相关论文: SiameseNorm: Breaking the Barrier to Reconciling P…

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture…

Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, many challenges remain in training deep transformer networks,…

Transformer networks have become the preferred architecture for many tasks due to their state-of-the-art performance. However, the optimal way to implement residual connections in Transformer, which are essential for effective training, is…

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

We evaluate three simple, normalization-centric changes to improve Transformer training. First, we show that pre-norm residual connections (PreNorm) and smaller initializations enable warmup-free, validation-based training with large…

Traditional audio-visual methods rely on independent audio and visual backbones, which is costly and not scalable. In this work, we investigate using an audio-visual siamese network (AVSiam) for efficient and scalable audio-visual…

Recently, DeepNorm scales Transformers into extremely deep (i.e., 1000 layers) and reveals the promising potential of deep scaling. To stabilize the training of deep models, DeepNorm (Wang et al., 2022) attempts to constrain the model…

Transformers have achieved great success in machine learning applications. Normalization techniques, such as Layer Normalization (LayerNorm, LN) and Root Mean Square Normalization (RMSNorm), play a critical role in accelerating and…

Selecting a layer normalization (LN) strategy that stabilizes training and speeds convergence in Transformers remains difficult, even for today's large language models (LLM). We present a comprehensive analytical foundation for…

Reconstructing MR images using deep neural networks from undersampled k-space data without using fully sampled training references offers significant value in practice, which is a self-supervised regression problem calling for effective…

Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear…

From the perspective of the layer normalization (LN) positions, the architectures of Transformers can be categorized into two types: Post-LN and Pre-LN. Recent Transformers tend to be Pre-LN because, in Post-LN with deep Transformers (e.g.,…

The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as…

Convolutional Siamese neural networks have been recently used to track objects using deep features. Siamese architecture can achieve real time speed, however it is still difficult to find a Siamese architecture that maintains the…

The placement of normalization layers, specifically Pre-Norm and Post-Norm, remains an open question in Transformer architecture design. In this work, we rethink these approaches through the lens of manifold optimization, interpreting the…

Rotation is among the long prevailing, yet still unresolved, hard challenges encountered in visual object tracking. The existing deep learning-based tracking algorithms use regular CNNs that are inherently translation equivariant, but not…

Transformers have achieved great success in effectively processing sequential data such as text. Their architecture consisting of several attention and feedforward blocks can model relations between elements of a sequence in parallel…

Recent object tracking methods depend upon deep networks or convoluted architectures. Most of those trackers can hardly meet real-time processing requirements on mobile platforms with limited computing resources. In this work, we introduce…

In the context of cellular networks, users located at the periphery of cells are particularly vulnerable to substantial interference from neighbouring cells, which can be represented as a two-user interference channel. This study introduces…

Efficient tracking has garnered attention for its ability to operate on resource-constrained platforms for real-world deployment beyond desktop GPUs. Current efficient trackers mainly follow precision-oriented trackers, adopting a…