Related papers: MoTE: Reconciling Generalization with Specializati…

Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs)…

Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning. How can we recycle large collections of expert language models to…

Text-to-image diffusion has attracted vast attention due to its impressive image-generation capabilities. However, when it comes to human-centric text-to-image generation, particularly in the context of faces and hands, the results often…

Large Mixture of Experts (MoE) models could achieve state-of-the-art quality on various language tasks, including machine translation task, thanks to the efficient model scaling capability with expert parallelism. However, it has brought a…

We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for efficient language modeling. Our approach addresses the…

Cross-modal distillation has been widely used to transfer knowledge across different modalities, enriching the representation of the target unimodal one. Recent studies highly relate the temporal synchronization between vision and sound to…

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…

With the revolution of generative AI, video-related tasks have been widely studied. However, current state-of-the-art video models still lag behind image models in visual quality and user control over generated content. In this paper, we…

Mixture of expert (MoE) models are a promising approach to increasing model capacity without increasing inference cost, and are core components of many state-of-the-art language models. However, current MoE models typically use only few…

The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and textual understanding. Without sufficient temporal…

Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video…

Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…

Parameter-efficient fine-tuning has demonstrated promising results across various visual adaptation tasks, such as classification and segmentation. Typically, prompt tuning techniques have harnessed knowledge from a single pre-trained…

To build an artificial neural network like the biological intelligence system, recent works have unified numerous tasks into a generalist model, which can process various tasks with shared parameters and do not have any task-specific…

The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised…

The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability…

Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks,…

Machine learning models often need to adapt to new data after deployment due to structured or unstructured real-world dynamics. The Continual Learning (CL) framework enables continuous model adaptation, but most existing approaches either…

Quantization method plays a crucial role in improving model efficiency and reducing deployment costs, enabling the widespread application of deep learning models on resource-constrained devices. However, the quantization process inevitably…

Automated surgical gesture recognition is of great importance in robot-assisted minimally invasive surgery. However, existing methods assume that training and testing data are from the same domain, which suffers from severe performance…