Recent advancements in speech-to-speech dialogue systems leverage LLMs for multimodal interactions, yet they remain hindered by fine-tuning requirements, high computational overhead, and text-speech misalignment. Existing speech-enabled LLMs often degrade conversational quality by modifying the LLM, thereby compromising its linguistic capabilities. In contrast, we propose LLMVoX, a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming TTS system that generates high-quality speech with low latency, while fully preserving the capabilities of the base LLM. Our approach achieves a significantly lower Word Error Rate compared to speech-enabled LLMs, while operating at comparable latency and UTMOS score. By decoupling speech synthesis from LLM processing via a multi-queue token streaming system, LLMVoX supports seamless, infinite-length dialogues. Its plug-and-play design also facilitates extension to various tasks with different backbones. Furthermore, LLMVoX generalizes to new languages with only dataset adaptation, attaining a low Character Error Rate on an Arabic speech task. Additionally, we have integrated LLMVoX with a Vision-Language Model to create an omni-model with speech, text, and vision capabilities, without requiring additional multimodal training. Our code base and project page is available at https://mbzuai-oryx.github.io/LLMVoX .

With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4, Gemini, and Qwen) outperform traditional OCR approaches (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.

Existing Large Multimodal Models (LMMs) generally focus on only a few regions and languages. As LMMs continue to improve, it is increasingly important to ensure they understand cultural contexts, respect local sensitivities, and support low-resource languages, all while effectively integrating corresponding visual cues. In pursuit of culturally diverse global multimodal models, our proposed All Languages Matter Benchmark (ALM-bench) represents the largest and most comprehensive effort to date for evaluating LMMs across 100 languages. ALM-bench challenges existing models by testing their ability to understand and reason about culturally diverse images paired with text in various languages, including many low-resource languages traditionally underrepresented in LMM research. The benchmark offers a robust and nuanced evaluation framework featuring various question formats, including true/false, multiple choice, and open-ended questions, which are further divided into short and long-answer categories. ALM-bench design ensures a comprehensive assessment of a model's ability to handle varied levels of difficulty in visual and linguistic reasoning. To capture the rich tapestry of global cultures, ALM-bench carefully curates content from 13 distinct cultural aspects, ranging from traditions and rituals to famous personalities and celebrations. Through this, ALM-bench not only provides a rigorous testing ground for state-of-the-art open and closed-source LMMs but also highlights the importance of cultural and linguistic inclusivity, encouraging the development of models that can serve diverse global populations effectively. Our benchmark is publicly available.

Effective communication between humans and collaborative robots is essential for seamless Human-Robot Collaboration (HRC). In noisy industrial settings, nonverbal communication, such as gestures, plays a key role in conveying commands and information to robots efficiently. While existing literature has thoroughly examined gesture recognition and robots' responses to these gestures, there is a notable gap in exploring the design of these gestures. The criteria for creating efficient HRC gestures are scattered across numerous studies. This paper surveys the design principles of HRC gestures, as contained in the literature, aiming to consolidate a set of criteria for HRC gesture design. It also examines the methods used for designing and evaluating HRC gestures to highlight research gaps and present directions for future research in this area.

Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMMs to videos either lack the grounding capabilities (e.g., VideoChat, Video-ChatGPT, Video-LLaMA) or do not utilize the audio-signals for better video understanding (e.g., Video-ChatGPT). Addressing these gaps, we propose PG-Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework uses an off-the-shelf tracker and a novel grounding module, enabling it to spatially localize objects in videos following user instructions. We evaluate PG-Video-LLaVA using video-based generative and question-answering benchmarks and introduce new benchmarks specifically designed to measure prompt-based object grounding performance in videos. Further, we propose the use of Vicuna over GPT-3.5, as utilized in Video-ChatGPT, for video-based conversation benchmarking, ensuring reproducibility of results which is a concern with the proprietary nature of GPT-3.5. Our framework builds on SoTA image-based LLaVA model and extends its advantages to the video domain, delivering promising gains on video-based conversation and grounding tasks. Project Page: https://github.com/mbzuai-oryx/Video-LLaVA

Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language features. Besides, several approaches have also been suggested to generate a pseudo-word token from the reference image, which is further integrated into the relative caption for CIR. However, these pseudo-word-based prompting methods have limitations when target image encompasses complex changes on reference image, e.g., object removal and attribute modification. In this work, we demonstrate that learning an appropriate sentence-level prompt for the relative caption (SPRC) is sufficient for achieving effective composed image retrieval. Instead of relying on pseudo-word-based prompts, we propose to leverage pretrained V-L models, e.g., BLIP-2, to generate sentence-level prompts. By concatenating the learned sentence-level prompt with the relative caption, one can readily use existing text-based image retrieval models to enhance CIR performance. Furthermore, we introduce both image-text contrastive loss and text prompt alignment loss to enforce the learning of suitable sentence-level prompts. Experiments show that our proposed method performs favorably against the state-of-the-art CIR methods on the Fashion-IQ and CIRR datasets. The source code and pretrained model are publicly available at https://github.com/chunmeifeng/SPRC

In class incremental learning (CIL) setting, groups of classes are introduced to a model in each learning phase. The goal is to learn a unified model performant on all the classes observed so far. Given the recent popularity of Vision Transformers (ViTs) in conventional classification settings, an interesting question is to study their continual learning behaviour. In this work, we develop a Debiased Dual Distilled Transformer for CIL dubbed $\textrm{D}^3\textrm{Former}$. The proposed model leverages a hybrid nested ViT design to ensure data efficiency and scalability to small as well as large datasets. In contrast to a recent ViT based CIL approach, our $\textrm{D}^3\textrm{Former}$ does not dynamically expand its architecture when new tasks are learned and remains suitable for a large number of incremental tasks. The improved CIL behaviour of $\textrm{D}^3\textrm{Former}$ owes to two fundamental changes to the ViT design. First, we treat the incremental learning as a long-tail classification problem where the majority samples from new classes vastly outnumber the limited exemplars available for old classes. To avoid the bias against the minority old classes, we propose to dynamically adjust logits to emphasize on retaining the representations relevant to old tasks. Second, we propose to preserve the configuration of spatial attention maps as the learning progresses across tasks. This helps in reducing catastrophic forgetting by constraining the model to retain the attention on the most discriminative regions. $\textrm{D}^3\textrm{Former}$ obtains favorable results on incremental versions of CIFAR-100, MNIST, SVHN, and ImageNet datasets. Code is available at https://tinyurl.com/d3former

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate e.g., the ImageNet trained model, and transferred to change the decision of an unknown (black-box) model trained on an image dataset. However, attacks generated from image models do not capture the dynamic nature of a moving object or a changing scene due to a lack of temporal cues within image models. This leads to reduced transferability of adversarial attacks from representation-enriched image models such as Supervised Vision Transformers (ViTs), Self-supervised ViTs (e.g., DINO), and Vision-language models (e.g., CLIP) to black-box video models. In this work, we induce dynamic cues within the image models without sacrificing their original performance on images. To this end, we optimize temporal prompts through frozen image models to capture motion dynamics. Our temporal prompts are the result of a learnable transformation that allows optimizing for temporal gradients during an adversarial attack to fool the motion dynamics. Specifically, we introduce spatial (image) and temporal (video) cues within the same source model through taskspecific prompts. Attacking such prompts maximizes the adversarial transferability from image-to-video and image-to-image models using the attacks designed for image models. As an example, an iterative attack launched from image model Deit-B with temporal prompts reduces generalization (top1 % accuracy) of a video model by 35% on Kinetics-400. Our approach also improves adversarial transferability to image models by 9% on ImageNet w.r.t the current state-of-the-art approach. Our attack results indicate that the attacker does not need specialized architectures, e.g., divided space-time attention, 3D convolutions, or multi-view convolution networks for different data modalities. Image models are effective surrogates to optimize an adversarial attack to fool black-box models in a changing environment over time.

In recent years, significant progress has been achieved for 3D object detection on point clouds thanks to the advances in 3D data collection and deep learning techniques. Nevertheless, 3D scenes exhibit a lot of variations and are prone to sensor inaccuracies as well as information loss during pre-processing. Thus, it is crucial to design techniques that are robust against these variations. This requires a detailed analysis and understanding of the effect of such variations. This work aims to analyze and benchmark popular point-based 3D object detectors against several data corruptions. To the best of our knowledge, we are the first to investigate the robustness of point-based 3D object detectors. To this end, we design and evaluate corruptions that involve data addition, reduction, and alteration. We further study the robustness of different modules against local and global variations. Our experimental results reveal several intriguing findings. For instance, we show that methods that integrate Transformers at a patch or object level lead to increased robustness, compared to using Transformers at the point level.