相关论文: Data-efficient Large Vision Models through Sequent…

Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by…

When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning in multimodal large language models (MLLMs). Effective reasoning, therefore, hinges on knowing…

Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…

In self-supervised learning, a model is trained to solve a pretext task, using a data set whose annotations are created by a machine. The objective is to transfer the trained weights to perform a downstream task in the target domain. We…

With the recent progress in large-scale vision and language representation learning, Vision Language Pre-training (VLP) models have achieved promising improvements on various multi-modal downstream tasks. Albeit powerful, these models have…

Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they require considerable computational resources for training and…

Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because…

Self-attention has the promise of improving computer vision systems due to parameter-independent scaling of receptive fields and content-dependent interactions, in contrast to parameter-dependent scaling and content-independent interactions…

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any…

General Purpose Vision (GPV) systems are models that are designed to solve a wide array of visual tasks without requiring architectural changes. Today, GPVs primarily learn both skills and concepts from large fully supervised datasets.…

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with…

Large Multimodal Models (LMMs) have recently demonstrated remarkable visual understanding performance on both vision-language and vision-centric tasks. However, they often fall short in integrating advanced, task-specific capabilities for…

The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies…

Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning due to overreliance on textual information and reduced visual dependency. In this study, we empirically analyze…

Automated visualization recommendations (vis-rec) help users to derive crucial insights from new datasets. Typically, such automated vis-rec models first calculate a large number of statistics from the datasets and then use machine-learning…