Related papers: Dynamic Multi-Expert Projectors with Stabilized Ro…

The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i.e., the…

The recent Segment Anything Model (SAM) represents a significant breakthrough in scaling segmentation models, delivering strong performance across various downstream applications in the RGB modality. However, directly applying SAM to…

The scaling of large language models (LLMs) has revolutionized their capabilities in various tasks, yet this growth must be matched with efficient computational strategies. The Mixture-of-Experts (MoE) architecture stands out for its…

Recent advances demonstrate that scaling Large Vision-Language Models (LVLMs) effectively improves downstream task performances. However, existing scaling methods enable all model parameters to be active for each token in the calculation,…

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing…

Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world deployment. The Mixture of Experts (MoE) architecture offers a…

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…

Extending large language models to low-resource languages is essential for global accessibility, but training separate models per language is prohibitively expensive. Mixture-of-Experts (MoE) architectures address this by adding sparse…

Mixture-of-Experts (MoE) enables efficient scaling of large language models (LLMs) with sparsely activated experts during inference. To effectively deploy large MoE models on memory-constrained devices, many systems introduce *expert…

Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE models have focused primarily on coarse-grained MoE…

Training multilingual automatic speech recognition (ASR) systems is challenging because acoustic and lexical information is typically language specific. Training multilingual system for Indic languages is even more tougher due to lack of…

Sparse mixture of experts (SMoE) have emerged as an effective approach for scaling large language models while keeping a constant computational cost. Regardless of several notable successes of SMoE, effective training such architecture…

Perceptual ambiguity and task conflict limit multitask robotic manipulation via imitation learning. We propose a framework combining a Language-Conditioned Visual Representation (LCVR) module and a Language-conditioned Mixture-ofExperts…

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading…

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

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…

Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR…

Sparse Mixture of Experts (SMoE) enables scalable parameter growth in large language models (LLMs) by selectively activating a subset of experts, and its large parameter count necessitates distributed deployment for inference. However,…

Mixture-of-experts (MoE) models that employ sparse activation have demonstrated effectiveness in significantly increasing the number of parameters while maintaining low computational requirements per token. However, recent studies have…