相关论文: PANDA: Prompt Transfer Meets Knowledge Distillatio…

This work proposes POMP, a prompt pre-training method for vision-language models. Being memory and computation efficient, POMP enables the learned prompt to condense semantic information for a rich set of visual concepts with over…

Domain generalization is critical in computational pathology (CPath) due to inherent domain shifts caused by variations in staining protocols, scanner devices, and imaging settings across clinical centers. Vision-language models (VLMs),…

Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…

Deep neural networks often have a huge number of parameters, which posts challenges in deployment in application scenarios with limited memory and computation capacity. Knowledge distillation is one approach to derive compact models from…

Test-time adaptation (TTA) aims to transfer knowledge from a source model to unknown test data with potential distribution shifts in an online manner. Many existing TTA methods rely on entropy as a confidence metric to optimize the model.…

A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continually training a model often leads to a well-known…

Deep neural network architectures have attained remarkable improvements in scene understanding tasks. Utilizing an efficient model is one of the most important constraints for limited-resource devices. Recently, several compression methods…

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly…

Recently, Mixture of Experts (MoE) Transformers have garnered increasing attention due to their advantages in model capacity and computational efficiency. However, studies have indicated that MoE Transformers underperform vanilla…

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

While the numerous parameters in Large Language Models (LLMs) contribute to their superior performance, this massive scale makes them inefficient and memory-hungry. Thus, they are hard to deploy on commodity hardware, such as one single…

Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models.…

Visual Prompt Tuning (VPT) has proven effective for parameter-efficient adaptation of pre-trained vision models to downstream tasks by inserting task-specific learnable prompt tokens. Despite its empirical success, a comprehensive…

Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient…

In this paper, we propose a novel knowledge transfer framework that introduces continuous normalizing flows for progressive knowledge transformation and leverages multi-step sampling strategies to achieve precision knowledge transfer. We…

This survey reviews prompt tuning, a parameter-efficient approach for adapting language models by prepending trainable continuous vectors while keeping the model frozen. We classify existing approaches into two categories: direct prompt…

Robust multimodal human sensing must overcome the critical challenge of missing modalities. Two principal barriers are the Representation Gap between heterogeneous data and the Contamination Effect from low-quality modalities. These…

Knowledge distillation(KD) aims to improve the performance of a student network by mimicing the knowledge from a powerful teacher network. Existing methods focus on studying what knowledge should be transferred and treat all samples equally…

Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a…