arXiv subjects

Puneet Sharma

Publications and source records attributed to Puneet Sharma.

At least 19 recordsLinked to original sources

arXiv2026

CMRVision: A Foundation Model for Cardiac MR Image Analysis

Cardiac magnetic resonance (CMR) imaging provides complementary information on cardiac anatomy, function, and tissue characterization across multiple sequences and views. In this work, we investigate foundation model pretraining for 2D CMR and introduce CMRVision, a CMR-specific foundation model trained using DINOv3-style self-supervised learning on a multi-center, multi-sequence cohort of 36 million CMR images. We systematically evaluate architectural and training design choices for domain-specific pretraining. CMRVision is evaluated on two downstream tasks: multi-task segmentation across cine, late gadolinium enhancement (LGE), and mapping sequences, and cine view classification. Our experiments show that CMR-specific pretraining, smaller patch sizes, and patch-level objectives consistently improve downstream performance. Across a multi-task segmentation benchmark, CMRVision achieved the strongest overall performance, outperforming prior natural-image (NI), medical-image, supervised, and CMR foundation model baselines. Improvements were modest but consistent across structures and sequences, with Dice scores ranging from 0.940-0.967 for LV and 0.855-0.905 for myocardium, and reaching 0.929 for RV, 0.920 for LA, and 0.931 for RA. The largest gains were observed for myocardium segmentation in LGE and mapping images. In a zero-shot segmentation task on unseen LGE long-axis views, the model achieved an average Dice score of 0.692, demonstrating cross-view generalization. For cine view classification, CMRVision achieved the highest average accuracy (0.906), compared to prior methods reported in the literature. These results highlight the potential of CMRVision to support robust and generalizable cardiac MRI analysis across multiple sequences and views.

cs.CV↗

arXiv2026

MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI

Cardiac magnetic resonance imaging (CMR) produces rich sequential data such as temporal cine videos and spatial LGE/mapping stacks, yet most deep learning approaches process individual 2D slices, discarding this context. We present MR-JEPA, a self-supervised video foundation model for CMR that extends LeJEPA to 3D spatiotemporal inputs through tubelet tokenization, spatiotemporal masking augmentation, and initialization from a 2D CMR foundation model. Unlike prior CMR video models limited to cine data, MR-JEPA is pretrained on multi-sequence data (cine, LGE, mapping) from 10,505 patients across two centers without annotations. We evaluate the frozen encoder on six downstream tasks using a unified multi-view gated attention architecture: LV ejection fraction, RV ejection fraction, three myocardial strains (GLS, GCS, GRS), and four-class disease detection. MR-JEPA outperforms other compared methods on all five regression tasks, including both a domain-specific CMR model pretrained on more data with text supervision and a natural-video foundation model, achieving an LV EF MAE of 4.79% (r =0.764) and a GLS MAE of 1.87 (r=0.805), with 21-27% MAE reductions over baselines on strain tasks. For disease detection, MR-JEPA achieved a macro AUG of 0.868, remaining competitive with the domain-specific baseline despite using a fully self-supervised pretraining objective. These results demonstrate the potential of a unified video encoder for robust, multi-view utilization of diverse CMR sequences in clinical cardiac quantification and diagnosis.

cs.CV↗

arXiv2026

Proximal Relations in Asymptotically Commutative Non-Autonomous Dynamical Systems

In this paper, we investigate various forms of proximal relations for non-autonomous dynamical systems. In particular, we introduce the notion of pointwise asymptotic commutativity and asymptotic commutativity, and show that these are strictly weaker than classical commutativity. We establish conditions under which different proximal relations, including proximality, syndetic proximality, and regional proximality, exhibit invariance and structural properties. In particular, we relate proximality with equicontinuity and weak mixing, and characterize conditions where proximal relations become trivial or maximal. Further, for systems generated by uniformly and strongly convergent sequences, we derive connections between proximal pairs of the system, its product systems, and the corresponding limiting system. Several examples are provided to demonstrate the necessity of the assumptions and the sharpness of the results.

math.DS↗

arXiv2026

A Unified Model for Highly Accurate ECG-Free Dynamic Coronary Roadmapping Using Spatio-Temporal Transformers

Percutaneous Coronary Intervention (PCI) is a minimally invasive procedure used to restore coronary blood flow obstructed by atherosclerotic plaque. During PCI, repeated injections of iodine-based contrast agents are required to visualize the coronary arteries and guide interventional devices. However, frequent contrast injections increase radiation exposure and the risk of contrast-induced nephropathy, with acute kidney injury reported in up to 30% of patients with renal impairment. Dynamic Coronary Roadmapping (DRM) reduces these risks by overlaying a precomputed angiographic vessel map onto live fluoroscopy and continuously updating it throughout the procedure. Accurate DRM relies on precise cardiac phase matching between angiography and fluoroscopy, together with reliable catheter tip tracking for motion compensation. These tasks remain challenging in ECG-free settings and when only limited manual annotations are available. We present a unified DRM framework that simultaneously performs cardiac phase matching and catheter tip tracking for accurate real-time guidance. Our method employs a large-scale spatio-temporal encoder pretrained on 16 million X-ray frames to learn cardiac motion dynamics. To the best of our knowledge, this is the first application of large-scale spatio-temporal pretraining for motion compensation in DRM. We further introduce auxiliary tasks based on ECG R-peak detection and catheter tip tracking, improving optimization while eliminating the need for extensive catheter mask annotations. Finally, a majority-voting postprocessing strategy aggregates temporal predictions, improving robustness and providing a confidence score that correlates with phase-matching error. Comprehensive evaluation on clinical X-ray datasets demonstrates state-of-the-art performance, achieving low temporal misalignment and robust phase-matching accuracy suitable for real-time DRM.

eess.IV↗

arXiv2026

MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces

The fast pace of artificial intelligence~(AI) innovation demands an agile methodology for observation, reproduction and optimization of distributed machine learning~(ML) workload behavior in production AI systems and enables efficient software-hardware~(SW-HW) co-design for future systems. We present Chakra, an open and portable ecosystem for performance benchmarking and co-design. The core component of Chakra is an open and interoperable graph-based representation of distributed AI/ML workloads, called Chakra execution trace~(ET). These ETs represent key operations, such as compute, memory, and communication, data and control dependencies, timing, and resource constraints. Additionally, Chakra includes a complementary set of tools and capabilities to enable the collection, analysis, generation, and adoption of Chakra ETs by a broad range of simulators, emulators, and replay tools. We present analysis of Chakra ETs collected on production AI clusters and demonstrate value via real-world case studies. Chakra has been adopted by MLCommons and has active contributions and engagement across the industry, including but not limited to NVIDIA, AMD, Meta, Keysight, HPE, and Scala, to name a few.

cs.DC↗

arXiv2026

LGESynthNet: Controlled Scar Synthesis for Improved Scar Segmentation in Cardiac LGE-MRI Imaging

Segmentation of enhancement in LGE cardiac MRI is critical for diagnosing various ischemic and non-ischemic cardiomyopathies. However, creating pixel-level annotations for these images is challenging and labor-intensive, leading to limited availability of annotated data. Generative models, particularly diffusion models, offer promise for synthetic data generation, yet many rely on large training datasets and often struggle with fine-grained conditioning control, especially for small or localized features. We introduce LGESynthNet, a latent diffusion-based framework for controllable enhancement synthesis, enabling explicit control over size, location, and transmural extent. Formulated as inpainting using a ControlNet-based architecture, the model integrates: (a) a reward model for conditioning-specific supervision, (b) a captioning module for anatomically descriptive text prompts, and (c) a biomedical text encoder. Trained on just 429 images (79 patients), it produces realistic, anatomically coherent samples. A quality control filter selects outputs with high conditioning-fidelity, which when used for training augmentation, improve downstream segmentation and detection performance, by up-to 6 and 20 points respectively.

cs.AI↗

arXiv2026

Resilience Meets Autonomy: Governing Embodied AI in Critical Infrastructure

Critical infrastructure increasingly incorporates embodied AI for monitoring, predictive maintenance, and decision support. However, AI systems designed to handle statistically representable uncertainty struggle with cascading failures and crisis dynamics that exceed their training assumptions. This paper argues that Embodied AIs resilience depends on bounded autonomy within a hybrid governance architecture. We outline four oversight modes and map them to critical infrastructure sectors based on task complexity, risk level, and consequence severity. Drawing on the EU AI Act, ISO safety standards, and crisis management research, we argue that effective governance requires a structured allocation of machine capability and human judgement.

cs.AI↗

arXiv2026

Hippocampus: An Efficient and Scalable Memory Module for Agentic AI

Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency and poor storage scalability. We introduce Hippocampus, an agentic memory management system that uses compact binary signatures for semantic search and lossless token-ID streams for exact content reconstruction. Its core is a Dynamic Wavelet Matrix (DWM) that compresses and co-indexes both streams to support ultra-fast search in the compressed domain, thus avoiding costly dense-vector or graph computations. This design scales linearly with memory size, making it suitable for long-horizon agentic deployments. Empirically, our evaluation shows that Hippocampus reduces end-to-end retrieval latency by up to 31$\times$ and cuts per-query token footprint by up to 14$\times$, while maintaining accuracy on both LoCoMo and LongMemEval benchmarks.

cs.AI↗

arXiv2026

Using Multi-Instance Learning to Identify Unique Polyps in Colon Capsule Endoscopy Images

Identifying unique polyps in colon capsule endoscopy (CCE) images is a critical yet challenging task for medical personnel due to the large volume of images, the cognitive load it creates for clinicians, and the ambiguity in labeling specific frames. This paper formulates this problem as a multi-instance learning (MIL) task, where a query polyp image is compared with a target bag of images to determine uniqueness. We employ a multi-instance verification (MIV) framework that incorporates attention mechanisms, such as variance-excited multi-head attention (VEMA) and distance-based attention (DBA), to enhance the model's ability to extract meaningful representations. Additionally, we investigate the impact of self-supervised learning using SimCLR to generate robust embeddings. Experimental results on a dataset of 1912 polyps from 754 patients demonstrate that attention mechanisms significantly improve performance, with DBA L1 achieving the highest test accuracy of 86.26\% and a test AUC of 0.928 using a ConvNeXt backbone with SimCLR pretraining. This study underscores the potential of MIL and self-supervised learning in advancing automated analysis of Colon Capsule Endoscopy images, with implications for broader medical imaging applications.

cs.CV↗

arXiv2026

Using deep learning for predicting cleansing quality of colon capsule endoscopy images

In this study, we explore the application of deep learning techniques for predicting cleansing quality in colon capsule endoscopy (CCE) images. Using a dataset of 500 images labeled by 14 clinicians on the Leighton-Rex scale (Poor, Fair, Good, and Excellent), a ResNet-18 model was trained for classification, leveraging stratified K-fold cross-validation to ensure robust performance. To optimize the model, structured pruning techniques were applied iteratively, achieving significant sparsity while maintaining high accuracy. Explainability of the pruned model was evaluated using Grad-CAM, Grad-CAM++, Eigen-CAM, Ablation-CAM, and Random-CAM, with the ROAD method employed for consistent evaluation. Our results indicate that for a pruned model, we can achieve a cross-validation accuracy of 88% with 79% sparsity, demonstrating the effectiveness of pruning in improving efficiency from 84% without compromising performance. We also highlight the challenges of evaluating cleansing quality of CCE images, emphasize the importance of explainability in clinical applications, and discuss the challenges associated with using the ROAD method for our task. Finally, we employ a variant of adaptive temperature scaling to calibrate the pruned models for an external dataset.

cs.CV↗

arXiv2025

EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography

Echocardiography is the most widely used imaging modality in cardiology, yet its interpretation remains labor-intensive and inherently multimodal, requiring view recognition, quantitative measurements, qualitative assessments, and guideline-based reasoning. While recent vision-language models (VLMs) have achieved broad success in natural images and certain medical domains, their potential in echocardiography has been limited by the lack of large-scale, clinically grounded image-text datasets and the absence of measurement-based reasoning central to echo interpretation. We introduce EchoGround-MIMIC, the first measurement-grounded multimodal echocardiography dataset, comprising 19,065 image-text pairs from 1,572 patients with standardized views, structured measurements, measurement-grounded captions, and guideline-derived disease labels. Building on this resource, we propose EchoVLM, a vision-language model that incorporates two novel pretraining objectives: (i) a view-informed contrastive loss that encodes the view-dependent structure of echocardiographic imaging, and (ii) a negation-aware contrastive loss that distinguishes clinically critical negative from positive findings. Across five types of clinical applications with 36 tasks spanning multimodal disease classification, image-text retrieval, view classification, chamber segmentation, and landmark detection, EchoVLM achieves state-of-the-art performance (86.5% AUC in zero-shot disease classification and 95.1% accuracy in view classification). We demonstrate that clinically grounded multimodal pretraining yields transferable visual representations and establish EchoVLM as a foundation model for end-to-end echocardiography interpretation. We will release EchoGround-MIMIC and the data curation code, enabling reproducibility and further research in multimodal echocardiography interpretation.

cs.CV↗

arXiv2025

A Unified AI Approach for Continuous Monitoring of Human Health and Diseases from Intensive Care Unit to Home with Physiological Foundation Models (UNIPHY+)

We present UNIPHY+, a unified physiological foundation model (physioFM) framework designed to enable continuous human health and diseases monitoring across care settings using ubiquitously obtainable physiological data. We propose novel strategies for incorporating contextual information during pretraining, fine-tuning, and lightweight model personalization via multi-modal learning, feature fusion-tuning, and knowledge distillation. We advocate testing UNIPHY+ with a broad set of use cases from intensive care to ambulatory monitoring in order to demonstrate that UNIPHY+ can empower generalizable, scalable, and personalized physiological AI to support both clinical decision-making and long-term health monitoring.

cs.AI↗

arXiv2025

Dynamics of Enveloping Semigroup of Flows

In this article, we relate the dynamics of a flow $(X, T)$ with the dynamics of the induced flow $(E(X), T)$ where $E(X)$ is the enveloping semigroup of flow $(X, T)$. We establish that a flow $(X, T)$ is distal if and only if the induced flow is also distal. We prove that while the induced flow on the enveloping semigroup of an equicontinuous flow is equicontinuous, the converse holds when $(X, T)$ is point transitive. We prove that for any flow $(X,T)$, $(E(X),T)$ is isomorphic to $(E(E(X)),T)$. We show that if a distal flow contains a minimal sensitive subsystem, the induced flow on the enveloping semigroup is also sensitive. We relate various forms of rigidity for a flow with rigidity for the induced flow. We also establish that for any proximal flow $(X, T)$, if T is abelian then the induced flow $(E(X),T)$ is also proximal.

math.DS↗

arXiv2025

Palladium: A DPU-enabled Multi-Tenant Serverless Cloud over Zero-copy Multi-node RDMA Fabrics

Serverless computing promises enhanced resource efficiency and lower user costs, yet is burdened by a heavyweight, CPU-bound data plane. Prior efforts exploiting shared memory reduce overhead locally but fall short when scaling across nodes. Furthermore, serverless environments can have unpredictable and large-scale multi-tenancy, leading to contention for shared network resources. We present Palladium, a DPU-centric serverless data plane that reduces the CPU burden and enables efficient, zero-copy communication in multi-tenant serverless clouds. Despite the limited general-purpose processing capability of the DPU cores, Palladium strategically exploits the DPU's potential by (1) offloading data transmission to high-performance NIC cores via RDMA, combined with intra-node shared memory to eliminate data copies across nodes, and (2) enabling cross-processor (CPU-DPU) shared memory to eliminate redundant data movement, which overwhelms wimpy DPU cores. At the core of Palladium is the DPU-enabled network engine (DNE) -- a lightweight reverse proxy that isolates RDMA resources from tenant functions, orchestrates inter-node RDMA flows, and enforces fairness under contention. To further reduce CPU involvement, Palladium performs early HTTP/TCP-to-RDMA transport conversion at the cloud ingress, bridging the protocol mismatch before client traffic enters the RDMA fabric, thus avoiding costly protocol translation along the critical path. We show that careful selection of RDMA primitives (i.e., two-sided instead of one-sided) significantly affects the zero-copy data plane. Our preliminary experimental results show that enabling DPU offloading in Palladium improves RPS by 20.9x. The latency is reduced by a factor of 21x in the best case, all the while saving up to 7 CPU cores, and only consuming two wimpy DPU cores.

cs.NI↗

arXiv2025

Towards Easy and Realistic Network Infrastructure Testing for Large-scale Machine Learning

This paper lays the foundation for Genie, a testing framework that captures the impact of real hardware network behavior on ML workload performance, without requiring expensive GPUs. Genie uses CPU-initiated traffic over a hardware testbed to emulate GPU to GPU communication, and adapts the ASTRA-sim simulator to model interaction between the network and the ML workload.

cs.NI↗

arXiv2025

Fake It Till You Make It: Using Synthetic Data and Domain Knowledge for Improved Text-Based Learning for LGE Detection

Detection of hyperenhancement from cardiac LGE MRI images is a complex task requiring significant clinical expertise. Although deep learning-based models have shown promising results for the task, they require large amounts of data with fine-grained annotations. Clinical reports generated for cardiac MR studies contain rich, clinically relevant information, including the location, extent and etiology of any scars present. Although recently developed CLIP-based training enables pretraining models with image-text pairs, it requires large amounts of data and further finetuning strategies on downstream tasks. In this study, we use various strategies rooted in domain knowledge to train a model for LGE detection solely using text from clinical reports, on a relatively small clinical cohort of 965 patients. We improve performance through the use of synthetic data augmentation, by systematically creating scar images and associated text. In addition, we standardize the orientation of the images in an anatomy-informed way to enable better alignment of spatial and text features. We also use a captioning loss to enable fine-grained supervision and explore the effect of pretraining of the vision encoder on performance. Finally, ablation studies are carried out to elucidate the contributions of each design component to the overall performance of the model.

cs.CV↗

arXiv2025

A Novel Tracking Framework for Devices in X-ray Leveraging Supplementary Cue-Driven Self-Supervised Features

To restore proper blood flow in blocked coronary arteries via angioplasty procedure, accurate placement of devices such as catheters, balloons, and stents under live fluoroscopy or diagnostic angiography is crucial. Identified balloon markers help in enhancing stent visibility in X-ray sequences, while the catheter tip aids in precise navigation and co-registering vessel structures, reducing the need for contrast in angiography. However, accurate detection of these devices in interventional X-ray sequences faces significant challenges, particularly due to occlusions from contrasted vessels and other devices and distractions from surrounding, resulting in the failure to track such small objects. While most tracking methods rely on spatial correlation of past and current appearance, they often lack strong motion comprehension essential for navigating through these challenging conditions, and fail to effectively detect multiple instances in the scene. To overcome these limitations, we propose a self-supervised learning approach that enhances its spatio-temporal understanding by incorporating supplementary cues and learning across multiple representation spaces on a large dataset. Followed by that, we introduce a generic real-time tracking framework that effectively leverages the pretrained spatio-temporal network and also takes the historical appearance and trajectory data into account. This results in enhanced localization of multiple instances of device landmarks. Our method outperforms state-of-the-art methods in interventional X-ray device tracking, especially stability and robustness, achieving an 87% reduction in max error for balloon marker detection and a 61% reduction in max error for catheter tip detection.

cs.CV↗

arXiv2024

EchoApex: A General-Purpose Vision Foundation Model for Echocardiography

Quantitative evaluation of echocardiography is essential for precise assessment of cardiac condition, monitoring disease progression, and guiding treatment decisions. The diverse nature of echo images, including variations in probe types, manufacturers, and pathologies, poses challenges for developing artificial intelligent models that can generalize across different clinical practice. We introduce EchoApex, the first general-purpose vision foundation model echocardiography with applications on a variety of clinical practice. Leveraging self-supervised learning, EchoApex is pretrained on over 20 million echo images from 11 clinical centres. By incorporating task-specific decoders and adapter modules, we demonstrate the effectiveness of EchoApex on 4 different kind of clinical applications with 28 sub-tasks, including view classification, interactive structure segmentation, left ventricle hypertrophy detection and automated ejection fraction estimation from view sequences. Compared to state-of-the-art task-specific models, EchoApex attains improved performance with a unified image encoding architecture, demonstrating the benefits of model pretraining at scale with in-domain data. Furthermore, EchoApex illustrates the potential for developing a general-purpose vision foundation model tailored specifically for echocardiography, capable of addressing a diverse range of clinical applications with high efficiency and efficacy.

cs.CV↗