Related papers: StrokeNUWA: Tokenizing Strokes for Vector Graphic …
The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning or incur a significant drawback to energy efficiency, making…
Professionals working in technical domain typically hand-draw (on whiteboard, paper, etc.) technical diagrams (e.g., flowcharts, block diagrams, etc.) during discussions; however, if they want to edit these later, it needs to be drawn from…
Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…
We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components. First, Dynamic…
The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and…
Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the…
The classification of short texts is a common subtask in Information Retrieval (IR). Recent advances in graph machine learning have led to interest in graph-based approaches for low resource scenarios, showing promise in such settings.…
State-of-the-art text spotting systems typically aim to detect isolated words or word-by-word text in images of natural scenes and ignore the semantic coherence within a region of text. However, when interpreted together, seemingly isolated…
The unprecedented advancements in Large Language Models (LLMs) have profoundly impacted natural language processing but have yet to fully embrace the realm of scalable vector graphics (SVG) generation. While LLMs encode partial knowledge of…
Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-video understanding results in substantial token counts,…
Image tokenizers map images to sequences of discrete tokens, and are a crucial component of autoregressive transformer-based image generation. The tokens are typically associated with spatial locations in the input image, arranged in raster…
Typical video modeling methods, such as LLava, represent videos as sequences of visual tokens, which are then processed by the LLM backbone for effective video understanding. However, this approach leads to a massive number of visual…
We present Neural 3D Strokes, a novel technique to generate stylized images of a 3D scene at arbitrary novel views from multi-view 2D images. Different from existing methods which apply stylization to trained neural radiance fields at the…
Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…
Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into…
Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent…
Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years. However, their high computational costs remain a significant barrier to their practical deployment. In particular, the…
Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance;…
Multi-modal large language models (MLLMs) utilizing instruction-following data, such as LLaVA, have achieved great progress in the industry. A major limitation in these models is that visual tokens consume a substantial portion of the…
In this study, we introduce a novel method called group-wise \textbf{VI}sual token \textbf{S}election and \textbf{A}ggregation (VISA) to address the issue of inefficient inference stemming from excessive visual tokens in multimoal large…