Related papers: Cached Adaptive Token Merging: Dynamic Token Reduc…

K-means clustering, a classic and widely-used clustering technique, is known to exhibit suboptimal performance when applied to non-linearly separable data. Numerous adjustments and modifications have been proposed to address this issue,…

Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an…

To enhance the quality and speed of data processing and protect the privacy and security of the data, edge computing has been extensively applied to support data-intensive intelligent processing services at edge. Among these data-intensive…

Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation and are especially…

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…

Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their…

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made…

Text-to-image diffusion models have demonstrated unprecedented capabilities for flexible and realistic image synthesis. Nevertheless, these models rely on a time-consuming sampling procedure, which has motivated attempts to reduce their…

Diffusion Policy has demonstrated strong visuomotor modeling capabilities, but its high computational cost renders it impractical for real-time robotic control. Despite huge redundancy across repetitive denoising steps, existing diffusion…

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on…

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…

Model merging aims to combine multiple task-specific expert models into a single model while preserving generalization across diverse tasks. However, interference among experts, especially when they are trained on different objectives,…

Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embeddings optimized for…

Diffusion models have demonstrated great potential in generating high-quality content for images, natural language, protein domains, etc. However, how to perform user-preferred targeted generation via diffusion models with only black-box…

Diffusion transformer (DiT) models have achieved remarkable success in image generation, thanks for their exceptional generative capabilities and scalability. Nonetheless, the iterative nature of diffusion models (DMs) results in high…

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Generative depth estimation methods leverage the rich visual priors stored in pre-trained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic…

Text-to-Video applications receive increasing attention from the public. Among these, diffusion models have emerged as the most prominent approach, offering impressive quality in visual content generation. However, it still suffers from…

Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based methods, Adjoint Matching (AM) provides a principled…