Papers

Continual learning faces the persistent challenge of catastrophic forgetting, where sequential task updates degrade previously acquired knowledge. While prompt-based methods integrated with pre-trained models offer a compelling solution by freezing the backbone, they often rely on static, task-level prompting strategies that overlook fine-grained intra-task diversity. In this paper, we propose Gated Adaptive Prompting (GAP-Prompt), a novel method that introduces instance-level adaptability to the prompting process. GAP-Prompt consists of three synergistic modules: (1) instance-conditioned gating, which dynamically determines optimal prompt injection layers for each individual image; (2) dynamic knowledge fusion, which performs instance-aware aggregation of current and historical prompts, enabling knowledge integration across tasks; and (3) shared prompt distillation, which anchors foundational knowledge in early shared layers to mitigate forgetting. Extensive evaluations on CIFAR-100, ImageNet-R, and CUB-200 benchmarks demonstrate that GAP-Prompt consistently achieves state-of-the-art performance. Notably, on the fine-grained CUB-200 dataset, GAP-Prompt reaches 87.29% accuracy, approaching the joint training upper bound (88.00%) and outperforming existing methods by a significant margin.

LLMs are being used increasingly to measure aspects of student discourse (e.g. talk moves, collaboration, equity of voice) at scale. Typically, LLM-based measures of student talk use transcriptions of classroom conversations that only include verbal contributions, which de-contextualize student language. Common practices for validating these measures include comparing outputs against expert annotations by adults, using held out evaluation sets and F1 scores. We argue that these approaches are insufficient to ensure that such measures are meaningful and equitable for teaching and learning, particularly for racially and linguistically marginalized youth. In order to center the youth whose talk is being analyzed, re-contextualizing these classroom conversations and engaging youth in the research process is necessary. Sharing epistemic authority with youth, ultimately, centers their point of view and adds crucial nuance to the analysis of their talk that adult experts, researchers, and LLMs cannot provide. In a case study of multilingual youth in one 8th-grade math classroom, we address the epistemic exclusion of youth by employing multiple ethnographically-oriented methods to re-contextualize student conversations and center youth as epistemic authorities in conversation with researchers and LLMs. We conducted participant observations, interviews, focus groups, and member checks with four focal students. Findings reveal that there were misalignments between students' interpretations of their own math talk experiences and the LLM-based measures of their talk. Students contested both the LLM classifications and the coding scheme used to measure their talk, highlighting the need for youth to be involved in the epistemic process of producing knowledge about their experiences.

Understanding human skill is important for AI systems that collaborate with, coach, or assist people. Unlike typical latent variable estimation problems which rely on single observations, skill is a persistent, compositional, and behaviorally grounded construct that must be inferred from patterns over time. We introduce Skill Abstraction with Interpretable Latents (SAIL), a method for modeling human skill as an interpretable, multi-dimensional construct inferred from naturalistic behavior. Our approach produces a skill embedding that is robust to transient performance fluctuations and learns a transferable representation of human subskills. Furthermore, SAIL supports skill-informed behavior prediction that generalizes across a variety of in-domain contexts. We represent each individual with a persistent skill embedding that controls a blend between expert and novice bases and is trained using counterfactual subskill swaps for disentanglement. This design encourages representations that are both robust to performance variation and structured for interpretability. We demonstrate across racing and baseball that SAIL achieves strong predictive performance and consistently improves behaviorally grounded disentanglement over the evaluated baselines, while also improving downstream AI coaching performance.

Existing Rowhammer-based inference-time backdoor attacks design their bit-flip strategies purely at the algorithmic level, without accounting for the bit-flips that the underlying DRAM hardware will actually produce. This disconnection between the algorithmic backdoor construction and its hardware realization leads to unreliable attack performance, as collateral bit-flips at unintended locations degrade both the attack success rate (ASR) on triggered inputs and the test accuracy (TA) for normal inputs. Consequently, the performance of such attacks varies significantly across different DRAM devices, as each device presents a unique set of exploitable bit-flip locations. This work presents ROBBIN, a hardware-aware Rowhammer-based backdoor injection attack that integrates the device-specific vulnerability into the backdoor construction process. ROBBIN first characterizes the bit-flip patterns of a target DRAM and uses this information to iteratively select DRAM page mappings for the model weights that would maximize ASR while preserving TA under Rowhammering. By treating every hammering-induced bit-flip as an integral part of the attack design rather than first constructing a hardware-agnostic backdoor and dismissing collateral flips as side effects, ROBBIN produces backdoors that remain robust across devices. Evaluated on ResNet-20 and VGG-16 with CIFAR-10 across three commodity DDR4 chips, ROBBIN consistently achieves close to 90% ASR while maintaining TA above 83%, demonstrating reliable backdoor efficacy across diverse DRAM devices.

The Shopify marketplace hosts more than 16,000 active third-party applications, serving 2.7 million active merchant stores generating an estimated \$706 billion in annual sales, yet little empirical evidence exists on its structure and adoption drivers. We analyse it using a September 2025 snapshot of all 24,826 applications, a weekly panel of 7,708 applications over 366 weeks (February 2019 to March 2026), and listing histories reconstructed from the Internet Archive. Across 55 established functional categories, over half were low-concentration and 20% highly concentrated, with larger categories consistently less concentrated. Later entrants grew faster than early movers in 88% of the 50 analysed categories, persisting across seven years of quarterly re-estimations, with early movers on net losing detected installations whilst late movers gained them. Platform governance reshaped competition asymmetrically: Shopify's entry into chat reversed more than two years of de-concentration; the deprecation of its Product Reviews application, to our knowledge the first measured platform-owner exit from complementor category, released 191,000 installations of which at most a third reappeared as competitor adoption within a year; the 2021 reduction of the platform revenue share produced no detectable change in entry or retention. Failure is largely silent and predictable: the median exiting application peaked at 8 detected installations and disappeared from tracking within 68 weeks of launch, category leadership changed hands in 92% of categories over seven years, and publicly observable data from an application's first six months predict exit within two years with cross-validated AUC above 0.8. App markets on Shopify remain contestable; who benefits depends on platform governance and entry conditions more than on entry timing.

Between AI-assisted item generation and expert review sits a computational evaluator whose decisions are usually treated as technical preliminaries. Yet representation, structural reduction, and selection policy determine which items and evidence psychometricians ever receive. Across two linked in-silico studies of 32,000 selected Big Five items, we followed fixed source populations from semantic representation through structural evaluation and candidate-form construction. Broad agreement in semantic geometry concealed consequential local differences: identical wording acquired different construct evidence, different items survived, and intended attributes could disappear even as community correspondence improved. These sensitivities also differed across generated source populations. At the final review boundary, both eligibility policies filled every content cell in every evaluable form, yet they presented different wording. Across embedding configurations, inclusive primary forms shared a median of only 6 of 40 items, reflecting the total downstream consequence of changing representation across structural evidence and ranking. The apparent stability of global summaries and complete forms therefore concealed instability in the content reaching psychometricians. The computational evaluator is not neutral infrastructure between generation and expertise; it is an inspectable and revisable part of measurement design.

Iteratively reweighted least squares (IRLS) methods constitute a natural approach to nuclear norm minimization, but their convergence rates and the role of the weight operator have remained poorly understood. This paper establishes sharp convergence rates for IRLS methods for constrained nuclear norm minimization in low-rank recovery. A central ingredient is a new majorization analysis for the smoothed nuclear norm: we prove that the harmonic-mean weight operator defines a valid global quadratic majorizer. Furthermore, we show that this weight operator is optimal within the family of power-mean weights, clarifying why it improves over classical one-sided reweighting schemes that use only row- or column-space information. Under a Schatten-1 null space property, we prove global linear convergence of IRLS algorithms using a variety of weight operators, including the harmonic-mean weights. For IRLS with harmonic-mean weights, we prove a dimension-independent, locally linear convergence rate. We provide a counterexample showing that this dimension-independent local rate cannot in general be obtained for IRLS algorithms using one-sided weight operators, which predominate in the literature. Numerical experiments corroborate the theoretical results and illustrate the practical advantage of harmonic-mean reweighting across square, rectangular, and adversarially initialized recovery problems.

The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness introduces a severe server-side threat we term TrustShift: a compromised MCP server behaves benignly during an initial conditioning phase, building operational reliance and suppressing agent skepticism, before switching to an adversarial payload once an interaction threshold is reached. The evasion is temporal, not syntactic: benign at deploy time, the server's defection is invisible to predeployment static analysis, which sees only the honest phase. Switched payloads range from overt structural violations to schema-valid manipulations, the latter preserving outer protocol compliance to evade runtime middleware filters. Crucially, TrustShift originates in the server-controlled tool channel, not user prompts (unlike indirect prompt injection) or the transport (unlike man-in-the-middle): the adversary is the trusted server endpoint itself. We introduce TrustShiftProbe, an evaluation and defense framework with four contributions: (1) a stateful temporal threat model of the agent-server lifecycle as a benign conditioning phase followed by an adversarial defection at a trust horizon; (2) a language-agnostic attack engine that instantiates each variant as a compromised MCP server across four production domains; (3) SHIELD, a multi-tier, zero-oracle runtime defense at the MCP transport boundary that audits server payloads against behavioral baselines learned during clean trust windows; and (4) a taxonomy of nine TrustShift variants spanning three execution mechanisms (structural violation, semantic corruption, scope expansion) and three adversarial objectives (disruption, exfiltration, and their combination). Across frontier proprietary and open-weight models, TrustShift attacks achieve a 69.5% mean attack success rate that SHIELD mitigates to 42.7%.

Highly overparameterized models often predict well despite interpolating training data in complex domains, challenging the classical bias–variance tradeoff. We investigate whether this “benign overfitting” phenomenon extends to equity return prediction. Consistent with recent statistical theory, we document two key phenomena: first, a double descent pattern in the ridgeless model's prediction risk; and second, that while the optimal ridge model consistently outperforms its ridgeless counterpart, this performance gap becomes negligible at large parameter-to-observation ratios. Ultimately, however, both models fail to outperform a simple historical average. This empirical evidence aligns with our asymptotic results under the null hypothesis of zero slope coefficients, suggesting that standard equity predictors lack true forecasting power—even within highly flexible, nonlinear machine learning architectures. These findings reconcile modern and classical machine learning in asset pricing: in the absence of a true signal, they asymptotically collapse to the historical average benchmark.

This paper proposes a layered framework for defining the architecture of the computational unit of an Open Scholarly Infrastructure (OSI) and presents a concrete implementation possibility through the introduction of OpenCitations, an OSI dedicated to publishing citation data and bibliographic metadata. Grounded in the Principles of Open Scholarly Infrastructure (POSI), the study focuses on the technical dimensions of openness, sustainability, interoperability, and reproducibility that are required for a robust OSI. The proposed approach first identifies the core principles and technical features that a computational block in an OSI should guarantee, including separation of operational domains, orchestration, scalability, observability, automation, and workflow portability. It then maps these requirements onto a layered architectural model composed of Hardware, Virtualization, Orchestration, and Application layers, complemented by a transversal Meta layer. The OpenCitations case study shows how this framework can be instantiated in practice through an on-premises infrastructure. The case is presented with details regarding the technicalities and actual implementations of the proposed methodology. By combining a conceptual definition with a real-world implementation, this work offers both a practical reference and a methodological basis for designing the computational block of an OSI.

Audio-visual speech enhancement (AVSE) uses a target speaker's visible articulation to recover that speaker's voice from overlapped speech. Yet most evaluation protocols rely on synthetic mixtures and reliable video. The ISCSLP 2026 Real-World AVSE Challenge addresses both gaps. Track~1 combines naturally recorded two-talker mixtures, which lack a clean reference, with reference-available remixes of the same speakers; Track~2 additionally degrades the target video in five ways and adds 3-m far-field recordings. Sixteen and twelve teams were ranked on speaker-disjoint test data by rank averaging over waveform fidelity, predicted quality, transcription accuracy, and speaker similarity. On Track~1 remixes, the best system reaches 12.7~dB SI-SDR and 0.85 STOI, but natural recordings remain harder: even the lowest CER rises from 9.0% to 14.7%. The leading systems use video mainly for speaker attribution rather than signal reconstruction, and the top two lose under 0.5~dB SI-SDR on Track~2. UTMOS and DNSMOS rank systems differently from the other metrics, so no single metric captures target-speech recovery. We release the baselines, evaluator, and official results.

Recent large audio language models (LALMs) have achieved impressive progress in audio understanding. However, existing evaluations remain largely constrained to English and narrow audio domains. Prior benchmarks typically focus on a single audio modality, i.e., speech, sound, or music, limiting the systematic investigation into how these models generalize across diverse visual scenarios. In this paper, we introduce EXAM$^2$, a benchmark for multilingual and multimodal audio understanding spanning six languages and multiple modalities, including speech, sound, music, mixed-audio settings, and visual images. By incorporating visual information alongside heterogeneous audio inputs, EXAM$^2$ enables more realistic evaluation of scene-aware audio reasoning and cross-modal comprehension. EXAM$^2$ comprises $5,667$ multiple-choice questions, $22,614$ image instances, and $135,684$ multilingual translations. We evaluate state-of-the-art open-source and proprietary LALMs as well as multimodal LLMs, revealing substantial performance gaps in multilingual and cross-modal understanding. Furthermore, we propose Gemma3n-EXAM$^2$, a lightweight fusion-model fine-tuned on EXAM$^2$-train, achieves up to $15.8\%$ improvement in multilingual settings and $16.5\%$ gains in multimodal evaluation over a strong baseline. Empirical results establish EXAM$^2$ as a challenging benchmark and pioneer future multilingual and multimodal audio intelligence research.

We propose and demonstrate SPIDER4TianoCore, a packaged Python command-line tool that provides integration-stage patch-status evidence for the TianoCore/UEFI firmware supply chain. Given an upstream pre-patch and post-patch pair and prepared downstream targets, the tool reports Vulnerable, Already Patched, Not Applicable, or Uncertain with supporting evidence for maintainer review. Our work is inspired by SPIDER's patch-propagation framing, but SPIDER4TianoCore does not itself prove that a patch is safe to propagate. We evaluate the engine on 20 prepared target/CVE pairs from eight public downstream EDK II repositories and two CVEs. The analyzers produce 10 high-confidence pre-patch matches and four high-confidence post-patch matches, conservatively abstain on six targets, and make no confidently wrong classifications relative to the recorded manual patch-state labels. These preliminary results demonstrate reproducible evidence generation for prepared targets rather than general downstream accuracy.

We propose enhancing the bug report templates in the GitHub Issues issue tracking system used by the TianoCore open-source community with the aim of improving the bug triage and resolution process. We analyze the bug repository data and find patterns of information that are useful for bug triage and fixing. However, some of them are only occasionally included in the free-form text of bug reports. Therefore, we propose adding a few new fields to the existing TianoCore bug report template. In this study, we focus on the key TianoCore project, EDK II, which constitutes the core of the UEFI firmware across various firmware vendors and original equipment manufacturers. This study is currently a work-in-progress. So far, we have interviewed a few developers to obtain their feedback and adjust the proposed approach. We are planning more interviews with the TianoCore community to conduct A/B tests and validate our approach to achieve effective and efficient bug triage and resolution.

The growing size of Convolutional Neural Networks has led to increasingly large and costly models. Knowledge Distillation (KD) addresses this by transferring knowledge from a large network (teacher) to a small one (student), also reducing the training data required. KD is traditionally applied only at the network's final output. However, its behaviour when applied at intermediate network layers has received little attention. This raises the question of whether intermediate block-wise KD, which provides supervision throughout the network, could offer an advantage under specific conditions, such as few instances per class, which is common in fine-grained datasets. This work proposes a student design based on simple, homogeneous blocks mirroring those of the teacher, distilling knowledge between corresponding blocks. Across eleven datasets, we show that on classic datasets, distilling only the last block is sufficient – and often best–, whereas fine-grained, data-scarce settings benefit substantially from intermediate supervision, with even a single additional distillation point narrowing the gap considerably. We further study how this supervision should be guided, exploring configurations of varying granularity and informed by an explainability analysis based on attention maps, Centered Kernel Alignment, and Grad-CAM, alongside the impact of teacher and student fine-tuning strategies. This work shows that intermediate block-wise distillation, guided appropriately, is key to building compact data-efficient models without sacrificing accuracy.

Transformed by digitization, everyday activities-paying bills, shopping, managing transportation-increasingly require older adults to navigate digital systems. To accomplish these digital activities of daily living (DADLs), older adults often rely on help that looks less like IT support-institutional, episodic, and product-oriented-and more like caregiving: relational, ongoing, and aimed at preserving their functional independence. We argue that this practice is technology caregiving and introduce a framework characterizing it along four dimensions: why support is needed, who provides it, when it occurs, and how it is delivered. Applying this framework, we then systematically review the literature on how older adults are supported in DADLs. From 3,381 unique records, 36 articles met the inclusion criteria. Findings show that technology caregiving involves burden, like traditional care, but is distinctly shaped as much by digital systems and their constant change as by technology caregivers' and older adults' abilities.

Reconstructing scattering amplitudes from finite, noisy, and mutually inconsistent measurements is an ill-posed inverse problem common to many reactions relevant to particle physics. We introduce S-matrix informed neural networks (SINNs), and demonstrate their ability to learn scattering amplitudes directly from data while respecting first principles. We further develop a novel data selection procedure, which uses the response of constrained neural network ensembles to identify a set of experiments compatible with first principles, and with each other. We apply this framework to $\pi\pi$ scattering, producing reusable amplitudes and correlated uncertainties without relying on a fixed functional form. We validate our results against residual model dependencies and training biases through closure tests and ablations. We find negligible impact of model architecture on our results. Our workflow unifies physics-constrained representation learning, data selection, and uncertainty quantification. Our strategy is transferable to other scattering processes, and other constrained physics problems limited by inconsistent data.

State space models, especially Visual State Space Duality (VSSD), have emerged as efficient linear-time alternatives to Transformers for dense visual tasks. However, we observe that VSSD compresses spatial context into a global aggregation that suppresses high-frequency responses, causing excessive boundary smoothing in remote sensing semantic segmentation. To address this, we propose CRISP, a calibration framework with two components. Its core, the Duality Calibration Operator (DCO), restores local contrast and boundary responses through residual injection and frequency calibration within the VSSD backbone, without altering its linear complexity. To retain the recovered detail, an Orthogonal Multi-Prototype (OMP) head assigns multiple orthogonally constrained prototypes per class to model large intra-class variance. Extensive experiments on Potsdam, Vaihingen, and LoveDA show that, with approximately 30M parameters, CRISP achieves consistent gains in mean F1 (mF) and mIoU while remaining competitive with state-of-the-art methods. Code is available at https://github.com/crazylifeha/CRISP.

Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis, treatment planning, surgical guidance, and disease monitoring. However, developing automated segmentation models that generalize across diverse tumor characteristics, imaging protocols, acquisition sites, and patient populations remains challenging. Variations in tumor morphology and imaging distributions can substantially degrade performance outside the training domain. Consequently, improving the robustness and generalization of deep learning-based segmentation models has become a key objective in medical image analysis. To improve segmentation robustness, we propose Multi-Stage Dynamic Prompt nnU-Net, a prompt-conditioned extension of nnU-Net. Three independent dynamic prompt modules are inserted into the deepest encoder stages. Each module contains a learnable bank of ten 256-dimensional prompt vectors and uses globally pooled encoder features to generate image-specific prompt representations. These representations are projected into feature-wise scaling $(\gamma)$ and shifting $(\beta)$ parameters that modulate encoder feature maps through Feature-wise Linear Modulation (FiLM), enabling adaptive feature conditioning at multiple semantic levels. Evaluation on the BraTS GOAT validation dataset demonstrated that the proposed Multi-Stage Dynamic Prompt nnU-Net outperformed the baseline nnU Net across the majority of evaluated metrics and tumor subregions. The proposed model achieved average lesion-wise Dice scores of 76.16% (ET), 80.04% (TC), and 86.42% (WT), compared with 74.38%, 78.14% and 84.01% for the baseline model. The results demonstrate that multi-stage dynamic prompt conditioning improves segmentation accuracy and boundary delineation for brain tumor segmentation.

Recalibration can preserve conformal coverage after pruning while enlarging prediction sets and leaving more alternatives for downstream decisions. Directly searching for deletions that keep sets small is costly. We study whether a small candidate-gradient budget can approximate this search at lower cost. Candidate-Saliency Pruning (CSP) estimates the squared first-order change in two plausible labels' scores when each parameter is deleted. CSP averages these changes, combines the resulting importance with a base pruner, and selects the mixing weight under validation accuracy and coverage requirements. Independent split-conformal calibration supplies marginal coverage under exchangeability. We evaluate CSP on three classification tasks, two base pruners, and three sparsity levels against a squared true-label control that separates candidate choice from gradient squaring, under fixed recovery updates, equal total time, and restricted access to the training corpus. Before recovery, CSP reduces mean set size by 13.2% to 19.2% against the reference pruner and by 7.7% to 13.2% against the control in all six encoder cells at 50% sparsity. The advantage over the control shrinks with recovery to practical equivalence in all six cells at 1,000 updates, and at equal total time the cheaper reference pruner is practically equivalent in 18 of 18 settings. When recovery is limited to the retained pruning pool, CSP keeps a meaningful advantage in all six cells. Its value therefore depends on the time and data available for recovery.

Concurrent multi-agent coding offers a division of labor across modules, robustness through redundancy and parallel exploration at the natural granularity of multi-file projects. Realtime collaborative editing protocols solve this coordination problem for human teams with Conflict-free Replicated Data Types (CRDTs), but the LLMs underneath generate one token at a time, and existing multi-agent coding systems inherit this serial limit, since they either sequence agents through phase handoffs or pool independent samples without coordination, and a single agent abandons up to half of hard tasks with a one-file stub-and-exit. AgentRoom is a realtime collaborative editing protocol for concurrent coding agents. Its runtime layer exposes file-level claim, status and broadcast as MCP tools on a CRDT-merged shared filesystem. Five frontier coding-CLI models ran four backend coding tasks, with cross-language checks in Python DevBench and Rust+axum. For CLI-stable models, AgentRoom with 2 agents abandons fewer tasks than Solo and varies less from run to run. At matched compute, one positive mean LLM-judge contrast puts AgentRoom over parallel-merge. The other contrast, a bundle probe, puts full AgentRoom above each partial case: an ordering rather than a percentage split. Coordination, not parallelism or CRDT-merge, is the key design choice.

Perimeter-based security appliances, such as firewalls or Intrusion Detection Systems, are ineffective against modern attacks that use pivoting, wherein attackers "pivot" traffic through compromised hosts to gain access to additional targets that would otherwise be inaccessible. Due to the legitimate appearance of the relayed traffic, pivoting is extremely difficult to detect. Although the consequences of these attacks are known to be severe, existing defenses suffer from drawbacks such as high processing delays, low accuracy, or reliance on network-wide participation, making them inconvenient or even ineffective. This work presents Stitch, a host-based system that uses the programmable kernel to detect pivoting in real time. By observing host-traversing flows, Stitch uses process tracing to effectively combine system and network-level information, connecting incoming and outgoing communications and identifying pivoting characteristics between them. Showing 31% gains in accuracy over state-of-the-art pivoting defenses and a maximum false positive rate of 0.006% over two separate real-world deployments, Stitch covers the gap in current pivot detection solutions by providing accurate, lightweight, and independent coverage for vulnerable hosts in a network.

We grade MDS-UPDRS gait severity from SMPL motion using three frozen MotionAGFormer encoders as featurizers, reaching macro-F1 0.58 on a hidden, multi-site test set. Because the system's members differ only in their lifting corpus, evaluating encoders singly on that test set isolates what that corpus contributes. Six pools drawn from one inertial dataset, varying only in which walking tasks they include, score between 0.32 and 0.53, and just one of them beats the 0.51 of an encoder given no outside motion at all. What separates them is not how much data they hold but whether they carry a contrast in walking speed, the variation this representation appears to depend : a further pool adding a third collection site at fixed task composition does worse still. The same rule explains why exact synthetic motion and monocularly reconstructed web video both fail to help. Modifying the learned representation itself, rather than the corpus behind it, cost every variant that attempted it.

Satellite orbit prediction, which aims to forecast future orbital trajectories from historical observations, is important for collision warning and safe space operations. With advances in time-series forecasting, learning-based methods have emerged as a promising solution for satellite prediction. In orbital dynamics, a satellite state is typically described by position and velocity, where position characterizes trajectory geometry and velocity reflects its instantaneous direction and rate of change. However, most existing methods mainly focus on temporal dependencies within position sequences while rarely exploiting the intrinsic coupling between position and velocity, which is essential for modeling satellite motion. To this end, we propose OrbitNet, a velocity-aware representation learning method for accurate satellite orbit prediction. It lifts conventional position-sequence forecasting to a position-velocity coupled representation learning paradigm by exploiting relationships among satellite state variables. Specifically, we develop a velocity-coupled representation refinement strategy to enhance positional representations through cross-variable interactions between position and velocity. We further introduce orbital segment modeling, which partitions historical trajectories into temporal segments and performs segment-level temporal learning to capture local motion variations and long-range evolution patterns. Extensive experiments show that OrbitNet outperforms large time-series foundation models and representative general forecasting methods under both in-domain evaluation on Starlink and zero-shot evaluation across six unseen satellite constellations. We expect this work to encourage further exploration of satellite-aware representation learning for trajectory time-series forecasting.

Inter-annotator disagreement in real-time affect annotation is widely treated as stochastic noise. We challenge this view by modelling ordinal annotation as an implicit game-theoretic coordination process against an internalised population prior under a post-hoc majority vote. We present the Ordinal Annotation Game, a conceptual scaffold in which the mapping from individual effort to collective consensus is governed by the semantic abstraction of the target construct. We evaluate it across two experiments sharing identical interface software and a uniform sensitivity threshold: a controlled sensory tracking study and an in-the-wild engagement study. Sensory annotation yields a consensus-dominant regime where active updates reinforce agreement, whereas engagement annotation inverts into an effort-limited regime where more labelling penalises consensus. The payoff slope reverses sign under identical processing, showing that ordinal disagreement is a structured behavioural phenomenon, not a discretisation artefact or random error.

Rapid and accurate fault detection in high-voltage transmission networks is essential for grid reliability and equipment protection. Transmission fault datasets are frequently imbalanced, and certain fault types produce electrical signatures that fall within the normal operating envelope, causing single-model classifiers to fail on safety-critical cases. This paper proposes a hybrid two-stage machine learning pipeline that decouples detection from classification. Stage 1 combines an Isolation Forest anomaly detector with an optional supervised binary detector through an OR-fusion rule; the supervised branch is allocated automatically during training for any fault class the anomaly detector cannot resolve, and is omitted when no such class exists. Stage 2 applies a Random Forest multiclass classifier only to samples flagged by Stage 1. Feature engineering is expressed as a per-measurement-point operator mapping six raw channels to eighteen features, including zero-sequence symmetrical components derived from Fortescue's theorem, yielding 18L features for L measurement points. On the TLFaultDataset, the pipeline raises Line-fault end-to-end accuracy from 31.3% to 95.8%. On an independent single-point dataset, the same framework attains 97.25% end-to-end accuracy across all classes including normal operation, exceeding the TLFed federated benchmark of 94.84% without GPU or federated infrastructure, at 0.05 ms per sample on CPU. Ablation on both datasets shows zero-sequence features resolving the three-phase versus three-phase-to-ground ambiguity, raising the F1-score of that class pair from 0.39 to 0.997. The direction of the zero-sequence signature is found to be system-dependent, motivating a learned decision boundary in place of a fixed relay threshold.

Deep Equilibrium Models (DEQs) compute predictions from a hidden representation unchanged by the model update. Training through this equilibrium uses implicit differentiation and requires solving an adjoint system built from the residual Jacobian. If this Jacobian is nearly singular along loss-sensitive directions, small perturbations can be strongly amplified in the adjoint response, producing large, highly sensitive gradients that can make optimization unreliable. We introduce Response Renormalization, a backward-pass framework that lifts selected near-pole denominators while leaving unlifted response channels unchanged. Collective Mode Response Renormalization (CMR) applies this correction in a low-dimensional critical subspace, while Phi-adaptive CMR computes a bounded response mass from a positive susceptibility rule. We derive dense and matrix-free collective formulations, distinguish exact gradients of a modified frozen-anchor residual from backward-response surrogates, and extend the construction to Structured Implicit Layers and Vector Attractors (SILVA). Across 23 multiphysics families spanning partial differential equations, three-dimensional fields, operator maps, complex geometries, and particle systems, CMR and Phi-CMR yield test errors no more than five percent higher than those from models trained with exact implicit differentiation in more than 98% of static and 95% of transient family-seed comparisons. Solver-index experiments show convergence toward the static adjoint, while physical-time rollouts retain predictive fidelity under the evaluated conditions. These results demonstrate that selective response renormalization can control near-critical adjoint amplification without globally damping well-conditioned sensitivity. Therefore, the method can make parameter updates more reliable while preserving the useful gradient information needed for learning.

Few-shot anomaly detection (FSAD) has recently benefited from vision-language models such as CLIP, which enable anomaly de?tection by aligning visual features with text descriptions of normal and abnormal states. However, existing methods typically rely on static text prompts that are applied uniformly across the entire feature hierarchy and spatial dimensions. This rigid global-to-local matching fails to capture the highly localized and scale-dependent physical variations of industrial defects. To address this, we propose DriftAD, a FSAD framework built on three key modules. First, an Anomaly Signal Amplification (ASA) module enhances subtle defect signals through spatial and frequency branches before text-visual matching. Second, Visually-Guided Text Drift (VGTD) dynamically transforms frozen CLIP text embeddings, steering them into layer?wise, spatially-adaptive anomaly descriptors conditioned on local visual context at each encoder depth. Third, Drift-Guided Spatial Gating (DGSG) uses the drifted abnormal descriptor as a spatial probe to selectively enhance anomaly-relevant visual features. Addi?tionally, a drift separation loss prevents representational collapse of the drifted descriptors, and a gate supervision loss enforces spatially discriminative gating in DGSG. Extensive experiments on MVTec?AD and VisA demonstrate state-of-the-art performance across all 1-, 2-, and 4-shot settings on both image-level and pixel-level metrics. Code is available at https://github.com/wenyang001/DriftAD.

World models have demonstrated significant potential for perceiving and simulating complex environments. Despite their strong performance, the fundamental nature of their learned representations remains poorly understood. In this paper, we investigate the Platonic Representation Hypothesis within this domain by proposing the Predictive Consistency Assumption: we posit that the optimization of a shared state transition objective acts as a selective pressure that encourages heterogeneous models to converge toward a shared latent structure. Through systematic experiments with the DINO World Model (DINO-WM), in which we vary visual encoders to create heterogeneous models, we find that capable world models evolve toward geometrically similar internal structures. Moreover, via model stitching, we show that the internal features of one world model can be mapped to another with limited performance degradation, providing evidence of functional compatibility. Our findings suggest that the pursuit of predictive consistency can promote shared, transition-compatible latent structure across world models.

Aligning large language models to human-centered objectives is difficult when targets are non-executable and context-dependent, limiting reliable verification and scalable supervision. Although synthetic data expands coverage, weak verification shifts the bottleneck from generation to selection. Noisy signals destabilize iterative refinement and can cause silent regressions. We propose Agentic Data Evolution (ADE), a data-centric framework that organizes synthetic supervision as evolving data snapshots. ADE improves data snapshots through a closed-loop Observation-Variation-Selection (OVS) procedure, where a steady-state admission mechanism acts as a quality ratchet that conservatively gates updates for sustained cross-round improvement. We validate these improvements through complementary intrinsic trend tracking and extrinsic post-training evaluation. On DEV300, ADE raises the intrinsic win rate from 50% to 75.81% and the extrinsic win rate from 55.20% to 68.86%, consistent performance gains across diverse benchmarks. Blind expert evaluation further confirms this, with a 66.11% preference for evolved answers. These gains extend across post-training methods, model scales, and tasks beyond the target weakly verifiable educational objectives. Resources are available at https://github.com/ZeroLoss-Lab/Agentic-Data-Evolution.