Papers

Bitcoin's pseudonymous nature makes it challenging to analyze user-level activity, since a single user may control multiple identifiers (addresses). Existing heuristic-based methods attempt to identify addresses belonging to the same user, but they often produce flat cluster assignments with limited modularity and are prone to errors such as merging different users together. In this work, we propose a method for refining heuristic-obtained clusters by grounding our clustering on contrastive embeddings yielded by graph neural networks. Our contributions are threefold: (i) we release a publicly available dataset of Bitcoin transaction graphs containing a substantial number of clusters; (ii) we propose a methodology for learning address embeddings consistent with heuristics, and back it up with theoretical guiding intuitions; (iii) through hierarchical clustering, we enable a finer analysis of heuristic clusters and provide a quantitative criterion for flagging suspicious merges.

Autonomous agent runtimes execute tool actions that mutate databases, repositories, and cloud services across organizational boundaries. Authorization and local compensation cover pre-action admission and in-runtime rollback, but neither settles the residual harm left after a permitted action fails. We design Recourse, a smart-contract settlement protocol for compensable agent side effects that binds each admitted action to scope, recovery, evidence, payout, and collateral. Recourse separates ex ante eligibility from ex post objective settleability: typed receipts make objective residual claims computable under an optimistic-oracle challenge pattern, while subjective or incomplete claims route to ERC-792 arbitration or exclusion. We implement the contract suite, deploy it on Base Sepolia, build adapters against Postgres, Git, and cloud-compatible local sandboxes, and evaluate the system on a deterministic harness, sandbox traces, adversarial sweeps, and property-based fuzzing. Against authorization-only and local-compensation baselines, bonded coverage cuts uncompensated harm. The on-chain tier supplies neutral custody, public challenge, non-cooperative payout, and portable history under cross-organizational trust assumptions.

Dexterous manipulation with multi-fingered robot hands promises human-level dexterity, but collecting large-scale dexterous robot hand data remains difficult. Learning from human demonstrations has emerged as a scalable alternative to robot teleoperation, providing strong priors on object interaction and contact strategies. Recent sim-to-real RL methods incorporate such priors, but often (i) omit rewards that explicitly incentivize precise contact, yielding weak real-world performance, and/or (ii) generalize poorly to unseen object instances. We propose DemoMimic (Dexterous Motion Mimic), a policy that manipulates objects by focusing on their geometry local to the contact points. Its contact-centric rewards encourage precise contact and improve sim-to-real consistency, yielding a single real-world policy that transfers across objects of varying shape, scale, mass, and friction wherever local contact structure is preserved. Real-world ablations show that DemoMimic achieves 71% success across 16 objects, four tasks, and two robot-hand embodiments, with the smallest sim-to-real drop compared to baselines.

A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states into tokens. But a lens reading reflects both the hidden state and the readout (the unembedding matrix) used to decode it. Many lenses are fit on a corpus, and we show that two lenses differing only in their fitting corpus can report different tokens for the same hidden states. We call this dependence corpus conditionality. To examine readout structure independently of the fitting corpus, we introduce Sparse Readout Prism (SRP), which decomposes the readout using only its weights and expresses any token logit or logit difference as a sum of contributions from sparse readout features. This reveals readout features as a new unit of analysis for lens readings, exposing structure that token identities can obscure and enabling comparisons across tokens, contexts, layers, and lenses. Replacing the original readout with SRP's sparse approximation reconstructs 8.9-17.3 percentage points more of the tested logit differences than the strongest of six baselines built on geometric relations among readout rows. Ablating features shifts logit differences in proportion to their SRP contributions. Although token readings vary with the fitting corpus, the dominant readout feature remains stable. Because SRP uses no corpus in its construction, it provides a control independent of the fitting corpus for lens analyses.

Modern supply chain operations can require coordinating replenishment across thousands of heterogeneous items under correlated stochastic demand, heterogeneous lead times, and shared fixed ordering costs, yielding observation spaces exceeding $10^4$ dimensions. At this scale, rolling-horizon stochastic mixed-integer linear programs (MILPs) become prohibitively slow, while standard reinforcement learning (RL) methods face increasingly challenging credit assignment in high-dimensional action spaces. We introduce OR-Transformer, a deep reinforcement learning framework for joint replenishment under stochastic demand, with an item-permutation-equivariant Transformer architecture and pathwise-gradient training through the inventory dynamics. Across problem sizes up to 1,024 inventory items, OR-Transformer increasingly outperforms learning-based and rolling-horizon MILP baselines as scale grows. It also reduces online decision-making time by over 4 million times relative to MILP solvers, enabling real-time, large-scale deep RL in supply chain operations.

Long-horizon agents execute thousands of actions, resulting in sequential failures rather than isolated errors. When a coding agent deletes a production database or a prompt injection spreads across agents, the incident raises questions of causality, authority, and non-repudiable third-party verification. The Agent Flight Recorder captures each agent action as a structured, canonically serialized event binding eight semantic fields from intent through execution to provenance. Hash chaining and Merkle batching provide tamper evidence and compact inclusion proofs. For cross-organizational disputes where no party's infrastructure qualifies as neutral ground, periodic on-chain anchoring of epoch roots lets any verifier with the disclosed payload and Merkle proof check the record independently, without pre-agreeing on a trusted intermediary. The on-chain footprint is minimal: each anchor stores a 32-byte epoch root and a back-pointer, and no event content touches the chain. We evaluate the system across five cumulative ablation configurations on synthetic agent workloads. The full system adds ~48 microseconds median per-event latency and 512 bytes per event. L2 anchoring costs $2.30 per 100K events at 100-event epochs. The full integrity stack detects edit, delete, reorder, and fork tampering at 100% with zero false positives. Structured forensic queries achieve 1.0 precision on guardrail and delegation lookups where unstructured text search yields 0.013 and 0.077 respectively.

In large-scale disaster scenarios, rapid localization of missing persons is a critical challenge for search-and-rescue (SAR) operations. Unmanned aerial vehicles (UAVs) equipped with radio frequency (RF) receivers can support RF-based localization by collecting signals emitted from mobile devices at spatially distributed sensing locations. This paper addresses the resulting waypoint-selection problem: determining a minimum set of UAV waypoints that provides at least threefold coverage of every potential target location. We formulate this task as an extended k-coverage problem that independently defines the UAV-navigable and target regions, and derive an exact-penalty quadratic unconstrained binary optimization (QUBO) formulation with a sufficient penalty condition that preserves feasibility and minimum waypoint cardinality. The QUBO is mapped to an Ising-form cost Hamiltonian and evaluated using the quantum approximate optimization algorithm (QAOA) on both a noise-free simulator and IBM's 127-qubit Eagle processor. On the tested simulator instances, QAOA recovers the known minimum-cardinality solutions. Across the rectangular hardware test cases, the mean 3-coverage ratio exceeded 95%. In the campus-scale evaluation, ten hardware executions achieved 99.3% mean 3-coverage with a 90% feasible-run rate, while the shortest feasible flight path was up to 37.0% shorter than those of the deterministic grid-based baselines. Additional comparisons with classical optimization and learning-based baselines are provided, together with computational and quantum-resource analyses for larger generated instances. These results establish an exact QUBO representation for RF-based SAR waypoint selection and characterize its implementation on current gate-based quantum hardware.

Generative Flow Networks (GFlowNets) for structure-based drug design condition on one rigid protein structure. A flexible target holds several distinct structural shapes, its conformations, each occupied for a fraction of the simulation time. Scoring a candidate against all of them raises an open question: how do K scores become one reward? The designer cannot choose arbitrarily. Populations carry simulation error, and biology dictates which conformations are deal-breakers, so a candidate that fails one is disqualified, not merely ranked lower. No standard rule captures this. We compose the reward from a conditional value-at-risk (CVaR), a worst-case score rule, and an ambiguity radius expressing distrust in the stated weights. Together, these define a family of targets, amortised by a single conditional GFlowNet. We answer whether such a sampler can be trained on fully enumerable synthetic worlds, where every error is exact rather than estimated. Pricing the tail rather than averaging moves 2-10 times more mass to candidates that pass every conformation. One network covers the family to within 0.37-2.7x the error of a perfect sampler. An exact-KL oracle, a copy trained on the true target, shows if a shortfall is the optimiser's or the architecture's. When good candidates are rare, exploration decides: injecting unseen states finds 0.987-1.000 of good regions, while reweighting visited finds 0.35-0.76.

Higher-order interaction components are important for signal, image, and video modeling, but explicit high-order operators often suffer from rapidly increasing parameter and computational costs. This paper presents kVNN, a learnable kernelized Volterra Neural operator for compact higher-order filtering. The motivation is to use kernelization to improve the efficiency of Volterra-type neural operators while providing a structured interpretation of their higher-order components. The proposed formulation combines the order-wise structure of Volterra filtering with learnable polynomial-kernel atoms, allowing different interaction orders to be represented by separate learnable centers and coefficients. This order-decoupled representation avoids explicit high-order tensor parameterization and can be implemented as a CNN-compatible layer. Experiments on representative vision tasks show that kVNN achieves a favorable accuracy–efficiency trade-off.

The attention prefilling phase of long-context LLM inference scales quadratically, making self-attention a severe computational bottleneck. Traditional sparse attention methods mitigate this through fixed patterns or offline profiling, but lack the flexibility to adapt to input-dependent attention structure. Recent dynamic methods address this by routing heads to sparse patterns in real-time, but rely on indirect routing proxies with overhead and budget allocation mechanisms that overlook the post-softmax mass hierarchy. We present CRISP (Cliff-awaRe Input-adaptive Sparse Prefilling), which identifies and addresses two structural challenges in this dynamic routing paradigm. First, we show that the routing decision can be read directly off the structure of the proxy attention map. We replace the Jensen-Shannon Divergence (JSD) routing with C_struct, a structural proxy that measures mass at Vertical-Slash compatible positions and reproduces JSD's routing decisions while eliminating both the pooled matmul and subsequent KL divergence overhead. Second, we formalize the post-softmax mass cliff and demonstrate theoretically that strictly cumulative coverage thresholds accumulate O(n) background noise at long contexts. CRISP navigates this via a sink-aware threshold grounded in the noise floor. Empirically, across InfiniteBench, RULER and LongBench on two model families, CRISP is the strongest sparse method overall and matches or exceeds exact dense attention on retrieval-heavy benchmarks, recovering up to +28.0 pp on retrieval tasks over baselines and achieving up to a 5.30x attention speedup at 512k tokens, driven primarily by our O(n) noise elimination during selection while preserving structural integrity.

Recent work identifies a mid-depth band of verbalisable, causally potent representations in a standard feedforward transformer — a functional analogue of a global workspace. Whether the same workspace functionality emerges when depth is implemented through recurrence rather than a stack of distinct layers remains unknown. Looped and depth-recurrent transformers provide a direct test of this question because they reuse the same weights across depth. We extend the Jacobian lens to iterated architectures using a virtual-unrolling adapter. We apply the full workspace suite — lens fitting, readout, and eleven causal experiment families — to Ouro-2.6B (48 layers looped 4 times, deeply supervised) and Huginn-0125 (a 4-layer core recurred 16 times, trained for latent reasoning), using Qwen3.6-27B (64 untied layers) as the standard baseline. We find that a workspace forms in the iterated part of each architecture, but that recurrence changes how it can be accessed. Ouro reconstructs workspace content in every loop, and linear transport cannot carry that content across loop boundaries; writes and ablations must therefore span every remaining loop. Huginn carries content forward across all sixteen recurrences, while reads, writes, and ablations act only within a sliding window of roughly two recurrences. Whether newly injected content can be verbalised tracks explicit per-iteration supervision; whether existing content can be steered does not.

Maize kernel traits such as row number, kernels per row, and kernel size vary largely for genetic reasons and are consistently associated with regions of the genome that influence yield. Manual measurement of these traits, however, cannot keep pace with the volume of maize generated in a breeding program. To address this, we developed and validated a fully automated pipeline for extracting these traits from 3D point clouds of corn ears, built on a recently developed video-to-point-cloud platform. Raw video frames are processed through COLMAP and NeRF, the ear is isolated via density-based separation, and the point cloud is distance-calibrated to physical units. The calibrated ear point cloud was Z-axis aligned via PCA and cylindrically unwrapped to a 2D image. We enhanced contrast and performed zero-fine-tuning instance segmentation using Cellpose-SAM. A triple-juxtaposed unwrap strategy was used to prevent double-counting at the seam. The pipeline achieved kernel count R^2 = 0.921 (MAPE = 10.33%) and kernel row number within +-2 rows for 95.2% of ears (MAE = 0.75 rows) on a 168-ear held-out set from the 268-ear labeled dataset. The resulting multi-trait dataset has known genotype identity for each ear, positioning it for phenotype-to-genotype association analyses.

Energy poverty is nearly absent from NLP-for-social-good, and the little existing work is either static retrieval/QA or relies on carbon-intensive cloud LLMs, a self-defeating "computational irony" for a humanitarian setting. We present EqGrid, a closed-loop simulation in which a low-frequency, open-weight LLM policy agent sets price and carbon bounds and targeted subsidies over a community of empirically-grounded household personas, while high-frequency multi-agent RL traders clear a continuous double auction constrained by a physical distribution grid (IEEE-33-bus with Dynamic Operating Envelopes). Our contribution is threefold and directly addresses how to measure the social impact of AI: (i) grounded personas (region-matched socio-demographics) whose load curves are checked for shape and level realism against real smart-meter data; (ii) formal energy-poverty equity metrics (Energy Burden, Gini of EB, LIHC) showing the intervention reduces burden inequality without raising net grid cost; and (iii) a compute-efficiency frontier that measures how much equity performance survives compressing the policy agent from a 235B teacher down to a sub-1B model deployable on a laptop, in estimated energy/carbon per decision. A decoupled-safety design (the LLM sets bounds; a validate-and-project grid gate executes) yields zero grid-constraint violations versus 55 under direct LLM control. On energy-poverty equity, the LLM policy lowers the Gini of energy burden to 0.305 (from 0.351) and mean burden by 28% while cutting cost (outperforming a tuned rule baseline), and a 3B-active model retains 95% of the benefit at roughly 9x lower inference energy than the teacher, with even a 0.8B on-device model retaining 92% at roughly 24x lower energy. We will release code and configs.

Finite elements provide accurate and efficient methods for the numerical solution of partial differential equations by means of restricting variational problems to finite-dimensional approximating spaces. However, they do not, in general, guarantee enforcement of bounds constraints inherent in the original problem. We propose two approaches to enforcing bounds constraints for time-dependent problems. First, we propose general projective methods which result from a systematic modification of any abstract time-stepping scheme. Second, we present a monolithic technique for which we take a modified formulation of implicit single-stage Runge-Kutta methods and general implicit multistep methods as prototypical examples. By solving a constrained optimization problem, we are able to ensure that the bounds constraints are enforced by the approximate solution at the discrete time levels, obtaining (formally) high order methods both in space and time. Numerical examples for the linear heat and advection equations and nonlinear Allen-Cahn equation are given.

Reliable attractor recall conventionally requires broad basins of attraction. However, in reservoir-computing based associative memory, temporal cues reliably recover dynamical memories despite basins dominated by unpredictable, riddled-like regions. We reveal that memory basins exhibit an “octopus-like” structure: a robust “head” near the attractor and thin, intertwined “tentacles” spanning state space. Initial states in tentacular regions yield near-zero uncertainty exponents, making the recalled memory effectively unpredictable at finite precision. Yet, cue-driven generalized synchronization bypasses this unpredictability, driving the system into the robust basin head. This mechanism yields a quantitative relation linking minimum cue duration, synchronization rate, and basin-head radius. Trained recurrent neural networks exhibit similar geometry, suggesting this phenomenon extends beyond reservoir computing.

In product entity resolution, relationship definitions constantly evolve with business needs, yet adapting to each change traditionally requires slow, costly human annotation that is often noisy and carries no reasoning. Large vision-language models (VLMs) prompted zero-shot can adapt to a new definition immediately and supply the reasoning that human labels lack, but their cost and latency are prohibitive at production scale. We present MERGED, a distillation framework that transfers not just labels but structured reasoning from large teacher VLMs into a compact 7B-parameter student, requiring no human annotation for training. Multiple teachers label each product pair and articulate the reasoning behind their decision: agreement pairs supply supervised fine-tuning, while disagreements are resolved by a meta-judge into preference pairs for Direct Preference Optimization. Evaluated against human-labeled ground truth on a multilingual e-commerce dataset, the resulting student improves PR-AUC by 13.79% over the same backbone trained on human labels and surpasses the larger Qwen2.5-32B-VL baseline by 6.32% at 6x lower cost, while also yielding tighter label-reasoning consistency (over 10% above Qwen2.5-32B-VL). Moreover, re-applying MERGED from an existing checkpoint adapts to a new relationship definition with only 10K samples, improving PR-AUC by 6.97% over zero-shot and outperforming from-scratch training. MERGED enables rapid adaptation to evolving relationship definitions, supporting a new one in days rather than months, at a cost and latency suitable for large-scale industrial deployment.

This work studies the optimization of physical plant characteristics and controller parameters for sustainability. Environmental sustainability is strongly correlated with the development and operation of energy systems, with data centers as the preeminent modern example. Data centers, and the grid technologies that provide their power, consume nonnegligible amounts of global energy and pose a risk to increase greenhouse gas (GHG) emissions and electronic waste. Addressing such issues requires improved plant design and control strategies, often approached through optimization-based methods. However, there are noticeable gaps regarding data center and microgrid design: (i) simultaneous optimization of plant and controller features is rarely explored, and (ii) sustainability criteria are not emphasized. This work addresses these gaps by establishing a generalized, sustainability-centric control co-design (CCD) framework for energy systems. Uniquely, the CCD framework defines and categorizes sustainability metrics into three lifecycle stages - manufacturing, operation, and disposal - supporting optimization and comparative analysis of the metrics for different design options. To exemplify its use, the CCD framework is applied to a microgrid-driven data center system, providing a family of sustainability metrics correlated to plant and controller parameters. The analysis enabled by the framework supports the determination of tradeoffs between different types of environmental sustainability metrics. The system designs identified by the proposed framework show substantial improvements to environmental sustainability categories as compared to designs identified through baseline procedures.

Clinical prediction can saturate for two different reasons: a fitted learner may fail to extract available information, or the recorded variables may impose a population frontier. We separate these quantities through the learner gap and the measurement-channel ceiling. Optimal balanced accuracy is characterized by total-variation separation, yielding architecture invariance, a sharp partial-identification result under replacement contamination, a cross-fitted ceiling estimator, and exact conditions for multimodal decision improvement. We add two finite-sample diagnostics, namely a label-permutation optimism floor and an underfit curve, and validate the audit on three real cohorts: UCI readmission ($n=99{,}343$), BRFSS diabetes ($n=253{,}680$), and NHANES HbA1c ($n=10{,}219$). Well-tuned gradient boosting nearly reaches the estimated frontier in UCI and BRFSS, whereas deliberately or practically deficient learners retain large gaps. NHANES yields a null difference between questionnaire and measured marginal frontiers but a significant joint complementarity gain, refining the simplistic claim that an objective modality must dominate. Across all cohorts, modest AUROC gains coexist with substantially larger Bayes decision-flip rates, and several architectures estimate similar frontiers while their achieved balanced accuracy differs sharply. A PRISMA-guided synthesis of 104 clinical tasks then shows that the same channel-level regularities recur across more than 18 disease categories: a broad but non-universal structured-clinical region, diminishing same-channel gains across model families, and higher performance when measurement channels change. The framework converts saturation from an empirical observation into an auditable decision: improve the learner when headroom remains; improve measurement when it does not.

Integrated sensing, communication, and computation (ISCC) provides a promising framework for indoor human-centric applications. In these applications, short-term human pose prediction facilitates continuous human pose tracking and proactive resource allocation. This paper proposes a Cramer-Rao bound (CRB)-guided sensing framework and investigates a problem of minimizing prediction error in resource-constrained ISCC systems. Specifically, a pose prediction model (ET-Mamba) is first developed to predict human joint positions for continuous tracking. To account for computation-resource limitations, lightweight prediction heads are attached to different inference layers, enabling adaptive-depth pose prediction. A CRB-guided perturbation strategy is then introduced to translate sensing uncertainty at different sensing SNR levels into point-cloud perturbations. Based on that, an empirical relationship among pose prediction error, sensing SNR, and model inference depth is established. Furthermore, to improve prediction accuracy under limited resources, this paper formulates a resource allocation optimization problem that minimizes the pose prediction error by jointly optimizing the beamforming matrix, model inference depth, and computation frequency. To solve this mixed-integer non-convex optimization problem, we propose an alternating optimization (AO)-based algorithm, where closed-form updates and semidefinite programming (SDP) are integrated into the iterative solution process. Simulation results show that the proposed method effectively improves pose prediction performance by up to 35 percent under resource constraints, verifying the effectiveness of conducting joint sensing, communication, and computation design in ISCC systems.

Large language models (LLMs) are increasingly used for research quality evaluation, with prior work exploring their scoring accuracy and the plausibility of review rationales. However, less is known about whether external score guidance changes the evidence presented in the generated review as well as the final score. This study uses 98 Allied Health Professions research outputs submitted for internal REF-style assessment, with specialist human review reports and adjudicated 1-4 reference scores. No-guidance baseline reviews are compared with oracle-guided reviews, where the supplied score is set to the rounded human reference score; extracted evaluation points are used to compare human and LLM evidence use. Using this design, oracle guidance improves scoring accuracy, with score-following checks showing that models do not simply copy the supplied score. Corrected score mismatches are associated with changes in the generated review frame, showing that the score signal can steer review rationales. This effect is direction-dependent: LLM reviews cover human strength or upgrade points more reliably than human weakness or downgrade points, with the weakest alignment for expert downgrade evidence. The results show that score-guided review generation can be evaluated at the level of review evidence, as well as the final score.

We present a cohesive framework for simulating seismic wave propagation utilizing quantum computing paradigms and their classical tensor network equivalents. We detail a quantum circuit-based formulation for the explicit finite-difference time-domain (FDTD) solution of the two-dimensional acoustic wave equation and map this quantum architecture onto a tensor train representation, namely for Matrix Product State (MPS). The MPS solver enables deterministic simulation of large-scale wavefield dynamics on classical high-performance computing systems. We demonstrate the MPS representation by computing 2D seismic wavefields on the Marmousi model. Our results indicate that the MPS representation is a viable direction for computing and scaling wavefield propagation.

Assessments of cultural alignment have become an important part of the development and improvement of large language models (LLMs). However, the majority of the evaluations treat culture as a single snapshot, investigating only whether a model represents a society accurately at the current time. Research in cultural psychology shows that cultural values change at different rates and directions over time. Therefore, a "culturally aware" model should capture not only where a culture is today but also how it has changed over time. We examine this missing dimension of cultural awareness using more than two decades of the World Values Survey data. We compare the cultural trajectories of 40 countries with the trajectories produced by four state-of-the-art (SOTA) LLMs on the Inglehart-Welzel cultural map. Our findings show that while models generally place countries close to their most recent surveyed positions, these representations tend to lag several years behind that position. They also capture only part of the magnitude of the observed change, introduce movement where little occurred, and rarely reproduce reversals in countries' trajectories. These findings point to temporal flattening and suggest that snapshot accuracy can give an incomplete picture of cultural awareness in LLMs and have implications for model evaluation, representational harms, and the governance of culturally aware AI systems.

Multi-camera systems are increasingly practical for robotics, AR/VR, and autonomous driving because complementary views reduce depth ambiguity and preserve visibility under occlusion. Existing point-tracking benchmarks, however, focus on a single video or static multi-camera rigs. None test long-term 3D point tracking across several synchronized views under camera motion. We introduce TAPVid-MV (Tracking Any Point in Video across Multiple Views), the first benchmark for this setting. It contains a curated set of 238 sequences, 1,004 calibrated camera streams, and 74,147 point tracks across seven subsets spanning indoor and outdoor domains, from robotics and human activity to driving and synthetic procedural scenes. We obtain these trajectories using dataset-specific auxiliary modalities: sensor depth, LiDAR, SLAM and SfM points, human meshes, posed object meshes, and simulation. Every sequence and trajectory is visually verified by human annotators. Across more than 30 baselines, no method comes close to solving the task. Surprisingly, existing multi-view point trackers do not consistently outperform monocular point trackers. By evaluating reconstruction and point tracking on the same datasets, TAPVid-MV helps distinguish errors in recovered geometry from errors in point correspondence. Through this joint analysis, we identify geometry recovery as a major bottleneck for accurate 3D point tracking. Beyond multi-view 3D point tracking, our released annotations support monocular 2D and 3D point tracking, future-trajectory prediction, and 4D reconstruction. Project page: https://tapvidmv.github.io/

Power-outage planning requires scenarios before an event occurs. These scenarios must represent uncertainty in magnitude, timing, and duration while preserving temporal dependence. However, severe events are rare, and data from any single region contain few examples of extreme outage and restoration patterns. To address this challenge, we introduce OutageDiT, a foundation model for generating seven-day outage trajectories at 15-minute resolution, trained on outage and weather records across the United States. Specifically, a condition encoder processes historical context and known future covariates once per forecast, and a shallow flow-matching decoder reuses the resulting horizon-aligned states to sample complete outage trajectories. This enables point forecasting, uncertainty quantification, and conditional scenario generation within one deep generative model. Across outage forecasting benchmarks, OutageDiT improves forecast accuracy and scenario quality over strong baselines and supports zero-shot transfer to held-out regions. Together, these results position conditional outage scenario generation as a bridge from outage forecasting to operational planning under uncertainty.

Large language models (LLMs) are increasingly discussed as tools for peer review, but their value is often assessed through human-likeness, perceived usefulness, or textual overlap with reviewer comments. This study shifts attention from whether LLMs resemble human reviewers to what functions of scientific critique they perform. Using ICLR 2025 peer-review data, we compare human reviews with LLM reviews generated under baseline and expert prompts. We operationalize scientific critique through two review acts, weakness critique and scientific questioning, and annotate point-level review text using five theory-guided frameworks: Anderson's knowledge types, Toulmin's argumentation model, Graesser's question depth, SOLO cognitive complexity, and Hattie's feedback functions. The results reveal a differentiated critique profile. Human reviews placed greater emphasis on scientific framing and revision guidance, more often identifying higher-order weaknesses and asking questions oriented toward improvement. LLM reviews showed higher rates of explanatory depth, integrative reasoning, and explicit argument structuring. Expert prompting did not make LLM critique uniformly more human-like; it partially narrowed some gaps but mainly amplified LLM-specific tendencies toward integration and formal argumentation. These findings show that LLM-assisted peer review changes the functional composition of review text, making it important to distinguish LLM-amplified critique from areas requiring human prioritization and accountable judgement.

Recent inference-time hallucination mitigation methods for large vision-language models (LVLMs) report strong gains on hallucination benchmarks. However, it remains unclear whether lower hallucination scores reflect improved multimodal grounding or more conservative generation. We evaluate six mitigation methods across three LVLMs and four benchmarks, including hallucination-focused evaluation and the diverse capability benchmark MMStar. Our analysis reveals two consistent patterns. First, hallucination reduction is often coupled with reduced informativeness: methods that lower hallucination rates also reduce object recall, visual coverage, or response detailedness. Second, improvements on hallucination benchmarks do not reliably transfer to broader multimodal capabilities, with methods showing inconsistent or degraded performance on fine-grained perception and reasoning tasks. Our findings suggest that current evaluation protocols may overestimate progress by rewarding conservative generation. We argue that hallucination mitigation should be evaluated as a faithfulness–informativeness–capability trade-off rather than through hallucination scores alone.

The objective of this paper is to match dictionary sign videos to corresponding signs in continuous signing videos, where a match is defined by the visual similarity alone - the handshape and motion relative to the body. To achieve this, we learn a prototype-structured sign embedding space from continuous video annotated with signs, where each learnable prototype corresponds to a sign class. Isolated dictionary videos are then mapped into this sign space, enabling the matching between dictionary exemplars and continuous sign instances. This design supports direct dictionary-guided sign matching through embedding similarity and naturally extends to unseen signs using only dictionary exemplars. Experiments on ASL-Citizen dictionary retrieval, ChaLearn OSLWL dictionary-to-continuous sign matching, and using BOBSL's CSLR2 evaluation for automatic sign annotation demonstrate strong generalisation across datasets, tasks and sign languages. Without benchmark-specific supervision, the learned representation transfers effectively across American, British, and Spanish Sign Languages, outperforming prior methods on all three benchmarks. Project page: https://www.robots.ox.ac.uk/~vgg/research/signmatch/

The Fokker-Planck partial differential equation (FP-PDE) governs uncertainty evolution in stochastic dynamical systems. In orbital dynamics, solving the FP-PDE is challenging because of nonlinear motion, high-dimensional states, and large space-time domains. We develop a physics-informed neural network (PINN) approach that approximates the FP-PDE solution as a single space-time probability density, while also quantifying its worst-case approximation error. This approach is, in principle, independent of the choice of state coordinates and neural network architecture. Specifically, to enforce probability density function (PDF) properties into the neural network, we design a Physics-informed Gaussian mixture model (PINN-GMM). Then a companion error PINN learns the dynamics of the approximation error and yields time-dependent bounds that define an ambiguity set of PDFs. This ambiguity set enables rigorous computation of upper and lower bounds on event probabilities through tractable linear programs. Numerical studies on illustrative 1D examples and several 4D–6D orbital test cases demonstrate accurate uncertainty propagation, correct and informative error bounds, and improved reliability over common uncertainty-propagation baseline methods (Gaussian approximation, unscented transform, and Gaussian mixture model). Constructing the PINN-GMM requires offline training, making it costlier than the baseline approximations; once trained, however, a single forward pass returns the density at any time in sub-millisecond time $(0.16~\mathrm{ms}$ in our implementation).

Activation steering suppresses undesired behaviors in language models by adding a steering vector to the hidden state during generation. Recent conditional methods such as CAST and DSAS improve the behavior-capability trade-off by deciding when to intervene, but once active, they apply the full dense vector to all hidden dimensions, regardless of whether a neuron carries concept information or already lies in the desired regime. We introduce dimension-level conditioning as a complementary axis of selectivity that also decides which neurons to intervene on. Our method, GAPS (Gated Activation steering via Posterior and Separability), combines two training-free gates: a static separability gate that restricts steering to neurons with statistically reliable concept information (via AUROC), and a dynamic posterior gate that steers a neuron only when its current activation is better explained by the undesired concept under a Gaussian model. The gates add O(D) overhead per token, and they plug into existing conditional methods. On toxicity mitigation (RealToxicityPrompts) and concept removal (OneSeC) with Gemma-3 (4B) and Qwen-3 (1.7B), GAPS consistently matches or improves the Pareto front of its token-level counterparts; under a fixed capability budget, DSAS+GAPS reduces Gemma-3's toxicity rate from 6.52% to 0.48%, versus 3.52% for DSAS alone. Ablations attribute most of the gain to the posterior gate.

The transition from 5G to 6G is becoming concrete: the ITU-R IMT-2030 framework has established the high-level vision and capability set for 6G, while 3GPP Release 21 has defined the path toward the first 6G specifications. This raises a deliberately provocative question for the research and standards communities: will there be a 7G, and if so, what would justify it? This paper argues that 7G should not be treated as an inevitable numbering exercise or as a catalogue of more ambitious radio targets. Instead, its justification should depend on whether post-6G systems introduce needs or coordination problems that cannot be met by 6G/6G-Advanced, Wi-Fi, NTN, private cellular, neutral-host deployments, edge-cloud platforms, or complementary wireless and software-based systems. To support this assessment, the paper develops a readiness framework covering demand-led need, system-level discontinuity, coordination value, sustainability and circularity, trust, and geopolitical viability. It then applies the framework to candidate 7G discontinuities, including agentic network operation, RF-native computing, quantum-enabled interworking, policy-aware spectrum governance, grid-interactive infrastructure, outcome-assured services, and regionalized standards. The contribution is not a prediction of a fixed 7G architecture, but a structured basis for deciding whether 7G should become a distinct mobile generation, an extension of 6G evolution, or a broader post-6G infrastructure fabric.