arXiv subjects

Anirban Mukhopadhyay

Publications and source records attributed to Anirban Mukhopadhyay.

At least 19 recordsLinked to original sources

arXiv2026

Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunities

Neural Cellular Automata (NCAs) are a new type of neural network architecture which enable accurate and robust inference at extremely small model sizes. Recently, NCAs have advanced to become interesting low-resource alternatives to convolution- and attention-based architectures for various tasks such as image analysis, synthetic image generation, and simulation. The rapid development and increased research interest necessitate a comprehensive review of the emerging technology. This review provides an overview of the fundamentals of NCAs, applications to medical imaging, as well as insights into the state of the art. We analyze recent modifications to the originally proposed NCA architecture with respect to their efficiency and accuracy. Furthermore, we review practical applications in real-world scenarios with a focus on medical image analysis, segmentation, classification, registration, depth estimation, and image synthesis. Finally, we identify several advantages of NCAs, research gaps, and conclude with an analysis of future opportunities for NCAs in medical applications in confined settings or areas that have particular demands for robustness or efficient data processing.

cs.CV↗

arXiv2026

Reversibility and its asymptotic counting in Picard group

We investigate reversible elements in the Picard modular group $\mathrm{PSL}(2,\mathbb{Z}[i])$. We show that reversibility coincides with strong reversibility for Kleinian groups, in particular for the Picard group. We classify reversible elements in the Picard group and characterize loxodromic reversible elements up to conjugacy. We prove that each such conjugacy class contains exactly eight special representatives. We also obtain asymptotic estimates for the number of reversible conjugacy classes with bounded trace.

math.GR↗

arXiv2026

Coarse to Fine: Iterative Adversarial Neural Cellular Automata for Medical Image Synthesis

Large-scale, publicly available datasets have driven advances in deep learning, but privacy and legal restrictions often limit data sharing in medical imaging. Synthetic data generation offers a privacy-friendly alternative to enable the training of high-performance models on health data. While most state-of-the-art generative models produce high-quality images, they remain computationally expensive, which limits their applicability on resource-constrained hardware. We propose StyleGANCA, the first lightweight general-purpose NCA-based generative adversarial network. The architecture integrates a StyleGAN-inspired mapping network and adaptive style modulation into a multi-scale NCA synthesis process, enabling latent-controlled image generation through iterative local interactions. We evaluate StyleGANCA on BloodMNIST and PathMNIST against adversarial, variational, diffusion, and NCA-based baselines. Experimental results demonstrate that StyleGANCA achieves competitive image quality with substantially fewer parameters than baseline architectures, achieving the best FID and KID scores on PathMNIST with only 617k parameters. Furthermore, downstream experiments show that the generated images preserve class-specific information and effectively support the training of multi-class classifiers. Our code is publicly available at: https://github.com/MECLabTUDA/StyleGANCA

cs.CV↗

arXiv2026

Sterilizable Scene Graph Generation for Operating Rooms

Scene graph generation from surgical video enables a holistic and structured understanding of surgical scenes by modeling objects and their semantic relationships. Despite recent advances, state-of-the-art approaches rely on large, parameter-heavy deep learning models that are impractical for deployment in the operating room (OR) due to hardware footprint, hygiene constraints, latency, and data privacy concerns. To the best of our knowledge, this is the first scene graph generation method built on NCAs and the first NCA framework capable of learning structured representations. We introduce SG-NCA, a lightweight scene graph generation framework based on Neural Cellular Automata (NCA), designed for inference in fanless devices critical for OR hygiene protocols. SG-NCA is the first scene graph generation combining NCA-based multiclass segmentation for efficient object detection and feature extraction with a lightweight relation predictor. We evaluate SG-NCA on videos of cataract surgery and cholecystectomy, demonstrating performance comparable to established baselines while requiring 55x fewer parameters. We showcase deployment on fanless edge devices better suited for the OR and demonstrate downstream applications such as surgical video captioning, highlighting SG-NCA's potential for affordable, privacy-preserving, and OR-ready intraoperative scene understanding.

cs.CV↗

arXiv2026

Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

Federated learning (FL) enables collaborative model training across distributed clients while keeping data local. A central challenge is determining which client updates are beneficial for aggregation with respect to each client's target domain. Existing methods typically address this problem in parameter space by comparing model parameters or gradients. However, parameter-space similarity can be a poor proxy for predictive behavior, especially under heterogeneous, non-IID data. Consequently, updates that are misaligned with a client's target domain, including those caused by heterogeneous data or malfunctioning clients, may degrade local model performance. We propose Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space. LIGHTYEAR uses an NTK-based agreement score to characterize predictive behavior and determine a personalized aggregation set for each client. By relating model parameters to local predictive responses, the Neural Tangent Kernel (NTK) provides a more expressive criterion for update selection than parameter-space similarity alone. Because function-space information is not available before aggregation in conventional centralized FL, LIGHTYEAR uses a peer-to-peer (P2P) topology in which clients exchange updates directly and evaluate incoming models on private validation data. Each client selects only updates that are beneficial for its own target domain and aggregates them using a regularized rule that improves stability under heterogeneity. Across five datasets and nine baseline methods, LIGHTYEAR consistently outperforms centralized FL baselines and existing P2P approaches.

cs.LG↗

arXiv2026

Group Equivariant Diffusion for Anomaly Detection in Computational Cytology

Computational cytology on whole-slide images is challenging because malignant cells are rare, heterogeneous, and annotated slides are scarce. Anomaly detection frameworks can be trained on normal slide-negative patches and then applied at test time to flag abnormal patches in held-out slides. Most unsupervised anomaly detection approaches including generative ones (GAN-based and diffusion-based), are tuned to organ-level imaging and require large curated datasets. In cytology the signal is cell-centric: rotating or flipping a single-cell patch does not change its diagnostic class, yet standard diffusion models treat transformed views as distinct inputs, leading to transformation-dependent reconstructions and unstable anomaly scores. We propose a D4-equivariant diffusion framework that enforces rotation and reflection symmetry both architecturally, via a D4-equivariant U-Net, and at inference, via equivariant noise coupling and (optionally) frame averaging. This alignment with biological invariance yields transformation-consistent pseudo-healthy reconstructions and more stable anomaly ranking under symmetry. On two publicly available cytology datasets of bone marrow and peripheral blood smears, our D4-equivariant diffusion models achieve higher AUC and retrieve more abnormal cells in the top K predictions than non-equivariant generative baselines, a deep one-class, and a multiple instance learning based method, while substantially reducing score variance across rotations and flips. Code is available at https://swchmida.github.io/D4diffCyto/.

cs.CV↗

arXiv2026

SWoMo: Neuro-Symbolic World Model for Cataract Surgery Simulation

Realistic surgical simulation plays a crucial role in training novice surgeons and in the development of autonomous agents. World models can scale such simulation environments to realistic and diverse procedures by predicting future patient states conditioned on current observations and surgical actions. However, current state-of-the-art approaches often fail to satisfy key criteria required for clinical applicability, including visual realism, physically grounded interactions, and the ability to simulate scenarios beyond the training distribution. Hence, we introduce SWoMo, a neuro-symbolic world model for cataract surgery simulation that decouples motion generation from visual realism. The symbolic component, consisting of a rule-based simulator and scene graph representations, models motion dynamics and tool-tissue interactions, while a diffusion model produces realistic visual appearance, including textures and tissue deformations. We propose an inverse pairing strategy that reconstructs real surgical videos in the simulator to obtain paired simulated and real videos, which are then used to train our video diffusion model for the reverse objective of sim-to-real translation. Our experiments show both qualitative and quantitative improvements over prior work. We demonstrate that our simulator further satisfies the key criteria, including generalisation to unseen interaction geometries, improvements in downstream phase detection, and unsupervised video style transfer. The code, data, and model weights are available at: https://ssharvienkumar.github.io/SWoMo/

cs.CV↗

arXiv2026

Dynamics of a Spin-Wave Active Ring Resonator Driven by Harmonic-Null Square-Wave and Unipolar 8-bit Walsh Code Modulations

Spin-wave active ring resonators (SWARRs) based on yttrium iron garnet (YIG) films exhibit rich nonlinear dynamics that make them promising platforms for physical reservoir computing. We present systematic and experimentally simple methods to characterize a SWARR's nonlinear behavior and memory. We first use a third harmonic elimination method to probe the nonlinear response. A drive frequency $f_\mathrm{d}$ is modulated by a square-wave pattern engineered to have a spectral null at $3/T$, which is then applied as input to the SWARR. The power spectra at the output of the YIG delay line allow us to identify five distinct regions within a drive frequency range of $2.15 < f_\text{d} < 2.2\ \text{GHz}$ where nonlinearity was observed as frequency peaks at $f_\mathrm{d} \pm \frac{3}{T}$. The STM duration of the SWARR was estimated to be approximately 300 ns using a modulation pattern derived from the sequency-ordered 8-bit unipolar Walsh family. The nonlinear dynamics of the SWARR were further quantified by decomposing its temporal response to analog Walsh pulses in terms of the input Walsh codewords. The proposed methods of harmonic elimination and Walsh-function decomposition together provide a practical and general framework for the design and optimization of tunable spin-wave reservoir computers.

physics.app-ph↗

arXiv2026

Exploring The Impact Of Proactive Generative AI Agent Roles In Time-Sensitive Collaborative Problem-Solving Tasks

Collaborative problem-solving under time pressure is common but difficult, as teams must generate ideas quickly, coordinate actions, and track progress. Generative AI offers new opportunities to assist, but we know little about how proactive agents affect the dynamics of real-time, co-located teamwork. We studied two forms of proactive support in digital escape rooms: a facilitator agent that offered summaries and group structures, and a peer agent that proposed ideas and answered queries. In a within-subjects study with 24 participants, we compared group performance and processes across three conditions: no AI, peer, and facilitator. Results show that the peer agent occasionally enhanced problem-solving by offering timely hints and memory support; however, it also disrupted flow, increased workload, and created over-reliance. In comparison, the facilitator agent provided light scaffolding but had a limited impact on outcomes. We provide design considerations for proactive generative AI agents based on our findings.

cs.HC↗

arXiv2025

Injection dynamics in spin-wave active ring oscillator (SWARO)

We investigated injection locking in spin-wave active ring oscillators (SWAROs) operating in the multi-mode regime. By applying external RF signals with varying frequency and power, we identified the locking behavior of individual modes and extracted the total locking ranges from spectral measurements. The results show asymmetric evolution of the lower and upper locking boundaries with drive power for the lower-frequency SWARO modes, while the highest-frequency mode exhibits nearly symmetric behavior. A maximum locking range of over 11 MHz is observed at a drive power of -10 dBm. To interpret these results, we develop an Adler-like model that captures the dependence of the locking range on drive power, showing good agreement for the higher-frequency modes. For the lowest-frequency mode, however, the model underestimates the locking range at low drive and saturates at high drive power levels, while the experimental range increases monotonically, indicating the influence of multi-mode interactions. These findings establish SWARO as a useful platform for exploring injection phenomena in spin-wave ring systems with delayed feedback and motivate the development of extended injection models that account for multi-mode dynamics.

physics.app-ph↗

arXiv2025

Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning

Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy by keeping data local. Traditional FL approaches rely on a centralized, star-shaped topology, where a central server aggregates model updates from clients. However, this architecture introduces several limitations, including a single point of failure, limited personalization, and poor robustness to distribution shifts or vulnerability to malfunctioning clients. Moreover, update selection in centralized FL often relies on low-level parameter differences, which can be unreliable when client data is not independent and identically distributed, and offer clients little control. In this work, we propose a decentralized, peer-to-peer (P2P) FL framework. It leverages the flexibility of the P2P topology to enable each client to identify and aggregate a personalized set of trustworthy and beneficial updates.This framework is the Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR). Central to our method is an agreement score, computed on a local validation set, which quantifies the semantic alignment of incoming updates in the function space with respect to the clients reference model. Each client uses this score to select a tailored subset of updates and performs aggregation with a regularization term that further stabilizes the training. Our empirical evaluation across five datasets shows that the proposed approach consistently outperforms both, centralized baselines and existing P2P methods in terms of client-level performance, particularly under adversarial and heterogeneous conditions.

cs.LG↗

arXiv2025

OctreeNCA: Single-Pass 184 MP Segmentation on Consumer Hardware

Medical applications demand segmentation of large inputs, like prostate MRIs, pathology slices, or videos of surgery. These inputs should ideally be inferred at once to provide the model with proper spatial or temporal context. When segmenting large inputs, the VRAM consumption of the GPU becomes the bottleneck. Architectures like UNets or Vision Transformers scale very poorly in VRAM consumption, resulting in patch- or frame-wise approaches that compromise global consistency and inference speed. The lightweight Neural Cellular Automaton (NCA) is a bio-inspired model that is by construction size-invariant. However, due to its local-only communication rules, it lacks global knowledge. We propose OctreeNCA by generalizing the neighborhood definition using an octree data structure. Our generalized neighborhood definition enables the efficient traversal of global knowledge. Since deep learning frameworks are mainly developed for large multi-layer networks, their implementation does not fully leverage the advantages of NCAs. We implement an NCA inference function in CUDA that further reduces VRAM demands and increases inference speed. Our OctreeNCA segments high-resolution images and videos quickly while occupying 90% less VRAM than a UNet during evaluation. This allows us to segment 184 Megapixel pathology slices or 1-minute surgical videos at once.

cs.CV↗

arXiv2025

ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning

Federated Learning (FL) allows the training of deep neural networks in a distributed and privacy-preserving manner. However, this concept suffers from malfunctioning updates sent by the attending clients that cause global model performance degradation. Reasons for this malfunctioning might be technical issues, disadvantageous training data, or malicious attacks. Most of the current defense mechanisms are meant to require impractical prerequisites like knowledge about the number of malfunctioning updates, which makes them unsuitable for real-world applications. To counteract these problems, we introduce a novel method called Angular Support for Malfunctioning Client Resilience (ASMR), that dynamically excludes malfunctioning clients based on their angular distance. Our novel method does not require any hyperparameters or knowledge about the number of malfunctioning clients. Our experiments showcase the detection capabilities of ASMR in an image classification task on a histopathological dataset, while also presenting findings on the significance of dynamically adapting decision boundaries.

cs.LG↗

arXiv2025

Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge

Deep learning models have achieved state-of-the-art performance in automated Cardiac Magnetic Resonance (CMR) analysis. However, the efficacy of these models is highly dependent on the availability of high-quality, artifact-free images. In clinical practice, CMR acquisitions are frequently degraded by respiratory motion, yet the robustness of deep learning models against such artifacts remains an underexplored problem. To promote research in this domain, we organized the MICCAI CMRxMotion challenge. We curated and publicly released a dataset of 320 CMR cine series from 40 healthy volunteers who performed specific breathing protocols to induce a controlled spectrum of motion artifacts. The challenge comprised two tasks: 1) automated image quality assessment to classify images based on motion severity, and 2) robust myocardial segmentation in the presence of motion artifacts. A total of 22 algorithms were submitted and evaluated on the two designated tasks. This paper presents a comprehensive overview of the challenge design and dataset, reports the evaluation results for the top-performing methods, and further investigates the impact of motion artifacts on five clinically relevant biomarkers. All resources and code are publicly available at: https://github.com/CMRxMotion

eess.IV↗

arXiv2025

Equitable Federated Learning with NCA

Federated Learning (FL) is enabling collaborative model training across institutions without sharing sensitive patient data. This approach is particularly valuable in low- and middle-income countries (LMICs), where access to trained medical professionals is limited. However, FL adoption in LMICs faces significant barriers, including limited high-performance computing resources and unreliable internet connectivity. To address these challenges, we introduce FedNCA, a novel FL system tailored for medical image segmentation tasks. FedNCA leverages the lightweight Med-NCA architecture, enabling training on low-cost edge devices, such as widely available smartphones, while minimizing communication costs. Additionally, our encryption-ready FedNCA proves to be suitable for compromised network communication. By overcoming infrastructural and security challenges, FedNCA paves the way for inclusive, efficient, lightweight, and encryption-ready medical imaging solutions, fostering equitable healthcare advancements in resource-constrained regions.

cs.CV↗

arXiv2025

SG2VID: Scene Graphs Enable Fine-Grained Control for Video Synthesis

Surgical simulation plays a pivotal role in training novice surgeons, accelerating their learning curve and reducing intra-operative errors. However, conventional simulation tools fall short in providing the necessary photorealism and the variability of human anatomy. In response, current methods are shifting towards generative model-based simulators. Yet, these approaches primarily focus on using increasingly complex conditioning for precise synthesis while neglecting the fine-grained human control aspect. To address this gap, we introduce SG2VID, the first diffusion-based video model that leverages Scene Graphs for both precise video synthesis and fine-grained human control. We demonstrate SG2VID's capabilities across three public datasets featuring cataract and cholecystectomy surgery. While SG2VID outperforms previous methods both qualitatively and quantitatively, it also enables precise synthesis, providing accurate control over tool and anatomy's size and movement, entrance of new tools, as well as the overall scene layout. We qualitatively motivate how SG2VID can be used for generative augmentation and present an experiment demonstrating its ability to improve a downstream phase detection task when the training set is extended with our synthetic videos. Finally, to showcase SG2VID's ability to retain human control, we interact with the Scene Graphs to generate new video samples depicting major yet rare intra-operative irregularities.

cs.CV↗

arXiv2025

eNCApsulate: NCA for Precision Diagnosis on Capsule Endoscopes

Wireless Capsule Endoscopy is a non-invasive imaging method for the entire gastrointestinal tract, and is a pain-free alternative to traditional endoscopy. It generates extensive video data that requires significant review time, and localizing the capsule after ingestion is a challenge. Techniques like bleeding detection and depth estimation can help with localization of pathologies, but deep learning models are typically too large to run directly on the capsule. Neural Cellular Automata (NCA) for bleeding segmentation and depth estimation are trained on capsule endoscopic images. For monocular depth estimation, we distill a large foundation model into the lean NCA architecture, by treating the outputs of the foundation model as pseudo ground truth. We then port the trained NCA to the ESP32 microcontroller, enabling efficient image processing on hardware as small as a camera capsule. NCA are more accurate (Dice) than other portable segmentation models, while requiring more than 100x fewer parameters stored in memory than other small-scale models. The visual results of NCA depth estimation look convincing, and in some cases beat the realism and detail of the pseudo ground truth. Runtime optimizations on the ESP32-S3 accelerate the average inference speed significantly, by more than factor 3. With several algorithmic adjustments and distillation, it is possible to eNCApsulate NCA models into microcontrollers that fit into wireless capsule endoscopes. This is the first work that enables reliable bleeding segmentation and depth estimation on a miniaturized device, paving the way for precise diagnosis combined with visual odometry as a means of precise localization of the capsule -- on the capsule.

cs.CV↗

arXiv2025

Improved Compact Genetic Algorithms with Efficient Caching

Compact Genetic Algorithms (cGAs) are condensed variants of classical Genetic Algorithms (GAs) that use a probability vector representation of the population instead of the complete population. cGAs have been shown to significantly reduce the number of function evaluations required while producing outcomes similar to those of classical GAs. However, cGAs have a tendency to repeatedly generate the same chromosomes as they approach convergence, resulting in unnecessary evaluations of identical chromosomes. This article introduces the concept of caching in cGAs as a means of avoiding redundant evaluations of the same chromosomes. Our proposed approach operates equivalently to cGAs, but enhances the algorithm's time efficiency by reducing the number of function evaluations. We also present a data structure for efficient cache maintenance to ensure low overhead. The proposed caching approach has an asymptotically constant time complexity on average. The proposed method further generalizes the caching mechanism with higher selection pressure for elitism-based cGAs. We conduct a rigorous analysis based on experiments on benchmark optimization problems using two well-known cache replacement strategies. The results demonstrate that caching significantly reduces the number of function evaluations required while maintaining the same level of performance accuracy.

cs.NE↗