Linear probes are widely used to interpret and evaluate neural representations, yet their reliability remains unclear, as probes may appear accurate in some regimes but collapse unpredictably in others. We uncover a spectral mechanism behind this phenomenon and formalize it as the Spectral Identifiability Principle (SIP), a verifiable Fisher-inspired condition for probe stability. When the eigengap separating task-relevant directions is larger than the Fisher estimation error, the estimated subspace concentrates and accuracy remains consistent, whereas closing this gap induces instability in a phase-transition manner. Our analysis connects eigengap geometry, sample size, and misclassification risk through finite-sample reasoning, providing an interpretable diagnostic rather than a loose generalization bound. Controlled synthetic studies, where Fisher quantities are computed exactly, confirm these predictions and show how spectral inspection can anticipate unreliable probes before they distort downstream evaluation.

T able 1: Robustness to model mismatch. Top-1 accuracy of SIPS at the third time quartile (Q3), evaluated on data generated by humans, RL agents, and mismatched models. We ran SIPS assuming r =2, q =0.95, T =10, and a Manhattan ( h Matched parameters are starred (*). We thank the reviewers for engaging carefully with our paper, and for providing helpful and constructive feedback. We will expand on these experiments in the final paper with more domains and cross-method comparisons.

The study presents a novel approach for quantifying cellular interactions in digital pathology using deep learning-based image cytometry. Traditional methods struggle with the diversity and heterogeneity of cells within tissues. To address this, we introduce the Spatial Interaction Potential (SIP) and the Co-Localization Index (CLI), leveraging deep learning classification probabilities. SIP assesses the potential for cell-to-cell interactions, similar to an electric field, while CLI incorporates distances between cells, accounting for dynamic cell movements. Our approach enhances traditional methods, providing a more sophisticated analysis of cellular interactions. We validate SIP and CLI through simulations and apply them to colorectal cancer specimens, demonstrating strong correlations with actual biological data. This innovative method offers significant improvements in understanding cellular interactions and has potential applications in various fields of digital pathology.

Navigating the ultrasound (US) probe to the standardized imaging plane (SIP) for image acquisition is a critical but operator-dependent task in conventional freehand diagnostic US. Robotic US systems (RUSS) offer the potential to enhance imaging consistency by leveraging real-time US image feedback to optimize the probe pose, thereby reducing reliance on operator expertise. However, determining the proper approach to extracting generalizable features from the US images for probe pose adjustment remain challenging. In this work, we propose a SIP navigation framework for RUSS, exemplified in the context of robotic lung ultrasound (LUS). This framework facilitates automatic probe adjustment when in proximity to the SIP. This is achieved by explicitly extracting multiple anatomical features presented in real-time LUS images and performing non-patient-specific template matching to generate probe motion towards the SIP using image-based visual servoing (IBVS). This framework is further integrated with the active-sensing end-effector (A-SEE), a customized robot end-effector that leverages patient external body geometry to maintain optimal probe alignment with the contact surface, thus preserving US signal quality throughout the navigation. The proposed approach ensures procedural interpretability and inter-patient adaptability. Validation is conducted through anatomy-mimicking phantom and in-vivo evaluations involving five human subjects. The results show the framework's high navigation precision with the probe correctly located at the SIP for all cases, exhibiting positioning error of under 2 mm in translation and under 2 degree in rotation. These results demonstrate the navigation process's capability to accomondate anatomical variations among patients.

Large language models (LLMs) have become a significant workload since their appearance. However, they are also computationally expensive as they have billions of parameters and are trained with massive amounts of data. Thus, recent works have developed dedicated CUDA kernels for LLM training and inference instead of relying on compilergenerated ones, so that hardware resources are as fully utilized as possible. In this work, we explore the possibility of GPU native instruction optimization to further push the CUDA kernels to extreme performance. Contrary to prior works, we adopt an automatic optimization approach by defining a search space of possible GPU native instruction schedules, and then we apply stochastic search to perform optimization. Experiments show that SIP can further improve CUDA kernel throughput by automatically discovering better GPU native instruction schedules and the optimized schedules are tested by 10 million test samples.

To stay competitive, the Low- or Middle-Income Countries (LMICs) need to embrace Industry 4.0 and Logistics 4.0. This requires government-level interventions and policy-making to incentivize quality product solutions and drive innovation in traditionally resistant economic sectors. In this position paper, we support the establishment of Smart Industrial Parks (SIPs) with a focus on enhancing operational efficiencies and bringing together MSMEs and startups targeting niche clientele with innovative Industry 4.0 solutions. SIPs along with the phased deployment of well-planned robotic automation technologies shall enable bringing down India's untenable logistics costs. Toward the successful execution of SIPs, we are required to implement the efficient allocation of manufacturing resources and capabilities within SIPs. Thus, we emphasize the importance of efficient resource utilization, collaboration, and technology adoption in industrial parks to promote industrial development and economic growth. We advocate the use of a cloud-based cyber-physical system for real-time data access and analysis in SIPs. Such centralized cloud-based monitoring of factory floors, warehouses, and industrial units using IoT infrastructure shall improve decision-making, efficiency, and safety. Digital Twins (DTs), which are cyber-replicas of physical systems, could play a significant role in enabling simulation, optimization, and real-time monitoring of smart manufacturing and distributed manufacturing systems. However, there are several challenges involved in implementing DTs in distributed manufacturing systems, such as defining data schemas and collaboration protocols, ensuring interoperability, the need for effective authentication technology, distributed machine learning models, and scalability to manage multiple DTs.

Newly arriving nodes in dynamics networks would gradually make the node embedding space drifted and the retraining of node embedding and downstream models indispensable. An exact threshold size of these new nodes, below which the node embedding space will be predicatively maintained, however, is rarely considered in either theory or experiment. From the view of matrix perturbation theory, a threshold of the maximum number of new nodes that keep the node embedding space approximately equivalent is analytically provided and empirically validated. It is therefore theoretically guaranteed that as the size of newly arriving nodes is below this threshold, embeddings of these new nodes can be quickly derived from embeddings of original nodes. A generation framework, Space-Invariant Projection (SIP), is accordingly proposed to enables arbitrary static MF-based embedding schemes to embed new nodes in dynamics networks fast. The time complexity of SIP is linear with the network size. By combining SIP with four state-of-the-art MF-based schemes, we show that SIP exhibits not only wide adaptability but also strong empirical performance in terms of efficiency and efficacy on the node classification task in three real datasets.

This abstracts the core ideas beyond logic programming as such to encompass frameworks from probabilistic databases, probabilistic finite model theory and discrete lifted Bayesian networks. To demonstrate the usefulness of such a general approach, we completely characterise the projective families of distributions representable in the generalised distribution semantics and we demonstrate both that large classes of interesting projective families cannot be represented in a generalised distribution semantics and that already a very limited fragment of logic programming (acyclic determinate logic programs) in the determinsitic part suffices to represent all those projective families that are representable in the generalised distribution semantics at all.