficient or…

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands --…

Developing efficient software and hardware has never been harder whether it is for a tiny IoT device or an Exascale supercomputer. Apart from the ever growing design and optimization complexity, there exist even more fundamental problems…

Humans possess a remarkable ability to acquire knowledge efficiently and apply it across diverse modalities through a coherent and shared understanding of the world. Inspired by this cognitive capability, we introduce a concept-centric…

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and transfer learning, often fail to adequately serve the unique…

Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but their memory and compute requirements remain a concern for practical…

Machine learning, notably deep learning, has significantly propelled molecular investigations within the biochemical sphere. Traditionally, modeling for such research has centered around a handful of paradigms. For instance, the prediction…

Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional…

Diffusion Probabilistic Models (DPMs) have recently demonstrated impressive results on various generative tasks.Despite its promises, the learned representations of pre-trained DPMs, however, have not been fully understood. In this paper,…

The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of…

The aim of knowledge base completion is to predict unseen facts from existing facts in knowledge bases. In this work, we introduce the first approach for transfer of knowledge from one collection of facts to another without the need for…

Advances in networks, accelerators, and cloud services encourage programmers to reconsider where to compute -- such as when fast networks make it cost-effective to compute on remote accelerators despite added latency. Workflow and…

Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective strategy to adapt VLMs while preserving their pre-trained…

Knowledge Management is crucial for capturing and transferring expertise within universities, especially in high staff turnover contexts where expertise loss disrupts teaching. Documenting teachers' workflows is time-intensive and diverts…

Prompt learning is a new learning paradigm which reformulates downstream tasks as similar pretraining tasks on pretrained models by leveraging textual prompts. Recent works have demonstrated that prompt learning is particularly useful for…

Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying…

Vision-Language Models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage VLMs' potential in adapting to downstream tasks, context optimization methods like Prompt Tuning are essential.…