Hisham Cholakkal

Abdulaziz Amer Aleissaee, Amandeep Kumar, Rao Muhammad Anwer et al.

Deep learning-based algorithms have seen a massive popularity in different areas of remote sensing image analysis over the past decade. Recently, transformers-based architectures, originally introduced in natural language processing, have pervaded computer vision field where the self-attention mechanism has been utilized as a replacement to the popular convolution operator for capturing long-range dependencies. Inspired by recent advances in computer vision, remote sensing community has also witnessed an increased exploration of vision transformers for a diverse set of tasks. Although a number of surveys have focused on transformers in computer vision in general, to the best of our knowledge we are the first to present a systematic review of recent advances based on transformers in remote sensing. Our survey covers more than 60 recent transformers-based methods for different remote sensing problems in sub-areas of remote sensing: very high-resolution (VHR), hyperspectral (HSI) and synthetic aperture radar (SAR) imagery. We conclude the survey by discussing different challenges and open issues of transformers in remote sensing. Additionally, we intend to frequently update and maintain the latest transformers in remote sensing papers with their respective code at: https://github.com/VIROBO-15/Transformer-in-Remote-Sensing

Muhammad Awais, Muzammal Naseer, Salman Khan et al.

Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world environment can be better described in human language, naturally governed by grammatical rules and other modalities such as audio and depth. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. These models are referred to as foundational models. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions. In this survey, we provide a comprehensive review of such emerging foundational models, including typical architecture designs to combine different modalities (vision, text, audio, etc), training objectives (contrastive, generative), pre-training datasets, fine-tuning mechanisms, and the common prompting patterns; textual, visual, and heterogeneous. We discuss the open challenges and research directions for foundational models in computer vision, including difficulties in their evaluations and benchmarking, gaps in their real-world understanding, limitations of their contextual understanding, biases, vulnerability to adversarial attacks, and interpretability issues. We review recent developments in this field, covering a wide range of applications of foundation models systematically and comprehensively. A comprehensive list of foundational models studied in this work is available at \url{https://github.com/awaisrauf/Awesome-CV-Foundational-Models}.

Jiale Cao, Yanwei Pang, Rao Muhammad Anwer et al.

We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at \url{https://github.com/JialeCao001/PSTR}.

Jean Lahoud, Jiale Cao, Fahad Shahbaz Khan et al.

The success of the transformer architecture in natural language processing has recently triggered attention in the computer vision field. The transformer has been used as a replacement for the widely used convolution operators, due to its ability to learn long-range dependencies. This replacement was proven to be successful in numerous tasks, in which several state-of-the-art methods rely on transformers for better learning. In computer vision, the 3D field has also witnessed an increase in employing the transformer for 3D convolution neural networks and multi-layer perceptron networks. Although a number of surveys have focused on transformers in vision in general, 3D vision requires special attention due to the difference in data representation and processing when compared to 2D vision. In this work, we present a systematic and thorough review of more than 100 transformers methods for different 3D vision tasks, including classification, segmentation, detection, completion, pose estimation, and others. We discuss transformer design in 3D vision, which allows it to process data with various 3D representations. For each application, we highlight key properties and contributions of proposed transformer-based methods. To assess the competitiveness of these methods, we compare their performance to common non-transformer methods on 12 3D benchmarks. We conclude the survey by discussing different open directions and challenges for transformers in 3D vision. In addition to the presented papers, we aim to frequently update the latest relevant papers along with their corresponding implementations at: https://github.com/lahoud/3d-vision-transformers.

Mubashir Noman, Wafa Al Ghallabi, Daniya Najiha et al.

One of the key factors behind the recent success in visual tracking is the availability of dedicated benchmarks. While being greatly benefiting to the tracking research, existing benchmarks do not pose the same difficulty as before with recent trackers achieving higher performance mainly due to (i) the introduction of more sophisticated transformers-based methods and (ii) the lack of diverse scenarios with adverse visibility such as, severe weather conditions, camouflage and imaging effects. We introduce AVisT, a dedicated benchmark for visual tracking in diverse scenarios with adverse visibility. AVisT comprises 120 challenging sequences with 80k annotated frames, spanning 18 diverse scenarios broadly grouped into five attributes with 42 object categories. The key contribution of AVisT is diverse and challenging scenarios covering severe weather conditions such as, dense fog, heavy rain and sandstorm; obstruction effects including, fire, sun glare and splashing water; adverse imaging effects such as, low-light; target effects including, small targets and distractor objects along with camouflage. We further benchmark 17 popular and recent trackers on AVisT with detailed analysis of their tracking performance across attributes, demonstrating a big room for improvement in performance. We believe that AVisT can greatly benefit the tracking community by complementing the existing benchmarks, in developing new creative tracking solutions in order to continue pushing the boundaries of the state-of-the-art. Our dataset along with the complete tracking performance evaluation is available at: https://github.com/visionml/pytracking

Long Li, Junwei Han, Ni Zhang et al.

Most previous co-salient object detection works mainly focus on extracting co-salient cues via mining the consistency relations across images while ignoring explicit exploration of background regions. In this paper, we propose a Discriminative co-saliency and background Mining Transformer framework (DMT) based on several economical multi-grained correlation modules to explicitly mine both co-saliency and background information and effectively model their discrimination. Specifically, we first propose a region-to-region correlation module for introducing inter-image relations to pixel-wise segmentation features while maintaining computational efficiency. Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules. We also design a token-guided feature refinement module to enhance the discriminability of the segmentation features under the guidance of the learned tokens. We perform iterative mutual promotion for the segmentation feature extraction and token construction. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method. The source code is available at: https://github.com/dragonlee258079/DMT.

Omkar Thawakar, Sanath Narayan, Jiale Cao et al.

State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computations. We argue that such an attention computation ignores the multi-scale spatio-temporal feature relationships that are crucial to tackle target appearance deformations in videos. To address this issue, we propose a transformer-based VIS framework, named MS-STS VIS, that comprises a novel multi-scale spatio-temporal split (MS-STS) attention module in the encoder. The proposed MS-STS module effectively captures spatio-temporal feature relationships at multiple scales across frames in a video. We further introduce an attention block in the decoder to enhance the temporal consistency of the detected instances in different frames of a video. Moreover, an auxiliary discriminator is introduced during training to ensure better foreground-background separability within the multi-scale spatio-temporal feature space. We conduct extensive experiments on two benchmarks: Youtube-VIS (2019 and 2021). Our MS-STS VIS achieves state-of-the-art performance on both benchmarks. When using the ResNet50 backbone, our MS-STS achieves a mask AP of 50.1 %, outperforming the best reported results in literature by 2.7 % and by 4.8 % at higher overlap threshold of AP_75, while being comparable in model size and speed on Youtube-VIS 2019 val. set. When using the Swin Transformer backbone, MS-STS VIS achieves mask AP of 61.0 % on Youtube-VIS 2019 val. set. Our code and models are available at https://github.com/OmkarThawakar/MSSTS-VIS.

Omkar Thawakar, Abdelrahman Shaker, Sahal Shaji Mullappilly et al.

The latest breakthroughs in large vision-language models, such as Bard and GPT-4, have showcased extraordinary abilities in performing a wide range of tasks. Such models are trained on massive datasets comprising billions of public image-text pairs with diverse tasks. However, their performance on task-specific domains, such as radiology, is still under-investigated and potentially limited due to a lack of sophistication in understanding biomedical images. On the other hand, conversational medical models have exhibited remarkable success but have mainly focused on text-based analysis. In this paper, we introduce XrayGPT, a novel conversational medical vision-language model that can analyze and answer open-ended questions about chest radiographs. Specifically, we align both medical visual encoder (MedClip) with a fine-tuned large language model (Vicuna), using a simple linear transformation. This alignment enables our model to possess exceptional visual conversation abilities, grounded in a deep understanding of radiographs and medical domain knowledge. To enhance the performance of LLMs in the medical context, we generate ~217k interactive and high-quality summaries from free-text radiology reports. These summaries serve to enhance the performance of LLMs through the fine-tuning process. Our approach opens up new avenues the research for advancing the automated analysis of chest radiographs. Our open-source demos, models, and instruction sets are available at: https://github.com/mbzuai-oryx/XrayGPT.

Omkar Thawakar, Sanath Narayan, Hisham Cholakkal et al.

Existing video instance segmentation (VIS) approaches generally follow a closed-world assumption, where only seen category instances are identified and spatio-temporally segmented at inference. Open-world formulation relaxes the close-world static-learning assumption as follows: (a) first, it distinguishes a set of known categories as well as labels an unknown object as `unknown' and then (b) it incrementally learns the class of an unknown as and when the corresponding semantic labels become available. We propose the first open-world VIS approach, named OW-VISFormer, that introduces a novel feature enrichment mechanism and a spatio-temporal objectness (STO) module. The feature enrichment mechanism based on a light-weight auxiliary network aims at accurate pixel-level (unknown) object delineation from the background as well as distinguishing category-specific known semantic classes. The STO module strives to generate instance-level pseudo-labels by enhancing the foreground activations through a contrastive loss. Moreover, we also introduce an extensive experimental protocol to measure the characteristics of OW-VIS. Our OW-VISFormer performs favorably against a solid baseline in OW-VIS setting. Further, we evaluate our contributions in the standard fully-supervised VIS setting by integrating them into the recent SeqFormer, achieving an absolute gain of 1.6\% AP on Youtube-VIS 2019 val. set. Lastly, we show the generalizability of our contributions for the open-world detection (OWOD) setting, outperforming the best existing OWOD method in the literature. Code, models along with OW-VIS splits are available at \url{https://github.com/OmkarThawakar/OWVISFormer}.

Mubashir Noman, Mustansar Fiaz, Hisham Cholakkal et al.

Current transformer-based change detection (CD) approaches either employ a pre-trained model trained on large-scale image classification ImageNet dataset or rely on first pre-training on another CD dataset and then fine-tuning on the target benchmark. This current strategy is driven by the fact that transformers typically require a large amount of training data to learn inductive biases, which is insufficient in standard CD datasets due to their small size. We develop an end-to-end CD approach with transformers that is trained from scratch and yet achieves state-of-the-art performance on four public benchmarks. Instead of using conventional self-attention that struggles to capture inductive biases when trained from scratch, our architecture utilizes a shuffled sparse-attention operation that focuses on selected sparse informative regions to capture the inherent characteristics of the CD data. Moreover, we introduce a change-enhanced feature fusion (CEFF) module to fuse the features from input image pairs by performing a per-channel re-weighting. Our CEFF module aids in enhancing the relevant semantic changes while suppressing the noisy ones. Extensive experiments on four CD datasets reveal the merits of the proposed contributions, achieving gains as high as 14.27\% in intersection-over-union (IoU) score, compared to the best-published results in the literature. Code is available at \url{https://github.com/mustansarfiaz/ScratchFormer}.

Amandeep Kumar, Ankan Kumar Bhunia, Sanath Narayan et al.

We present a method to efficiently generate 3D-aware high-resolution images that are view-consistent across multiple target views. The proposed multiplane neural radiance model, named GMNR, consists of a novel α-guided view-dependent representation (α-VdR) module for learning view-dependent information. The α-VdR module, faciliated by an α-guided pixel sampling technique, computes the view-dependent representation efficiently by learning viewing direction and position coefficients. Moreover, we propose a view-consistency loss to enforce photometric similarity across multiple views. The GMNR model can generate 3D-aware high-resolution images that are viewconsistent across multiple camera poses, while maintaining the computational efficiency in terms of both training and inference time. Experiments on three datasets demonstrate the effectiveness of the proposed modules, leading to favorable results in terms of both generation quality and inference time, compared to existing approaches. Our GMNR model generates 3D-aware images of 1024 X 1024 pixels with 17.6 FPS on a single V100. Code : https://github.com/VIROBO-15/GMNR

Nian Liu, Kepan Nan, Wangbo Zhao et al.

Few-Shot Video Object Segmentation (FSVOS) aims to segment objects in a query video with the same category defined by a few annotated support images. However, this task was seldom explored. In this work, based on IPMT, a state-of-the-art few-shot image segmentation method that combines external support guidance information with adaptive query guidance cues, we propose to leverage multi-grained temporal guidance information for handling the temporal correlation nature of video data. We decompose the query video information into a clip prototype and a memory prototype for capturing local and long-term internal temporal guidance, respectively. Frame prototypes are further used for each frame independently to handle fine-grained adaptive guidance and enable bidirectional clip-frame prototype communication. To reduce the influence of noisy memory, we propose to leverage the structural similarity relation among different predicted regions and the support for selecting reliable memory frames. Furthermore, a new segmentation loss is also proposed to enhance the category discriminability of the learned prototypes. Experimental results demonstrate that our proposed video IPMT model significantly outperforms previous models on two benchmark datasets. Code is available at https://github.com/nankepan/VIPMT.

Muhammad Maaz, Abdelrahman Shaker, Hisham Cholakkal et al.

In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. It is of great interest to build resource-efficient general purpose networks due to their usefulness in several application areas. In this work, we strive to effectively combine the strengths of both CNN and Transformer models and propose a new efficient hybrid architecture EdgeNeXt. Specifically in EdgeNeXt, we introduce split depth-wise transpose attention (STDA) encoder that splits input tensors into multiple channel groups and utilizes depth-wise convolution along with self-attention across channel dimensions to implicitly increase the receptive field and encode multi-scale features. Our extensive experiments on classification, detection and segmentation tasks, reveal the merits of the proposed approach, outperforming state-of-the-art methods with comparatively lower compute requirements. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K, outperforming MobileViT with an absolute gain of 2.2% with 28% reduction in FLOPs. Further, our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K. The code and models are available at https://t.ly/_Vu9.

Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal et al.

The pose-guided person image generation task requires synthesizing photorealistic images of humans in arbitrary poses. The existing approaches use generative adversarial networks that do not necessarily maintain realistic textures or need dense correspondences that struggle to handle complex deformations and severe occlusions. In this work, we show how denoising diffusion models can be applied for high-fidelity person image synthesis with strong sample diversity and enhanced mode coverage of the learnt data distribution. Our proposed Person Image Diffusion Model (PIDM) disintegrates the complex transfer problem into a series of simpler forward-backward denoising steps. This helps in learning plausible source-to-target transformation trajectories that result in faithful textures and undistorted appearance details. We introduce a 'texture diffusion module' based on cross-attention to accurately model the correspondences between appearance and pose information available in source and target images. Further, we propose 'disentangled classifier-free guidance' to ensure close resemblance between the conditional inputs and the synthesized output in terms of both pose and appearance information. Our extensive results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios. We also show how our generated images can help in downstream tasks. Our code and models will be publicly released.

Yahia Dalbah, Jean Lahoud, Hisham Cholakkal

Scene understanding plays an essential role in enabling autonomous driving and maintaining high standards of performance and safety. To address this task, cameras and laser scanners (LiDARs) have been the most commonly used sensors, with radars being less popular. Despite that, radars remain low-cost, information-dense, and fast-sensing techniques that are resistant to adverse weather conditions. While multiple works have been previously presented for radar-based scene semantic segmentation, the nature of the radar data still poses a challenge due to the inherent noise and sparsity, as well as the disproportionate foreground and background. In this work, we propose a novel approach to the semantic segmentation of radar scenes using a multi-input fusion of radar data through a novel architecture and loss functions that are tailored to tackle the drawbacks of radar perception. Our novel architecture includes an efficient attention block that adaptively captures important feature information. Our method, TransRadar, outperforms state-of-the-art methods on the CARRADA and RADIal datasets while having smaller model sizes. https://github.com/YahiDar/TransRadar

Mustansar Fiaz, Moein Heidari, Rao Muhammad Anwer et al.

Microscopic image segmentation is a challenging task, wherein the objective is to assign semantic labels to each pixel in a given microscopic image. While convolutional neural networks (CNNs) form the foundation of many existing frameworks, they often struggle to explicitly capture long-range dependencies. Although transformers were initially devised to address this issue using self-attention, it has been proven that both local and global features are crucial for addressing diverse challenges in microscopic images, including variations in shape, size, appearance, and target region density. In this paper, we introduce SA2-Net, an attention-guided method that leverages multi-scale feature learning to effectively handle diverse structures within microscopic images. Specifically, we propose scale-aware attention (SA2) module designed to capture inherent variations in scales and shapes of microscopic regions, such as cells, for accurate segmentation. This module incorporates local attention at each level of multi-stage features, as well as global attention across multiple resolutions. Furthermore, we address the issue of blurred region boundaries (e.g., cell boundaries) by introducing a novel upsampling strategy called the Adaptive Up-Attention (AuA) module. This module enhances the discriminative ability for improved localization of microscopic regions using an explicit attention mechanism. Extensive experiments on five challenging datasets demonstrate the benefits of our SA2-Net model. Our source code is publicly available at \url{https://github.com/mustansarfiaz/SA2-Net}.

Yahia Dalbah, Jean Lahoud, Hisham Cholakkal

The performance of perception systems developed for autonomous driving vehicles has seen significant improvements over the last few years. This improvement was associated with the increasing use of LiDAR sensors and point cloud data to facilitate the task of object detection and recognition in autonomous driving. However, LiDAR and camera systems show deteriorating performances when used in unfavorable conditions like dusty and rainy weather. Radars on the other hand operate on relatively longer wavelengths which allows for much more robust measurements in these conditions. Despite that, radar-centric data sets do not get a lot of attention in the development of deep learning techniques for radar perception. In this work, we consider the radar object detection problem, in which the radar frequency data is the only input into the detection framework. We further investigate the challenges of using radar-only data in deep learning models. We propose a transformers-based model, named RadarFormer, that utilizes state-of-the-art developments in vision deep learning. Our model also introduces a channel-chirp-time merging module that reduces the size and complexity of our models by more than 10 times without compromising accuracy. Comprehensive experiments on the CRUW radar dataset demonstrate the advantages of the proposed method. Our RadarFormer performs favorably against the state-of-the-art methods while being 2x faster during inference and requiring only one-tenth of their model parameters. The code associated with this paper is available at https://github.com/YahiDar/RadarFormer.

Sara Pieri, Jose Renato Restom, Samuel Horvath et al.

Federated Learning (FL) is a promising research paradigm that enables the collaborative training of machine learning models among various parties without the need for sensitive information exchange. Nonetheless, retaining data in individual clients introduces fundamental challenges to achieving performance on par with centrally trained models. Our study provides an extensive review of federated learning applied to visual recognition. It underscores the critical role of thoughtful architectural design choices in achieving optimal performance, a factor often neglected in the FL literature. Many existing FL solutions are tested on shallow or simple networks, which may not accurately reflect real-world applications. This practice restricts the transferability of research findings to large-scale visual recognition models. Through an in-depth analysis of diverse cutting-edge architectures such as convolutional neural networks, transformers, and MLP-mixers, we experimentally demonstrate that architectural choices can substantially enhance FL systems' performance, particularly when handling heterogeneous data. We study 19 visual recognition models from five different architectural families on four challenging FL datasets. We also re-investigate the inferior performance of convolution-based architectures in the FL setting and analyze the influence of normalization layers on the FL performance. Our findings emphasize the importance of architectural design for computer vision tasks in practical scenarios, effectively narrowing the performance gap between federated and centralized learning. Our source code is available at https://github.com/sarapieri/fed_het.git.

Amandeep Kumar, Ankan kumar Bhunia, Sanath Narayan et al.

In this work, we propose a few-shot colorectal tissue image generation method for addressing the scarcity of histopathological training data for rare cancer tissues. Our few-shot generation method, named XM-GAN, takes one base and a pair of reference tissue images as input and generates high-quality yet diverse images. Within our XM-GAN, a novel controllable fusion block densely aggregates local regions of reference images based on their similarity to those in the base image, resulting in locally consistent features. To the best of our knowledge, we are the first to investigate few-shot generation in colorectal tissue images. We evaluate our few-shot colorectral tissue image generation by performing extensive qualitative, quantitative and subject specialist (pathologist) based evaluations. Specifically, in specialist-based evaluation, pathologists could differentiate between our XM-GAN generated tissue images and real images only 55% time. Moreover, we utilize these generated images as data augmentation to address the few-shot tissue image classification task, achieving a gain of 4.4% in terms of mean accuracy over the vanilla few-shot classifier. Code: \url{https://github.com/VIROBO-15/XM-GAN}

Hanoona Rasheed, Muhammad Maaz, Sahal Shaji Mullappilly et al.

Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded responses. However, they are limited to only referring to a single object category at a time, require users to specify the regions, or cannot offer dense pixel-wise object grounding. In this work, we present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentation masks. GLaMM not only grounds objects appearing in the conversations but is flexible enough to accept both textual and optional visual prompts (region of interest) as input. This empowers users to interact with the model at various levels of granularity, both in textual and visual domains. Due to the lack of standard benchmarks for the novel setting of visually Grounded Conversation Generation (GCG), we introduce a comprehensive evaluation protocol with our curated grounded conversations. Our proposed GCG task requires densely grounded concepts in natural scenes at a large-scale. To this end, we propose a densely annotated Grounding-anything Dataset (GranD) using our proposed automated annotation pipeline that encompasses 7.5M unique concepts grounded in a total of 810M regions available with segmentation masks. Besides GCG, GLaMM also performs effectively on several downstream tasks, e.g., referring expression segmentation, image and region-level captioning and vision-language conversations.

Sahal Shaji Mullappilly, Mohammed Irfan Kurpath, Omair Mohamed et al.

We introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically grounded, free-form answers beyond multiple-choice formats. MediX-R1 fine-tunes a baseline vision-language backbone with Group Based RL and a composite reward tailored for medical reasoning: an LLM-based accuracy reward that judges semantic correctness with a strict YES/NO decision, a medical embedding-based semantic reward to capture paraphrases and terminology variants, and lightweight format and modality rewards that enforce interpretable reasoning and modality recognition. This multi-signal design provides stable, informative feedback for open-ended outputs where traditional verifiable or MCQ-only rewards fall short. To measure progress, we propose a unified evaluation framework for both text-only and image+text tasks that uses a Reference-based LLM-as-judge in place of brittle string-overlap metrics, capturing semantic correctness, reasoning, and contextual alignment. Despite using only $\sim51$K instruction examples, MediX-R1 achieves excellent results across standard medical LLM (text-only) and VLM (image + text) benchmarks, outperforming strong open-source baselines and delivering particularly large gains on open-ended clinical tasks. Our results demonstrate that open-ended RL with comprehensive reward signals and LLM-based evaluation is a practical path toward reliable medical reasoning in multimodal models. Our trained models, curated datasets and source code are available at https://medix.cvmbzuai.com

Xiaoheng Jiang, Xinyi Wu, Hisham Cholakkal et al. · ibm-research

Convolutional Neural Network (CNN) based crowd counting methods have achieved promising results in the past few years. However, the scale variation problem is still a huge challenge for accurate count estimation. In this paper, we propose a multi-scale feature aggregation network (MSFANet) that can alleviate this problem to some extent. Specifically, our approach consists of two feature aggregation modules: the short aggregation (ShortAgg) and the skip aggregation (SkipAgg). The ShortAgg module aggregates the features of the adjacent convolution blocks. Its purpose is to make features with different receptive fields fused gradually from the bottom to the top of the network. The SkipAgg module directly propagates features with small receptive fields to features with much larger receptive fields. Its purpose is to promote the fusion of features with small and large receptive fields. Especially, the SkipAgg module introduces the local self-attention features from the Swin Transformer blocks to incorporate rich spatial information. Furthermore, we present a local-and-global based counting loss by considering the non-uniform crowd distribution. Extensive experiments on four challenging datasets (ShanghaiTech dataset, UCF_CC_50 dataset, UCF-QNRF Dataset, WorldExpo'10 dataset) demonstrate the proposed easy-to-implement MSFANet can achieve promising results when compared with the previous state-of-the-art approaches.

Mohammed Khaleed Almansoori, Mustansar Fiaz, Hisham Cholakkal

Person search (PS) is a challenging computer vision problem where the objective is to achieve joint optimization for pedestrian detection and re-identification (ReID). Although previous advancements have shown promising performance in the field under fully and weakly supervised learning fashion, there exists a major gap in investigating the domain adaptation ability of PS models. In this paper, we propose a diligent domain adaptive mixer (DDAM) for person search (DDAP-PS) framework that aims to bridge a gap to improve knowledge transfer from the labeled source domain to the unlabeled target domain. Specifically, we introduce a novel DDAM module that generates moderate mixed-domain representations by combining source and target domain representations. The proposed DDAM module encourages domain mixing to minimize the distance between the two extreme domains, thereby enhancing the ReID task. To achieve this, we introduce two bridge losses and a disparity loss. The objective of the two bridge losses is to guide the moderate mixed-domain representations to maintain an appropriate distance from both the source and target domain representations. The disparity loss aims to prevent the moderate mixed-domain representations from being biased towards either the source or target domains, thereby avoiding overfitting. Furthermore, we address the conflict between the two subtasks, localization and ReID, during domain adaptation. To handle this cross-task conflict, we forcefully decouple the norm-aware embedding, which aids in better learning of the moderate mixed-domain representation. We conduct experiments to validate the effectiveness of our proposed method. Our approach demonstrates favorable performance on the challenging PRW and CUHK-SYSU datasets. Our source code is publicly available at \url{https://github.com/mustansarfiaz/DDAM-PS}.

Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Jinxing Zhou et al.

Long-form multimodal video understanding requires integrating vision, speech, and ambient audio with coherent long-range reasoning. Existing benchmarks emphasize either temporal length or multimodal richness, but rarely both and while some incorporate open-ended questions and advanced metrics, they mostly rely on single-score accuracy, obscuring failure modes. We introduce LongShOTBench, a diagnostic benchmark with open-ended, intent-driven questions; single- and multi-turn dialogues; and tasks requiring multimodal reasoning and agentic tool use across video, audio, and speech. Each item includes a reference answer and graded rubric for interpretable, and traceable evaluation. LongShOTBench is produced via a scalable, human-validated pipeline to ensure coverage and reproducibility. All samples in our LongShOTBench are human-verified and corrected. Furthermore, we present LongShOTAgent, an agentic system that analyzes long videos via preprocessing, search, and iterative refinement. On LongShOTBench, state-of-the-art MLLMs show large gaps: Gemini-2.5-Flash achieves 52.95%, open-source models remain below 30%, and LongShOTAgent attains 44.66%. These results underscore the difficulty of real-world long-form video understanding. LongShOTBench provides a practical, reproducible foundation for evaluating and improving MLLMs. All resources are available on GitHub: https://github.com/mbzuai-oryx/longshot.

Fatima Albreiki, Sultan Abughazal, Jean Lahoud et al.

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.

Mustansar Fiaz, Hisham Cholakkal, Sanath Narayan et al.

Person search is a challenging problem with various real-world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery images. Although, the previous study focuses on rich feature information learning, it is still hard to retrieve the query person due to the occurrence of appearance deformations and background distractors. In this paper, we propose a novel attention-aware relation mixer (ARM) module for person search, which exploits the global relation between different local regions within RoI of a person and make it robust against various appearance deformations and occlusion. The proposed ARM is composed of a relation mixer block and a spatio-channel attention layer. The relation mixer block introduces a spatially attended spatial mixing and a channel-wise attended channel mixing for effectively capturing discriminative relation features within an RoI. These discriminative relation features are further enriched by introducing a spatio-channel attention where the foreground and background discriminability is empowered in a joint spatio-channel space. Our ARM module is generic and it does not rely on fine-grained supervision or topological assumptions, hence being easily integrated into any Faster R-CNN based person search methods. Comprehensive experiments are performed on two challenging benchmark datasets: CUHKSYSU and PRW. Our PS-ARM achieves state-of-the-art performance on both datasets. On the challenging PRW dataset, our PS-ARM achieves an absolute gain of 5 in the mAP score over SeqNet, while operating at a comparable speed.

Dhanalaxmi Gaddam, Jean Lahoud, Fahad Shahbaz Khan et al.

Existing deep learning-based 3D object detectors typically rely on the appearance of individual objects and do not explicitly pay attention to the rich contextual information of the scene. In this work, we propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework, which takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene at multiple levels to predict a set of object bounding-boxes along with their corresponding semantic labels. To this end, we propose to utilize a context enhancement network that captures the contextual information at different levels of granularity followed by a multi-stage refinement module to progressively refine the box positions and class predictions. Extensive experiments on the large-scale ScanNetV2 benchmark reveal the benefits of our proposed method, leading to an absolute improvement of 2.0% over the baseline. In addition to 3D object detection, we investigate the effectiveness of our CMR3D framework for the problem of 3D object counting. Our source code will be publicly released.

Komal Kumar, Ankan Deria, Abhishek Basu et al.

Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, either unsafe-text paired with safe-image groundtruth or negative/positive image pairs, making them impractical to scale. Furthermore, offline reinforcement learning and supervised fine-tuning approaches that generate synthetic data offline suffer from catastrophic forgetting, degrading generation quality. We propose a novel online reinforcement learning framework that addresses both data scarcity and model degradation through post-training with Group Relative Policy Optimization (GRPO) on both negative and positive text prompts. To eliminate the need for fine-tuning specialized safe/unsafe reward models, we introduce a \textit{steering reward mechanism} that exploits an inherent property of CLIP embeddings: steering text representations toward positive safety directions and away from negative ones in the embedding space. Our online-policy approach enables the model to learn from diverse prompts, including explicit unsafe content, without catastrophic forgetting. Extensive experiments demonstrate that our method reduces inappropriate content to 18.07\% (vs. 48.9\% for SD v1.4) and nudity detections to 15 (vs. 646 baseline) while improving compositional generation quality from 42.08\% to 47.83\% on GenEval. Remarkably, these safety gains generalize to out-of-domain unsafe prompts across seven harm categories, achieving state-of-the-art performance without supervised paired data or reward tuning. Github: https://github.com/MAXNORM8650/SafeDiffusion-R1.

Mubashir Noman, Noor Ahsan, Muzammal Naseer et al.

Large multimodal models (LMMs) have shown encouraging performance in the natural image domain using visual instruction tuning. However, these LMMs struggle to describe the content of remote sensing images for tasks such as image or region grounding, classification, etc. Recently, GeoChat make an effort to describe the contents of the RS images. Although, GeoChat achieves promising performance for various RS tasks, it struggles to describe the changes between bi-temporal RS images which is a key RS task. This necessitates the development of an LMM that can describe the changes between the bi-temporal RS images. However, there is insufficiency of datasets that can be utilized to tune LMMs. In order to achieve this, we introduce a change description instruction dataset that can be utilized to finetune an LMM and provide better change descriptions for RS images. Furthermore, we show that the LLaVA-1.5 model, with slight modifications, can be finetuned on the change description instruction dataset and achieve favorably better performance.

Mohamed El Amine Boudjoghra, Salwa K. Al Khatib, Jean Lahoud et al.

Existing 3D instance segmentation methods typically assume that all semantic classes to be segmented would be available during training and only seen categories are segmented at inference. We argue that such a closed-world assumption is restrictive and explore for the first time 3D indoor instance segmentation in an open-world setting, where the model is allowed to distinguish a set of known classes as well as identify an unknown object as unknown and then later incrementally learning the semantic category of the unknown when the corresponding category labels are available. To this end, we introduce an open-world 3D indoor instance segmentation method, where an auto-labeling scheme is employed to produce pseudo-labels during training and induce separation to separate known and unknown category labels. We further improve the pseudo-labels quality at inference by adjusting the unknown class probability based on the objectness score distribution. We also introduce carefully curated open-world splits leveraging realistic scenarios based on inherent object distribution, region-based indoor scene exploration and randomness aspect of open-world classes. Extensive experiments reveal the efficacy of the proposed contributions leading to promising open-world 3D instance segmentation performance.

Long Li, Nian Liu, Dingwen Zhang et al.

Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.

Abdelrahman Shaker, Ahmed Heakl, Jaseel Muhammad et al.

Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on edge devices. We present Mobile-O, a compact vision-language-diffusion model that brings unified multimodal intelligence to a mobile device. Its core module, the Mobile Conditioning Projector (MCP), fuses vision-language features with a diffusion generator using depthwise-separable convolutions and layerwise alignment. This design enables efficient cross-modal conditioning with minimal computational cost. Trained on only a few million samples and post-trained in a novel quadruplet format (generation prompt, image, question, answer), Mobile-O jointly enhances both visual understanding and generation capabilities. Despite its efficiency, Mobile-O attains competitive or superior performance compared to other unified models, achieving 74% on GenEval and outperforming Show-O and JanusFlow by 5% and 11%, while running 6x and 11x faster, respectively. For visual understanding, Mobile-O surpasses them by 15.3% and 5.1% averaged across seven benchmarks. Running in only ~3s per 512x512 image on an iPhone, Mobile-O establishes the first practical framework for real-time unified multimodal understanding and generation on edge devices. We hope Mobile-O will ease future research in real-time unified multimodal intelligence running entirely on-device with no cloud dependency. Our code, models, datasets, and mobile application are publicly available at https://amshaker.github.io/Mobile-O/

Omkar Thawakar, Dinura Dissanayake, Ketan More et al.

Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual reasoning and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing step-by-step visual reasoning in large language models (LMMs) through three key contributions. First, we introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. The benchmark presents a diverse set of challenges with eight different categories ranging from complex visual perception to scientific reasoning with over 4k reasoning steps in total, enabling robust evaluation of LLMs' abilities to perform accurate and interpretable visual reasoning across multiple steps. Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps, emphasizing both correctness and logical coherence. The proposed metric offers deeper insights into reasoning performance compared to traditional end-task accuracy metrics. Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach, where tasks are progressively organized to facilitate incremental skill acquisition and problem-solving. The proposed LlamaV-o1 is designed for multi-step reasoning and learns step-by-step through a structured training paradigm. Extensive experiments show that our LlamaV-o1 outperforms existing open-source models and performs favorably against close-source proprietary models. Compared to the recent Llava-CoT, our LlamaV-o1 achieves an average score of 67.3 with an absolute gain of 3.8\% across six benchmarks while being 5 times faster during inference scaling. Our benchmark, model, and code are publicly available.

Mubashir Noman, Muzammal Naseer, Hisham Cholakkal et al.

Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. Different from standard natural image datasets, remote sensing data is acquired from various sensor technologies and exhibit diverse range of scale variations as well as modalities. Existing satellite image pre-training methods either ignore the scale information present in the remote sensing imagery or restrict themselves to use only a single type of data modality. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities. Our proposed approach, named SatMAE++, performs multi-scale pre-training and utilizes convolution based upsampling blocks to reconstruct the image at higher scales making it extensible to include more scales. Compared to existing works, the proposed SatMAE++ with multi-scale pre-training is equally effective for both optical as well as multi-spectral imagery. Extensive experiments on six datasets reveal the merits of proposed contributions, leading to state-of-the-art performance on all datasets. SatMAE++ achieves mean average precision (mAP) gain of 2.5\% for multi-label classification task on BigEarthNet dataset. Our code and pre-trained models are available at \url{https://github.com/techmn/satmae_pp}.

Komal Kumar, Tajamul Ashraf, Omkar Thawakar et al.

Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications. Pretraining on vast web-scale data has laid the foundation for these models, yet the research community is now increasingly shifting focus toward post-training techniques to achieve further breakthroughs. While pretraining provides a broad linguistic foundation, post-training methods enable LLMs to refine their knowledge, improve reasoning, enhance factual accuracy, and align more effectively with user intents and ethical considerations. Fine-tuning, reinforcement learning, and test-time scaling have emerged as critical strategies for optimizing LLMs performance, ensuring robustness, and improving adaptability across various real-world tasks. This survey provides a systematic exploration of post-training methodologies, analyzing their role in refining LLMs beyond pretraining, addressing key challenges such as catastrophic forgetting, reward hacking, and inference-time trade-offs. We highlight emerging directions in model alignment, scalable adaptation, and inference-time reasoning, and outline future research directions. We also provide a public repository to continually track developments in this fast-evolving field: https://github.com/mbzuai-oryx/Awesome-LLM-Post-training.

Mubashir Noman, Mustansar Fiaz, Hisham Cholakkal et al.

Deep learning has shown remarkable success in remote sensing change detection (CD), aiming to identify semantic change regions between co-registered satellite image pairs acquired at distinct time stamps. However, existing convolutional neural network and transformer-based frameworks often struggle to accurately segment semantic change regions. Moreover, transformers-based methods with standard self-attention suffer from quadratic computational complexity with respect to the image resolution, making them less practical for CD tasks with limited training data. To address these issues, we propose an efficient change detection framework, ELGC-Net, which leverages rich contextual information to precisely estimate change regions while reducing the model size. Our ELGC-Net comprises a Siamese encoder, fusion modules, and a decoder. The focus of our design is the introduction of an Efficient Local-Global Context Aggregator module within the encoder, capturing enhanced global context and local spatial information through a novel pooled-transpose (PT) attention and depthwise convolution, respectively. The PT attention employs pooling operations for robust feature extraction and minimizes computational cost with transposed attention. Extensive experiments on three challenging CD datasets demonstrate that ELGC-Net outperforms existing methods. Compared to the recent transformer-based CD approach (ChangeFormer), ELGC-Net achieves a 1.4% gain in intersection over union metric on the LEVIR-CD dataset, while significantly reducing trainable parameters. Our proposed ELGC-Net sets a new state-of-the-art performance in remote sensing change detection benchmarks. Finally, we also introduce ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings, while achieving comparable performance. Project url https://github.com/techmn/elgcnet.

Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan et al.

In this paper, we introduce BiMediX, the first bilingual medical mixture of experts LLM designed for seamless interaction in both English and Arabic. Our model facilitates a wide range of medical interactions in English and Arabic, including multi-turn chats to inquire about additional details such as patient symptoms and medical history, multiple-choice question answering, and open-ended question answering. We propose a semi-automated English-to-Arabic translation pipeline with human refinement to ensure high-quality translations. We also introduce a comprehensive evaluation benchmark for Arabic medical LLMs. Furthermore, we introduce BiMed1.3M, an extensive Arabic-English bilingual instruction set covering 1.3 Million diverse medical interactions, resulting in over 632 million healthcare specialized tokens for instruction tuning. Our BiMed1.3M dataset includes 250k synthesized multi-turn doctor-patient chats and maintains a 1:2 Arabic-to-English ratio. Our model outperforms state-of-the-art Med42 and Meditron by average absolute gains of 2.5% and 4.1%, respectively, computed across multiple medical evaluation benchmarks in English, while operating at 8-times faster inference. Moreover, our BiMediX outperforms the generic Arabic-English bilingual LLM, Jais-30B, by average absolute gains of 10% on our Arabic medical benchmark and 15% on bilingual evaluations across multiple datasets. Our project page with source code and trained model is available at https://github.com/mbzuai-oryx/BiMediX .

Ayesha Ishaq, Jean Lahoud, Ketan More et al.

While large multimodal models (LMMs) have demonstrated strong performance across various Visual Question Answering (VQA) tasks, certain challenges require complex multi-step reasoning to reach accurate answers. One particularly challenging task is autonomous driving, which demands thorough cognitive processing before decisions can be made. In this domain, a sequential and interpretive understanding of visual cues is essential for effective perception, prediction, and planning. Nevertheless, common VQA benchmarks often focus on the accuracy of the final answer while overlooking the reasoning process that enables the generation of accurate responses. Moreover, existing methods lack a comprehensive framework for evaluating step-by-step reasoning in realistic driving scenarios. To address this gap, we propose DriveLMM-o1, a new dataset and benchmark specifically designed to advance step-wise visual reasoning for autonomous driving. Our benchmark features over 18k VQA examples in the training set and more than 4k in the test set, covering diverse questions on perception, prediction, and planning, each enriched with step-by-step reasoning to ensure logical inference in autonomous driving scenarios. We further introduce a large multimodal model that is fine-tuned on our reasoning dataset, demonstrating robust performance in complex driving scenarios. In addition, we benchmark various open-source and closed-source methods on our proposed dataset, systematically comparing their reasoning capabilities for autonomous driving tasks. Our model achieves a +7.49% gain in final answer accuracy, along with a 3.62% improvement in reasoning score over the previous best open-source model. Our framework, dataset, and model are available at https://github.com/ayesha-ishaq/DriveLMM-o1.

Sahal Shaji Mullappilly, Abdelrahman Shaker, Omkar Thawakar et al.

Climate change is one of the most significant challenges we face together as a society. Creating awareness and educating policy makers the wide-ranging impact of climate change is an essential step towards a sustainable future. Recently, Large Language Models (LLMs) like ChatGPT and Bard have shown impressive conversational abilities and excel in a wide variety of NLP tasks. While these models are close-source, recently alternative open-source LLMs such as Stanford Alpaca and Vicuna have shown promising results. However, these open-source models are not specifically tailored for climate related domain specific information and also struggle to generate meaningful responses in other languages such as, Arabic. To this end, we propose a light-weight Arabic Mini-ClimateGPT that is built on an open-source LLM and is specifically fine-tuned on a conversational-style instruction tuning curated Arabic dataset Clima500-Instruct with over 500k instructions about climate change and sustainability. Further, our model also utilizes a vector embedding based retrieval mechanism during inference. We validate our proposed model through quantitative and qualitative evaluations on climate-related queries. Our model surpasses the baseline LLM in 88.3% of cases during ChatGPT-based evaluation. Furthermore, our human expert evaluation reveals an 81.6% preference for our model's responses over multiple popular open-source models. Our open-source demos, code-base and models are available here https://github.com/mbzuai-oryx/ClimateGPT.

Sahal Shaji Mullappilly, Abhishek Singh Gehlot, Rao Muhammad Anwer et al.

Conventional open-world object detection (OWOD) problem setting first distinguishes known and unknown classes and then later incrementally learns the unknown objects when introduced with labels in the subsequent tasks. However, the current OWOD formulation heavily relies on the external human oracle for knowledge input during the incremental learning stages. Such reliance on run-time makes this formulation less realistic in a real-world deployment. To address this, we introduce a more realistic formulation, named semi-supervised open-world detection (SS-OWOD), that reduces the annotation cost by casting the incremental learning stages of OWOD in a semi-supervised manner. We demonstrate that the performance of the state-of-the-art OWOD detector dramatically deteriorates in the proposed SS-OWOD setting. Therefore, we introduce a novel SS-OWOD detector, named SS-OWFormer, that utilizes a feature-alignment scheme to better align the object query representations between the original and augmented images to leverage the large unlabeled and few labeled data. We further introduce a pseudo-labeling scheme for unknown detection that exploits the inherent capability of decoder object queries to capture object-specific information. We demonstrate the effectiveness of our SS-OWOD problem setting and approach for remote sensing object detection, proposing carefully curated splits and baseline performance evaluations. Our experiments on 4 datasets including MS COCO, PASCAL, Objects365 and DOTA demonstrate the effectiveness of our approach. Our source code, models and splits are available here - https://github.com/sahalshajim/SS-OWFormer

Mohammad Almansoori, Komal Kumar, Hisham Cholakkal

In this work, we introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents designed to evaluate and enhance LLM performance in dynamic diagnostic settings. Unlike prior approaches, our framework requires doctor agents to actively engage with patients through multi-turn conversations, requesting relevant medical examinations (e.g., temperature, blood pressure, ECG) and imaging results (e.g., MRI, X-ray) from a measurement agent to mimic the real-world diagnostic process. Additionally, we incorporate self improvement mechanisms that allow models to iteratively refine their diagnostic strategies. We enhance LLM performance in our simulated setting by integrating multi-agent discussions, chain-of-thought reasoning, and experience-based knowledge retrieval, facilitating progressive learning as doctor agents interact with more patients. We also introduce an evaluation benchmark for assessing the LLM's ability to engage in dynamic, context-aware diagnostic interactions. While MedAgentSim is fully automated, it also supports a user-controlled mode, enabling human interaction with either the doctor or patient agent. Comprehensive evaluations in various simulated diagnostic scenarios demonstrate the effectiveness of our approach. Our code, simulation tool, and benchmark are available at \href{https://medagentsim.netlify.app/}.

Sara Ghaboura, Ketan More, Ritesh Thawkar et al.

Understanding historical and cultural artifacts demands human expertise and advanced computational techniques, yet the process remains complex and time-intensive. While large multimodal models offer promising support, their evaluation and improvement require a standardized benchmark. To address this, we introduce TimeTravel, a benchmark of 10,250 expert-verified samples spanning 266 distinct cultures across 10 major historical regions. Designed for AI-driven analysis of manuscripts, artworks, inscriptions, and archaeological discoveries, TimeTravel provides a structured dataset and robust evaluation framework to assess AI models' capabilities in classification, interpretation, and historical comprehension. By integrating AI with historical research, TimeTravel fosters AI-powered tools for historians, archaeologists, researchers, and cultural tourists to extract valuable insights while ensuring technology contributes meaningfully to historical discovery and cultural heritage preservation. We evaluate contemporary AI models on TimeTravel, highlighting their strengths and identifying areas for improvement. Our goal is to establish AI as a reliable partner in preserving cultural heritage, ensuring that technological advancements contribute meaningfully to historical discovery. Our code is available at: \url{https://github.com/mbzuai-oryx/TimeTravel}.

Amrin Kareem, Jean Lahoud, Hisham Cholakkal

Recent advancements in 3D perception systems have significantly improved their ability to perform visual recognition tasks such as segmentation. However, these systems still heavily rely on explicit human instruction to identify target objects or categories, lacking the capability to actively reason and comprehend implicit user intentions. We introduce a novel segmentation task known as reasoning part segmentation for 3D objects, aiming to output a segmentation mask based on complex and implicit textual queries about specific parts of a 3D object. To facilitate evaluation and benchmarking, we present a large 3D dataset comprising over 60k instructions paired with corresponding ground-truth part segmentation annotations specifically curated for reasoning-based 3D part segmentation. We propose a model that is capable of segmenting parts of 3D objects based on implicit textual queries and generating natural language explanations corresponding to 3D object segmentation requests. Experiments show that our method achieves competitive performance to models that use explicit queries, with the additional abilities to identify part concepts, reason about them, and complement them with world knowledge. Our source code, dataset, and trained models are available at https://github.com/AmrinKareem/PARIS3D.

Wafa Alghallabi, Ritesh Thawkar, Sara Ghaboura et al.

Arabic poetry is one of the richest and most culturally rooted forms of expression in the Arabic language, known for its layered meanings, stylistic diversity, and deep historical continuity. Although large language models (LLMs) have demonstrated strong performance across languages and tasks, their ability to understand Arabic poetry remains largely unexplored. In this work, we introduce \emph{Fann or Flop}, the first benchmark designed to assess the comprehension of Arabic poetry by LLMs in 12 historical eras, covering 14 core poetic genres and a variety of metrical forms, from classical structures to contemporary free verse. The benchmark comprises a curated corpus of poems with explanations that assess semantic understanding, metaphor interpretation, prosodic awareness, and cultural context. We argue that poetic comprehension offers a strong indicator for testing how good the LLM understands classical Arabic through Arabic poetry. Unlike surface-level tasks, this domain demands deeper interpretive reasoning and cultural sensitivity. Our evaluation of state-of-the-art LLMs shows that most models struggle with poetic understanding despite strong results on standard Arabic benchmarks. We release "Fann or Flop" along with the evaluation suite as an open-source resource to enable rigorous evaluation and advancement for Arabic language models. Code is available at: https://github.com/mbzuai-oryx/FannOrFlop.

Sahal Shaji Mullappilly, Mohammed Irfan Kurpath, Sara Pieri et al.

We introduce BiMediX2, a bilingual (Arabic-English) Bio-Medical EXpert Large Multimodal Model that supports text-based and image-based medical interactions. It enables multi-turn conversation in Arabic and English and supports diverse medical imaging modalities, including radiology, CT, and histology. To train BiMediX2, we curate BiMed-V, an extensive Arabic-English bilingual healthcare dataset consisting of 1.6M samples of diverse medical interactions. This dataset supports a range of medical Large Language Model (LLM) and Large Multimodal Model (LMM) tasks, including multi-turn medical conversations, report generation, and visual question answering (VQA). We also introduce BiMed-MBench, the first Arabic-English medical LMM evaluation benchmark, verified by medical experts. BiMediX2 demonstrates excellent performance across multiple medical LLM and LMM benchmarks, achieving state-of-the-art results compared to other open-sourced models. On BiMed-MBench, BiMediX2 outperforms existing methods by over 9% in English and more than 20% in Arabic evaluations. Additionally, it surpasses GPT-4 by approximately 9% in UPHILL factual accuracy evaluations and excels in various medical VQA, report generation, and report summarization tasks. Our trained models, instruction set, and source code are available at https://github.com/mbzuai-oryx/BiMediX2

Sambal Shikhar, Mohammed Irfan Kurpath, Sahal Shaji Mullappilly et al.

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 .

Mohamed Fazli Imam, Rufael Fedaku Marew, Jameel Hassan et al.

In the era of foundation models, CLIP has emerged as a powerful tool for aligning text & visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visual features for fine-grained tasks. In contrast, SSL-pretrained models like DINO excel at extracting rich visual features due to their specialized training paradigm. Yet, these SSL models require an additional supervised linear probing step, which relies on fully labeled data which is often expensive and difficult to obtain at scale. In this paper, we propose a label-free prompt-tuning method that leverages the rich visual features of self-supervised learning models (DINO) and the broad textual knowledge of large language models (LLMs) to largely enhance CLIP-based image classification performance using unlabeled images. Our approach unfolds in three key steps: (1) We generate robust textual feature embeddings that more accurately represent object classes by leveraging class-specific descriptions from LLMs, enabling more effective zero-shot classification compared to CLIP's default name-specific prompts. (2) These textual embeddings are then used to produce pseudo-labels to train an alignment module that integrates the complementary strengths of LLM description-based textual embeddings & DINO's visual features. (3) Finally, we prompt-tune CLIP's vision encoder through DINO-assisted supervision using the trained alignment module. This three-step process allows us to harness the best of visual & textual foundation models, resulting in a powerful and efficient approach that surpasses state-of-the-art label-free classification methods. Notably, our framework, NoLA (No Labels Attached), achieves an average absolute gain of 3.6% over the state-of-the-art LaFTer across 11 diverse image classification datasets. Our code & models can be found at https://github.com/fazliimam/NoLA.

Tajamul Ashraf, Amal Saqib, Hanan Ghani et al.

Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn queries, limited visual modalities, and lack a framework to assess reasoning quality over multiple steps as required in real-world settings. To address this, we introduce Agent-X, a large-scale benchmark for evaluating vision-centric agents multi-step and deep reasoning capabilities in real-world, multimodal settings. Agent- X features 828 agentic tasks with authentic visual contexts, including images, multi-image comparisons, videos, and instructional text. These tasks span six major agentic environments: general visual reasoning, web browsing, security and surveillance, autonomous driving, sports, and math reasoning. Our benchmark requires agents to integrate tool use with explicit, stepwise decision-making in these diverse settings. In addition, we propose a fine-grained, step-level evaluation framework that assesses the correctness and logical coherence of each reasoning step and the effectiveness of tool usage throughout the task. Our results reveal that even the best-performing models, including GPT, Gemini, and Qwen families, struggle to solve multi-step vision tasks, achieving less than 50% full-chain success. These findings highlight key bottlenecks in current LMM reasoning and tool-use capabilities and identify future research directions in vision-centric agentic reasoning models. Our data and code are publicly available at https://github.com/mbzuai-oryx/Agent-X

Sara Ghaboura, Ketan More, Wafa Alghallabi et al.

As Large Multimodal Models (LMMs) become more capable, there is growing interest in evaluating their reasoning processes alongside their final outputs. However, most benchmarks remain focused on English, overlooking languages with rich linguistic and cultural contexts, such as Arabic. To address this gap, we introduce the Comprehensive Arabic Multimodal Reasoning Benchmark (ARB), the first benchmark designed to evaluate step-by-step reasoning in Arabic across both textual and visual modalities. ARB spans 11 diverse domains, including visual reasoning, document understanding, OCR, scientific analysis, and cultural interpretation. It comprises 1,356 multimodal samples paired with 5,119 human-curated reasoning steps and corresponding actions. We evaluated 12 state-of-the-art open- and closed-source LMMs and found persistent challenges in coherence, faithfulness, and cultural grounding. ARB offers a structured framework for diagnosing multimodal reasoning in underrepresented languages and marks a critical step toward inclusive, transparent, and culturally aware AI systems. We release the benchmark, rubric, and evaluation suit to support future research and reproducibility. Code available at: https://github.com/mbzuai-oryx/ARB

Ayesha Ishaq, Jean Lahoud, Fahad Shahbaz Khan et al.

Large Multimodal Models (LMMs) have recently gained prominence in autonomous driving research, showcasing promising capabilities across various emerging benchmarks. LMMs specifically designed for this domain have demonstrated effective perception, planning, and prediction skills. However, many of these methods underutilize 3D spatial and temporal elements, relying mainly on image data. As a result, their effectiveness in dynamic driving environments is limited. We propose to integrate tracking information as an additional input to recover 3D spatial and temporal details that are not effectively captured in the images. We introduce a novel approach for embedding this tracking information into LMMs to enhance their spatiotemporal understanding of driving scenarios. By incorporating 3D tracking data through a track encoder, we enrich visual queries with crucial spatial and temporal cues while avoiding the computational overhead associated with processing lengthy video sequences or extensive 3D inputs. Moreover, we employ a self-supervised approach to pretrain the tracking encoder to provide LMMs with additional contextual information, significantly improving their performance in perception, planning, and prediction tasks for autonomous driving. Experimental results demonstrate the effectiveness of our approach, with a gain of 9.5% in accuracy, an increase of 7.04 points in the ChatGPT score, and 9.4% increase in the overall score over baseline models on DriveLM-nuScenes benchmark, along with a 3.7% final score improvement on DriveLM-CARLA. Our code is available at https://github.com/mbzuai-oryx/TrackingMeetsLMM