Related papers: DIMoE-Adapters: Dynamic Expert Evolution for Conti…

Mixture-of-Experts (MoE) architectures have emerged as a cornerstone of modern AI systems. In particular, MoEs route inputs dynamically to specialized experts whose outputs are aggregated through weighted summation. Despite their widespread…

Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to streaming data/tasks. In this work, we consider a general and yet…

The sparsely activated mixture-of-experts (MoE) transformer has become a common architecture for large language models (LLMs) due to its sparsity, which requires fewer computational demands while easily scaling the model size. In MoE…

The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference,…

The ability to continuously learn remains elusive for deep learning models. Unlike humans, models cannot accumulate knowledge in their weights when learning new tasks, mainly due to an excess of plasticity and the low incentive to reuse…

The field of natural language processing (NLP) has made significant strides in recent years, particularly in the development of large-scale vision-language models (VLMs). These models aim to bridge the gap between text and visual…

Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on dynamic expert clustering and structured compression to…

With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these models is composed of lots of dense algebras, requiring a…

The Mixture of Experts (MoE) models are an emerging class of sparsely activated deep learning models that have sublinear compute costs with respect to their parameters. In contrast with dense models, the sparse architecture of MoE offers…

As deep learning models expand, the pre-training-fine-tuning paradigm has become the standard approach for handling various downstream tasks. However, shared parameters can lead to diminished performance when dealing with complex datasets…

Lifelong sequence generation (LSG), a problem in continual learning, aims to continually train a model on a sequence of generation tasks to learn constantly emerging new generation patterns while avoiding the forgetting of previous…

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…

MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability…

The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing. Despite the success, most existing…

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters…

Incremental multi-view clustering aims to achieve stable clustering results while addressing the stability-plasticity dilemma (SPD) in view-incremental scenarios. The core challenge is that the model must have enough plasticity to quickly…

Large Language Models (LLMs) encounter significant challenges in continual learning due to catastrophic forgetting, where new information overwrites previously acquired knowledge. This limitation leads to substantial environmental and…

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…

Mixture-of-Experts (MoE) models have emerged as a promising direction for scaling vision architectures efficiently. Among them, Soft MoE improves training stability by assigning each token to all experts via continuous dispatch weights.…

To reduce the computational and memory overhead of Large Language Models, various approaches have been proposed. These include a) Mixture of Experts (MoEs), where token routing affects compute balance; b) gradual pruning of model…