Related papers: A Unified Virtual Mixture-of-Experts Framework:Enh…

Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make…

Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks, however, they have issues like (a) High Memory Usage, due to duplication of the network layers into multiple copies as…

Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off between accuracy and computation in an MoE model typically…

Mixture-of-Experts (MoE) architectures are increasingly used to efficiently scale large language models. However, in production inference, request batching and speculative decoding significantly amplify expert activation, eroding these…

With the breakthrough progress of large language models (LLMs) in natural language processing and multimodal tasks, efficiently deploying them on resource-constrained edge devices has become a critical challenge. The Mixture of Experts…

Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting previously acquired abilities. Existing approaches either internalize knowledge by…

Current training-free methods tackle MLLM hallucination with separate strategies: either enhancing visual signals or suppressing text inertia. However, these separate methods are insufficient due to critical trade-offs: simply enhancing…

Training AI models that generalize across tasks and domains has long been among the open problems driving AI research. The emergence of Foundation Models made it easier to obtain expert models for a given task, but the heterogeneity of data…

Sparsely-activated Mixture-of-experts (MoE) models allow the number of parameters to greatly increase while keeping the amount of computation for a given token or a given sample unchanged. However, a poor expert routing strategy (e.g. one…

The Mixture-of-Experts (MoE) paradigm has emerged as a promising solution to scale up model capacity while maintaining inference efficiency. However, deploying MoE models across heterogeneous end-cloud environments poses new challenges in…

Mixture-of-Experts (MoE) models have recently demonstrated exceptional performance across a diverse range of applications. The principle of sparse activation in MoE models facilitates an offloading strategy, wherein active experts are…

Language Model (LM)-based Text-to-Speech (TTS) systems often generate hallucinated speech that deviates from input text. Existing mitigation strategies either demand excessive training resources or introduce significant inference latency.…

Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing…

Large language models, such as OpenAI's ChatGPT, have demonstrated exceptional language understanding capabilities in various NLP tasks. Sparsely activated mixture-of-experts (MoE) has emerged as a promising solution for scaling models…

In cross-border e-commerce, search relevance modeling faces the dual challenge of extreme linguistic diversity and fine-grained semantic nuances. Existing approaches typically rely on scaling up a single monolithic Large Language Model…

Low-light enhancement has wide applications in autonomous driving, 3D reconstruction, remote sensing, surveillance, and so on, which can significantly improve information utilization. However, most existing methods lack generalization and…

In this paper, we present the practical problems and the lessons learned at short-video services from Kuaishou. In industry, a widely-used multi-task framework is the Mixture-of-Experts (MoE) paradigm, which always introduces some shared…

Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost of training and evaluating models. Efficient Pareto front…

In a distributed mixture-of-experts (MoE) system, a server collaborates with multiple specialized expert clients to perform inference. The server extracts features from input data and dynamically selects experts based on their areas of…

Large language models and vision transformers have demonstrated impressive zero-shot capabilities, enabling significant transferability in downstream tasks. The fusion of these models has resulted in multi-modal architectures with enhanced…