Papers

Modern text-to-image models produce high-fidelity images but still struggle with compositional prompts that require instance identity, attribute ownership, counting, spatial ordering, and role-sensitive relations. We introduce Panoptic Scene Program Diffusion Transformer (PSP-DiT), a diffusion-transformer architecture that treats a panoptic scene program as a first-class latent variable rather than an external control signal or post-hoc parse. PSP-DiT jointly denoises image latents and scene-program latents through coupled transformer streams, while panoptic grounding and cycle-consistency objectives tie object instances, attributes, relations, and counts to visual support in the generated image. Under matched training and inference settings, PSP-DiT improves over a strong flat-text baseline across GenEval 2, SANEval-Simple, PSG-Score, and DetailMaster, with the largest gains on counting, attribute binding, role-sensitive relations, and long structured prompts. The method preserves image quality, adds modest inference overhead, and remains robust to imperfect scene programs.

Magnetic resonance imaging involves an inherent trade-off among spatial resolution, acquisition time, and noise. This trade-off contributes to long scan times and high cost. Deep learning has improved image denoising, but cardiac MRI remains difficult because high-resolution, rapid acquisitions generally lack corresponding low-noise ground truth. Self-supervised denoising offers a potential solution by learning from noisy image pairs or even single noisy acquisitions. However, we show that Noise2Void-style blind-spot denoising, which uses a mean squared error (MSE) loss and assumes zero-mean, independent and identically distributed (i.i.d.) noise, is poorly suited to MR magnitude images. When applied to short-axis $T2$-weighted and $T1\rho$-weighted cardiac MRI with synthetic Rician noise, it produces biased denoised images and biased parametric maps of $T2$ and $T1\rho$. To address this limitation, we formulate self-supervised denoising as maximum likelihood estimation under a known Rician noise model. This yields unbiased denoisers that are competitive with supervised baselines.

Artificial intelligence (AI)-based weather prediction is approaching the skill of physical numerical weather prediction (NWP) systems at a fraction of the computational cost. This is particularly promising for Africa, where rainfall extremes are intensifying and many forecasting centres lack the infrastructure to run physical models at extended lead times. We present a calibrated comparison of GraphCast, GenCast and the Functional Generative Network (FGN) against the physical NWP model IFS for rainfall prediction across Africa. Deterministic and probabilistic forecasts are postprocessed using Isotonic Distributional Regression and evaluated with the Continuous Ranked Probability Score against IMERG, RFEv2 and CHIRPS across seasons, wet and dry regimes, elevation zones and lead times. All models retain skill beyond climatology across most seasons and at extended lead times. AI models generally outperform IFS in wet regions, whereas IFS performs better in dry, high-elevation areas, where its finer resolution better represents orographic controls on rainfall. Across observational datasets and seasons, AI models achieve a median improvement of approximately 5% over IFS. GraphCast achieves calibrated skill comparable to the ensemble-based FGN, although FGN provides greater significant skill at longer lead times. These results highlight the potential of calibrated AI weather prediction to provide accessible and computationally efficient rainfall forecasts across Africa, while demonstrating the continuing importance of spatial resolution, ensemble design and regional characteristics.

We study whether a manually specified runtime supervisor can correct recurring failures of an existing end-to-end parking policy in a fixed CARLA parking lot. The vision-based Transformer architecture is inherited from Yang et al.; our contribution is a timed, rule-based Parametric Safety Shield (PSS) applied to its control outputs. The PSS uses hand-calibrated speed, position, and duration thresholds to intervene in observed failure modes, including boundary exits, delayed braking, and stalled or oscillatory control. In the reported closed-loop evaluation, 16 held-out target slots and six initial poses are each evaluated in four rounds (384 attempts per configuration). Target success increases from 327/384 (85.16%) for the retrained policy to 375/384 (97.66%) with the PSS; mean position and orientation errors among successful attempts are 0.21m and 0.33 degrees. These results show an improvement within this simulator setup. The repeated attempts share one map, vehicle, and sensor configuration, and the PSS uses simulator world coordinates; thus the results do not establish generalization to other lots or real vehicles, or a formal safety guarantee.

Changes in listener acoustics require active noise control (ANC) filters to be redesigned for new acoustic paths. We introduce PRIME-ANC, a shared neural synthesizer that learns a bounded, path-dependent logmagnitude correction to a regularized path-ratio base. Minimum-phase reconstruction and truncation produce finite-impulse-response (FIR) filters; training optimizes their noise-control performance. Across ten random training/test splits per dataset, PRIME-ANC achieves average held-out one-third-octave reductions of 18.81 and 17.76 dB over 50 Hz-5 kHz on a ten-path dataset and a public earphone database, respectively. On original earphone measurements, it improves upon the path-ratio base by 7.89 dB. Ablation studies support the contributions of both the analytic base and the path-dependent correction. Given calibrated paths for a held-out listener condition, PRIME-ANC generates a path-specific FIR without iterative optimization. With three Gauss-Newton updates, it reaches 21.43 dB reduction, approaching direct weighted least-squares design while producing lower amplification and root-mean-square control output.

Many planning and control tasks for tendon-driven continuum robots (TDCRs) require the complete Cartesian backbone geometry. We present a reduced Cartesian framework for planar, axially compressible TDCRs that propagates equilibrium configurations along prescribed tendon-force and tendon-displacement trajectories. The backbone is represented by two global position fields. Following exact variation, a Taylor-Galerkin reduction condenses prescribed spatial properties and distributed loads into offline moment vectors, yielding analytic reduced residuals and Jacobians without online spatial quadrature or numerical differentiation. Analytical differentiation and residual correction yield first-order rate systems requiring one fixed-dimensional linear solve per rate evaluation after initial equilibrium alignment on a regular branch. Across four simulated cases covering variable tendon routing, nonuniform geometry, axial compression, and their combined effects, the propagated Cartesian shapes and distributed strains closely match pointwise geometrically variable-strain (GVS) equilibrium solutions. Residual correction suppresses propagation drift across the tested step sizes while adding only about 0.98% to the mean update time of uncorrected Euler. The proposed method requires 0.508 ms per update on average, approximately 11 times faster than pointwise GVS solves. Displacement-driven experiments yield a maximum normalized mean backbone position error of 1.02% and a maximum end-effector position error of 0.28%. These results support efficient and accurate Cartesian full-shape prediction along prescribed actuation paths.

General-purpose multimodal agents can write robot-control programs, but repeated exploration and model-mediated action selection can make execution slow. We study how external body knowledge, successful experience, and executable skills improve an XLeRobot controlled by GPT-6-Astra in a simulated and a physical elevator-button task. In 30 fixed-start simulation trials, complete robot geometry and camera information reduce mean completion time by 57.4% relative to a baseline with only the common control interface and no prior experience; images with synchronized action and state records reduce it by 68.6% without additional body assets. In nine paired comparisons (18 trials) at starts displaced by 10-100 cm, experience recorded at the original start reduces mean time by 58-63% relative to no experience, demonstrating generalization to the tested new starting positions. During experience experiments, GPT-6-Astra spontaneously generates a short visual-feedback program. Researcher-refactored versions reduce mean local-task time by 29-31% in 27 simulation trials. Finally, 12 real-robot trials using operator-confirmed button contact demonstrate sim2real reuse: at a shared nominal start, simulation XML assets and simulation experience reduce mean time by 53.0% and 49.9%, respectively; real experience also transfers to two new starts. These results suggest a practical way to build general-purpose manipulation experiments around GPT-6-Astra: supply machine-readable body descriptions and synchronized demonstrations, and turn useful agent-generated feedback routines into reusable skills, while the agent adapts actions from current images. We release all task prompts, trial-level experimental data, and acquired skill implementations at https://github.com/hesd10/astra-robot-sim2real.

Networking defenses against traffic analysis fill idle slots with cover traffic, yet the physical layer carrying it still hands upper layers the erasure-only model of a silent-idle link, leaving the cover content unexploited. We shape that content: the idle-slot waveform is drawn from the codebook complement under a design distribution, the litter distribution, chosen to defeat a public-design passive observer while the upper layer keeps its block z-channel model. The maximum a posteriori (MAP) receiver reduces to a single threshold on the log-likelihood ratio between the best codeword and the prior-weighted litter aggregate; its errors are silent corruptions the upper layer cannot detect and erasures that retransmission absorbs. Receiver design is thus one-dimensional, minimizing erasure under a cap on silent corruption, and the joint design a Stackelberg game against a Kullback-Leibler (KL) indistinguishability metric, solved by an alternating convex relaxation and corroborated by an independent reinforcement-learning policy. On a rate-$3/4$ $(16,12)$ parity-check (LDPC) code against an observer who knows her own channel but whose channel the transmitter knows only statistically, shaped litter cuts the observer's Stein detection exponent by $41$ to $48\%$ relative to uniform cover, flat over a $10$~dB span and in the activity rate. Below the point where the legitimate link turns reliable, no cover distribution admits an operating point; at that point shaping costs about one percent of throughput, and nothing measurable $2$~dB above it.

Contextual image misuse pairs an image with a misleading claim. We study image-claim correspondence in fact-checked pairs containing out-of-context reuse, visual manipulation, or both. Existing pair-based detectors often compress the two modalities into a global compatibility score or learn a highly flexible interaction module, which can obscure a decisive local mismatch. We introduce directional multiscale coverage, a compact representation that summarizes local image-claim affinity in both directions and at three spatial scales. At each scale, each direction is summarized by its mean, lower quartile, and two thresholded support ratios; the signed difference between directional means completes a nine-dimensional scale descriptor. Concatenating the three scales yields a compact local representation for a lightweight global-local classifier. Under leakage-aware three-fold, three-seed evaluation on the Snopes subset of the Fauxtography benchmark, UNMATCH achieves 69.82 Macro-F1 and 71.05 balanced accuracy, exceeding the MCOT adaptation by 2.60 and 2.16 points. A matched-reassigned intervention shows that breaking the observed pairing lowers coverage and increases both discrepancy and false-pair probability.

Accurate and rapid prediction of the aerodynamic drag coefficient ($C_D$) is essential for vehicle design, particularly during early-stage design, where many candidate geometries must be evaluated. Although computational fluid dynamics (CFD) provides reliable aerodynamic estimates, its high computational cost limits large-scale design exploration. This paper proposes the hierarchical graph-pooling Transolver (HGPTrans), which combines hierarchical graph pooling with Transolver-based attention to directly predict $C_D$ from vehicle surface meshes. Motivated by the fact that vehicle aerodynamics depends on both local geometric features and long-range interactions among spatially distant surface regions, HGPTrans integrates three complementary components. Graph isomorphism convolutions encode discriminative local geometry, Transolver-style slice attention captures global interactions with linear computational complexity, and information-redundancy-aware hierarchical pooling progressively removes redundant nodes while preserving informative geometric structures. The model is trained and evaluated on the large-scale DrivAerNet and DrivAerNet++ datasets, where it achieves the lowest mean absolute error and mean squared error among the evaluated baselines. Its generalization capability is further assessed through transfer learning on a real-vehicle dataset containing both sedans and sport utility vehicles (SUVs), achieving relative $L_1$ errors of 1.56% (sedans) and 2.12% (SUVs) with an inference time of approximately $0.293$ s per vehicle. This corresponds to an acceleration of several orders of magnitude relative to high-fidelity CFD while keeping the predicted drag coefficients within a few percent of the CFD reference. Ablation studies confirm each component's contribution and reveal the effects of depth and pooling ratio.

Complementarity analyses of multimodal systems commonly report an oracle ceiling (the fraction of examples on which at least one unimodal branch is correct) and interpret the gap between it and realized fusion accuracy as recoverable headroom. We show that this ceiling is not a fusion target. Using frozen self-supervised audio and visual encoders with a trained head, we measure the ceiling and realized gain on CREMA-D under two audio encoders (one whose fine-tuning lineage includes CREMA-D, one clean) and on EAV under the contaminated encoder. Replacing the fine-tuned encoder with a self-supervised one triples the headroom, from +0.055to +0.186. A second clean encoder and a controlled degradation of the contaminated one fall on the same curve, so provenance moves the headroom by changing audio-branch accuracy. Concatenation realizes at most about half of the headroom (converted fraction 0.55), and on EAV the converted fraction is indistinguishable from zero despite larger headroom. A learned router is beaten by plain concatenation everywhere. Oracle headroom measures branch disagreement, not a fusion budget.

Long-context clinical AI systems can miss relevant patient history when prior admissions fall outside the active reasoning context. In ICU monitoring, this can cause early vital-sign drift to appear nonspecific even when it resembles a prior deterioration pattern. SMARtCARE addresses this gap through a four-state clinical decision-support architecture: Stable, Meta-cognitive, Assisted, and Regulated (Revoked). Rather than automatically retrieving prior records, SMARtCARE uses a lossy six-channel fingerprint of the patient's prior trajectory. When current drift matches that fingerprint and the prior record is absent from context, the system raises a Meta-cognitive escalation for clinician review; full retrieval occurs only through clinician action in the Assisted state. A patient-identity guard is designed to enforce correct attribution across data loading, logging, and audit layers. Evaluation combines a synthetic Monte Carlo study that validates the state-transition logic and estimator stability, not clinical performance, with real-data runs on both the MIMIC-III and MIMIC-IV Clinical Database Demos. On MIMIC-III, one prior-pattern recurrence was identified among 14 two-admission patients; on MIMIC-IV, the same pipeline produced no fingerprint matches among 9 two-admission patients, which illustrates a key limitation of a fixed canonical pattern library. Across both runs all logged decisions were fully traceable and correctly attributed. The results support SMARtCARE as a traceable, privacy-aware mechanism for surfacing middle-context risk; they are not a clinical efficacy claim.

How many assignments can a language model recall before it loses track of which value belongs to which entity? We measure this limit using continuous recall curves for 12 models at or below 3B parameters and a threshold sweep over 30 open models up to 12B. On the continuous curves, the load at which recall falls halfway to chance follows $K_{50}=cN^{\alpha}$, with $\alpha=0.820$ and $R^2=0.73$. The broader sweep shows an eightfold range associated with pretraining recipe, although the continuous curves show no detectable recipe effect after controlling for scale, with few modern models in the fit. We derive why interference can lower measured capacity by reducing single-binding recall even when the load-dependent recall profile is unchanged. Direct task training also exceeds the extrapolated zero-shot law, but different measurement criteria prevent interpreting that comparison as a capacity gain. Its formation times follow a power-law form in two independent codebases, conditional on runs that succeed. Together, these results characterize capacity at the model's query interface. Bounds on joint recall and a decomposition of policy errors connect this measurement to working memory and instruction following, without treating recall as a measure of alignment. The controlled task also provides a baseline for testing whether binding limits constrain world-state tracking; the present experiments do not measure state updates or downstream transfer.

Successful training of deep neural networks is highly dependent on the distribution of the initial weights. If the weights are too large, network training blows up; if they are too small, the model fails to learn features. Stable initialization is the optimal moderation between these two extremes. The conventional theory of random networks uses the Central Limit Theorem to control inter-neuron dependencies, which introduces distributional approximation error and coupling between layers. For networks with sine activations, we derive the uniform-phase initialization, which obviates distributional approximation and fully decouples the layers. Ours is the first work to use the sine function's periodic symmetry. Models trained with the uniform-phase initialization outperform the state of the art in neural representation tasks like image and audio fitting. We find that our untuned models are competitive with the best-tuned baselines from previous work and support $\mu$P width scaling.

Online audio-visual target-speaker extraction aims to remove competing voices while preserving speech quality and bounding lookahead. Existing extractors are built and evaluated for separation on synthetic mixtures, leaving listening quality and meeting behavior largely untested. We introduce Audio-Visual Personalized Voice Quality Enhancement (AV-PVQE), which approaches these requirements from the other direction. We start from a personalized speech enhancement model that reconstructs a requested voice at high quality but confuses the target in 46% of two-speaker mixtures despite clean enrollment. Adding mouth features at its speaker-conditioning input and jointly fine-tuning the visual and reconstruction networks reduces this rate to 1.6%, with no future frames and 20 ms of algorithmic delay. Compared with an online autoregressive audio-visual extractor, AV-PVQE yields separation gains on two synthetic benchmarks and larger gains on recorded meetings, and keeps its advantage on excerpts with more speakers than the fine-tuning mixtures. In personalized P.835 listening tests on two meeting corpora, it improves overall quality over this extractor by 0.57 and 0.63 MOS, with similar mean rating relative to the starting model. Preservation and rejection tests show that it keeps the target intact when no competing voice is present and suppresses competing speech when the target is absent.

Mission-critical UAVs increasingly rely on split vision-language model (VLM) perception under tight onboard-resource and wireless-communication constraints. However, corruption of transmitted intermediate features creates a deployment mismatch for clean-trained split interfaces, while stronger channel-aware codecs can impose substantial onboard cost. We present FreshLatent, a lightweight channel-aware latent adapter that trains a power-normalized encoder-decoder through wireless corruption while keeping the surrounding VLM frozen. We formulate deployment around a mission-conditioned perception requirement and embedded interface cost, linking channel quality and communication budget to the operating conditions under which perception remains usable. At 0 dB and the tightest communication budget, FreshLatent improves gIoU and cIoU over clean split compression by 20.79 and 20.87 points, respectively. At the most adverse evaluated SNR (0 dB), across all three communication budgets, FreshLatent recovers 63.5-69.1% of the gIoU improvement achieved by a much heavier, range-trained feature-JSCC codec. On an NVIDIA Jetson AGX Xavier in 10-W mode, FreshLatent uses 37-40x fewer encoder parameters, 7.7-9.9x lower edge-interface latency, and 8.8-10.0x lower edge-interface energy than the heavier codec. Together, these results show that lightweight channel-aware adaptation can recover a substantial fraction of the robustness of a much larger communication interface while broadening quality-valid operation under constrained wireless conditions.

Machine-learning policies have attracted increasing interest for ride-hailing fleet control in recent years. Reinforcement learning, in particular, requires a structured simulation environment that specifies observations, actions, rewards, and decision epochs for training and evaluation. For electric fleets, this environment must also capture the interaction among stochastic demand, vehicle operations, and capacitated charging infrastructure. We present OpenHail, an open-source Gymnasium environment for joint control of electric ride-hailing fleets. Its fixed-size observation–action interface exposes request assignment, repositioning, and charging to a single policy. The event-driven simulator represents requests with pickup deadlines, vehicle job queues, battery dynamics, and finite-capacity charging facilities with first-in–first-out queues. A configurable decision-epoch mechanism separates internal simulator events from policy interactions, supporting event-driven, periodic, hybrid, and policy-requested control within the same operational model. The software provides seeded instances, feasible-action utilities, evaluation tools, operational metrics, and baseline policies. The source code is available at https://github.com/tommaso-schettini/openhail.

We present a frequency-modulated (FM) haptic display based on piezoelectric vibrating actuators. Existing haptic displays commonly encode haptic intensity through the deformation amplitude of individual haptic pixels. Although amplitude-modulated (AM) approaches have enabled compact haptic pixels, independently controlling the deformation amplitude of a large number of pixels can require increasingly complex and bulky driving systems, posing challenges for scaling toward high-density, large-area wearable displays. To address this scaling challenge, we investigate an FM design principle in which haptic intensity is encoded through vibration frequency. We further develop a Shared-Source Frequency Modulation (SSFM) structure in which multiple haptic pixels are powered by a common power amplifier while their vibration spectrum are controlled individually, reducing the need for independent high-power amplification at each pixel. A proof-of-concept piezoelectric haptic display was built and evaluated on rendering spatial and temporal haptic patterns through volunteer tests. The results show that participants reliably distinguished spatial and temporal patterns encoded using FM principles within the investigated operating range. These findings demonstrate the feasibility of FM-based distributed haptic rendering and suggest a potential pathway toward more compact driving architectures for future high-density, large-area wearable haptic displays.

Audio large language models allow users to interact with the model through speech. When an input recording is too degraded, the model may misinterpret the user's query and respond based on an incorrect transcription. In this paper, we study model-conditional transcription reliability: whether an Audio LLM can recognize when its own transcription is unreliable. We first prompt the Audio LLM to assess whether its own transcription would be reliable, and find that the model is a poor judge of its own transcription reliability: in most cases, it predicts that its transcription will be reliable. We find that existing approaches, including speech quality predictors, audio LLM generation uncertainty, and transcript-conditioned WER estimation, provide limited signals for detecting transcription failures. In contrast, we discover that transcription reliability is strongly represented in the model's audio-encoder representations. Based on this observation, we devise a lightweight reliability predictor that operates on representations extracted by the frozen audio encoder and predicts the reliability class before generation. The reliability predictor can trigger a clarification request from the user when their voice query is predicted to be unreliable, while allowing reliable queries to proceed without modifying the underlying Audio LLM. Our predictor achieves 81.10% in-domain and 78.09% cross-domain macro-F1 scores, outperforming the strongest baselines by 10.33 and 11.93 points, respectively. Finally, we show that reliability labels can transfer across Audio LLM families, and that transfer performance is closely related to the alignment of their model-specific reliability boundaries.

Recent generative video editing models enable video content modification (e.g., changing a character) but target short clips. Extending them to full multi-shot videos requires tedious work to locate relevant content across shots, segment it into clips, craft context-aware editing prompts for each clip, and repeatedly articulate complex editing intent. To address this, we explore an interaction paradigm for editing through underlying video structures (e.g., scripts, scenes, characters, shots, and their relationships). We present CraftTrace, an interactive prototype that transforms a video into a malleable, multilevel structure for generative editing. Users work in task-centric workspaces to modify elements or reshape relationships, while an AI agent translates and propagates changes across the video. A user study and expert review show that this structure helps users understand videos, formulate and refine editing intent, and explore alternatives, supporting rapid prototyping during early-stage exploration and full video post-production.

Mobile virtual reality (MVR) provides low-cost access to extended reality (XR), but its limited input restricts use of common locomotion techniques such as head-decoupled and velocity-controlled steering. Using a low-cost controller with an audio-based button, we compared gaze- and controller-directed steering and teleportation in MVR. We included a controller pitch-based speed-control technique enabling continuous head-decoupled steering. Performance and participant feedback indicate that gaze was better suited to teleportation, whereas controller pointing better supports steering in primed search. We compare with similar techniques in standard VR and derive design considerations for low-cost, narrow-FOV hardware, demonstrating the potential to support varied travel techniques and velocity control in low-fidelity XR.

Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM agents that compose tool calls. Work on agents that generate governance artifacts evaluates output quality, not who may authorize an artifact for use. A published policy is what the decision point enforces, so publication is a governance event, and agents that are both policy subjects and policy authors write the norms that bind them. We name this the authorship hazard and state one principle: an agent is a subject of the governance plane, never an author of it. Its authorization channel to publication is closed by construction; its influence channel, drafting what humans approve, becomes an enforcement problem. Across 90 preregistered edits to the paper's running agreement, each evaluated on 344,512 requests, the six that only reclassify a field all change authorization and narrow a duty without touching policy text, and a policy-diff classifier passes all six. Read as worded, the privilege-delta conditions also pass 33 of 69 effective policy-text edits; read as covering any relaxation, none. Treating classification as authorship routes all six to review; the registry this requires is not yet built. At the execution boundary, protected fields reach the model in 105 of 105 cases under prompt-stated duties and in 0 of 105 under a compiled tool-call constraint, but values outside named fields are exposed in 7 of 7. At the review share measured, a central approval pool needs one approver per 20 to 138 participants.

Dermoscopy classifiers built on Vision Transformers process all image patches uniformly, although diagnostic evidence is concentrated in the lesion region. Existing token pruning methods reduce tokens using generic saliency or similarity signals, but rarely ask whether the retained subset still contains the lesion. This paper introduces MedTokenBudget, a supervised post-backbone token routing framework that learns to construct compact lesion-enriched representations when auxiliary lesion masks are available. Its Lesion-Aware Token Scoring (LATS) module fuses attention entropy, feature norm, and local feature contrast through a learned scorer, then routes the top-$K$ patches under a target budget. LATS is trained with budget curriculum learning, diversity regularization, attention distillation, and lesion-mask supervision. The trained router is evaluated with a lesion retention rate that directly measures how much ground-truth lesion evidence survives the token budget. On ISIC 2019, mask-supervised LATS consistently outperforms Random and ToMe at headline budgets while retaining substantially more lesion patches. Code is provided for reproducibility, and complete tabulated results are included in the supplementary material.

On Jan. 30, 2026, the U.S. Department of Justice released a mixed-media collection concerning Jeffrey Epstein, including about three million pages of PDFs. We describe the Epstein Files Engine, an A.I. agent The New York Times deployed to investigate the files. The Engine translated reporter questions into Google BigQuery SQL queries across three corpora: Epstein-related releases, the Times's archive and external, Epstein-related news headlines. It used an LLM to plan queries and returned citation-rich answers a reporter could verify and trust. More than 100 journalists used the Engine, and it contributed to at least 20 published stories. We report how reporters queried it and describe Diff, our text-and-visual duplicate matching method that amplified novelty signals and allowed the Engine to surface genuinely new information. We argue that newsroom agents serve newsrooms best not as autonomous writers, but as interfaces to source material and institutional knowledge.

Multi-shot agentic video generation requires consistent character appearance, stable spatial layout across camera angles, and continuous character state between shots. When every shot is a separate request to a frozen generator, repeated text does not determine appearance, layout or state. We therefore recast the problem as condition construction and present MVAgent, a multi-agent pipeline whose agents collaborate through typed conditioning inputs. Because an environment image shows one viewpoint, a Spatial Grounding agent samples views from generated camera-traversal clips and anchors each shot to the view matching its framing. As generated shots drift from the plan, an Observer records how each shot ends in a continuity memory, from which a Transition agent builds character action and spatial references for the next shot. An Orchestrator composes these inputs into each request. Since a request reveals its effect only after rendering, we train it by agentic reinforcement learning with Trunk-GDPO, which compares rendered candidates at every shot rather than once per video and continues the best as the trunk. With generator and judges frozen, MVAgent attains the highest cross-shot consistency and narrative-planning quality among the compared methods on ViMax-Bench and is preferred over the strongest agentic baseline in human evaluation.

A robot that probes a few times before one irreversible action, such as tapping a surface before inserting a peg, must decide when the evidence is enough to commit. We argue that this decision rests on two conditions that existing methods do not separate: the belief must still cover the truth in the coordinate that decides the action, and the failure model that scores actions must track realized failure. We audit both conditions separately, offline and with ground truth, on a deployed probe-then-commit pipeline: a particle belief, a scenario failure score, and one commit. On simulated insertion, more taps sharpen the belief while the truth leaves its support on 16.9% of episodes and the failure score turns optimistic by 0.31. Conformal calibration restores coverage but not the decision: confidently wrong instances still pass a confidence gate. The audit's signatures instead point at the observation model, where a hand scan finds a 2.1 mm error in the tap boundary. Correcting that one number cuts failure from 0.354 to 0.112 on untouched instances and transfers unrefitted to a second engine, while in a third engine the same audit suggests an execution-model mismatch instead. Across seven task families in three engines, a few probes at a fixed executor reduce miss or failure. On a physical arm inserting a tool into a rigid pocket by touch, the gain and the audit's two conditions reproduce, and replaying the recorded taps under an injected model error shows the audit's signature on real data. Additional materials are available at https://sites.google.com/view/auditbeforeyoucommit.

As high-impact, low-probability disturbances such as extreme weather events increase in frequency, enhancing power grid resilience has become a critical priority. Mobile Energy Storage Systems (MESSs) have strong potential for helping with this purpose due to their high operational flexibility and fast deployability. They can be rapidly relocated to supply critical loads, support islanded operation, and adapt to changing conditions of the grid, making them a promising addition or alternative to conventional resilience-providing methods. This paper proposes a three-stage framework for scheduling MESS units. In the first stage (Normal Operation), charging/discharging scheduling of MESSs at buses is optimized for economic arbitrage. Upon receiving an early warning signal, the second stage (Proactive Positioning) shifts the focus to resilience. Here, the model determines the optimal staging points within the transportation network to minimize the expected time of arrival at critical loads, considering the probability distribution of line outages. The third stage (Dynamic Relocation) addresses the post-event restoration phase, in which MESSs are relocated in response to grid updates, such as subsequent line failures. Furthermore, a graph neural network-based solution approach is proposed to further enhance computational efficiency in determining the optimal placing of MESS units during the pre-allocation and relocation stages. The simulation results demonstrate that the proposed framework reduces expected energy not served and improves the restoration speed.

Deep reinforcement learning (DRL) enables adaptive intrusion detection in dynamic network environments but also exposes intrusion detection systems (IDS) to adversarial threats such as universal adversarial perturbations (UAPs), which apply a single input-agnostic perturbation to degrade detection performance across traffic. Probabilistic Robustness (PR), as a post-hoc evaluation metric, provides a principled, population-level measure of adversarial impact that conceptually aligns with the universality objective of UAPs, i.e., PR quantifies the prevalence of misclassification in the input space, making it a natural signal for guiding UAP generation. Hence, we propose PR-based UAP, which represents the first integration of an explicit PR-driven objective into generating UAPs against DRL-based IDS. Building on this formulation, we introduce PX-UAP, which leverages explainable artificial intelligence (XAI) to guide perturbation shaping under realistic domain constraints, and provides a rigorous theoretical analysis of its design. Extensive experiments demonstrate that PX-UAP consistently outperforms state-of-the-art UAP methods in attack effectiveness.

Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, multi-step workflows, synthesizes it into artifacts (documents, presentations, spreadsheets), and navigates program interfaces to produce a coherent final product. Such workflows demand reasoning and synthesis, decomposition of complex tasks, as well as visual and spatial understanding. To study agents on workflows like these, we introduce KNOWS, a benchmark of open-ended, complex, browser-based tasks that jointly evaluate these capabilities, with each task culminating in a produced artifact. To write tasks, we develop a task design rubric and a protocol for ensuring that tasks meet the requirements. Each task is paired with an evaluator, a program that combines deterministic checks with LLM judgments to balance the richness, reliability, and automation tradeoff inherent to agent evaluation. We evaluate and analyze frontier computer-use agents and browser-based harnesses. They achieve moderate scores on partial-success metrics, but the best performer fully succeeds in fewer than 3% of our complex, long-horizon tasks. Failures on visual steps render the resulting artifacts unusable, even when agents complete more than 50% of other evaluation steps. Our results expose limitations of current agents acting as end-to-end assistants, and call for progress on tool use, visual understanding, and long-horizon reasoning.

Fast and spatially heterogeneous fluctuations from distributed energy resources call for voltage regulation that is both fast and responsive to changing operating conditions. Local linear Volt/VAR control offers the advantage of promptly regulating voltages without real-time communication, but its performance depends critically on the choice of control gains. Optimizing these gains for a system-level objective, however, typically requires an accurate network model or centralized communication. In this work, we uncover a structural property that enables such optimization using only local measurements. Specifically, by exploiting the self-adjoint structure of the closed-loop voltage dynamics, we show that each component of the system-level objective gradient can be exactly recovered from a self-convolution of the corresponding bus's voltage deviation trajectory. Building on this result, we develop a simple decentralized gain optimization method in which each bus updates its control gain using only its local data trajectory. Simulation results demonstrate that the proposed approach effectively updates the Volt/VAR control gains in response to changing operating conditions while requiring only local information.