相关论文: SDBERT: SparseDistilBERT, a faster and smaller BER…

Large-scale pre-trained language models have shown remarkable results in diverse NLP applications. Unfortunately, these performance gains have been accompanied by a significant increase in computation time and model size, stressing the need…

Recently, large pre-trained models have significantly improved the performance of various Natural LanguageProcessing (NLP) tasks but they are expensive to serve due to long serving latency and large memory usage. To compress these models,…

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing distillation methods that rely on layer-wise and feature-wise…

Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in…

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…

In pursuit of faster computation, Efficient Transformers demonstrate an impressive variety of approaches -- models attaining sub-quadratic attention complexity can utilize a notion of sparsity or a low-rank approximation of inputs to reduce…

As the third-generation neural network, the Spiking Neural Network (SNN) has the advantages of low power consumption and high energy efficiency, making it suitable for implementation on edge devices. More recently, the most advanced SNN,…

Large pre-trained transformer-based language models have achieved impressive results on a wide range of NLP tasks. In the past few years, Knowledge Distillation(KD) has become a popular paradigm to compress a computationally expensive model…

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…

Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…

Modern Natural Language Processing (NLP) models based on Transformer structures represent the state of the art in terms of performance on very diverse tasks. However, these models are complex and represent several hundred million parameters…

There are various optimization techniques in the realm of 3D, including point cloud-based approaches that use mesh, texture, and voxels which optimize how you store, and how do calculate in 3D. These techniques employ methods such as…

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

The sparse transformer can reduce the computational complexity of the self-attention layers to $O(n)$, whilst still being a universal approximator of continuous sequence-to-sequence functions. However, this permutation variant operation is…

Despite pre-trained language models such as BERT have achieved appealing performance in a wide range of natural language processing tasks, they are computationally expensive to be deployed in real-time applications. A typical method is to…

Pre-trained large-scale language models such as BERT have gained a lot of attention thanks to their outstanding performance on a wide range of natural language tasks. However, due to their large number of parameters, they are…

We perform knowledge distillation (KD) benchmark from task-specific BERT-base teacher models to various student models: BiLSTM, CNN, BERT-Tiny, BERT-Mini, and BERT-Small. Our experiment involves 12 datasets grouped in two tasks: text…

Identifying words that impact a task's performance more than others is a challenge in natural language processing. Transformers models have recently addressed this issue by incorporating an attention mechanism that assigns greater attention…

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…