Related papers: ZipAR: Parallel Auto-regressive Image Generation t…
Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…
Autoregressive (AR) models, common in sequence generation, are limited in many biological tasks such as de novo peptide sequencing and protein modeling by their unidirectional nature, failing to capture crucial global bidirectional token…
The past decades have witnessed the rapid development of image and video coding techniques in the era of big data. However, the signal fidelity-driven coding pipeline design limits the capability of the existing image/video coding…
Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An…
This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach…
Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…
The rapid advancement of image-generation technologies has made it possible for anyone to create photorealistic images using generative models, raising significant security concerns. To mitigate malicious use, tracing the origin of such…
Robotic and animal mapping systems share many of the same objectives and challenges, but differ in one key aspect: where much of the research in robotic mapping has focused on solving the data association problem, the grid cell neurons…
The goal of this work is to efficiently identify visually similar patterns in images, e.g. identifying an artwork detail copied between an engraving and an oil painting, or recognizing parts of a night-time photograph visible in its daytime…
LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…
Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens. However,…
Generative image models have emerged as a promising technology to produce realistic images. Despite potential benefits, concerns grow about its misuse, particularly in generating deceptive images that could raise significant ethical, legal,…
Tensor parallelism is an essential technique for distributed training of large neural networks. However, automatically determining an optimal tensor parallel strategy is challenging due to the gigantic search space, which grows…
This work leverages the continuous sweeping motion of LiDAR scanning to concentrate object detection efforts on specific regions that receive a change in point data from one frame to another. We achieve this by using a sliding time window…
Generative models, such as GANs, learn an explicit low-dimensional representation of a particular class of images, and so they may be used as natural image priors for solving inverse problems such as image restoration and compressive…
Generative models learned from training using deep learning methods can be used as priors in inverse under-determined inverse problems, including imaging from sparse set of measurements. In this paper, we present a novel hierarchical…
Reversibility in artificial neural networks allows us to retrieve the input given an output. We present feature alignment, a method for approximating reversibility in arbitrary neural networks. We train a network by minimizing the distance…
Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent across domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to modify a reference image…
Recent progress in panoramic image generation has underscored two critical limitations in existing approaches. First, most methods are built upon diffusion models, which are inherently ill-suited for equirectangular projection (ERP)…