CSDformer: A Conversion Method for Fully Spike-Driven Transformer

• URL: http://arxiv.org/abs/2509.17461v1
• Date: Mon, 22 Sep 2025 07:55:03 GMT
• Title: CSDformer: A Conversion Method for Fully Spike-Driven Transformer
• Authors: Yuhao Zhang, Chengjun Zhang, Di Wu, Jie Yang, Mohamad Sawan,
• Abstract summary: Spike-based transformer is a novel architecture aiming to enhance the performance of spiking neural networks.<n>We propose CSDformer, a novel conversion method for fully spike-driven transformers.<n>CSDformer achieves high performance under ultra-low latency, while dramatically reducing both computational complexity and training overhead.
• Score: 11.852241487470797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spike-based transformer is a novel architecture aiming to enhance the performance of spiking neural networks while mitigating the energy overhead inherent to transformers. However, methods for generating these models suffer from critical limitations: excessive training costs introduced by direct training methods, or unavoidably hardware-unfriendly operations in existing conversion methods. In this paper, we propose CSDformer, a novel conversion method for fully spike-driven transformers. We tailor a conversion-oriented transformer-based architecture and propose a new function NReLU to replace softmax in self-attention. Subsequently, this model is quantized and trained, and converted into a fully spike-driven model with temporal decomposition technique. Also, we propose delayed Integrate-andFire neurons to reduce conversion errors and improve the performance of spiking models. We evaluate CSDformer on ImageNet, CIFAR-10 and CIFAR-100 datasets and achieve 76.36% top-1 accuracy under 7 time-steps on ImageNet, demonstrating superiority over state-of-the-art models. Furthermore, CSDformer eliminates the need for training SNNs, thereby reducing training costs (reducing computational resource by 75% and accelerating training speed by 2-3$\times$). To the best of our knowledge, this is the first fully spike-driven transformer-based model developed via conversion method, achieving high performance under ultra-low latency, while dramatically reducing both computational complexity and training overhead.

Related papers

• MeanFlow Transformers with Representation Autoencoders [71.45823902973349]
  MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data.<n>We develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE)<n>We achieve a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256.
  arXiv  Detail & Related papers  (2025-11-17T06:17:08Z)
• Large Language Models Inference Engines based on Spiking Neural Networks [5.529385616266398]
  We explore spiking neural networks (SNNs) to design transformer models.<n>A challenge in training large-scale SNNs is inefficient and time-consuming.<n>We propose NeurTransformer, a methodology for designing transformer-based SNN for inference.
  arXiv  Detail & Related papers  (2025-09-30T18:11:13Z)
• Accelerating Transformers in Online RL [47.99822253865053]
  transformer-based models in Reinforcement Learning (RL)<n>We propose a method that uses the Accelerator policy as a transformer's trainer.<n>We show that applying our algorithm not only enables stable training of transformers but also reduces training time on image-based environments by up to a factor of two.
  arXiv  Detail & Related papers  (2025-09-30T11:57:14Z)
• Emergent Agentic Transformer from Chain of Hindsight Experience [96.56164427726203]
  We show that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches. This is the first time that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
  arXiv  Detail & Related papers  (2023-05-26T00:43:02Z)
• TransCODE: Co-design of Transformers and Accelerators for Efficient Training and Inference [6.0093441900032465]
  We propose a framework that simulates transformer inference and training on a design space of accelerators. We use this simulator in conjunction with the proposed co-design technique, called TransCODE, to obtain the best-performing models. The obtained transformer-accelerator pair achieves 0.3% higher accuracy than the state-of-the-art pair.
  arXiv  Detail & Related papers  (2023-03-27T02:45:18Z)
• Online Convolutional Re-parameterization [51.97831675242173]
  We present online convolutional re- parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks.
  arXiv  Detail & Related papers  (2022-04-02T09:50:19Z)
• A Fast Post-Training Pruning Framework for Transformers [74.59556951906468]
  Pruning is an effective way to reduce the huge inference cost of large Transformer models. Prior work on model pruning requires retraining the model. We propose a fast post-training pruning framework for Transformers that does not require any retraining.
  arXiv  Detail & Related papers  (2022-03-29T07:41:11Z)
• TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting [6.393659160890665]
  We propose the concept of tightly-coupled convolutional Transformer(TCCT) and three TCCT architectures. Our experiments on real-world datasets show that our TCCT architectures could greatly improve the performance of existing state-of-art Transformer models.
  arXiv  Detail & Related papers  (2021-08-29T08:49:31Z)
• Finetuning Pretrained Transformers into RNNs [81.72974646901136]
  Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. A linear-complexity recurrent variant has proven well suited for autoregressive generation. This work aims to convert a pretrained transformer into its efficient recurrent counterpart.
  arXiv  Detail & Related papers  (2021-03-24T10:50:43Z)
• Understanding the Difficulty of Training Transformers [120.99980924577787]
  We show that unbalanced gradients are not the root cause of the instability of training. We propose Admin to stabilize the early stage's training and unleash its full potential in the late stage.
  arXiv  Detail & Related papers  (2020-04-17T13:59:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.