相关论文: SAViR-T: Spatially Attentive Visual Reasoning with…

Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lean more on textual cues than visual evidence and the risk of…

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted…

The emergence of vision transformers (ViTs) in image classification has shifted the methodologies for visual representation learning. In particular, ViTs learn visual representation at full receptive field per layer across all the image…

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent…

Raven's Progressive Matrices (RPMs) is an established benchmark to examine the ability to perform high-level abstract visual reasoning (AVR). Despite the current success of algorithms that solve this task, humans can generalize beyond a…

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting…

This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the understanding of mathematical rules such as progression or…

Generating videos is a complex task that is accomplished by generating a set of temporally coherent images frame-by-frame. This limits the expressivity of videos to only image-based operations on the individual video frames needing network…

Abstract reasoning refers to the ability to analyze information, discover rules at an intangible level, and solve problems in innovative ways. Raven's Progressive Matrices (RPM) test is typically used to examine the capability of abstract…

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…

Visual abstract reasoning tasks present challenges for deep neural networks, exposing limitations in their capabilities. In this work, we present a neural network model that addresses the challenges posed by Raven's Progressive Matrices…

Recent neuro-symbolic approaches have successfully extracted symbolic rule-sets from CNN-based models to enhance interpretability. However, applying similar techniques to Vision Transformers (ViTs) remains challenging due to their lack of…

Large Vision-Language Models (LVLMs) achieve impressive performance across multiple tasks. A significant challenge, however, is their prohibitive inference cost when processing high-resolution visual inputs. While visual token pruning has…

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…

Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision. A cornerstone of their success lies in the attention mechanism, which models relationships…

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…

We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…

Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…