相关论文: CaTok: Taming Mean Flows for One-Dimensional Causa…
Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…
Decoder-only large language models (LLMs) have been increasingly adopted to build embedding models for diverse tasks. To overcome the inherent limitations of causal attention in representation learning, many existing methods modify the…
Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based…
Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…
Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived from them recover bidirectional capability through…
In voice conversion (VC) applications, diffusion and flow-matching models have exhibited exceptional speech quality and speaker similarity performances. However, they are limited by slow conversion owing to their iterative inference.…
Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…
Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…
Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize truly novel, out-of-distribution concepts. Existing methods…
Current image captioning works usually focus on generating descriptions in an autoregressive manner. However, there are limited works that focus on generating descriptions non-autoregressively, which brings more decoding diversity. Inspired…
Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…
People see text. Humans read by recognizing words as visual objects, including their shapes, layouts, and patterns, before connecting them to meaning, which enables us to handle typos, distorted fonts, and various scripts effectively.…
We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a popular approach by learning the identity mapping on the…
Real-time transmission of video over wireless networks remains highly challenging, even with advanced deep models, particularly under severe channel conditions such as limited bandwidth and weak connectivity. In this paper, we propose…
Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…
In this paper, we introduce SemHiTok, a unified image Tokenizer via Semantic-Guided Hierarchical codebook that provides consistent discrete representations for multimodal understanding and generation. Recently, unified image tokenizers have…
The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…
Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these models face efficiency challenges due to their sequential…
Video Large Language Models (Video LLMs) have achieved remarkable results in video understanding tasks. However, they often suffer from heavy computational overhead due to the large number of visual tokens generated from multiple video…
Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by…