arXiv subjects

Salman Khan

Publications and source records attributed to Salman Khan.

At least 109 records · Page 6Linked to original sources

arXiv2025

A Culturally-diverse Multilingual Multimodal Video Benchmark & Model

Large multimodal models (LMMs) have recently gained attention due to their effectiveness to understand and generate descriptions of visual content. Most existing LMMs are in English language. While few recent works explore multilingual image LMMs, to the best of our knowledge, moving beyond the English language for cultural and linguistic inclusivity is yet to be investigated in the context of video LMMs. In pursuit of more inclusive video LMMs, we introduce a multilingual Video LMM benchmark, named ViMUL-Bench, to evaluate Video LMMs across 14 languages, including both low- and high-resource languages: English, Chinese, Spanish, French, German, Hindi, Arabic, Russian, Bengali, Urdu, Sinhala, Tamil, Swedish, and Japanese. Our ViMUL-Bench is designed to rigorously test video LMMs across 15 categories including eight culturally diverse categories, ranging from lifestyles and festivals to foods and rituals and from local landmarks to prominent cultural personalities. ViMUL-Bench comprises both open-ended (short and long-form) and multiple-choice questions spanning various video durations (short, medium, and long) with 8k samples that are manually verified by native language speakers. In addition, we also introduce a machine translated multilingual video training set comprising 1.2 million samples and develop a simple multilingual video LMM, named ViMUL, that is shown to provide a better tradeoff between high-and low-resource languages for video understanding. We hope our ViMUL-Bench and multilingual video LMM along with a large-scale multilingual video training set will help ease future research in developing cultural and linguistic inclusive multilingual video LMMs. Our proposed benchmark, video LMM and training data will be publicly released at https://mbzuai-oryx.github.io/ViMUL/.

cs.CL↗

arXiv2025

DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models

Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often faces challenges in striking a trade-off between aligning with the target distribution: learning a novel concept from a limited image for personalization and retaining the instruction ability needed for unifying multiple tasks, all while maintaining editability (aligning with a variety of prompts or in-context generation). In this work, we introduce DEFT, Decompositional Efficient Fine-Tuning, an efficient fine-tuning framework that adapts a pre-trained weight matrix by decomposing its update into two components with two trainable matrices: (1) a projection onto the complement of a low-rank subspace spanned by a low-rank matrix, and (2) a low-rank update. The single trainable low-rank matrix defines the subspace, while the other trainable low-rank matrix enables flexible parameter adaptation within that subspace. We conducted extensive experiments on the Dreambooth and Dreambench Plus datasets for personalization, the InsDet dataset for object and scene adaptation, and the VisualCloze dataset for a universal image generation framework through visual in-context learning with both Stable Diffusion and a unified model. Our results demonstrated state-of-the-art performance, highlighting the emergent properties of efficient fine-tuning. Our code is available on \href{https://github.com/MAXNORM8650/DEFT}{DEFTBase}.

cs.CV↗

arXiv2025

How Good are Foundation Models in Step-by-Step Embodied Reasoning?

Embodied agents operating in the physical world must make decisions that are not only effective but also safe, spatially coherent, and grounded in context. While recent advances in large multimodal models (LMMs) have shown promising capabilities in visual understanding and language generation, their ability to perform structured reasoning for real-world embodied tasks remains underexplored. In this work, we aim to understand how well foundation models can perform step-by-step reasoning in embodied environments. To this end, we propose the Foundation Model Embodied Reasoning (FoMER) benchmark, designed to evaluate the reasoning capabilities of LMMs in complex embodied decision-making scenarios. Our benchmark spans a diverse set of tasks that require agents to interpret multimodal observations, reason about physical constraints and safety, and generate valid next actions in natural language. We present (i) a large-scale, curated suite of embodied reasoning tasks, (ii) a novel evaluation framework that disentangles perceptual grounding from action reasoning, and (iii) empirical analysis of several leading LMMs under this setting. Our benchmark includes over 1.1k samples with detailed step-by-step reasoning across 10 tasks and 8 embodiments, covering three different robot types. Our results highlight both the potential and current limitations of LMMs in embodied reasoning, pointing towards key challenges and opportunities for future research in robot intelligence. Our data and code will be made publicly available.

cs.CV↗

arXiv2025

Promptception: How Sensitive Are Large Multimodal Models to Prompts?

Despite the success of Large Multimodal Models (LMMs) in recent years, prompt design for LMMs in Multiple-Choice Question Answering (MCQA) remains poorly understood. We show that even minor variations in prompt phrasing and structure can lead to accuracy deviations of up to 15% for certain prompts and models. This variability poses a challenge for transparent and fair LMM evaluation, as models often report their best-case performance using carefully selected prompts. To address this, we introduce Promptception, a systematic framework for evaluating prompt sensitivity in LMMs. It consists of 61 prompt types, spanning 15 categories and 6 supercategories, each targeting specific aspects of prompt formulation, and is used to evaluate 10 LMMs ranging from lightweight open-source models to GPT-4o and Gemini 1.5 Pro, across 3 MCQA benchmarks: MMStar, MMMU-Pro, MVBench. Our findings reveal that proprietary models exhibit greater sensitivity to prompt phrasing, reflecting tighter alignment with instruction semantics, while open-source models are steadier but struggle with nuanced and complex phrasing. Based on this analysis, we propose Prompting Principles tailored to proprietary and open-source LMMs, enabling more robust and fair model evaluation.

cs.CV↗

arXiv2025

Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments

Recent advancements in Large Language Models (LLMs) have paved the way for Vision Large Language Models (VLLMs) capable of performing a wide range of visual understanding tasks. While LLMs have demonstrated impressive performance on standard natural images, their capabilities have not been thoroughly explored in cluttered datasets where there is complex environment having deformed shaped objects. In this work, we introduce a novel dataset specifically designed for waste classification in real-world scenarios, characterized by complex environments and deformed shaped objects. Along with this dataset, we present an in-depth evaluation approach to rigorously assess the robustness and accuracy of VLLMs. The introduced dataset and comprehensive analysis provide valuable insights into the performance of VLLMs under challenging conditions. Our findings highlight the critical need for further advancements in VLLM's robustness to perform better in complex environments. The dataset and code for our experiments will be made publicly available.

cs.CV↗

arXiv2025

Beyond Simple Edits: Composed Video Retrieval with Dense Modifications

Composed video retrieval is a challenging task that strives to retrieve a target video based on a query video and a textual description detailing specific modifications. Standard retrieval frameworks typically struggle to handle the complexity of fine-grained compositional queries and variations in temporal understanding limiting their retrieval ability in the fine-grained setting. To address this issue, we introduce a novel dataset that captures both fine-grained and composed actions across diverse video segments, enabling more detailed compositional changes in retrieved video content. The proposed dataset, named Dense-WebVid-CoVR, consists of 1.6 million samples with dense modification text that is around seven times more than its existing counterpart. We further develop a new model that integrates visual and textual information through Cross-Attention (CA) fusion using grounded text encoder, enabling precise alignment between dense query modifications and target videos. The proposed model achieves state-of-the-art results surpassing existing methods on all metrics. Notably, it achieves 71.3\% Recall@1 in visual+text setting and outperforms the state-of-the-art by 3.4\%, highlighting its efficacy in terms of leveraging detailed video descriptions and dense modification texts. Our proposed dataset, code, and model are available at :https://github.com/OmkarThawakar/BSE-CoVR

cs.CV↗

arXiv2025

Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation

Video instance segmentation (VIS) has gained significant attention for its capability in tracking and segmenting object instances across video frames. However, most of the existing VIS approaches unrealistically assume that the categories of object instances remain fixed over time. Moreover, they experience catastrophic forgetting of old classes when required to continuously learn object instances belonging to new categories. To resolve these challenges, we develop a novel Hierarchical Visual Prompt Learning (HVPL) model that overcomes catastrophic forgetting of previous categories from both frame-level and video-level perspectives. Specifically, to mitigate forgetting at the frame level, we devise a task-specific frame prompt and an orthogonal gradient correction (OGC) module. The OGC module helps the frame prompt encode task-specific global instance information for new classes in each individual frame by projecting its gradients onto the orthogonal feature space of old classes. Furthermore, to address forgetting at the video level, we design a task-specific video prompt and a video context decoder. This decoder first embeds structural inter-class relationships across frames into the frame prompt features, and then propagates task-specific global video contexts from the frame prompt features to the video prompt. Through rigorous comparisons, our HVPL model proves to be more effective than baseline approaches. The code is available at https://github.com/JiahuaDong/HVPL.

cs.CV↗

arXiv2025

LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation

We present LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks. Our framework recasts DIS as an image-conditioned mask generation task within a latent diffusion model, enabling seamless integration of user controls. LawDIS is enhanced with macro-to-micro control modes. Specifically, in macro mode, we introduce a language-controlled segmentation strategy (LS) to generate an initial mask based on user-provided language prompts. In micro mode, a window-controlled refinement strategy (WR) allows flexible refinement of user-defined regions (i.e., size-adjustable windows) within the initial mask. Coordinated by a mode switcher, these modes can operate independently or jointly, making the framework well-suited for high-accuracy, personalised applications. Extensive experiments on the DIS5K benchmark reveal that our LawDIS significantly outperforms 11 cutting-edge methods across all metrics. Notably, compared to the second-best model MVANet, we achieve $F_β^ω$ gains of 4.6\% with both the LS and WR strategies and 3.6\% gains with only the LS strategy on DIS-TE. Codes will be made available at https://github.com/XinyuYanTJU/LawDIS.

cs.CV↗

arXiv2025

Vocabulary-free Fine-grained Visual Recognition via Enriched Contextually Grounded Vision-Language Model

Fine-grained image classification, the task of distinguishing between visually similar subcategories within a broader category (e.g., bird species, car models, flower types), is a challenging computer vision problem. Traditional approaches rely heavily on fixed vocabularies and closed-set classification paradigms, limiting their scalability and adaptability in real-world settings where novel classes frequently emerge. Recent research has demonstrated that combining large language models (LLMs) with vision-language models (VLMs) makes open-set recognition possible without the need for predefined class labels. However, the existing methods are often limited in harnessing the power of LLMs at the classification phase, and also rely heavily on the guessed class names provided by an LLM without thorough analysis and refinement. To address these bottlenecks, we propose our training-free method, Enriched-FineR (or E-FineR for short), which demonstrates state-of-the-art results in fine-grained visual recognition while also offering greater interpretability, highlighting its strong potential in real-world scenarios and new domains where expert annotations are difficult to obtain. Additionally, we demonstrate the application of our proposed approach to zero-shot and few-shot classification, where it demonstrated performance on par with the existing SOTA while being training-free and not requiring human interventions. Overall, our vocabulary-free framework supports the shift in image classification from rigid label prediction to flexible, language-driven understanding, enabling scalable and generalizable systems for real-world applications. Well-documented code is available on https://github.com/demidovd98/e-finer.

cs.CV↗

arXiv2025

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM-VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about "what", "where", "when", and "how" of a video. We make our work fully reproducible by providing data, training recipes, code & models. https://github.com/facebookresearch/perception_models

cs.CV↗

arXiv2025

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization. We introduce VideoMolmo, a large multimodal model tailored for fine-grained spatio-temporal pointing conditioned on textual descriptions. Building upon the Molmo architecture, VideoMolmo incorporates a temporal module utilizing an attention mechanism to condition each frame on preceding frames, ensuring temporal consistency. Additionally, our novel temporal mask fusion pipeline employs SAM2 for bidirectional point propagation, significantly enhancing coherence across video sequences. This two-step decomposition, i.e., first using the LLM to generate precise pointing coordinates, then relying on a sequential mask-fusion module to produce coherent segmentation, not only simplifies the task for the language model but also enhances interpretability. Due to the lack of suitable datasets, we curate a comprehensive dataset comprising 72k video-caption pairs annotated with 100k object points. To evaluate the generalization of VideoMolmo, we introduce VPoS-Bench, a challenging out-of-distribution benchmark spanning five real-world scenarios: Cell Tracking, Egocentric Vision, Autonomous Driving, Video-GUI Interaction, and Robotics. We also evaluate our model on Referring Video Object Segmentation (Refer-VOS) and Reasoning VOS tasks. In comparison to existing models, VideoMolmo substantially improves spatio-temporal pointing accuracy and reasoning capability. Our code and models are publicly available at https://github.com/mbzuai-oryx/VideoMolmo.

cs.CV↗

arXiv2025

Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model

Large-scale vision-language models (VLMs), such as CLIP, have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets. However, these methods often lack interpretability, as they compute the similarity between an entire query image and the embedded category words, making it difficult to explain their predictions. One approach to address this issue is to develop interpretable models by integrating language, where classifiers are built using discrete attributes, similar to human perception. This introduces a new challenge: how to effectively align local visual features with corresponding attributes based on pre-trained VLMs. To tackle this, we propose LaZSL, a locally-aligned vision-language model for interpretable ZSL. LaZSL employs local visual-semantic alignment via optimal transport to perform interaction between visual regions and their associated attributes, facilitating effective alignment and providing interpretable similarity without the need for additional training. Extensive experiments demonstrate that our method offers several advantages, including enhanced interpretability, improved accuracy, and strong domain generalization. Codes available at: https://github.com/shiming-chen/LaZSL.

cs.CV↗

arXiv2025

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

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

cs.CV↗

arXiv2025

VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos

Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and integrating spoken cues, often dispersed non-linearly over time. In such multimodal contexts, success hinges not just on perception, but on selectively identifying and integrating the right contextual details from a rich and noisy stream of content. To this end, we introduce VideoMathQA, a benchmark designed to evaluate whether models can perform such temporally extended cross-modal reasoning on videos. The benchmark spans 10 diverse mathematical domains, covering videos ranging from 10 seconds to over 1 hour. It requires models to interpret structured visual content, understand instructional narratives, and jointly ground concepts across visual, audio, and textual modalities. We employ graduate-level experts to ensure high quality, totaling over $920$ man-hours of annotation. To reflect real-world scenarios, questions are designed around three core reasoning challenges: direct problem solving, where answers are grounded in the presented question; conceptual transfer, which requires applying learned methods to new problems; and deep instructional comprehension, involving multi-step reasoning over extended explanations and partially worked-out solutions. Each question includes multi-step reasoning annotations, enabling fine-grained diagnosis of model capabilities. Through this benchmark, we highlight the limitations of existing approaches and establish a systematic evaluation framework for models that must reason, rather than merely perceive, across temporally extended and modality-rich mathematical problem settings. Our benchmark and evaluation code are available at: https://mbzuai-oryx.github.io/VideoMathQA

cs.CV↗

arXiv2025

MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks

Large multimodal models (LMMs) have shown remarkable progress in audio-visual understanding, yet they struggle with real-world scenarios that require complex reasoning across extensive video collections. Existing benchmarks for video question answering remain limited in scope, typically involving one clip per query, which falls short of representing the challenges of large-scale, audio-visual retrieval and reasoning encountered in practical applications. To bridge this gap, we introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in response to a query and link them together to generate the most informative answer. To this end, we present AVHaystacks, an audio-visual benchmark comprising 3100 annotated QA pairs designed to assess the capabilities of LMMs in multi-video retrieval and temporal grounding task. Additionally, we propose a model-agnostic, multi-agent framework MAGNET to address this challenge, achieving up to 89% and 65% relative improvements over baseline methods on BLEU@4 and GPT evaluation scores in QA task on our proposed AVHaystacks. To enable robust evaluation of multi-video retrieval and temporal grounding for optimal response generation, we introduce two new metrics, STEM, which captures alignment errors between a ground truth and a predicted step sequence and MTGS, to facilitate balanced and interpretable evaluation of segment-level grounding performance. Project: https://schowdhury671.github.io/magnet_project/

cs.CV↗

arXiv2025

Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning

Benefited from image-text contrastive learning, pre-trained vision-language models, e.g., CLIP, allow to direct leverage texts as images (TaI) for parameter-efficient fine-tuning (PEFT). While CLIP is capable of making image features to be similar to the corresponding text features, the modality gap remains a nontrivial issue and limits image recognition performance of TaI. Using multi-label image recognition (MLR) as an example, we present a novel method, called T2I-PAL to tackle the modality gap issue when using only text captions for PEFT. The core design of T2I-PAL is to leverage pre-trained text-to-image generation models to generate photo-realistic and diverse images from text captions, thereby reducing the modality gap. To further enhance MLR, T2I-PAL incorporates a class-wise heatmap and learnable prototypes. This aggregates local similarities, making the representation of local visual features more robust and informative for multi-label recognition. For better PEFT, we further combine both prompt tuning and adapter learning to enhance classification performance. T2I-PAL offers significant advantages: it eliminates the need for fully semantically annotated training images, thereby reducing the manual annotation workload, and it preserves the intrinsic mode of the CLIP model, allowing for seamless integration with any existing CLIP framework. Extensive experiments on multiple benchmarks, including MS-COCO, VOC2007, and NUS-WIDE, show that our T2I-PAL can boost recognition performance by 3.47% in average above the top-ranked state-of-the-art methods.

cs.CV↗

arXiv2025

TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation

Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO tasks, many remain limited by the scale, geographical coverage, and spectral diversity of their training data, factors critical for learning globally transferable representations. In this work, we introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery, combined with large spatial tiles and land-cover aware sampling to enrich spatial and semantic coverage. By treating sensing modalities as natural augmentations in our self-supervised approach, we unify radar and optical inputs via modality-specific patch embeddings and adaptive cross-attention fusion. Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism that incorporates class-frequency-aware regularization to address long-tailed distributions in land cover.TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench. Our code and pretrained models are publicly available at: https://github.com/mbzuai-oryx/TerraFM .

cs.CV↗

arXiv2025

Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs

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.

cs.CL↗