3.6k citations · 4.2k across the 77 of their papers we have counts for
86 papers
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
Pengfei Li, Naufal Suryanto, Sicheng Zhang +1
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowle…
SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs
Pengfei Li, Naufal Suryanto, Sicheng Zhang +2
Multimodal Large Language Models (MLLMs) show strong progress on vision-language tasks, yet their reliability in safety-critical settings remains underexplored. Fire-smoke understa…
CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray Interpretation
Adonay Demewez Gebremedhin, Wessam Shehieb, Sara Alansari +4
Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal reasoning. While longitudinal…
From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology
Basit Alawode, Moshira Ali Abdalla, Dwarikanath Mahapatra +2
Vision Transformers (ViTs) and their hierarchical variants have achieved strong performance in Computational Pathology (CPath). However, most are pre-trained on single-resolution W…
On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation
Sicheng Zhang, Zhonghao Yan, Binzhu Xie +4
Text-to-image (T2I) generation has achieved remarkable progress in recent years. However, existing research has largely focused on English-only settings, leaving cross-lingual perf…
ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models
Hashmat Shadab Malik, Toluwani Aremu, Samuele Poppi +2
Training-free test-time defenses offer a practical way to improve the adversarial robustness of CLIP-style vision--language models without modifying the pretrained model. However,…
CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
Hashmat Shadab Malik, Anees Ur Rehman Hashmi, Numan Saeed +3
Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer…
ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
Sicheng Zhang, Muzammal Naseer, Binzhu Xie +5
CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applicat…
SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking
Mohamad Alansari, Yonathan Michael, Hasan AlMarzouqi +3
We revisit the memory update mechanism in SAM2-based visual object tracking and identify confidence-only mask selection as the dominant cause of drift under occlusion, rapid motion…
Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
Hashmat Shadab Malik, Muzammal Naseer, Salman Khan
Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial attacks. Prior work on MLLM…
Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models
Hashmat Shadab Malik, Muzammal Naseer, Salman Khan
Vision-language models (VLMs) such as CLIP show strong zero-shot generalization but remain highly vulnerable to adversarial attacks. Adversarial training improves robustness but is…
Investigating Adversarial Robustness of Multi-modal Large Language Models
Hashmat Shadab Malik, Muzammal Naseer, Salman Khan
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e.g., CLIP) substantially e…
SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
Mohamad Alansari, Naufal Suryanto, Divya Velayudhan +3
Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models…
MUOT_3M: A 3 Million Frame Multimodal Underwater Benchmark and the MUTrack Tracking Method
Ahsan Baidar Bakht, Mohamad Alansari, Muhayy Ud Din +5
Underwater Object Tracking (UOT) is crucial for efficient marine robotics, large scale ecological monitoring, and ocean exploration; however, progress has been hindered by the scar…
LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs
Behzad Bozorgtabar, Dwarikanath Mahapatra, Sudipta Roy +3
Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging, but their reliability under domain shift hinges on calibrated uncertainty with guarantee…
EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning
Binzhu Xie, Shi Qiu, Sicheng Zhang +5
Robust 3D hand reconstruction in egocentric vision is challenging due to depth ambiguity, self-occlusion, and complex hand-object interactions. Prior methods mitigate these issues…
RedSage: A Cybersecurity Generalist LLM
Naufal Suryanto, Muzammal Naseer, Pengfei Li +5
Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks…
Rethinking Memory Design in SAM-Based Visual Object Tracking
Mohamad Alansari, Muzammal Naseer, Hasan Al Marzouqi +2
\noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2…
MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation
Syed Talal Wasim, Hamid Suleman, Olga Zatsarynna +2
We present MixANT, a novel architecture for stochastic long-term dense anticipation of human activities. While recent State Space Models (SSMs) like Mamba have shown promise throug…
CLDTracker: A Comprehensive Language Description for Visual Tracking
Mohamad Alansari, Sajid Javed, Iyyakutti Iyappan Ganapathi +2
VOT remains a fundamental yet challenging task in computer vision due to dynamic appearance changes, occlusions, and background clutter. Traditional trackers, relying primarily on…
DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation
Maregu Assefa, Muzammal Naseer, Iyyakutti Iyappan Ganapathi +3
Semi-supervised learning in medical image segmentation leverages unlabeled data to reduce annotation burdens through consistency learning. However, current methods struggle with cl…
STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection
Divya Velayudhan, Abdelfatah Ahmed, Mohamad Alansari +10
Advancements in Computer-Aided Screening (CAS) systems are essential for improving the detection of security threats in X-ray baggage scans. However, current datasets are limited i…
How Good is my Histopathology Vision-Language Foundation Model? A Holistic Benchmark
Roba Al Majzoub, Hashmat Malik, Muzammal Naseer +4
Recently, histopathology vision-language foundation models (VLMs) have gained popularity due to their enhanced performance and generalizability across different downstream tasks. H…
Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology
Hashmat Shadab Malik, Shahina Kunhimon, Muzammal Naseer +2
Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well st…