Large Language Models (LLMs) and Vision-Language Models (VLMs) remain highly vulnerable to adversarial attacks despite widespread adoption. Existing defenses typically require retraining, rely on heuristics, or fail under adaptive and out-of-distribution (OOD) conditions. We introduce EigenShield, a principled, inference-time, architecture-agnostic defense that leverages Random Matrix Theory (RMT) to suppress adversarial noise in high-dimensional embeddings. EigenShield uses spiked covariance modeling and a Robustness-based Nonconformity Score (RbNS) with quantile thresholding to isolate and preserve causal eigenvectors, filtering out adversarial components without model access or adversarial training. We develop a theoretical framework establishing conditions for asymptotic noise suppression and demonstrate effectiveness in both unimodal and multimodal settings. Empirically, EigenShield consistently improves robustness across threat models, reducing attack success rates (ASR) by up to 48% over state-of-the-art defenses, including adversarial training, UNIGUARD, CIDER, and input transformations. On jailbreak attacks, EigenShield lowers LLM ASR by up to 92.9% relative to undefended models. Under multimodal adversarial attacks, it reduces VLM ASR by up to 76.5%. Against adaptive attacks on LLMs, it achieves ASR reductions of up to 77.7%. In OOD settings, EigenShield maintains strong performance, reducing ASR by up to 88.4% for LLMs and 80.4% for VLMs.

Large Language Model (LLM) agents are now widely deployed in Ambient Intelligence (AmI) environments, where autonomous agents must sense, act, and coordinate at scale. As agent capabilities and interdependence increase, traditional reliability strategies such as isolated adaptive control, anomaly detection, or trust modeling have proven inadequate due to their fragmented and scenario-specific nature. Comprehensive architectures that enable integrated self-management, collective anomaly response, robust information dissemination, and privacy-preserving adaptation remain scarce. We propose a bio-autonomic framework for decentralized resilience in multi-agent LLM systems where a unified architecture systematically applies principles from biological autonomic systems to LLM-based multi-agent environments. Specifically, each agent implements an autonomic control loop, formally structured as Monitor-Analyze-Plan-Execute over a shared Knowledge base (MAPE-K), for self-regulation. At the system level, the framework integrates immune-inspired anomaly detection using the Dendritic Cell Algorithm, probabilistic computational trust, decentralized gossip for robust information sharing, and federated learning with homomorphic encryption for collaborative, privacy-preserving adaptation. This holistic approach enables LLM agent ecosystems to self-organize, detect and isolate faults, and collectively adapt as system complexity increases. Empirical evaluations show that our framework achieves substantially improved resilience and recovery compared to state-of-the-art multi-agent baselines.

Multi-objective optimization of analog circuits is hindered by high-dimensional parameter spaces, strong feedback couplings, and expensive transistor-level simulations. Evolutionary algorithms such as Non-dominated Sorting Genetic Algorithm II (NSGA-II) are widely used but treat all parameters equally, thereby wasting effort on variables with little impact on performance, which limits their scalability. We introduce CaDRO, a causal-guided dimensionality reduction framework that embeds causal discovery into the optimization pipeline. CaDRO builds a quantitative causal map through a hybrid observational-interventional process, ranking parameters by their causal effect on the objectives. Low-impact parameters are fixed to values from high-quality solutions, while critical drivers remain active in the search. The reduced design space enables focused evolutionary optimization without modifying the underlying algorithm. Across amplifiers, regulators, and RF circuits, CaDRO converges up to 10× faster than NSGA-II while preserving or improving Pareto quality. For instance, on the Folded-Cascode Amplifier, hypervolume improves from 0.56 to 0.94, and on the LDO regulator from 0.65 to 0.81, with large gains in non-dominated solutions.

Autonomous edge computing in robotics, smart cities, and autonomous vehicles relies on the seamless integration of sensing, processing, and actuation for real-time decision-making in dynamic environments. At its core is the sensing-to-action loop, which iteratively aligns sensor inputs with computational models to drive adaptive control strategies. These loops can adapt to hyper-local conditions, enhancing resource efficiency and responsiveness, but also face challenges such as resource constraints, synchronization delays in multimodal data fusion, and the risk of cascading errors in feedback loops. This article explores how proactive, context-aware sensing-to-action and action-to-sensing adaptations can enhance efficiency by dynamically adjusting sensing and computation based on task demands, such as sensing a very limited part of the environment and predicting the rest. By guiding sensing through control actions, action-to-sensing pathways can improve task relevance and resource use, but they also require robust monitoring to prevent cascading errors and maintain reliability. Multi-agent sensing-action loops further extend these capabilities through coordinated sensing and actions across distributed agents, optimizing resource use via collaboration. Additionally, neuromorphic computing, inspired by biological systems, provides an efficient framework for spike-based, event-driven processing that conserves energy, reduces latency, and supports hierarchical control-making it ideal for multi-agent optimization. This article highlights the importance of end-to-end co-design strategies that align algorithmic models with hardware and environmental dynamics, improve cross-layer inter-dependencies to improve throughput, precision, and adaptability for energy-efficient edge autonomy in complex environments.

Adversarial attacks exploit vulnerabilities in a model's decision boundaries through small, carefully crafted perturbations that lead to significant mispredictions. In 3D vision, the high dimensionality and sparsity of data greatly expand the attack surface, making 3D vision particularly vulnerable for safety-critical robotics. To enhance 3D vision's adversarial robustness, we propose a training objective that simultaneously minimizes prediction loss and mutual information (MI) under adversarial perturbations to contain the upper bound of misprediction errors. This approach simplifies handling adversarial examples compared to conventional methods, which require explicit searching and training on adversarial samples. However, minimizing prediction loss conflicts with minimizing MI, leading to reduced robustness and catastrophic forgetting. To address this, we integrate curriculum advisors in the training setup that gradually introduce adversarial objectives to balance training and prevent models from being overwhelmed by difficult cases early in the process. The advisors also enhance robustness by encouraging training on diverse MI examples through entropy regularizers. We evaluated our method on ModelNet40 and KITTI using PointNet, DGCNN, SECOND, and PointTransformers, achieving 2-5% accuracy gains on ModelNet40 and a 5-10% mAP improvement in object detection. Our code is publicly available at https://github.com/nstrndrbi/Mine-N-Learn.

We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional space. By leveraging principal component analysis (PCA), we identify a compact subspace of the training data. Optimizing prompts in this lower-dimensional space enhances training efficiency, as it focuses updates on the most relevant features while reducing computational overhead. Furthermore, since the model’s internal structure remains unaltered, the extensive knowledge gained from pretraining is fully preserved, ensuring that previously learned information is not compromised during adaptation. Our method achieves high knowledge retention in both task-incremental and domain-incremental continual learning setups while fine-tuning only 0.04% of the model’s parameters. Additionally, by integrating LoRA, we enhance adaptability to computational constraints, allowing for a tradeoff between accuracy and training cost. Experiments on the SuperGLUE benchmark demonstrate that our PCA-based prompt tuning combined with LoRA maintains full knowledge retention while improving accuracy, utilizing only 1% of the model’s parameters. These results establish our approach as a scalable and resource-efficient solution for continual learning in LLMs.

We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weights and activations while reserving high precision paths for targeted error compensation. This separation allows for distinct optimization of each precision level, thereby reducing memory and computation demands without compromising model accuracy. In the discussed approach, a floating-point model can be trained in the cloud and then downloaded to an edge device, where network weights and activations are directly quantized to meet the edge devices’ desired level (such as NF4/INT8). To address accuracy loss from quantization, surrogate paths are introduced, leveraging low-rank approximations on a layer-by-layer basis. These paths are trained with a sensitivity-based metric on minimal training data to recover accuracy loss under quantization as well as due to process variability such as when the main prediction path is implemented using analog acceleration. Our simulation results show that neural precision polarization enables ~464 TOPS/W MAC efficiency and reliability by integrating rank-8 error recovery paths with highly efficient, though potentially unreliable, bitplane-wise compute-in-memory processing.

Most scientific discoveries depend on identifying novel signals hidden in massive, noisy datasets generated by modern experiments. Traditional novelty detection methods are often insufficient in speed, robustness, and adaptability to resource-constrained environments. We discuss a perspective on a hierarchical framework for multi-level novelty detection spanning sensor signals, feature representations, and model outputs. At the signal level, we discuss analog circuits that extract statistical densities and moments in real-time, enabling interpretable and energy-efficient filtering. At the feature level, we introduce Likelihood Regret, an unsupervised measure that detects anomalies by retraining generative models on shared latent representations, with optimizations for embedded deployment. At the output level, we leverage predictive uncertainty, applying both compute-efficient Monte Carlo reuse and Monte Carlo-free techniques like evidential learning and conformal inference. Our framework demonstrates how integrating novelty detection across the sensing-to-inference can accelerate insights in domains such as high-energy physics.

Compute-in-Memory (CiM) architectures, particularly those leveraging SRAM-based arrays, present significant opportunities for accelerating deep learning by mitigating data movement bottlenecks in traditional von Neumann systems. SRAM-based CiM offers notable advantages, including speed, seamless CMOS integration, and compatibility with existing System-on-Chip (SoC) designs. However, challenges persist, primarily stemming from analog-domain computations that necessitate analog-to-digital (A/D) and digital-to-analog (D/A) conversions, leading to reduced accuracy, increased power overhead, and rigid operational constraints. To overcome these limitations, we propose MOSAIC, a novel CiM architecture designed around three foundational principles: (1) co-designing deep learning operators for CiM such as employing multiplication-free computations and frequency-domain processing to minimize/eliminate DAC/ADC overheads; (2) leveraging a memory-immersed digitization approach that utilizes parasitic bit-lines as capacitive DACs within CiM arrays, thereby significantly reducing peripheral complexity and enhancing scalability; and (3) orchestrating inference over a network of compact CiM µArrays by dynamically interconnecting them to provide flexibility, efficiency, and minimized computational overhead for varied inference workload characteristics. Collectively with these fundamental innovations, MOSAIC addresses critical bottlenecks in accuracy, scalability, and flexibility, unlocking CiM’s full potential for efficient deep learning in embedded systems.

This paper addresses the challenging problem of energy-efficient and uncertainty-aware pose estimation in insect-scale drones, which is crucial for tasks such as surveillance in constricted spaces and for enabling non-intrusive spatial intelligence in smart homes. Since tiny drones operate in highly dynamic environments, where factors like lighting and human movement impact their predictive accuracy, it is crucial to deploy uncertainty-aware prediction algorithms that can account for environmental variations and express not only the prediction but also confidence in the prediction. We address both of these challenges with Compute-in-Memory (CIM) which has become a pivotal technology for deep learning acceleration at the edge. While traditional CIM techniques are promising for energy-efficient deep learning, to bring in the robustness of uncertainty-aware predictions at the edge, we introduce a suite of novel techniques: First, we discuss CIM-based acceleration of Bayesian filtering methods uniquely by leveraging the Gaussian-like switching current of CMOS inverters along with co-design of kernel functions to operate with extreme parallelism and with extreme energy efficiency. Secondly, we discuss the CIM-based acceleration of variational inference of deep learning models through probabilistic processing while unfolding iterative computations of the method with a compute reuse strategy to significantly minimize the workload. Overall, our co-design methodologies demonstrate the potential of CIM to improve the processing efficiency of uncertainty-aware algorithms by orders of magnitude, thereby enabling edge robotics to access the robustness of sophisticated prediction frameworks within their extremely stringent area/power resources.

Complex sensors such as LiDAR, RADAR, and event cameras have proliferated in autonomous robotics to enhance perception and understanding of the environment. Meanwhile, these sensors are also vulnerable to diverse failure mechanisms that can intricately interact with their operational environment. In parallel, the limited availability of training data on complex sensors affects the reliability of their deep learning-based prediction flow, when their prediction models fail to generalize to environments not adequately captured in the training set. To address these reliability concerns, this paper introduces STARNet, a Sensor Trustworthiness and Anomaly Recognition Network designed to detect untrustworthy sensor streams that may arise from sensor malfunctions and/or challenging environments. STARNet employs the concept of likelihood regret (LR) for continuous evaluation of the trustworthiness of sensor streams. We tailor the framework to resource-constrained edge devices with two settings: a gradient-free framework suit- able for low-complexity hardware with fixed-point precision capabilities, and a low-rank tunability of underlying models for LR extraction, reducing the extraction workload. Through extensive simulations, we demonstrate the efficacy of STARNet in detecting untrustworthy sensor streams in unimodal and multimodal settings. In particular, the network shows superior performance in addressing internal sensor failures, such as cross-sensor interference and crosstalk. In diverse test scenarios involving adverse weather and sensor malfunctions, we show that STARNet enhances prediction accuracy by approximately 15% by filtering out untrustworthy sensor streams. STARNet is publicly available at https://github.com/nstrndrbi/STARNet.