相关论文: CIAR: Interval-based Collaborative Decoding for Im…
We study reasoning tasks through a framework that integrates auto-regressive (AR) and non-autoregressive (NAR) language models. AR models, which generate text sequentially, excel at producing coherent outputs but often suffer from slow…
Displaying high-quality images on edge devices, such as augmented reality devices, is essential for enhancing the user experience. However, these devices often face power consumption and computing resource limitations, making it challenging…
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. While this approach has been extended to the 3D domain for powerful shape generation, it still has two…
Composed image retrieval (CIR) is the task of retrieving a target image specified by a query image and a relative text that describes a semantic modification to the query image. Existing methods in CIR struggle to accurately represent the…
While inference-time scaling has significantly enhanced generative quality in large language and diffusion models, its application to vector-quantized (VQ) visual autoregressive modeling (VAR) remains unexplored. We introduce VAR-Scaling,…
Autoregressive (AR) models have shown great promise in image generation, yet they face a fundamental inefficiency stemming from their core component: a vast, unstructured vocabulary of visual tokens. This conventional approach treats tokens…
Content-based image retrieval (CBIR) is a task of retrieving images from their contents. Since retrieval process is a time-consuming task in large image databases, acceleration methods can be very useful. This paper presents a novel method…
In this paper, we present an efficient and effective single-stage framework (DiverGAN) to generate diverse, plausible and semantically consistent images according to a natural-language description. DiverGAN adopts two novel word-level…
Autoregressive generation is a powerful approach for high-fidelity image synthesis, but it remains computationally demanding and slow even on the most advanced accelerators. While speculative decoding has been explored to mitigate this…
Test-time scaling (TTS) has demonstrated remarkable success in enhancing large language models, yet its application to next-token prediction (NTP) autoregressive (AR) image generation remains largely uncharted. Existing TTS approaches for…
Despite substantial progress in anomaly synthesis methods, existing diffusion-based and coarse inpainting pipelines commonly suffer from structural deficiencies such as micro-structural discontinuities, limited semantic controllability, and…
Lipreading is an impressive technique and there has been a definite improvement of accuracy in recent years. However, existing methods for lipreading mainly build on autoregressive (AR) model, which generate target tokens one by one and…
We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…
Recent advances in generative image restoration (IR) have demonstrated impressive results. However, these methods are hindered by their substantial size and computational demands, rendering them unsuitable for deployment on edge devices.…
Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a.k.a., image description, has been remarkably advanced…
Composed image retrieval (CIR) is a vision language task that retrieves a target image using a reference image and modification text, enabling intuitive specification of desired changes. While effectively fusing visual and textual…
We present a novel algorithm to reduce tensor compute required by a conditional image generation autoencoder without sacrificing quality of photo-realistic image generation. Our method is device agnostic, and can optimize an autoencoder for…
The massive adoption of large language models (LLMs) demands efficient deployment strategies. However, the auto-regressive decoding process, which is fundamental to how most LLMs generate text, poses challenges to achieve efficient serving.…
Autoregressive pre-trained models combined with decoding methods have achieved impressive performance on complex reasoning tasks. While mainstream decoding strategies such as beam search can generate plausible candidate sets, they often…
Recently, autoregressive (AR) image models have demonstrated remarkable generative capabilities, positioning themselves as a compelling alternative to diffusion models. However, their sequential nature leads to long inference times,…