Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive applications demand high-resolution, resulting in significant computational overhead. Using OCR-extracted text in VLM prompts partially addresses this issue but underperforms compared to full-resolution counterpart, as it lacks the complete visual context needed for optimal performance. We introduce DocVLM, a method that integrates an OCR-based modality into VLMs to enhance document processing while preserving original weights. Our approach employs an OCR encoder to capture textual content and layout, compressing these into a compact set of learned queries incorporated into the VLM. Comprehensive evaluations across leading VLMs show that DocVLM significantly reduces reliance on high-resolution images for document understanding. In limited-token regimes (448$\times$448), DocVLM with 64 learned queries improves DocVQA results from 56.0% to 86.6% when integrated with InternVL2 and from 84.4% to 91.2% with Qwen2-VL. In LLaVA-OneVision, DocVLM achieves improved results while using 80% less image tokens. The reduced token usage allows processing multiple pages effectively, showing impressive zero-shot results on DUDE and state-of-the-art performance on MP-DocVQA, highlighting DocVLM's potential for applications requiring high-performance and efficiency.

Vision-Language (VL) models have garnered considerable research interest; however, they still face challenges in effectively handling text within images. To address this limitation, researchers have developed two approaches. The first method involves utilizing external Optical Character Recognition (OCR) tools to extract textual information from images, which is then prepended to other textual inputs. The second strategy focuses on employing extremely high-resolution images to improve text recognition capabilities. In this paper, we focus on enhancing the first strategy by introducing a novel method, named TAP-VL, which treats OCR information as a distinct modality and seamlessly integrates it into any VL model. TAP-VL employs a lightweight transformer-based OCR module to receive OCR with layout information, compressing it into a short fixed-length sequence for input into the LLM. Initially, we conduct model-agnostic pretraining of the OCR module on unlabeled documents, followed by its integration into any VL architecture through brief fine-tuning. Extensive experiments demonstrate consistent performance improvements when applying TAP-VL to top-performing VL models, across scene-text and document-based VL benchmarks.

Adversarial training aims to defend against *adversaries*: malicious opponents whose sole aim is to harm predictive performance in any way possible - a rather harsh perspective, which we assert results in unnecessarily conservative models. Instead, we propose to model opponents as simply pursuing their own goals, rather than working directly against the classifier. Employing tools from strategic modeling, our approach uses knowledge or beliefs regarding the opponent's possible incentives as inductive bias for learning. Our method of *strategic training* is designed to defend against opponents within an *incentive uncertainty set*: this resorts to adversarial learning when the set is maximal, but offers potential gains when it can be appropriately reduced. We conduct a series of experiments that show how even mild knowledge regarding the adversary's incentives can be useful, and that the degree of potential gains depends on how incentives relate to the structure of the learning task.

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis. These methods overcome the slowness of diffusion models by directly mapping noise to data, while maintaining a (relatively) simpler training. Consistency models enable a fast one- or few-step generation, but they typically fall somewhat short in sample quality when compared to their diffusion origins. In this work we propose a novel and highly effective technique for post-processing Consistency-based generated images, enhancing their perceptual quality. Our approach utilizes a joint classifier-discriminator model, in which both portions are trained adversarially. While the classifier aims to grade an image based on its assignment to a designated class, the discriminator portion of the very same network leverages the softmax values to assess the proximity of the input image to the targeted data manifold, thereby serving as an Energy-based Model. By employing example-specific projected gradient iterations under the guidance of this joint machine, we refine synthesized images and achieve an improved FID scores on the ImageNet 64x64 dataset for both Consistency-Training and Consistency-Distillation techniques.

Image editing has advanced significantly with the introduction of text-conditioned diffusion models. Despite this progress, seamlessly adding objects to images based on textual instructions without requiring user-provided input masks remains a challenge. We address this by leveraging the insight that removing objects (Inpaint) is significantly simpler than its inverse process of adding them (Paint), attributed to the utilization of segmentation mask datasets alongside inpainting models that inpaint within these masks. Capitalizing on this realization, by implementing an automated and extensive pipeline, we curate a filtered large-scale image dataset containing pairs of images and their corresponding object-removed versions. Using these pairs, we train a diffusion model to inverse the inpainting process, effectively adding objects into images. Unlike other editing datasets, ours features natural target images instead of synthetic ones; moreover, it maintains consistency between source and target by construction. Additionally, we utilize a large Vision-Language Model to provide detailed descriptions of the removed objects and a Large Language Model to convert these descriptions into diverse, natural-language instructions. We show that the trained model surpasses existing ones both qualitatively and quantitatively, and release the large-scale dataset alongside the trained models for the community.

The increasing use of transformer-based large language models brings forward the challenge of processing long sequences. In document visual question answering (DocVQA), leading methods focus on the single-page setting, while documents can span hundreds of pages. We present GRAM, a method that seamlessly extends pre-trained single-page models to the multi-page setting, without requiring computationally-heavy pretraining. To do so, we leverage a single-page encoder for local page-level understanding, and enhance it with document-level designated layers and learnable tokens, facilitating the flow of information across pages for global reasoning. To enforce our model to utilize the newly introduced document-level tokens, we propose a tailored bias adaptation method. For additional computational savings during decoding, we introduce an optional compression stage using our C-Former model, which reduces the encoded sequence length, thereby allowing a tradeoff between quality and latency. Extensive experiments showcase GRAM's state-of-the-art performance on the benchmarks for multi-page DocVQA, demonstrating the effectiveness of our approach.

The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image details. This limitation can be traced back to the image-text datasets; while their captions typically offer a general description of image content, they frequently omit salient details. Considering the magnitude of these datasets, manual reannotation is impractical, emphasizing the need for an automated approach. To address this challenge, we leverage existing captions and explore augmenting them with visual details using "frozen" vision experts including an object detector, an attribute recognizer, and an Optical Character Recognizer (OCR). Our proposed method, FuseCap, fuses the outputs of such vision experts with the original captions using a large language model (LLM), yielding comprehensive image descriptions. We automatically curate a training set of 12M image-enriched caption pairs. These pairs undergo extensive evaluation through both quantitative and qualitative analyses. Subsequently, this data is utilized to train a captioning generation BLIP-based model. This model outperforms current state-of-the-art approaches, producing more precise and detailed descriptions, demonstrating the effectiveness of the proposed data-centric approach. We release this large-scale dataset of enriched image-caption pairs for the community.

Perceptually Aligned Gradients (PAG) refer to an intriguing property observed in robust image classification models, wherein their input gradients align with human perception and pose semantic meanings. While this phenomenon has gained significant research attention, it was solely studied in the context of unimodal vision-only architectures. In this work, we extend the study of PAG to Vision-Language architectures, which form the foundations for diverse image-text tasks and applications. Through an adversarial robustification finetuning of CLIP, we demonstrate that robust Vision-Language models exhibit PAG in contrast to their vanilla counterparts. This work reveals the merits of CLIP with PAG (CLIPAG) in several vision-language generative tasks. Notably, we show that seamlessly integrating CLIPAG in a "plug-n-play" manner leads to substantial improvements in vision-language generative applications. Furthermore, leveraging its PAG property, CLIPAG enables text-to-image generation without any generative model, which typically requires huge generators.

Reading text in real-world scenarios often requires understanding the context surrounding it, especially when dealing with poor-quality text. However, current scene text recognizers are unaware of the bigger picture as they operate on cropped text images. In this study, we harness the representative capabilities of modern vision-language models, such as CLIP, to provide scene-level information to the crop-based recognizer. We achieve this by fusing a rich representation of the entire image, obtained from the vision-language model, with the recognizer word-level features via a gated cross-attention mechanism. This component gradually shifts to the context-enhanced representation, allowing for stable fine-tuning of a pretrained recognizer. We demonstrate the effectiveness of our model-agnostic framework, CLIPTER (CLIP TExt Recognition), on leading text recognition architectures and achieve state-of-the-art results across multiple benchmarks. Furthermore, our analysis highlights improved robustness to out-of-vocabulary words and enhanced generalization in low-data regimes.

Visual Question Answering (VQA) and Image Captioning (CAP), which are among the most popular vision-language tasks, have analogous scene-text versions that require reasoning from the text in the image. Despite their obvious resemblance, the two are treated independently and, as we show, yield task-specific methods that can either see or read, but not both. In this work, we conduct an in-depth analysis of this phenomenon and propose UniTNT, a Unified Text-Non-Text approach, which grants existing multimodal architectures scene-text understanding capabilities. Specifically, we treat scene-text information as an additional modality, fusing it with any pretrained encoder-decoder-based architecture via designated modules. Thorough experiments reveal that UniTNT leads to the first single model that successfully handles both task types. Moreover, we show that scene-text understanding capabilities can boost vision-language models' performance on general VQA and CAP by up to 2.69% and 0.6 CIDEr, respectively.