Related papers: Post-Training Quantization for Vision Mamba with k…

Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to their high computational and memory demands. Post-Training…

Point cloud registration (PCR) is a fundamental task in 3D computer vision and robotics. Most learning-based PCR methods rely on Transformer architectures, which suffer from quadratic computational complexity. This limitation restricts the…

Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break down at lower bit precision, and investigate quantization…

We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification. Unlike prior post-training or block-wise reconstruction methods, we jointly optimize over the…

World models learn an internal representation of environment dynamics, enabling agents to simulate and reason about future states within a compact latent space for tasks such as planning, prediction, and inference. However, running world…

The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism renders it particularly…

Mamba, a State Space Model (SSM), has recently shown competitive performance to Convolutional Neural Networks (CNNs) and Transformers in Natural Language Processing and general sequence modeling. Various attempts have been made to adapt…

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to security and privacy…

The post-training quantization (PTQ) challenge of bringing quantized neural net accuracy close to original has drawn much attention driven by industry demand. Many of the methods emphasize optimization of a specific degree-of-freedom (DoF),…

Despite the significant achievements of Vision Transformers (ViTs) in various vision tasks, they are constrained by the quadratic complexity. Recently, State Space Models (SSMs) have garnered widespread attention due to their global…

Mamba, a State Space Model (SSM) that accelerates training by recasting recurrence as a parallel scan, has recently emerged as a linearly-scaling alternative to self-attention. Because of its unidirectional nature, each state in Mamba only…

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…

Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy.…

With the commercialization of large language models (LLMs), weight-activation quantization has emerged to compress and accelerate LLMs, achieving high throughput while reducing inference costs. However, existing post-training quantization…

The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called…

Structural Health Monitoring (SHM) ensures the safety and longevity of infrastructure by enabling timely damage detection. Vision-based crack detection, combined with UAVs, addresses the limitations of traditional sensor-based SHM methods…

In the field of medical image segmentation, models based on both CNN and Transformer have been thoroughly investigated. However, CNNs have limited modeling capabilities for long-range dependencies, making it challenging to exploit the…

Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment.…

Medical video segmentation gains increasing attention in clinical practice due to the redundant dynamic references in video frames. However, traditional convolutional neural networks have a limited receptive field and transformer-based…