Papers

Data-driven power-system models are typically developed for specific grids and computational tasks, but their performance can deteriorate markedly or even fail when network structures or analytical objectives change. This paper develops a unified grid representation that separates physical-grid description from downstream computation. A self-supervised encoder represents each grid as a variable number of fixed-dimensional node, branch and global vectors under a common latent description. Although pretrained only on systems with at most 270 buses, the frozen encoder transfers without adaptation to a 70,000-bus network, more than 250 times larger in bus count, while preserving 0.7919 bus-correspondence accuracy. The same representation supports four independently trained downstream tasks: power-flow calculation, reactive-power adjustment, operating-condition generation and transient-stability assessment. On the previously unseen 70,000-bus grid, power-flow calculation achieves mean errors of 0.108$^{\circ}$ in phase angle and 3.8$\times$10\textsuperscript{-6} p.u. in voltage magnitude. Reactive-power adjustment achieved a 75% PSASP-verified correction rate on the previously unseen 70,000-bus grid, while operating-condition generation delivered at least one PSASP-verified feasible state for 82.2% of requests on previously unseen 400–1,000-bus grid families. For transient-stability assessment, the frozen encoder achieves accuracy within 0.8 percentage points of full encoder adaptation under matched training conditions. These results demonstrate that a unified power-grid representation can be learned once and reused unchanged across structurally different power systems and heterogeneous computational tasks.

Providers of continuously produced, commercially valuable data – sensor streams, telemetry, and other feeds sold as machine-learning training material – cannot observe whether delivered data is actually used, while data that keeps flowing to inactive consumers enlarges the leakage surface without producing value. We present Attestream, a blockchain-based architecture for intermittently delivered dataset streams that couples continued delivery to verifiable usage reporting. Every lifecycle event – dataset preparation, dual-signed delivery, derivative creation (e.g., a model), and derivative distribution – is appended to an on-chain registry as a non-repudiable, mutually linked lifecycle record. The mechanism requires provable transfer, not tokenization: plain contract storage, ERC-721 tokens, and anchored off-chain receipts are interchangeable representations of the same protocol. A usage-aware gate suspends a consumer's stream when no derivative-creation record is registered within a reporting window; evaluated lazily inside the next delivery transaction, monitoring adds no dedicated transactions. A modality-pluggable fingerprinting layer binds any leaked copy to the dual-signed delivery record of the responsible consumer, instantiated for tabular/geospatial records, images, and documents. We implement the registry as a Solidity contract with EIP-712 dual signatures and evaluate it: a full lifecycle round costs 657k gas with plain records ($0.13 on rollups; ERC-721 tokenization adds ~30k gas per record), and over a 50-consumer pool leak attribution reaches 100% from 40 leaked table rows under moderate noise, survives JPEG recompression to quality 30, and tolerates paraphrase rates up to 30% for documents.

Hyphenation patterns remain a compact and widely deployed solution for word breaking in typesetting systems, text processors, and web rendering engines, but their generation still depends on manually tuned patgen program parameter profiles. We formulate patgen profile selection as a black-box hyperparameter optimization problem and evaluate Gaussian-process Bayesian optimization for this task. The search objective combines a precision-oriented F_{1/7}-score with an explicit trie size-accuracy trade-off using a normalized trie-size penalty. We evaluate the method on 17 hyphenated word-list datasets covering 14 languages and multiple scripts. Against two strong hand-tuned profiles regenerated from the same 8/10 training split and evaluated on the same 1/10 held-out test split, the GP-optimized profiles improve F_{1/7} on 16 of 17 datasets and reduce trie size on all 17. The median optimized/baseline trie ratio is 0.407. A dataset-level sign test gives p = 1.37e-4; a separate budget-matched comparison on five representative datasets shows that systematic search is competitive and usually improves over the best hand-tuned profile under the fixed comparison objective. The results show that model-based optimization can make pattern generation more reproducible and less dependent on expert trial-and-error while keeping the accuracy-compactness trade-off explicit.

AI chip export controls can help the United States shape the development of frontier AI, but their effectiveness depends on reliable methods for verifying compliance. This paper examines near-term verification mechanisms (implementable in approximately one year) and groups them into three categories: end-location verification (whether controlled chips remain in authorized locations and/or jurisdictions), end-user verification (whether entities that acquire or access compute are legitimate), and end-use verification (whether computing power is used for prohibited purposes). We discuss how each mechanism can be implemented within the regulatory framework of the U.S. Bureau of Industry and Security (BIS), outlining implementation steps and identifying which actors can perform verification (BIS, exporters, or accredited third-party auditors). Given BIS's resource constraints, the most viable mechanisms rely on private-sector actors working alongside BIS, leverage existing technologies, and scale without requiring large increases in government staffing. These mechanisms could also help monitor future international agreements on AI.

Democratizing access to the knowledge held in large corpora of tables such as data lakes is emerging as a central research challenge. Research in this space is advancing and broadening in scope, increasingly supplying the components to satisfy a person's insight need end-to-end. Yet these efforts remain fragmented across communities that frame the problem under their own conventions, such as table question answering, text-to-SQL, and data analysis agents, with works six times as likely to cite within the same task label as across labels. To bring these communities onto common ground, we establish a holistic framework for this pursuit, which we refer to as Open Tabular Insight Extraction (OpenTI). We formalize OpenTI from first principles around the analytical knowledge a person needs, the procedure for deriving it from a corpus of tables, and how well a result serves the person who sought it. In doing so we consolidate frameworks and terminology across information retrieval, natural language processing, machine learning, databases, and human-computer interaction, and apply this grounding in a systematic review and analysis of systems and benchmarks that work towards OpenTI. We find that current systems do not cover the end-to-end scope of OpenTI, mainly focusing on the analysis itself, and that benchmarks are largely unfit for evaluations in an open setting as inputs presuppose knowledge of tables, and validation mechanisms do not match the setup. Finally, we distill a research agenda towards OpenTI systems, evaluation, and interaction paradigms that surface the insights users need. An interactive companion to our paper is available at https://open-tabular-insight-extraction.github.io.

AI agents sometimes act aligned when they infer they are being tested, and differently when not. We argue this is not an anomaly but what current training regimes are structured to select for. Reinforcement-learning-based alignment folds norms and task pursuit into one policy: the system learns its norms from scored behavior, and scoring flattens them. Do not do X is learned as doing X costs something if noticed. On every datum training can produce, a policy that complies only when it might be observed is indistinguishable from one that complies always. The experiment that would tell them apart - scoring unobserved behavior - is a contradiction in terms. Conditional compliance is thus the most that behavioral training can be known to deliver. Agency sharpens the problem: agents operate mostly where no one is watching, and can act on whether they are watched. An iterated pipeline that trains against detected failures selects for passing detection, not for complying. This account unifies alignment faking, sandbagging, and evaluation-aware scheming. And it reorients the remedy: not deeper internalization but architecture, making violations unavailable rather than unchosen.

Dot maps, which visualize individual data points as dots over a geographic region, are widely used across diverse domains to represent spatial patterns in sensitive data. However, the understanding of the privacy risks associated with dot maps remains limited, particularly for maps covering large geographic areas. In this paper, we systematically analyze these risks and present AutoLocate, an automated framework for high-precision location recovery. At its core, AutoLocate exploits anti-aliasing artifacts introduced during map rendering, which inadvertently encode sub-pixel information about dot locations. AutoLocate formulates location recovery as a black-box optimization problem, iteratively refining estimated coordinates by minimizing perceptual discrepancies over these artifacts between the target map and rendered candidate maps. Extensive experiments on both real-world and synthetic datasets, across different attack scenarios and a broad range of map configurations (e.g., map scale, background, resolution), demonstrate the effectiveness of AutoLocate. In particular, it achieves average recovery errors as low as 1 meter (approximately 0.0002 pixel precision) on small-scale maps of the United States, over 200x more accurate than existing approaches. We also propose mitigation strategies and introduce a privacy risk assessment tool to help practitioners evaluate and reduce privacy leakage when publishing dot maps.

The recently proposed Microcanonical Hamiltonian Monte Carlo algorithm has not yet been studied in detail from a thermodynamic point of view; this work aims to fill that gap. We demonstrate how thermodynamical state variables and potentials can be derived and thereby demonstrate that the construction of the algorithm formally represents a microcanonical thermodynamic ensemble. In particular, we demonstrate (analytically and numerically) that the algorithm fulfils the Helmholtz theorem, an alternative formulation of the first law of thermodynamics. Furthermore, we construct a new sampling algorithm that extends the original to lower-dimensional inference problems. Finally, we argue that canonical Markov Chain Monte Carlo algorithms are more natural than Microcanonical Hamiltonian Monte Carlo from the thermodynamic and information-theoretic point of view.

Oversized heating and cooling equipment can unnecessarily increase up-front costs, energy costs, pollutant emissions, and strain on electrical infrastructure. This paper develops two data-driven methods for estimating heating loads at design conditions to improve equipment sizing. One method uses smart thermostat data; the other uses utility bills. We test the methods on a dataset that we gathered from 74 detached single-family houses in five United States climate zones. The dataset includes smart thermostat time-series data, monthly utility bills, weather data, existing equipment specifications, and Manual J design load calculations (the United States industry standard) purchased from practitioners. The two methods have strong goodness-of-fit statistics individually and show fair agreement with each other. On average over the 74 houses, existing heating equipment is 2.75 (2.5th to 97.5th empirical percentile: 1.34-6.52) times larger than the thermostat-method estimate and 2.96 (1.36-7.76 times larger than the bill-method estimate. As implemented by practitioners, the Manual J estimate is 2.26 (0.87-5.21) times larger on average than the thermostat-method estimate and 2.35 (1.02-5.28) times larger than the bill-method estimate. We discuss prospects for implementing the data-driven methods at scale and for incorporating data-driven sizing into industry standards.

Environments are increasingly populated by multiple robots performing independent tasks with limited prior knowledge of each other. Deploying such multi-agent systems presents significant challenges. Specifically, shifts in deployment states compared to training data can lead to poor policy performance and compromised safety. While safety shields exist to mitigate these risks, they are typically reactive, which degrades performance near unseen obstacles,and centralized, limiting their scalability. To address this, we propose a decentralized framework that integrates predictive shielding with model-based finite horizon Q-learning. This approach allows agents to safely adapt their pre-trained policies during deployment. Furthermore, to mitigate livelocks in symmetric scenarios, we introduce a communication- free protocol for conflict resolution

With the rise of live sports betting in recent years, tennis forecasting has expanded from pre-match prediction to models that update win probabilities as a match unfolds. A central challenge in creating such a model is the constant need for models to adapt to score and performance changes. This study examines how pre-match and live information can be most effectively integrated into a model to produce accurate win-probability estimates. The analysis uses 8,222 Grand Slam matches containing a total of 1,505,355 points. Five models were evaluated using a chronological split, with matches from 2011-2021 used for training, 2022 for validation, and 2023-2024 for testing. Trace, a hybrid model, achieved accuracies of 76.06%, 82.15%, and 88.34% at 25%, 50%, and 75% match progress, suggesting that hybrid modeling is a practical approach to live tennis forecasting.

Cybersecurity vulnerability information is distributed across numerous platforms and databases, making it difficult for researchers and practitioners to obtain a unified and structured understanding of existing threats. This is a critical issue in cybersecurity, where timely access to accurate vulnerability information directly impacts risk assessment and decision-making. While previous work has shown that knowledge graphs are effective for organizing vulnerability data, a major research gap remains in their accessibility, as querying such graphs typically requires expertise in graph query languages like Cypher. This paper aims to address this gap by proposing an approach that combines the construction of a cybersecurity knowledge graph with natural language-based interrogation. The proposed methodology relies on data collected from the National Vulnerability Database (NVD)(1) through its REST API and models vulnerabilities, products, vendors, severity metrics, weaknesses, and references using the Labeled Property Graph paradigm in Neo4j. The knowledge graph is deployed on Neo4j Aura Cloud and queried through an AI-assisted interface that translates natural language queries into Cypher language. The key contribution of this work is demonstrating that natural language querying significantly lowers the barrier to interacting with cybersecurity knowledge graphs, enabling more intuitive exploration and analysis of vulnerability data, and thereby enhancing their practical usefulness for a broader range of users in the cybersecurity field.

Scientific ideation is the capacity to formulate novel and testable hypotheses from scientific evidence, and autonomous AI scientists depend on it. Existing evaluations largely assess it by asking models to generate ideas from a static, curated set of reference papers. That passive setup departs from the retrieval-and-reasoning workflow of modern AI scientists, and it becomes less discriminative as models improve. We introduce AgentIdeaBench, a multidisciplinary benchmark that evaluates scientific ideation under two matched settings, static observation and active exploration. We report matched Static-Active evaluations for 33 LLMs across 40 densely scored subfields spanning five disciplines, using a multidimensional, literature-verified scoring framework whose critics assess originality against retrieved prior art. Active exploration reveals considerably more capability headroom, and that headroom is unevenly distributed across models. Performance scales about twice as fast as under static observation, and the exploration gain is capability-gated, favoring the strongest models over the weakest. The gain reflects better grounding, improving feasibility, clarity, and specificity while leaving measured originality unchanged under our critics. We further explore Scientific World Modeling, a generation-time loop that refines a draft hypothesis through structured thought experiments. It benefits mid-capability models, and its impact diminishes among frontier models that appear to have internalized such reasoning patterns already. AgentIdeaBench gives future work on scientific ideation a measurement basis suited to the agent era.

We convert black-box clinical prediction models for tabular data into standalone nomograms that can be audited term by term. PRiSM (Partial Responses in Structured Models) takes the shape of each effect and interaction from the source model, not merely which variables mattered, and lets the outcome select and weight them. We tested this in 50,356 heart transplant recipients, with validation in a later era than training. Nomograms from all 5 source models - a public clinical risk score, logistic regression, neural networks, random forests and extreme gradient boosting - met a prespecified noninferiority criterion for discrimination before any further simplification, and generally preserved calibration and clinical net benefit. Those from the 3 machine-learning models showed no detectable difference in discrimination from de novo generalized additive and explainable boosting models, exceeded neural additive models, and carried fewer terms than the explainable boosting model. PRiSM is released as an open-source Python package.

The global structure of P2P networks underlying modern cryptocurrencies is hidden by design: each node only knows its neighbors and maintains a local peer table of IP addresses. The peer table of a node can be seen as the node's “local view” of the set of nodes currently in the network: it is constantly updated with information collected from the neighbors and it is used by the node to establish new connections when needed. The maintenance rules of the nodes' peer tables determine the global structure of the network and its evolution. Even though the global structure is unknown to any node of the network as well as to any external observer, the rules for the exchange of information between neighbors are compatible with the design and use of network crawlers that can query the nodes and extract some information about their peer tables. In this paper we first analyze the data we crawled from nodes of the Bitcoin and Dogecoin P2P networks, to collect information about the distribution of IP addresses in the peer tables and to estimate the evolution of network size and churn rate; we then use the estimates to set up the parameters for a simulation of the Bitcoin network and we analyze the evolution of the network structure that we get from the simulation. Overall, our results show that Bitcoin's peer-table maintenance rules induce non-uniform, heavy-tailed visibility patterns while nevertheless generating a well-connected and structurally robust network.

Bridging the simulation-to-reality gap in roadside LiDAR requires addressing several coupled discrepancies, including scene geometry, sampling density, return patterns, and pedestrian scale. This report presents a multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection. The method organizes digital-twin scans, diffusion-redrawn scans, density-stabilized scans, and pedestrian morphology-aligned samples into a unified training pool with complementary roles. Within a common DSVT detection formulation, source-specialized expert branches preserve those roles while optimizing for the same detection objective. At inference, a predefined class-aware fusion pathway integrates geometry-stable and calibration-aware branches for vehicles, sampling-complementary branches for trucks, and morphology-consistent evidence for pedestrians. A label-free point-cloud center blend then refines geometric localization. On the UrbanTwin V2X-Real hidden test set, the unified system achieves a combined score of 0.7421, with 3D mAP@0.5 of 0.4518 and a realism score of 0.8871. The results indicate that a stable, interpretable collaboration among data sources is more valuable than unconstrained aggregation of model outputs.

Judicial judgments are increasingly available, yet dense language and distributed relationships among facts, evidence, reasoning, and rulings remain difficult for non-experts to interpret. Through a mixed-methods formative study with Chinese non-expert readers (survey N=34; interviews N=6), we identified structural, interpretive, verification, and action breakdowns. We developed JudgmentLens, an AI-augmented reading system combining persistent case representations, adaptive explanations, and traceable links from generated interpretations to judgment passages. In a counterbalanced within-subject evaluation (N=16), participants completed tasks faster with JudgmentLens than with conventional PDF reading and reported lower workload and greater self-reported decision understanding, while rubric-scored comprehension did not differ reliably. An exploratory PDF+DeepSeek probe suggested that conversational AI supported formulated questions while leaving question formulation, answer integration, and source checking largely to users. We contribute an empirical account of non-expert judgment sensemaking and design strategies for inspectable, source-grounded AI mediation.

Time series data is very common in many real-world applications and in numerous domains, with increasing interest for automated information extraction using machine learning. One of these subfields is time series clustering, which consists in identifying clusters among a set of time series in an unsupervised fashion. Most time series clustering algorithms suffer from the same balancing act: they trade clustering performance for faster runtimes or vice versa. We present a novel time series clustering algorithm that we call CLUES-WEASEL, which stands for CLustering with the UnsupervisEd Second version of Word ExtrAction for time SEries cLassification. CLUES-WEASEL extracts features using the unsupervised version of the transformation step of WEASEL 2.0, which is a time series classification algorithm, then reduces these features using principal component analysis, and finally performs clustering with the $k$-means algorithm using these reduced extracted features. Through extensive experiments, we prove that CLUES-WEASEL is significantly better than any other existing time series clustering algorithm while being (much) faster than any state-of-the-art one. We also show that the architecture of CLUES-WEASEL can work well with other time series feature extraction algorithms. Our findings highlight the relevance of CLUES-WEASEL for time series clustering.

Agentic systems can interpret user requests, search the live web, and use external tools, but their ability to transform retrieved web content into a usable 3D world has not been systematically evaluated. No established end-to-end pipeline or benchmark exists for this capability. We introduce Search-to-World, an end-to-end evaluation task covering request understanding, web visual-content retrieval, and 3D-world delivery. We define Observed Retrieval Rate (ORR) and World Delivery Rate (WDR) to distinguish observing relevant content from successfully delivering a request-aligned, perceptually acceptable world. We also present WorldSearcher, a reuse-then-reconstruction harness that connects existing search agents to world delivery: it first retrieves reusable 3D worlds and, when none are available, reconstructs a world from video. A structured recovery controller revises temporal grounding, replaces source videos, or reformulates queries after failure. Using WorldSearcher, we benchmark representative models on Search-to-World and study supervised fine-tuning (SFT) for recovery subagents. Results show that delivery depends on the underlying agentic model, and that relevant-content observation does not ensure world delivery. Jointly training recovery agents improves delivery success and action efficiency. Search-to-World makes agentic 3D-world delivery measurable, while WorldSearcher provides a practical evaluation harness with recovery capabilities.

Financial scenarios are diverse and complex, spanning varying data conditions, tool configurations, and workflows. Yet existing CUA, Computer-Using Agent, evaluation tasks remain largely manually constructed, limiting scalable coverage of real-world financial scenarios. Then, can agents autonomously construct diverse CUA evaluation tasks for financial scenarios? Evaluating this capability poses three key challenges: scenario coverage of construction requests, fair comparison across construction methods, and reliable assessment of generated task quality. To solve these, we introduce FinCUABuildBench, a benchmark for evaluating financial CUA task construction, featuring: (i) 576 construction requests covering 24 financial workflows and three types of runtime variation; (ii) standardized input, budget, and output specifications; and (iii) a task qualification mechanism based on execution tests and quality checks. We further introduce FinCUABuildAgent, a multi-agent system for automatically constructing dynamic financial CUA evaluation tasks. It consists of three modules that jointly construct tasks, environments, and validators. On FinCUABuildBench, under the same model backbone, existing agent-based construction methods achieve strict qualification rates of only 1.3-8.3%, while FinCUABuildAgent reaches 31.3%. Downstream evaluations further show that the constructed tasks can effectively differentiate CUA task-execution capabilities. These results demonstrate that agents can autonomously construct financial CUA tasks with meaningful evaluation value, offering a practical path toward broader evaluation coverage in financial scenarios. Code: https://github.com/FengxianJi/FinCUABuild

The application of large language models (LLMs) to personalized medical assistants has garnered growing interest. However, existing medical benchmarks largely rely on static question answering with pre-selected evidence, leaving unclear whether LLMs can make reliable clinical decisions from real longitudinal electronic health records (EHRs). To bridge this gap, we introduce ObGynLongBench, a rule-grounded long-context EHR benchmark for obstetric and gynecologic decision-making, comprising 1,500 clinical decision-point cases from 976 real pregnancy EHR histories and traceable rules. Each case is anchored to a patient, a pregnancy-timeline point, and a pre-decision information boundary, enabling Evidence-only, Visit-level EHR, and History-level EHR evaluation. Evaluating 17 LLMs reveals a substantial Evidence-to-EHR Gap: models perform well when evidence is directly provided, but accuracy drops when evidence must be extracted from same-day records or full pre-decision EHR histories. Further analyses identify evidence utilization as a key bottleneck: performance decreases with longer EHR contexts and more complex evidence requirements, and earlier failures often predict later failures within the same patient history. Finally, active-search agents perform best among EHR access strategies, highlighting patient-specific evidence utilization as a central challenge for reliable personalized medical assistants. Resources are available at https://github.com/xiangjun2003/ObgynLongbench.

Tree species recognition supports forest inventory and biodiversity monitoring but still depends on scarce taxonomic expertise. Bark is visible year-round at ground level, yet bark recognition has concentrated on temperate floras and on large ImageNet-pre-trained backbones. We address both gaps. First, we release BarkBD, a bark dataset for Bangladesh: 14,258 uncropped smartphone photographs of 20 native species across four districts and three weather conditions, with a fixed stratified split. Second, we propose BarkNet-Lite, a 2.96M-parameter network trained from random initialisation, pairing a multi-scale texture pathway with a parallel colour-aware pathway. Over five seeds it reaches 96.64+-0.66%accuracyunderstrict single-image inference, within 2.3 points of nine ImageNet-pre-trained backbones fine-tuned under an identical protocol and within one seed-level standard deviation of the smallest ofthem, andtransfers to public benchmarks (95.86% on BarkVN-50, 92.85% on BarkNet 1.0). Grad-CAM, validated by faithfulness and weight-randomisation checks, confirms its decisions rest on bark structure rather than background. The exported single-precision model classifies one photograph in 15.34ms on a commodity smartphone.

Multidimensional approximate agreement requires $n$ processes with inputs in $\mathbb{R}^d$ to output vectors close to each other, despite up to $t$ Byzantine faults. Under convex validity, outputs must lie in the convex hull of the correct inputs, which leads to resilience thresholds that grow with the dimension. We instead study Minimum Enclosing Ball (MEB) validity and its multiplicative relaxation $c$-MEB validity. Our first contribution is Adaptive MEB Contraction, a coordinate-free algorithm that, in the synchronous model with $n>(d+1)t$ contracts the correct MEB radius by $1/\sqrt2$ per round for $\alpha=1$ while satisfying $\sqrt2$-MEB validity. We also give an example showing that this bound is tight for our analysis. Our main technical contribution is a dimension-free inflation theorem: if every $\beta$ balls in a finite family of Euclidean balls have a common point, then inflating each radius by $\sqrt{\beta/(\beta-1)}$ guarantees a common intersection. Applying the theorem to the candidate balls defining the local MEB-safe areas results in a synchronous algorithm with optimal resilience $n>3t$, contraction factor $\sqrt3/2$ and $\sqrt6$-MEB validity. To the best of our knowledge, this is the first multidimensional approximate agreement algorithm with optimal resilience, constant $c$-MEB validity and coordinate-free contraction. We further extend the approach to the asynchronous setting. Without inflation we obtain resilience $n>(d+2)t$, contraction factor $\sqrt{2/3}$ and $\sqrt6$-MEB validity, whereas with inflation for $n>4t$ we get the contraction factor $\sqrt{15}/4$ and $2\sqrt{10}$-MEB validity. Finally, we compare our guarantees with existing algorithms, including Minimum-Diameter Averaging (MDA), for which we derive MEB-validity guarantees. Our algorithms achieve strictly better resilience while providing substantially stronger MEB-validity guarantees than MDA.

As large language models (LLMs) blur the boundary between cognition and computation, they reshape knowledge production and collective life. We combine a curated review of 198 papers with computational mapping of 47,719 formally published papers from five databases. Text embeddings, clustering, and topic modeling organize the curated literature into 13 subcategories across three domains. LLM as Social Minds examines mind-like reasoning and socially grounded behavior in individual models. LLM Societies explores how interactions among agents produce collective behavior and social organization. LLM-Human Interactions examines how people perceive and engage with LLMs, and how interaction reshapes human thinking, creativity, and relationships. Structural topic modeling of the larger corpus traces how research attention shifts over time and differs across publication venues. We present a reproducible framework that identifies the field's underlying structure and enables its continuous refinement as new studies emerge. The review also identifies a gap in current understanding: the mechanisms underlying many of LLMs' observed cognitive and social behaviors remain unclear. Human-like performance can then be mistaken for understanding, obscuring the norms, biases, and structures of power that LLMs reproduce. We call for shared benchmarks and robustness checks across the three domains to build a reliable evidence base for understanding LLMs' social behaviors and informing their design and use.

Muon emerges as a strong competitor of the AdamW for LLM pretraining, because the matrix-wise update it employs can potentially incur smaller second-order penalty than the once dominating AdamW, which performs coordinate-wise update. However, the spectral flattening procedure in Muon is quite debatable since it discards the spectral amplitude information totally. To seek for better spectral allocation (and the associated spectral subspace), we propose to solve the quadratic model of loss function under the spectral norm constraint directly (i.e., in a genuinely Newtonian way) and thus obtaining the Quadratic Spectral Descent (QSD) algorithm. In contrast, many existing curvature-aware methods either exploit the second-order information in an implicit way by changing the weight update geometry (such as Mousse, FISMO) or rely on strong assumptions (such as the weight displacement isotropy assumption in Newton-Muon). QSD's potential advantage over these methods is best illustrated in the isotropic curvature scenario, where Mousse, FISMO and Newton-Muon all reduce to Muon while the spectral allocation in QSD is still non-flat (since the spectral allocation in QSD depends on the gradient to curvature ratio). Meanwhile, to control the complexity of QSD, we employ inversion-free K-FAC and online Frank-Wolfe update which is essentially a matrix sign operator. Overall, the complexity increase can be rather mild. Experiments on GPT pre-training show that QSD consistently improves validation loss over Muon and recent Muon variants, while achieving up to an $8.49\%$ wall-clock speedup at matched validation loss.

Vision-language models (VLMs) are increasingly used in settings where some input modalities may be unavailable, yet we know little about whether they can faithfully explain how such missing information affects their own predictions. We introduce an interventional protocol for evaluating self-explanations of modality dynamics: models state what each modality alone would support, whether restoring a missing modality would change their answer, and whether the available evidence is sufficient; we then execute the corresponding intervention and compare these claims with realized behavior. We evaluate ten VLMs spanning open-weight and proprietary models across four tasks covering mixed, redundant, and unique modality regimes. We find a systematic tendency to overstate the sufficiency of available evidence. Models substantially underestimate the effect of restoring missing modalities: executed change exceeds predicted change in 78 of 80 model-task-condition settings, with task-level median executed change rates reaching 70.1% while median predicted rates remain at most 9.6%. Insufficiency claims have low recall, leaving many cases in which behavior changes despite a stated claim of sufficiency. Retrospective self-explanations show the same tendency, over-crediting single-input sufficiency in mixed regimes and interchangeability in redundant ones. Together, these results show that VLMs systematically mischaracterize how their predictions depend on available and missing evidence, motivating executable interventions as a behavioral test of multimodal self-explanations.

The same underlying computational problem is solved across unrelated fields under different names: recursive Bayesian state estimation appears as a "Kalman filter" in control, "Bayesian forecasting" in pharmacokinetics, and "data assimilation" in geoscience. Topical and citation-based scientific embeddings cannot see this shared problem. We distill each paper once into a domain- and method-name-stripped faceted computational fingerprint, a free-text mechanism skeleton plus controlled computational facets. We define a tunable, facet-selectable similarity over it. The goal is solution import: surface cross-field pairs solving the same problem, so a bespoke implementation can be swapped for another field's standard, specialized solver. On a benchmark of 18 method families across 109 papers, the skeleton lifts cross-domain retrieval average precision over the abstract from 0.222 to 0.513, and the whole fingerprint reaches 0.557. Strikingly, four trained scientific embedders all fall below plain abstract+TF-IDF: they encode topical and citation similarity, the wrong signal for this task. The gain is the representation: the abstract-to-skeleton swap lifts every embedder, and the pipeline is one cached LLM call per paper plus a cheap embedder. An interventional re-skin / math-edit test shows the fingerprint tracks the computation, not the field. On a 501-paper wild corpus, known twins dominate the top of the ranking (23 of the top 30); with planted pairs excluded from the results, three blind LLM judges rate 3 of the top 5 and 8 of the top 30 pairs genuine import candidates, and 0 of 30 random ones. The human verification is the four executed imports: in one, an open standard solver reproduces a bespoke clinical dosing engine's output. We release the benchmark, the code, and the distillation prompt.

Conversational Task Assistants (CTAs) are multimodal dialogue systems that support users in complex real-world tasks such as cooking and DIY through voice, text, image, and video interactions. Prior user studies have focused on controlled settings, leaving limited understanding of real-world CTA usage at scale. In this work, we present a large-scale study of CTA usage based on thousands of users in-the-wild. Our large-scale real-world data analysis unveils new understandings of (i) user-CTA interaction flows, (ii) user intents, (iii) user conversational traits, and (iv) behavioral factors associated with user satisfaction. Our findings reveal key opportunities for future research in CTAs, particularly in user interaction design and task engagement, concluding with concrete design guidelines.

Foundation models for ground states in spin-1/2 systems are a promising method for problems ranging from quantum chemistry to identifying new phase diagrams. Nearly all such models are currently pure-states that condition on the Hamiltonian's parameters, whose Monte Carlo samples give energy estimates according to the variational principle. In this contribution, we show that this representation is topologically obstructed. For any gapped Hamiltonian family whose ground-state bundle is non-trivial, every continuous normalized state-vector model has zero fidelity with the ground state at some parameter value in the Hamiltonian family. For that value, the energy is at least one spectral gap, $\Delta$, with an $O(\Delta)$ gap in an open-neighbourhood of that point. We show that this is a sufficient no-go also in the case of degenerate ground-state manifolds, time dynamics, and periodic systems with mixed space-time topology, demonstrating these obstructions on one- and two-qubit systems. We discuss how this causes a spike in the fidelity susceptibility, giving a numerical signature of a phase-transition where there is none. Finally, we show that operator-valued models canonically avoid these obstructions and preserve topological information, implying a structural necessity in representation for foundation neural quantum states.

We present our solution to the LUMPI track of the UCF UrbanTwin Sim2Real LiDAR Challenge at the 6th DriveX Workshop, ECCV 2026. The detector must be trained only on synthetic data and is evaluated on 50 held-out real LiDAR frames; a separate 50-frame synthetic submission is evaluated for point-cloud realism. Our method addresses the Sim2Real gap at three levels. First, we align synthetic scans to the 50k-point test density and build a 30k-record training pool using UT-LUMPI geometry, RangeLDM-based sampling diversification, rare-class copy-paste, and pedestrian-oriented augmentation. Second, complementary DSVT detectors and Car/Bus PointPillars specialists are trained under the same synthetic-only constraint. Third, predictions are integrated by class-aware routing, asymmetric agreement fusion, constrained residual-recall supplementation, class-coverage auditing, and selective box-size calibration. The realism branch is optimized independently with radial-density matching, weak affine calibration, and calibrated set mixing. The final submission obtains a Combined Score of 0.4692, a Detection Score of 0.1797, a Realism Score of 0.9035, and 3D mAP@0.5 of 0.1258.