Related papers: StepVAR: Structure-Texture Guided Pruning for Visu…

In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown promising performance in video tasks due to their extended…

Recent advancements in visual autoregressive models (VAR) have demonstrated their effectiveness in image generation, highlighting their potential for real-world image super-resolution (Real-ISR). However, adapting VAR for ISR presents…

While artificial neural networks excel in unsupervised learning of non-sparse structure, classical statistical regression techniques offer better interpretability, in particular when sparseness is enforced by $\ell_1$ regularization,…

We propose a monocular depth estimation method based on visual autoregressive (VAR) priors, offering an alternative to diffusion-based approaches. Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise…

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing…

Monocular depth estimation has seen significant advances through discriminative approaches, yet their performance remains constrained by the limitations of training datasets. While generative approaches have addressed this challenge by…

As the size of transformer-based models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the…

The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have…

Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames,…

Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution…

Conventional wisdom suggests that autoregressive models are used to process discrete data. When applied to continuous modalities such as visual data, Visual AutoRegressive modeling (VAR) typically resorts to quantization-based approaches to…

Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index storage overhead. Existing training-free pruning methods either rely on heuristic layer choices or…

Large Multimodal Models (LMMs) have achieved significant success across various tasks. These models usually encode visual inputs into dense token sequences, which are then concatenated with textual tokens and jointly processed by a language…

We propose a novel variational Bayes approach to estimate high-dimensional vector autoregression (VAR) models with hierarchical shrinkage priors. Our approach does not rely on a conventional structural VAR representation of the parameter…

VAR is a new generation paradigm that employs 'next-scale prediction' as opposed to 'next-token prediction'. This innovative transformation enables auto-regressive (AR) transformers to rapidly learn visual distributions and achieve robust…

Recent visual autoregressive (AR) models have shown promising capabilities in text-to-image generation, operating in a manner similar to large language models. While test-time computation scaling has brought remarkable success in enabling…

Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or…

Diffusion models have achieved remarkable success in high-fidelity image generation but remain computationally demanding due to their multi-step denoising process and large model sizes. Although prior work improves efficiency either by…

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…

With the development of the convolutional neural network, image style transfer has drawn increasing attention. However, most existing approaches adopt a global feature transformation to transfer style patterns into content images (e.g.,…