相关论文: Optical Context Compression Is Just (Bad) Autoenco…

Multi-agent debate can improve reasoning quality and reduce hallucinations, but it incurs rapidly growing context as debate rounds and agent count increase. Retaining full textual histories leads to token usage that can exceed context…

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…

Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents where lengthy inputs incur high computational costs and…

Some forms of novel visual media enable the viewer to explore a 3D scene from arbitrary viewpoints, by interpolating between a discrete set of original views. Compared to 2D imagery, these types of applications require much larger amounts…

Earth observation (EO) plays a crucial role in creating and sustaining a resilient and prosperous society that has far reaching consequences for all life and the planet itself. Remote sensing platforms like satellites, airborne platforms,…

This paper addresses an ill-posed problem of recovering a color image from its compressively sensed measurement data. Differently from the typical 1D vector-based approach of the state-of-the-art methods, we exploit the nonlocal…

Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). However, this adaptation remains challenging, as it requires…

In recent years, notable advancements have been made in the domain of visual document understanding, with the prevailing architecture comprising a cascade of vision and language models. The text component can either be extracted explicitly…

Ultra-low bitrate image compression faces a critical challenge: preserving small-font scene text while maintaining overall visual quality. Region-of-interest (ROI) bit allocation can prioritize text but often degrades global fidelity,…

Variational Autoencoders (VAEs) have seen widespread use in learned image compression. They are used to learn expressive latent representations on which downstream compression methods can operate with high efficiency. Recently proposed…

Recent lightweight image captioning models using retrieved data mainly focus on text prompts. However, previous works only utilize the retrieved text as text prompts, and the visual information relies only on the CLIP visual embedding.…

We propose an end-to-end recurrent encoder-decoder based sequence learning approach for printed text Optical Character Recognition (OCR). In contrast to present day existing state-of-art OCR solution which uses connectionist temporal…

Semantic ID learning is a key interface in Generative Recommendation (GR) models, mapping items to discrete identifiers grounded in side information, most commonly via a pretrained text encoder. However, these text encoders are primarily…

Generating textual descriptions for images has been an attractive problem for the computer vision and natural language processing researchers in recent years. Dozens of models based on deep learning have been proposed to solve this problem.…

Embedding models are central to dense retrieval, semantic search, and recommendation systems, but their size often makes them impractical to deploy in resource-constrained environments such as browsers or edge devices. While smaller…

This paper explores the application of enhancement filtering techniques in neural video compression. Specifically, we categorize these techniques into in-loop contextual filtering and out-of-loop reconstruction enhancement based on whether…

Model compression is a critical area of research in deep learning, in particular in vision, driven by the need to lighten models memory or computational footprints. While numerous methods for model compression have been proposed, most focus…

To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships…

Visual understanding is inherently contextual -- what we focus on in an image depends on the task at hand. For instance, given an image of a person holding a bouquet of flowers, we may focus on either the person such as their clothing, or…

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…