相关论文: Distilling Morphology-Conditioned Hypernetworks fo…

With rising male infertility, sperm head morphology classification becomes critical for accurate and timely clinical diagnosis. Recent deep learning (DL) morphology analysis methods achieve promising benchmark results, but leave performance…

Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performance alone is not sufficient to satisfy the needs of practical…

Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…

Although more layers and more parameters generally improve the accuracy of the models, such big models generally have high computational complexity and require big memory, which exceed the capacity of small devices for inference and incurs…

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however,…

Data heterogeneity presents significant challenges for federated learning (FL). Recently, dataset distillation techniques have been introduced, and performed at the client level, to attempt to mitigate some of these challenges. In this…

Heterogeneous Federated Learning (HFL) has gained significant attention for its capacity to handle both model and data heterogeneity across clients. Prototype-based HFL methods emerge as a promising solution to address statistical and model…

Visual and semantic concepts are often structured in a hierarchical manner. For instance, textual concept `cat' entails all images of cats. A recent study, MERU, successfully adapts multimodal learning techniques from Euclidean space to…

We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher…

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset.…

Most existing federated learning algorithms are based on the vanilla FedAvg scheme. However, with the increase of data complexity and the number of model parameters, the amount of communication traffic and the number of iteration rounds for…

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

As large language models (LLMs) tackle increasingly complex tasks and longer documents, their computational and memory costs during inference become a major bottleneck. To address this, we propose PromptDistill, a novel, training-free…

Continual learning and machine unlearning are crucial challenges in machine learning, typically addressed separately. Continual learning focuses on adapting to new knowledge while preserving past information, whereas unlearning involves…

Recent work on distilling Whisper's knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. This results in small, efficient, and dedicated models. However, a critical step of…

When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that accelerates learning beyond what proprioception alone can achieve. However, vision-enabled policies tend to…

Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data. Existing FL methods either iteratively share local model…

We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems by distilling behaviors from auxiliary RL tasks. AuxDistill…

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…