相关论文: KADEL: Knowledge-Aware Denoising Learning for Comm…

Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora. While this endows LLMs with strong capabilities in generation and reasoning, it amplifies risks associated with sensitive,…

Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these deep code models have achieved great success, even state-of-the-art models suffer…

End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few…

With the increasing popularity of deep learning on edge devices, compressing large neural networks to meet the hardware requirements of resource-constrained devices became a significant research direction. Numerous compression methodologies…

Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…

Although Large Language Models (LLMs) have made significant progress in code generation, they still struggle with code generation tasks in specific scenarios. These scenarios usually necessitate the adaptation of LLMs to fulfill specific…

Accurate and effective channel state information (CSI) feedback is a key technology for massive multiple-input and multiple-output (MIMO) systems. Recently, deep learning (DL) has been introduced to enhance CSI feedback in massive MIMO…

Commit Message Generation (CMG) approaches aim to automatically generate commit messages based on given code diffs, which facilitate collaboration among developers and play a critical role in Open-Source Software (OSS). Very recently, Large…

Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions. However, effectively leveraging textual information for…

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

One of the biggest challenges that complicates applied supervised machine learning is the need for huge amounts of labeled data. Active Learning (AL) is a well-known standard method for efficiently obtaining labeled data by first labeling…

To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which transfers knowledge from a large "teacher" model to a smaller "student" model. However, KD on multimodal datasets such as vision-language…

Standard automatic methods for recognizing problematic development commits can be greatly improved via the incremental application of human+artificial expertise. In this approach, called EMBLEM, an AI tool first explore the software…

Accurate and effective channel state information (CSI) feedback is a key technology for massive multiple-input and multiple-output systems. Recently, deep learning (DL) has been introduced for CSI feedback enhancement through massive…

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…

Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model (i.e., student model) by transferring the information from…

Continual pretraining promises to adapt large language models (LLMs) to new domains using only unlabeled test-time data, but naively applying standard self-supervised objectives to instruction-tuned models is known to degrade their…

Recent studies on learning-based image denoising have achieved promising performance on various noise reduction tasks. Most of these deep denoisers are trained either under the supervision of clean references, or unsupervised on synthetic…

As semantic communication (SemCom) attracts growing attention as a novel communication paradigm, ensuring the security of transmitted semantic information over open wireless channels has become a critical issue. However, traditional…

This research investigates the enhancement of knowledge distillation (KD) processes in pre-trained models, an emerging field in knowledge transfer with significant implications for distributed training and federated learning environments.…