Related papers: ELT: Elastic Looped Transformers for Visual Genera…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on…

We propose Latte, a novel Latent Diffusion Transformer for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In…

Pretrained vision-language models (VLMs) like CLIP show strong zero-shot performance but struggle with generalization under distribution shifts. Test-Time Adaptation (TTA) addresses this by adapting VLMs to unlabeled test data in new…

Diffusion models are the standard toolkit for generative modelling of 3D atomic systems. However, for different types of atomic systems -- such as molecules and materials -- the generative processes are usually highly specific to the target…

Prior methods for controlling image generation are limited in their ability to be taught new tasks. In contrast, vision-language models, or VLMs, can learn tasks in-context and produce the correct outputs for a given input. We propose a…

Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…

Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion. To address these…

How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the…

The inverse-free extreme learning machine (ELM) algorithm proposed in [4] was based on an inverse-free algorithm to compute the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of…

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence,…

Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

Implicit generative models are difficult to train as no explicit density functions are defined. Generative adversarial nets (GANs) present a minimax framework to train such models, which however can suffer from mode collapse due to the…

Implicit Neural Networks (INRs) have emerged as powerful representations to encode all forms of data, including images, videos, audios, and scenes. With video, many INRs for video have been proposed for the compression task, and recent…

Large-scale fine-grained image retrieval (FGIR) aims to retrieve images belonging to the same subcategory as a given query by capturing subtle differences in a large-scale setting. Recently, Vision Transformers (ViT) have been employed in…

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal…

Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks. For the classification task that use pre-trained self-supervised models as backbones,…

Light field (LF) images containing information for multiple views have numerous applications, which can be severely affected by low-light imaging. Recent learning-based methods for low-light enhancement have some disadvantages, such as a…

Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-quality images in a few steps. NATs perform generation in a…