相关论文: Progressive Weight Loading: Accelerating Initial I…

Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data,…

Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods…

Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data…

We present our submission to the BabyLM challenge, aiming to push the boundaries of data-efficient language model pretraining. Our method builds upon deep mutual learning, introducing a student model search for diverse initialization. We…

Condensed datasets offer a compact representation of larger datasets, but training models directly on them or using them to enhance model performance through knowledge distillation (KD) can result in suboptimal outcomes due to limited…

Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like…

In this paper, we introduce InDistill, a method that serves as a warmup stage for enhancing Knowledge Distillation (KD) effectiveness. InDistill focuses on transferring critical information flow paths from a heavyweight teacher to a…

Deep learning achieved great progress recently, however, it is not easy or efficient to further improve its performance by increasing the size of the model. Multi-modal learning can mitigate this challenge by introducing richer and more…

Large language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing (NLP) tasks. However, these models are often difficult to deploy due to significant computational requirements and…

Weight space learning aims to extract information about a neural network, such as its training dataset or generalization error. Recent approaches learn directly from model weights, but this presents many challenges as weights are…

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Large Language Models (LLMs) have exhibited impressive capabilities in various tasks, yet their vast parameter sizes restrict their applicability in resource-constrained settings. Knowledge distillation (KD) offers a viable solution by…

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

Personalized Federated Learning (pFL) not only can capture the common priors from broad range of distributed data, but also support customized models for heterogeneous clients. Researches over the past few years have applied the weighted…

In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the…

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate…

Federated Learning (FL) is an innovative distributed machine learning paradigm that enables neural network training across devices without centralizing data. While this addresses issues of information sharing and data privacy, challenges…

Deep neural networks have achieved increasingly accurate results on a wide variety of complex tasks. However, much of this improvement is due to the growing use and availability of computational resources (e.g use of GPUs, more layers, more…