Papers

Retinal fundus photography is widely used for screening and monitoring ocular diseases, but many modern classification pipelines rely on deep latent representations and provide limited interpretability. This study develops an interpretable fundus image classification framework based on a ring-structured representation of the retinal vasculature centered on the optic disc. The method quantifies vessel geometry, color appearance, oxygenation-related vascular appearance, and vessel–background entropy within concentric retinal regions. These physiologically motivated descriptors are derived from vessel masks, image intensities, and optical-density measurements and aggregated across rings to capture spatial variation in vascular properties. Using only quantitative vascular descriptors, the proposed method achieved strong classification performance across three public fundus datasets. On HRF, it achieved 91.1% accuracy using automatically generated vessel masks, matching RETFound, a vision transformer pretrained on large-scale retinal fundus image data, under the same evaluation setting. Additional analyses suggest that pretrained image models are sensitive to acquisition-related spatial cues, including fundus scale and retinal position within the field of view, as well as broader non-vessel image characteristics. This framework may support interpretable disease classification, quantitative retinal phenotyping, and retinal biomarker discovery without requiring large task-specific training datasets.

Hyperparameter selection remains a key challenge in Bayesian optimization (BO) and Bayesian active learning (AL), as model misspecification can lead to suboptimal performance, while more accurate fully Bayesian treatments typically rely on computationally expensive MCMC sampling. This paper proposes a unified framework, KENDO (Kernel ENsemble Disagreement-aware Operator), that integrates Ensemble Gaussian Processes (EGP) with disagreement-aware acquisition strategies. The central idea is to replace hyperparameter sampling with a kernel ensemble and adaptive Bayesian weighting, combined with disagreement-aware acquisition strategies. Within this unified framework, we instantiate KENDO-BO for BO and KENDO-AL for Bayesian AL, demonstrating that both arise from a common self-correcting mechanism with task-specific acquisition objectives. We further extend the approach to multi-objective optimization via random scalarization that preserves the single-optimizer conditioning structure. Thorough numerical tests on synthetic and real-world benchmarks across single-objective optimization, multi-objective optimization, and active learning demonstrate that (i) KENDO-BO achieves competitive or superior optimization performance compared to state-of-the-art methods while reducing computational overhead by up to $5\times$ and (ii) KENDO-AL achieves superior predictive calibration over MCMC-based active learning baselines with up to $27\times$ speedup.

Claims that generative AI will soon write all of the code have led to predictions that programming is nearing its end. In this vision paper, we argue against this assumption that broader access to code generation necessarily democratizes software development, i.e., everyone can code but we have to distinguish between access and control: by access, we mean the ability of more people, including non-experts and less-experienced developers, to generate code-like artifacts with AI; by control, we mean the capacity to inspect, evaluate, integrate, maintain, and govern those artifacts as dependable software. While AI may broaden access to code production, control may become more concentrated among those who own or understand the code, software practices, infrastructure, evaluation practices, and deployment pipelines. Grounded in an expert panel, our vision paper argues that AI does not eliminate software engineering expertise but shifts where that expertise becomes most critical. The locus of software engineering expertise is shifting toward intent specification: orchestrating and governing AI behavior, evaluating software behavior, and integrating software systems. We conclude this paper by identifying research opportunities for education, tools, and policy that can help the software engineering community respond to the AI era with greater agency, accountability, and adaptability.

A vast amount of optical satellite data is being transmitted to Earth-based servers every day, and more than half of this data is affected by haze or clouds. Additionally, this data suffers from the fundamental trade-off between spatial and temporal resolution, which remains largely unresolved, making the acquisition of continuous high-resolution satellite observations of clouds an ongoing challenge. This work addresses this challenge by proposing two Deep Learning super-resolution methods for the accurate downscaling of SEVIRI cloud mask products, as well as a novel cross-sensor cloud mask dataset called SEVMOD-CM, created by spatially and temporally matching MODIS and SEVIRI satellite observations. The two proposed models are a CNN-based (SpatialCNN) and a GAN-based (SpatialGAN) Neural Network. Trained on the SEVIRI spectral and cloud mask products, the proposed methods predict the corresponding MODIS Cloud masks, achieving a 4x spatial enhancement across sensor domains. Both approaches are evaluated experimentally, and compared against the standard bicubic interpolation upsampling technique. The experimental results demonstrate the value of the proposed models and dataset for the remote sensing community, highlighting the benefits of applying super-resolution techniques to geostationary-derived cloud mask products for applications such as atmospheric monitoring, weather forecasting, disaster risk reduction, solar energy forecasting, and climate research.

World-Action Models (WAMs) jointly learn future visual prediction and action generation, using video dynamics as a representation-learning signal for robotic manipulation. However, their video latents are primarily optimized for visual prediction and are not explicitly encouraged to preserve cross-view geometric structure or spatially localized, object-relevant semantics. We propose GaussianWAM, a training-time representation-enhancement framework that organizes geometric and semantic supervision through a 3D Gaussian field. Given synchronized multi-view observations, frozen geometry and vision foundation models provide depth, camera parameters, and dense semantic features. GaussianWAM binds these heterogeneous signals to shared Gaussian primitives and renders spatially aligned semantic, depth, and coverage targets, which are distilled into the current-observation representations of the WAM. All teacher models, Gaussian components, and auxiliary prediction heads are removed after training, leaving the original WAM inference path without additional modules or forward computation. On LIBERO-Plus, GaussianWAM improves FastWAM from 52.05% to 71.29% and Cosmos Policy from 71.52% to 77.30%. Direct CLIP and VGGT distillation already establishes a strong FastWAM baseline of 69.37%, while Gaussian-field unification further improves it to 71.29%, supporting the benefit of spatially organizing heterogeneous teacher signals. GaussianWAM also improves performance on standard LIBERO and shows positive transfer trends on RoboTwin and real-world manipulation. These results suggest that training-time Gaussian distillation provides a practical way to inject geometry- and semantics-related supervision into WAM representations without changing their deployment architecture.

Lifted inference algorithms enable scalable probabilistic inference even for large object domains by leveraging the indistinguishability of objects in a probability distribution. An essential prerequisite for constructing a lifted representation is to identify commutative factors, i.e., functions whose output values are invariant under permutations of a subset of their input values, in a potential-based factorisation. In practice, however, parameters learned from data inevitably deviate even if associated objects are indistinguishable, causing their corresponding factors to be only approximately commutative instead of being exactly commutative. We address this problem by introducing the concept of {\epsilon}-commutativity, a relaxation of commutativity where output values are only approximately invariant under permutations of input values. Specifically, we show how {\epsilon}-commutativity can be exploited for lifted model construction, downstream probabilistic inference, and prove strict bounds on the induced approximation error, thereby ensuring the practical applicability of lifted model construction while maintaining highly accurate query results. These theoretical guarantees are confirmed empirically, demonstrating comparable query accuracy at lower runtime.

Optimization of hyperparameters is a critical factor to obtain optimal model performance. While existing research has predominantly concentrated on batch-learning scenarios, addressing the complexities inherent in data streams presents a challenge. The deployment of sophisticated methodologies to manage data streams becomes highly important. Consequently, the capacity for self-adjusting hyperparameters during on-line learning phases emerges as a goal. Many hyperparameters exhibit constraints and are confined within bounded search spaces, rendering specific solutions unacceptable upon applying optimization operators. To solve this issue, employing boundary constraint- handling techniques becomes imperative to rectify invalid solutions. This paper presents strategies for effectively managing boundary constraints within constrained numerical optimization problems. Recent methodologies, including heuristic and evolutionary-based optimization, employ a "boundary" strategy, wherein values that surpass boundary thresholds for a given hyperparameter are realigned to the respective limits. Our study introduces four strategies to navigate boundary constraints in online optimization algorithms. Through empirical investigations conducted on established datasets, we demonstrate that adopting boundary strategies outperforms the "boundary" strategy.

Linear programming (LP) formulations offer a conceptually elegant approach to infinite-horizon, model-free nonlinear optimal control in continuous spaces. However, in addition to the curse of dimensionality, their practical use is limited by the difficulty of consistently obtaining bounded solutions. In this work, we use moment-matching techniques to derive sufficient boundedness conditions in terms of the available dataset and the cost vector of the LP. Moreover, we discuss practical design methods for nonlinear systems and polynomial features.

While text-based hallucination detection is well studied, reference-free detection of factual alterations in speech remains underexplored, especially for low-resource languages. Our spoken benchmark comprises 12,013 English, Russian, and Kazakh news samples with three synthetic alteration types and three severity levels, pairing source articles with rewrites as text, synthesized audio, and ASR transcripts. We add 290 fact-checked misinformation items collected in Russian (225) and Kazakh (65), translated into the other language and rendered through the same TTS-ASR pipeline. We evaluate fine-tuned multilingual encoders and zero-shot multimodal decoders on text, transcripts, and audio. Detectors receive only target inputs without source articles or external evidence; the task evaluates reference-free classification rather than evidence-grounded verification. Encoder degradation from source text to transcripts generally tracks per-language ASR error on the binary task. Among decoders, only Gemma-3n exceeds the binary majority-class baseline in macro-F1, on transcripts only; the other four fall below their respective baselines. Comparisons between audio and transcripts are confounded by differences in evaluation coverage and class balance. Synthetic-trained detectors achieve 0.82–0.88 macro-F1 on real-world misinformation source text; Russian provenance analysis reveals veracity-related and model-dependent machine-style signals, a key confound in synthetic hallucination benchmarks.

Ultralow-latency communication is critical for emerging next-generation applications such as XR, real-time control, and distributed sensing. We present ECO-COMM, an event-camera-based optical communication system for ultra-low-latency device association and lightweight information exchange. By exploiting the asynchronous sensing and microsecond-level temporal resolution of event cameras, ECO-COMM captures high-frequency optical signals without frame-based acquisition delays. We identify and analyze key hardware-induced challenges in event-camera communication, including timestamp inconsistency, readout contention, trailing effects, and the inevitable refractory period, and develop hardware-aware mitigation techniques to address them. Focusing on a single transmitter-receiver optical link, ECO-COMM establishes the feasibility of practical ultra-low-latency event-camera communication using commercially available hardware.A prototype implementation using an eight-LED transmitter and an off-the-shelf event camera achieves device association within 15 microseconds, symbol latency as low as 100 microseconds, and end-to-end latency below 8 milliseconds for 32-byte payloads at 0.1% bit error rate. ECO-COMM establishes a practical and complementary communication paradigm for ultra-low-latency systems where responsiveness and temporal precision are paramount.

When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation—is there a motion in parameter space realising the group action in function space? We formulate this as a lifting problem for the realisation map $\Phi:\theta\mapsto f_\theta$, and show that a smooth parameter-space action exists only if the tangent space to the function's symmetry orbit lies within the image of $\mathrm d\Phi_\theta$, whose columns are the functional sensitivities of individual parameters. This condition is also sufficient for pointwise first-order lifting. Relaxing it in least squares yields two local parameter directions: one following the symmetry orbit, one descending towards the equivariant subspace, with residuals measuring what the parametrisation cannot reach. On a rotationally invariant classifier we find these directions induce their predicted function-space motion, but only locally: recomputed directions track the orbit and reduce the equivariance defect, while directions held fixed depart from both after training. The same holds for Hamiltonian neural networks trained on a rotationally symmetric potential, even though the architecture does not explicitly enforce the symmetry.

This paper presents a neural operator-based approach for the output feedback boundary stabilization of reaction diffusion PDEs. The classical output feedback backstepping design requires solving control and observer kernel equations for each reaction coefficient. To avoid computing these kernel functions, the output feedback control law is reformulated as a causal boundary operator that maps the reaction coefficient and the boundary measurement to the boundary control input. A hybrid DeepONet-LSTM neural operator is proposed to approximate this causal operator, where DeepONet encodes the spatial coefficient and LSTM captures the temporal dependence of the measurement history. We analyze the Lipschitz continuity of the boundary operator and prove the closed-loop practical stability with the learned controller. A modified loss is also introduced to improve the temporal regularity of the learned boundary input. Numerical results illustrate that the proposed neural operator controller effectively stabilizes the system.

Persian (Farsi) is often described as a low-resource language in natural language processing, but that label collapses distinct shortages into a single category. This paper argues that Persian is more precisely described as annotation-scarce, provided that the term is understood as a property of its NLP resource ecology rather than an intrinsic property of the language. The review covers 34 representative Persian text resources available by July 2026 and adds three quantitative cross-checks. First, independent web measurements place Persian among roughly the twenty most visible content languages: W3Techs reports Persian on about 0.9% of websites with a known content language, while Common Crawl CC-MAIN-2026-30 identifies Persian as the primary language of 0.7039% of HTML pages. Second, a selective speech review shows a long resource trajectory from FARSDAT to recent corpora containing hundreds or thousands of hours of speech. Third, a matched Persian-English comparison normalizes task-specific annotation volumes by relative Common Crawl web presence. The resulting ratios vary sharply: Persian syntax and news NER are comparatively dense, whereas natural-language inference falls below the web-proportional baseline. The evidence therefore does not support a simple claim that Persian is globally deficient in labeled volume. Instead, annotation scarcity is expressed through uneven task and domain coverage, incompatible schemes, access and documentation friction, and limited supervision for specialist domains, preference data, and varieties beyond standard Iranian Persian.

Predictive Coding (PC) is a neural learning paradigm that enables parallelizable neural network layer updates. However, the main bottleneck of PC Networks (PCN) is the sequential backwards error propagation. To tackle this, we introduce a training technique that pairs a Generative PCN with a support Encoding PCN. The two PCNs are trained in parallel to match their neural activations, without sequential propagation. We apply this to time series anomaly detection and show that our approach results in more stable, continuous, online learning.

Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training large language models. However, RLVR suffers from sparse task-level feedback, while OPD provides dense token-level guidance but ignores trajectory correctness, limiting its performance to that of the teacher. Combining them is a promising direction: OPD supplies dense supervisory signals, while RLVR provides task-level correctness. Nevertheless, existing integrations often rely on weighted combination or heuristic switching, introducing extra hyperparameters and trade-offs. We propose On-policy Distillation with Verifiable Reward (OPDVR), a simple yet effective method that seamlessly combines OPD and RLVR without adding any hyperparameters. We first reformulate the implicit reward of sampled-token OPD based on trajectory correctness, then apply a ReLU gating mechanism to ensure that correct trajectories receive non-negative rewards and incorrect ones receive non-positive rewards—thereby aligning the distillation signal with task success while preserving the teacher's distributional guidance. Furthermore, our modification transforms sampled-token OPD into a proper RLVR method, making it readily combinable with any policy gradient algorithm, such as GRPO. Experiments on six reasoning benchmarks show that OPDVR consistently outperforms standard OPD. Our code is available at https://github.com/LeapLabTHU/OPDVR.

Agentic systems increasingly gate actions on a model's own stated confidence, which assumes confidence tracks correctness at the moment of acting. We test this in a hidden-information chess variant where royal status can be secretly, repeatedly relocated between pieces, and where an agent's stated probability distribution over the opponent's hidden royal piece – elicited every turn, separately from the move it chooses – is scored against ground truth recoverable after the game. Across two independent batches, captures made at high stated confidence ($\geq 0.5$) about the hidden piece's location were correct in 1 of 62 cases. The calibration deficit is concentrated almost entirely in these events: 99.3% of it in the original batch, 98.7% in the replication. The same pattern, in weaker form, orders consistently (point estimates only; most pairwise gaps are not statistically distinguishable at this sample size) across four further model configurations spanning a second provider – reported as scope for the finding, not as evidence that capability predicts calibration: a same-model comparison at a fixed external leaderboard score shows a deliberation-budget change alone moves the metric by nearly as much as a large cross-model gap. In a separate seat, conventional evaluation axes – legality, cost, latency, completion rate – can dissociate entirely from belief quality, with the configuration winning on every conventional axis producing the worst belief quality tested. A model exhibiting this pattern can still win the game its belief was about, which is why outcome-only evaluation would not detect it.

Precision oncology necessitates a longitudinal model of patient state that captures cancer evolution and treatment over time, integrating multimodal observations. We introduce the oFM, a foundation model developed on a real-world oncology cohort of 1.67 million cancer patients that integrates clinical trajectories with DNA, RNA, and H&E pathology. Patient-level partitions were reserved for training, validation, and testing, with over one million patients used for training. The oFM encodes daily clinical and molecular episodes and, along with pathology images, integrates them over time to produce a patient state embedding. We evaluate frozen oFM embeddings against expert-curated clinical and molecular baseline features. In prognostic benchmarks, the oFM improved AUC for treatment response, progression-free survival, and overall survival (0.774 vs. 0.563 for overall survival). Across 11 comparative-treatment cohorts, the oFM embeddings achieved a three-fold higher pooled and scale-normalized treatment-benefit AUTOC than baseline features with improved benefit ranking in 9 of 11 cohorts, and provided stronger prognostic discrimination within both treatment arms. We also evaluated a mechanism discovery framework that interprets downstream models built on oFM embeddings by linking their predicted outcomes to clinically and biologically grounded mechanisms through an evidence-grounded temporal graph, enabling evaluation in clinical and drug-development applications.

This paper presents a wideband power amplifier (PA) designed and implemented in Infineon Technologies' 130-nm SiGe BiCMOS process for upper W-band and lower D-band applications. A complete load-pull simulation methodology is carried out, and a band pass filter (BPF)-based matching strategy is employed for the design of the output and inter-stage matching networks. The fabricated PA prototype achieves a small-signal gain 3-dB bandwidth of 71-133 GHz. Moreover, it maintains a relatively flat gain of approximately 15.7 dB over 75-128 GHz, with less than 1-dB fluctuation. The measured saturated output power is 8.8-11.7 dBm, while the measured peak power-added efficiency (PAE) is 7.2-11.1%. These results demonstrate the potential of SiGe BiCMOS technology for wideband and integrated transmitter front ends operating across the W-/D-band frequency range.

This paper presents a compact, fully differential, two-stage millimeter-wave (mm-wave) cascode power amplifier (PA) designed and implemented in a 22nm FD-SOI CMOS process (22FDX+). The PA employs the newly introduced extended-drain MOS (EDMOS) device in 22FDX+, together with a carefully engineered device core and transformer baluns. At 50 GHz, the prototype achieves 18.8 dBm saturated output power (PSAT), 18.1 dBm 1-dB compression output power P1dB, and 21% power-added efficiency (PAE) at P1dB. To the best of our knowledge, this work achieves the highest reported power density of 2.6 W/mm2 among single-way, two-stage CMOS cascode PAs.

One algorithmic composition may require a Csound score, engraved notation, real-time control, and a rehearsal click. Authored separately, their timelines drift. Temporal System is a Wolfram Language paclet that instead compiles one immutable store of typed entities on a rational beat timeline through backend-specific contracts. It emits Csound synthesis, beta MusicXML 4.0, OSC control, and click artifacts that remain synchronized because they share that store. Conversion to seconds, samples, or hertz occurs only at render time. Csound notes use stable named instruments in external .orc files; curves become k-rate signals declared against score p-fields. The click backend derives rehearsal audio from the same meter and tempo and reuses the Csound serializer. We describe the temporal, semantic, and rendering-contract layers, their practical trade-offs, and the limits of this proprietary authoring environment within an otherwise open-source ecosystem. The archived supplement exposes the reported outputs pending paclet release.

Video games provide a scalable source of training data for video world models, offering diverse environments, complex interactions, and abundant in-the-wild gameplay videos. However, raw gameplay footage entangles the game world with screen-space interfaces, introducing game-specific biases and irrelevant dynamics that hinder world-model training. To address this problem, we introduce GameUI-Taxonomy and G2WEngine, a full-stack framework that formalizes gameplay UI grounding and removal. G2WEngine automatically extracts reusable UI assets from real gameplay videos and synthesizes temporally coherent UI overlays on clean footage. Using this engine, we construct Game2World, comprising 96K synthetic paired videos with precise reconstruction targets and 1,079 in-the-wild clips from 303 games for realistic evaluation. Its asset library contains 5,132 verified UI elements across 21 taxonomy categories, collected from 1,010 representative gameplay frames. Based on Game2World, we propose GameCleaner, a mask-free gameplay UI removal model that combines multimodal semantic understanding with video editing capabilities. Unlike mask-based methods, GameCleaner directly identifies and removes diverse HUD elements while preserving the underlying scene content and temporal dynamics. In a controlled pilot, world models trained on UI-free gameplay improve overall VideoReward by 6.83% over those trained on UI-overlaid data. On UI-removal evaluation, GameCleaner achieves an average AAR of 95.36 on synthetic videos, outperforming the strongest temporal mask baseline by 57.3%, and obtains the best in-the-wild AAR of 80.05 with 99.8 background preservation. These results demonstrate the scalable potential of transforming Internet gameplay videos into high-quality world-model training data. Code, dataset, and model will be available at https://github.com/Dongping-Chen/Game2World.

Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the long sampling trajectories and heterogeneous multimodal computation of large models make inference prohibitively expensive. We present TurboT2VA, a distillation and inference framework for accelerating a 19B-parameter joint video-audio model. Large-scale T2VA distillation is challenged by modality-imbalanced optimization, the difficulty of continuous-time consistency training at scale, and the quality–diversity trade-off. TurboT2VA addresses these issues with per-modality normalization and a progressive curriculum comprising discrete consistency warm-up, continuous consistency refinement, and joint consistency–distribution matching. The curriculum first establishes a stable, diverse generation trajectory and only then introduces distribution-level refinement. On LTX-2, four-step distillation reduces generator latency from 50.52s to 2.51s at the standard evaluation resolution of 512$\times$768, achieving a 20.1$\times$ speedup while maintaining strong visual quality, audio fidelity, diversity, and video-audio synchronization. We further develop an architecture-aware inference stack that combines guarded W8A8 and fused operators, padded-text compaction, and modality-aware sparse attention while preserving dense cross-modal and text-conditioning paths. Under the high-resolution deployment setting at 1024$\times$1792, the complete stack reduces generator latency from 318.74s to 5.83s on one NVIDIA H20, achieving a 54.67$\times$ generator-only speedup. Inference code and generation demos are available at https://github.com/thu-ml/TurboDiffusion/tree/main/turbot2va.

Process mining is widely used to diagnose processes and identify performance and compliance issues. Specifically, Predictive Process Monitoring (PPM) techniques use AI models to predict outcomes of ongoing process instances. While these models can achieve high predictive performance, their black-box nature makes it difficult to understand the underlying reasons behind their output predictions. In this paper, we propose a novel approach for generating local (case-level) explanations of process monitor predictions based on the framework of actual causality. We define a causal model tailored to processes that captures temporal dependencies between events in a trace, thus allowing us to reason about causal influence of events on the predicted outcome. Our method uses this model implicitly to compute causes and quantify the importance of different events with respect to the predicted outcome. We present a practical, model-agnostic algorithm that approximates event responsibility given the process structure reflected in the causal model. We evaluate our approach on a range of datasets derived from real-life event logs from a standard PPM benchmark. Each dataset contains up to 130,000 traces, with trace lengths of up to 1,800 events and up to 400 distinct event types. We compare our approach with state-of-the-art local explanation methods. The results demonstrate that our approach produces more stable and concise explanations while maintaining competitive efficiency.

Referring surgical video segmentation requires segmenting a target instrument or tissue region across video frames according to a natural language expression. Recent Segment Anything Model 2 (SAM2) based two-stage methods (e.g., ReSurgSAM2) first ground the referred target in an initial or selected frame, then propagate the selected mask via tracking. Although effective, their performance is highly sensitive to the quality of the initial grounded mask: once an incorrect anchor is selected, subsequent tracking tends to propagate the error. This issue is especially challenging in surgical videos due to visually similar instruments, occlusion, and complex tissue-tool interactions. To address this issue, we propose ReGround-Surg, a lightweight reliability-guided anchor grounding framework to improve SAM2-based referring surgical video segmentation. It first predicts a text-conditioned spatial reliability map from the referring expression and current-frame visual features. The map is then reused in two complementary branches: a Gated Side Adapter enhances expression-relevant visual regions before text-to-vision fusion, while a Reliability-Weighted Vision-to-Text Attention module suppresses off-target visual evidence during prompt-token aggregation. Experiments on Ref-EndoVis17 and Ref-EndoVis18 show consistent improvements over state-of-the-art methods across three evaluation splits with negligible speed reduction. Code is publicly available at https://github.com/JiaxinWen1/ReGround-Surg.

As mobile phone adoption has surged, so have scams involving these devices. One such scam, known as SMiShing (or smishing) after Short Message Service (SMS), involves fraudsters sending phishing links via mobile texts. Despite the prevalence of SMiShing, there is a lack of data on who is most vulnerable to these attacks. Prior research on phishing (its email counterpart) suggests that susceptibility may vary by demographic and contextual factors. In two large-scale surveys, we use a previously published simulation method to collect data from representative samples of U.S. adult mobile phone users. Our findings indicate that younger individuals and college students are particularly vulnerable. Participants struggled to correctly identify legitimate messages, with the second study providing comparisons of financial message variants. Researchers, regulators, and telecoms can help users by creating mobile-specific interventions for under-24 and university customers and adding verifications and warnings.

Agentic Web search can retrieve relevant information without establishing that the retrieved content actually supports the claims used in an answer. Existing agents typically keep search and evidence recording in a linear interaction trace and optimize primarily for final-answer correctness, providing limited supervision for intermediate grounding. We present EviGraph, a deep-search framework that separates search execution from evidence recording while using a shared policy for the trainable roles. An executor plans concise queries, a frozen evidence verifier inspects source pages and returns verbatim evidence items with an explicit polarity, and the policy maps those items to add/support graph requests that are checked by a deterministic structural validator. The resulting graph serves both as persistent working memory and as a source of dense process rewards, enabling reinforcement learning to directly supervise evidence construction rather than only the final answer. On BrowseComp-Plus, a Qwen3-8B EviGraph agent achieves 35.9% accuracy under a matched interaction budget, compared with 26.9% for the same dual-role architecture without reinforcement learning and 2.7% for a monolithic agent, while generating fewer tokens per rollout. Consistent gains on BrowseComp, GAIA, and XBench indicate that explicitly structuring and rewarding evidence recording improves agentic search

Power outage prediction models are increasingly used in assessments of climate-driven infrastructure risk, yet current evaluation practices obscure whether these models generalize to the novel conditions such applications require. We identify three common methodological choices in power outage prediction models that influence their ability to generalize across spatial, temporal, and event-based settings. We compare the predictive performance impacts of different methodological decisions using publicly available data for the U.S. East Coast from 2018 to 2023 and feature sets derived from weather reanalysis and land-cover data, and embeddings from a GeoAI foundation model (Prithvi WxC). Specifically, we assess model performance under multiple test selection strategies, including unfiltered random splits, leave-one-state-out, and leave-one-event-out designs, which increasingly approximate real-world deployment conditions. While random train-test splits yield strong performance, we show that these results are inflated by spatial and temporal autocorrelation. Under spatial and temporal holdout experiments, predictive accuracy degrades substantially, with models often failing to outperform a simple null baseline. Incorporating GeoAI foundation model embeddings yields limited and inconsistent improvements, primarily for spatial generalization, and does not resolve poor event-level transferability. These findings suggest that, given current data availability and evaluation practices, publicly trained outage prediction models offer limited and uncertain operational value. Progress will likely require improved data coverage, more realistic evaluation protocols, and a shift in focus from marginal modeling advances toward addressing structural data constraints.

We introduce Maia 200, an advanced AI accelerator delivering high performance-10 145 Tflop/s FP4 and 5072 Tflop/s FP8 within a 750W TDP and 7 TB/s HBM bandwidth. Maia exemplifies a new class of Software Defined Locally Accessed Dataflow Architectures (SDLA), which explicitly program dataflow engines to orchestrate highly specialized memories and data movement engines. This approach shifts the focus from today's thread-centric to data-movement-centric architecture, improving efficiency and scalability. Our taxonomy of data management, inspired by Flynn's classification, highlights how SDLA addresses challenges in modern AI computing. Maia 200 achieves significant cost and energy savings while supporting massive parallelism for AI inference workloads, making it a compelling solution for next-generation high-performance computing systems.

Evaluations of generative language models frequently interpret observable behavioral traits, such as political stance, brand inclination, and normative framing, as manifestations of model weights, post-training alignment, or prompting. This interpretation risks conflating a foundation model with the multi-layered production system through which its outputs are ultimately served. Modern inference stacks support runtime interventions capable of modifying generation while model parameters remain frozen. We examine inference-time framing bias: systematic runtime steering of generated text toward institutional, ideological, or commercial frames without requiring changes to the underlying model parameters. We formalize the Inference Attribution Problem and establish an observational non-identifiability result showing that, under black-box observation alone, behaviorally equivalent deployed systems may arise from structurally distinct combinations of model parameters and inference policies. Consequently, observed behavioral bias does not uniquely identify the architectural layer responsible for it. We further characterize Probability Placement as a deployment pattern in which undisclosed commercial influence is embedded within an ostensibly organic assistant response through systematic probability-mass reallocation, distinguishing it from explicit token-auction mechanisms for generative advertising. Finally, we discuss implications for behavioral auditing, inference provenance, confidential computing, cryptographic attestation, the EU AI Act, the Digital Services Act, and advertising-disclosure principles. We argue that governance of generative systems must increasingly distinguish between auditing a model and auditing the deployed system that ultimately speaks.

Markov models are established tools for symbolic music, including non-homogeneous formulations. The narrower contribution examined here is an observation-driven estimation mechanism: overlapping sliding windows derive a trajectory of local transition kernels from one symbolic sequence rather than from an exogenous formal partition. We test this mechanism on 273 logical note events from Debussy's Syrinx (1913), using the often-proposed A-B-A' reading as a reference rather than ground truth. We apply the same validation to absolute-pitch and notated-duration kernels. At $L=6$, both reference boundaries attain the Jensen–Shannon maximum in both dimensions; the duration plateau is substantially narrower (64 of 267 comparisons) than the pitch plateau (210 of 267). Because the theoretical maximum for consecutive sliding-window comparisons is set by window geometry and equals $1/\sqrt{L-1}$ for maximal turnover of the entering/leaving transition, the pitch value at $L=6$ and its broad plateau are not, by themselves, strong evidence. Their cross-dimensional alignment is consistent with boundary sensitivity, while the broad plateaus preclude treating either curve alone as a unique automatic segmenter. Five-hundred-draw re-synthesis experiments quantify departure from the source in both dimensions and expose an exact-copy degeneracy at $L=2$.