Umair Nawaz

Bonan Ding, Umair Nawaz, Ufaq Khan et al.

Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality interference, allowing irrelevant channels to distract the model. To address this issue, we present a unified multimodal video understanding framework, named UniMVU, that performs instruction-aware fusion across video, audio, depth map, or any other modality inputs via two levels of dynamic gating: inner-modality gates emphasize salient regions within each modality, whereas modality-level gates re-weight whole streams; both are conditioned on the text instruction to adaptively balance modality importance. Our UniMVU combines cross-modal self-attention with instruction-driven inner-modality gating module and a modality-level gating module with control token; for time-aligned streams we further adopt a fast-to-slow fusion scheme that reduces redundancy. Across six benchmarks (AVQA, AVSD, Music-AVQA, ScanQA, SQA3D and MVBench), our UniMVU achieves consistent gains over static-fusion baselines achieving gains as high as 13.5 in terms of CIDEr metric. Further, our analysis shows that the gating mechanism aligns with the human-interpretable modality relevance, and ablations show the contributions of inner-modality and modality-level gating. Our UniMVU provides a simple, unified recipe for instruction-aware multimodal video understanding that scales to diverse modalities without hand-crafted fusion rules.

Umair Nawaz, Ahmed Heakl, Ufaq Khan et al.

Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing intermediate activations across denoising steps; however, existing methods largely rely on a Zero-Order Hold assumption i.e., reusing cached features as static snapshots when global drift is small. This often leads to ghosting artifacts, blur, and motion inconsistencies in dynamic scenes. We propose \textbf{WorldCache}, a Perception-Constrained Dynamical Caching framework that improves both when and how to reuse features. WorldCache introduces motion-adaptive thresholds, saliency-weighted drift estimation, optimal approximation via blending and warping, and phase-aware threshold scheduling across diffusion steps. Our cohesive approach enables adaptive, motion-consistent feature reuse without retraining. On Cosmos-Predict2.5-2B evaluated on PAI-Bench, WorldCache achieves \textbf{2.3$\times$} inference speedup while preserving \textbf{99.4\%} of baseline quality, substantially outperforming prior training-free caching approaches. Our code can be accessed on \href{https://umair1221.github.io/World-Cache/}{World-Cache}.

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

Umair Nawaz, Muhammad Zaigham Zaheer, Fahad Shahbaz Khan et al.

Crops, fisheries and livestock form the backbone of global food production, essential to feed the ever-growing global population. However, these sectors face considerable challenges, including climate variability, resource limitations, and the need for sustainable management. Addressing these issues requires efficient, accurate, and scalable technological solutions, highlighting the importance of artificial intelligence (AI). This survey presents a systematic and thorough review of more than 200 research works covering conventional machine learning approaches, advanced deep learning techniques (e.g., vision transformers), and recent vision-language foundation models (e.g., CLIP) in the agriculture domain, focusing on diverse tasks such as crop disease detection, livestock health management, and aquatic species monitoring. We further cover major implementation challenges such as data variability and experimental aspects: datasets, performance evaluation metrics, and geographical focus. We finish the survey by discussing potential open research directions emphasizing the need for multimodal data integration, efficient edge-device deployment, and domain-adaptable AI models for diverse farming environments. Rapid growth of evolving developments in this field can be actively tracked on our project page: https://github.com/umair1221/AI-in-Agriculture

Ufaq Khan, Umair Nawaz, L D M S S Teja et al.

Vision Language Models (VLMs) are increasingly used for tasks like medical report generation and visual question answering. However, fluent diagnostic text does not guarantee safe visual understanding. In clinical practice, interpretation begins with pre-diagnostic sanity checks: verifying that the input is valid to read (correct modality and anatomy, plausible viewpoint and orientation, and no obvious integrity violations). Existing benchmarks largely assume this step is solved, and therefore miss a critical failure mode: a model can produce plausible narratives even when the input is inconsistent or invalid. We introduce MedObvious, a 1,880-task benchmark that isolates input validation as a set-level consistency capability over small multi-panel image sets: the model must identify whether any panel violates expected coherence. MedObvious spans five progressive tiers, from basic orientation/modality mismatches to clinically motivated anatomy/viewpoint verification and triage-style cues, and includes five evaluation formats to test robustness across interfaces. Evaluating 17 different VLMs, we find that sanity checking remains unreliable: several models hallucinate anomalies on normal (negative-control) inputs, performance degrades when scaling to larger image sets, and measured accuracy varies substantially between multiple-choice and open-ended settings. These results show that pre-diagnostic verification remains unsolved for medical VLMs and should be treated as a distinct, safety-critical capability before deployment.

Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker et al.

Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories and the cost of manual annotation. We address this challenge with a vision-centric agent tuning framework that automatically synthesizes multimodal trajectories, generates step-wise preference pairs, and trains a VLM controller for robust tool-use reasoning. Our pipeline first constructs M-TRACE, a large-scale dataset of 28.5K multimodal tasks with 177K verified trajectories, enabling imitation-based trajectory tuning. Building on this, we develop MATRIX Agent, a controller finetuned on M-TRACE for step-wise tool reasoning. To achieve finer alignment, we further introduce Pref-X, a set of 11K automatically generated preference pairs, and optimize MATRIX on it via step-wise preference learning. Across three benchmarks, Agent-X, GTA, and GAIA, MATRIX consistently surpasses both open- and closed-source VLMs, demonstrating scalable and effective multimodal tool use. Our data and code is avaliable at https://github.com/mbzuai-oryx/MATRIX.

Asim Khan, Umair Nawaz, Lochan Kshetrimayum et al.

Tomato leaf diseases pose a significant challenge for tomato farmers, resulting in substantial reductions in crop productivity. The timely and precise identification of tomato leaf diseases is crucial for successfully implementing disease management strategies. This paper introduces a transformer-based model called TomFormer for the purpose of tomato leaf disease detection. The paper's primary contributions include the following: Firstly, we present a novel approach for detecting tomato leaf diseases by employing a fusion model that combines a visual transformer and a convolutional neural network. Secondly, we aim to apply our proposed methodology to the Hello Stretch robot to achieve real-time diagnosis of tomato leaf diseases. Thirdly, we assessed our method by comparing it to models like YOLOS, DETR, ViT, and Swin, demonstrating its ability to achieve state-of-the-art outcomes. For the purpose of the experiment, we used three datasets of tomato leaf diseases, namely KUTomaDATA, PlantDoc, and PlanVillage, where KUTomaDATA is being collected from a greenhouse in Abu Dhabi, UAE. Finally, we present a comprehensive analysis of the performance of our model and thoroughly discuss the limitations inherent in our approach. TomFormer performed well on the KUTomaDATA, PlantDoc, and PlantVillage datasets, with mean average accuracy (mAP) scores of 87%, 81%, and 83%, respectively. The comparative results in terms of mAP demonstrate that our method exhibits robustness, accuracy, efficiency, and scalability. Furthermore, it can be readily adapted to new datasets. We are confident that our work holds the potential to significantly influence the tomato industry by effectively mitigating crop losses and enhancing crop yields.

Ufaq Khan, Umair Nawaz, Adnan Qayyum et al.

Recent advancements in machine learning (ML) and deep learning (DL), particularly through the introduction of Foundation Models (FMs), have significantly enhanced surgical scene understanding within minimally invasive surgery (MIS). This paper surveys the integration of state-of-the-art ML and DL technologies, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Foundation Models like the Segment Anything Model (SAM), into surgical workflows. These technologies improve segmentation accuracy, instrument tracking, and phase recognition in surgical scene understanding. The paper explores the challenges these technologies face, such as data variability and computational demands, and discusses ethical considerations and integration hurdles in clinical settings. Highlighting the roles of FMs, we bridge the technological capabilities with clinical needs and outline future research directions to enhance the adaptability, efficiency, and ethical alignment of AI applications in surgery. Our findings suggest that substantial progress has been made; however, more focused efforts are required to achieve seamless integration of these technologies into clinical workflows, ensuring they complement surgical practice by enhancing precision, reducing risks, and optimizing patient outcomes.

Asim Khan, Umair Nawaz, Anwaar Ulhaq et al.

Deforestation, a major contributor to climate change, poses detrimental consequences such as agricultural sector disruption, global warming, flash floods, and landslides. Conventional approaches to urban street tree inventory suffer from inaccuracies and necessitate specialised equipment. To overcome these challenges, this paper proposes an innovative method that leverages deep learning techniques and mobile phone imaging for urban street tree inventory. Our approach utilises a pair of images captured by smartphone cameras to accurately segment tree trunks and compute the diameter at breast height (DBH). Compared to traditional methods, our approach exhibits several advantages, including superior accuracy, reduced dependency on specialised equipment, and applicability in hard-to-reach areas. We evaluated our method on a comprehensive dataset of 400 trees and achieved a DBH estimation accuracy with an error rate of less than 2.5%. Our method holds significant potential for substantially improving forest management practices. By enhancing the accuracy and efficiency of tree inventory, our model empowers urban management to mitigate the adverse effects of deforestation and climate change.

Numan Saeed, Salma Hassan, Shahad Hardan et al.

We present a publicly available multimodal dataset for head and neck cancer research, comprising 1123 annotated Positron Emission Tomography/Computed Tomography (PET/CT) studies from patients with histologically confirmed disease, acquired from 10 international medical centers. All studies contain co-registered PET/CT scans with varying acquisition protocols, reflecting real-world clinical diversity from a long-term, multi-institution retrospective collection. Primary gross tumor volumes (GTVp) and involved lymph nodes (GTVn) were manually segmented by experienced radiation oncologists and radiologists following established guidelines. We provide anonymized NifTi files, expert-annotated segmentation masks, comprehensive clinical metadata, and radiotherapy dose distributions for a patient subset. The metadata include TNM staging, HPV status, demographics, long-term follow-up outcomes, survival times, censoring indicators, and treatment information. To demonstrate its utility, we benchmark three key clinical tasks: automated tumor segmentation, recurrence-free survival prediction, and HPV status classification, using state-of-the-art deep learning models like UNet, SegResNet, and multimodal prognostic frameworks.

Asim Khan, Umair Nawaz, Anwaar Ulhaq et al.

In the Agriculture sector, control of plant leaf diseases is crucial as it influences the quality and production of plant species with an impact on the economy of any country. Therefore, automated identification and classification of plant leaf disease at an early stage is essential to reduce economic loss and to conserve the specific species. Previously, to detect and classify plant leaf disease, various Machine Learning models have been proposed; however, they lack usability due to hardware incompatibility, limited scalability and inefficiency in practical usage. Our proposed DeepLens Classification and Detection Model (DCDM) approach deal with such limitations by introducing automated detection and classification of the leaf diseases in fruits (apple, grapes, peach and strawberry) and vegetables (potato and tomato) via scalable transfer learning on AWS SageMaker and importing it on AWS DeepLens for real-time practical usability. Cloud integration provides scalability and ubiquitous access to our approach. Our experiments on extensive image data set of healthy and unhealthy leaves of fruits and vegetables showed an accuracy of 98.78% with a real-time diagnosis of plant leaves diseases. We used forty thousand images for the training of deep learning model and then evaluated it on ten thousand images. The process of testing an image for disease diagnosis and classification using AWS DeepLens on average took 0.349s, providing disease information to the user in less than a second.