Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. We propose key architectural innovations to: (i) bridge powerful pretrained vision-only and language-only models, (ii) handle sequences of arbitrarily interleaved visual and textual data, and (iii) seamlessly ingest images or videos as inputs. Thanks to their flexibility, Flamingo models can be trained on large-scale multimodal web corpora containing arbitrarily interleaved text and images, which is key to endow them with in-context few-shot learning capabilities. We perform a thorough evaluation of our models, exploring and measuring their ability to rapidly adapt to a variety of image and video tasks. These include open-ended tasks such as visual question-answering, where the model is prompted with a question which it has to answer, captioning tasks, which evaluate the ability to describe a scene or an event, and close-ended tasks such as multiple-choice visual question-answering. For tasks lying anywhere on this spectrum, a single Flamingo model can achieve a new state of the art with few-shot learning, simply by prompting the model with task-specific examples. On numerous benchmarks, Flamingo outperforms models fine-tuned on thousands of times more task-specific data.

This study examines the potential of utilizing Vision Language Models (VLMs) to improve the perceptual capabilities of semi-autonomous prosthetic hands. We introduce a unified benchmark for end-to-end perception and grasp inference, evaluating a single VLM to perform tasks that traditionally require complex pipelines with separate modules for object detection, pose estimation, and grasp planning. To establish the feasibility and current limitations of this approach, we benchmark eight contemporary VLMs on their ability to perform a unified task essential for bionic grasping. From a single static image, they should (1) identify common objects and their key properties (name, shape, orientation, and dimensions), and (2) infer appropriate grasp parameters (grasp type, wrist rotation, hand aperture, and number of fingers). A corresponding prompt requesting a structured JSON output was employed with a dataset of 34 snapshots of common objects. Key performance metrics, including accuracy for categorical attributes (e.g., object name, shape) and errors in numerical estimates (e.g., dimensions, hand aperture), along with latency and cost, were analyzed. The results demonstrated that most models exhibited high performance in object identification and shape recognition, while accuracy in estimating dimensions and inferring optimal grasp parameters, particularly hand rotation and aperture, varied more significantly. This work highlights the current capabilities and limitations of VLMs as advanced perceptual modules for semi-autonomous control of bionic limbs, demonstrating their potential for effective prosthetic applications.

The contemporary phenomenon of deepfakes, utilizing GAN or diffusion models for face swapping, presents a substantial and evolving threat in digital media, identity verification, and a multitude of other systems. The majority of existing methods for detecting deepfakes rely on training specialized classifiers to distinguish between genuine and manipulated images, focusing only on the image domain without incorporating any auxiliary tasks that could enhance robustness. In this paper, inspired by the zero-shot capabilities of Vision Language Models, we propose a novel VLM-based approach to image classification and then evaluate it for deepfake detection. Specifically, we utilize a new high-quality deepfake dataset comprising 60,000 images, on which our zero-shot models demonstrate superior performance to almost all existing methods. Subsequently, we compare the performance of the best-performing architecture, InstructBLIP, on the popular deepfake dataset DFDC-P against traditional methods in two scenarios: zero-shot and in-domain fine-tuning. Our results demonstrate the superiority of VLMs over traditional classifiers.

With the rapid rise of generative AI and synthetic media, distinguishing AI-generated images from real ones has become crucial in safeguarding against misinformation and ensuring digital authenticity. Traditional watermarking techniques have shown vulnerabilities to adversarial attacks, undermining their effectiveness in the presence of attackers. W e propose IConMark, a novel in-generation robust semantic watermarking method that embeds interpretable concepts into AI-generated images, as a first step toward interpretable watermarking. Unlike traditional methods, which rely on adding noise or perturbations to AI-generated images, IConMark incorporates meaningful semantic attributes, making it interpretable to humans and hence, resilient to adversarial manipulation. This method is not only robust against various image augmentations but also human-readable, enabling manual verification of watermarks. W e demonstrate a detailed evaluation of IConMark's effectiveness, demonstrating its superiority in terms of detection accuracy and maintaining image quality. Moreover, IConMark can be combined with existing watermarking techniques to further enhance and complement its robustness. W e introduce IConMark+SS and ICon-Mark+TM, hybrid approaches combining IConMark with StegaStamp and TrustMark, respectively, to further bolster robustness against multiple types of image manipulations. Our base watermarking technique (IConMark) and its variants (+TM and +SS) achieve 10.8%, 14.5%, and 15.9% higher mean area under the receiver operating characteristic curve (AUROC) scores for watermark detection, respectively, compared to the best baseline on various datasets.

Recent advancements in open-source Visual Language Models (VLMs) such as LLaVA, Qwen-VL, and Llama have catalyzed extensive research on their integration with diverse systems. The internet-scale general knowledge encapsulated within these models presents significant opportunities for enhancing autonomous driving perception, prediction, and planning capabilities. In this paper we propose VLAD, a vision-language autonomous driving model, which integrates a fine-tuned VLM with VAD, a state-of-the-art end-to-end system. We implement a specialized fine-tuning approach using custom question-answer datasets designed specifically to improve the spatial reasoning capabilities of the model. The enhanced VLM generates high-level navigational commands that VAD subsequently processes to guide vehicle operation. Additionally, our system produces interpretable natural language explanations of driving decisions, thereby increasing transparency and trustworthiness of the traditionally black-box end-to-end architecture. Comprehensive evaluation on the real-world nuScenes dataset demonstrates that our integrated system reduces average collision rates by 31.82% compared to baseline methodologies, establishing a new benchmark for VLM-augmented autonomous driving systems.

Recent Multimodal Large Language Models (MLLMs) achieve promising performance on visual and audio benchmarks independently. However, the ability of these models to process cross-modal information synchronously remains largely unexplored. In this paper, we introduce: 1) Daily-Omni, an Audio-Visual Questioning and Answering benchmark comprising 684 videos of daily life scenarios from diverse sources, rich in both audio and visual information, and featuring 1197 multiple-choice QA pairs across 6 major tasks; 2) Daily-Omni QA Generation Pipeline, which includes automatic annotation, QA generation and QA optimization, significantly improves efficiency for human evaluation and scalability of the benchmark; 3) Daily-Omni-Agent, a training-free agent utilizing open-source Visual Language Model (VLM), Audio Language Model (ALM) and Automatic Speech Recognition (ASR) model to establish a baseline for this benchmark. The results show that current MLLMs still struggle significantly with tasks requiring audio-visual integration, but combining VLMs and ALMs with simple temporal alignment techniques can achieve substantially better performance. Codes and benchmark are available at \href{https://github.com/Lliar-liar/Daily-Omni}{https://github.com/Lliar-liar/Daily-Omni}.

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. W e highlight the redundancy and inefficiency in current vision encoders, and seek to construct an adaptive compression method for mul-timodal data. In this work, we characterize a panoply of visual token selection and merging approaches through both benchmarking and qualitative analysis. In particular, we demonstrate that simple cluster-level token aggregation outperforms prior state-of-the-art works in token selection and merging, including merging at the vision encoder level and attention-based approaches. W e underline the redundancy in current vision encoders, and shed light on several puzzling trends regarding principles of visual token selection through cross-modal attention visualizations. This work is a first effort towards more effective encoding and processing of high-dimensional data, and paves the way for more scalable and sustainable multimodal systems.

Visual Language Models (VLMs) have become foundational models for document understanding tasks, widely used in the processing of complex multimodal documents across domains such as finance, law, and academia. However, documents often contain noise-like information, such as watermarks, which inevitably leads us to inquire: \emph{Do watermarks degrade the performance of VLMs in document understanding?} To address this, we propose a novel evaluation framework to investigate the effect of visible watermarks on VLMs performance. We takes into account various factors, including different types of document data, the positions of watermarks within documents and variations in watermark content. Our experimental results reveal that VLMs performance can be significantly compromised by watermarks, with performance drop rates reaching up to 36\%. We discover that \emph{scattered} watermarks cause stronger interference than centralized ones, and that \emph{semantic contents} in watermarks creates greater disruption than simple visual occlusion. Through attention mechanism analysis and embedding similarity examination, we find that the performance drops are mainly attributed to that watermarks 1) force widespread attention redistribution, and 2) alter semantic representation in the embedding space. Our research not only highlights significant challenges in deploying VLMs for document understanding, but also provides insights towards developing robust inference mechanisms on watermarked documents.

The rapid growth of video content demands efficient and precise retrieval systems. While vision-language models (VLMs) excel in representation learning, they often struggle with adaptive, time-sensitive video retrieval. This paper introduces a novel framework that combines vector similarity search with graph-based data structures. By leveraging VLM embeddings for initial retrieval and modeling contextual relationships among video segments, our approach enables adaptive query refinement and improves retrieval accuracy. Experiments demonstrate its precision, scalability, and robustness, offering an effective solution for interactive video retrieval in dynamic environments.

How can we build generalist robot systems? Scale may not be enough due to the significant multimodality of robotics tasks, lack of easily accessible data and the challenges of deploying on physical hardware. Meanwhile, most deployed robotic systems today are inherently modular and can leverage the independent generalization capabilities of each module to perform well. Therefore, this thesis seeks to tackle the task of building generalist robot agents by integrating these components into one: combining modularity with large-scale learning for general purpose robot control. The first question we consider is: how can we build modularity and hierarchy into learning systems? Our key insight is that rather than having the agent learn hierarchy and low-level control end-to-end, we can enforce modularity via planning to enable more efficient and capable robot learners. Next, we come to the role of scale in building generalist robot systems. To scale, neural networks require vast amounts of diverse data, expressive architectures to fit the data and a source of supervision to generate the data. We leverage a powerful supervision source: classical planning, which can generalize, but is expensive to run and requires access to privileged information to perform well in practice. We use these planners to supervise large-scale policy learning in simulation to produce generalist agents. Finally, we consider how to unify modularity with large-scale policy learning to build real-world robot systems capable of performing zero-shot manipulation. We do so by tightly integrating key ingredients of modular high and mid-level planning, learned local control, procedural scene generation and large-scale policy learning for sim2real transfer. We demonstrate that this recipe can produce a single, generalist agent that can solve challenging long-horizon manipulation tasks in the real world.