Related papers: Mixture of Modular Experts: Distilling Knowledge f…

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…

Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter…

The first-stage retrieval aims to retrieve a subset of candidate documents from a huge collection both effectively and efficiently. Since various matching patterns can exist between queries and relevant documents, previous work tries to…

Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in…

Multi-modal 3D understanding is a fundamental task in computer vision. Previous multi-modal fusion methods typically employ a single, dense fusion network, struggling to handle the significant heterogeneity and complexity across modalities,…

Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable performance without increasing per-token compute. However, can MoEs surpass dense architectures under strictly equal resource constraints --…

Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge of a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications,…

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges…

In this paper, we tackle the problem of domain shift. Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains. Such solutions are sub-optimal as…

Knowledge distillation (KD) is widely used to train small, high-performing student language models (LMs) using large teacher LMs. While effective in fine-tuning, KD during pre-training faces efficiency, flexibility, and effectiveness…

Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the…

Recent advancements in Neural Machine Translation (NMT) have significantly improved translation quality. However, the increasing size and complexity of state-of-the-art models present significant challenges for deployment on…

Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, training MoE from scratch in a large-scale setting still suffers from data-hungry and instability…

The use of pre-trained language models fine-tuned to address specific downstream tasks is a common approach in natural language processing (NLP). However, acquiring domain-specific knowledge via fine-tuning is challenging. Traditional…

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the…

Pre-trained language models have demonstrated superior performance in various natural language processing tasks. However, these models usually contain hundreds of millions of parameters, which limits their practicality because of latency…

Knowledge distillation (KD) is a well-known method for compressing neural models. However, works focusing on distilling knowledge from large multilingual neural machine translation (MNMT) models into smaller ones are practically…

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they…