Related papers: ToVE: Efficient Vision-Language Learning via Knowl…

Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer visual token…

Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…

Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not…

Recent advancements in language and vision assistants have showcased impressive capabilities but suffer from a lack of transparency, limiting broader research and reproducibility. While open-source models handle general image tasks…

Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime…

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…

Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category…

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or…

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance,…

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…

For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill knowledge from an…

Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains challenging, especially for efficient adaptation. Existing continual imitation learning (CIL) methods…

Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure…

The crux of Referring Video Object Segmentation (RVOS) lies in modeling dense text-video relations to associate abstract linguistic concepts with dynamic visual contents at pixel-level. Current RVOS methods typically use vision and language…

Transduction is a powerful paradigm that leverages the structure of unlabeled data to boost predictive accuracy. We present TransCLIP, a novel and computationally efficient transductive approach designed for Vision-Language Models (VLMs).…

We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, "visual sentences", in which we can represent raw images…

The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. While Vision Transformer (ViT) based models scale effectively…