arXiv:2607.10564v1 Announce Type: new
Abstract: We study online metric facility location with uniform opening costs in the random-order model (Meyerson FOCS'01). The best previous upper bound was a $3$-competitive randomized algorithm (Kaplan, Naori, Raz SODA'23), leaving a gap to the best known lower bound of $2$. In this work, we give two algorithms with improved competitive ratios: (i) a deterministic algorithm with a competitive ratio below $2.42$ and (ii) a randomized algorithm with a competitive ratio below $2.59$ and the additional property that it retains the asymptotically optimal $O(\log n/\log \log n)$ competitive ratio in the adversarial-order model. A key improvement is to take the arrival time of the request into consideration when making opening decisions: The arrival time carries geometric information about the local density around the request, which fundamentally helps the algorithm.
Science Journals
arXiv:2607.10774v1 Announce Type: new
Abstract: A binary Coxeter code associated with a finite Coxeter system $(W,S)$ is an ${\mathbb F}_2$-linear span of indicators of standard cosets of a fixed rank. Coxeter codes, introduced in a recent paper by N. Coble and A. Barg, are a generalization of Reed--Muller codes which arise when $W={\mathbb Z}_2^m$ is the Coxeter group of type $mA_1$. In that paper, the authors proposed a conjectural value for the minimum distance of a general Coxeter code. This conjecture is proved in the present work. As a consequence, we obtain a Coxeter-theoretic generalization of Reed's majority-logic decoding algorithm for Reed--Muller codes.
arXiv:2607.11510v1 Announce Type: new
Abstract: Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs (DAGs). In this paper, we propose \textbf{DAG-FM}, a novel foundation model architecture that amortizes causal discovery. Unlike direct matrix prediction, DAG-FM decomposes the causal discovery process into two auto-regressive stages using two specialized Transformer-based sub-modules: a leaf-node predictor and a parent-node predictor. To effectively model complex row-column interactions, we adopt a robust tabular interaction block to output feature-wise representations. Crucially, to handle diverse and unknown Functional Causal Model (FCM) assumptions in real-world scenarios, we introduce Mixture-of-Leaf-Experts (MoLE), allowing the model to dynamically route and adapt to identifiable mechanism families. Through an iterative inference algorithm, DAG-FM seamlessly extracts causal orderings and constructs valid DAGs. Extensive experiments demonstrate that DAG-FM achieves state-of-the-art performance on both synthetic benchmarks and complex real-world datasets, significantly outperforming traditional classical algorithms and recent foundation models in both accuracy and scalability.
arXiv:2607.07820v2 Announce Type: replace
Abstract: Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision for long-horizon interactions. We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools. DeepSearch-World contains 420K multi-hop QA tasks constructed from entity-level random walks and supports key agentic cognitive behaviors useful for self-evolving, including progress verification, grounded reflection, and failure recovery. DeepSearch-Evolve iteratively performs trajectory generation, filtering, data mixing, and fine-tuning to train stronger agents. Without distillation from more capable models, DeepSearch-World-9B achieves competitive performance compared with open-source agents, reaching 31.2% on BrowseComp, 61.5% on GAIA, and 93.4% on HotpotQA, showing that verifiable environments enable scalable self-evolution for long-horizon web agents. We will release the environment, 420K training pool, validation set, model, and code to facilitate future research on self-improving deep search agents.
arXiv:2607.11266v1 Announce Type: new
Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps. While existing reasoning step evaluators effectively detect logical fallacies and factual errors, our analysis reveals a critical blind spot: they fail to penalize valid but inefficient reasoning steps that inflate token usage without contributing to the solution. To systematically diagnose this limitation, we introduce RIV-GSM8K, a diagnostic benchmark injected with five distinct types of inefficiencies, including circular reasoning and excessive decomposition. Diagnostic experiments reveal that state-of-the-art evaluators struggle to distinguish these inefficiencies from necessary reasoning. To address this gap, we propose CAID (Context-Aware Information Density), a training-free metric grounded in information theory that identifies low-utility steps. To validate the metric's practical utility, we apply it within PACE, a post-hoc compression strategy. Additional control experiments show that the gains of PACE are not explained by trivial pruning: compared with random step removal and PRM-based compression baselines, it preserves accuracy at substantially higher compression rates. Empirical results on GSM8K, StrategyQA, and ARC-Challenge demonstrate that PACE reduces token consumption by 31-53% while maintaining accuracy, confirming that CAID successfully distills informational froth from reasoning chains without compromising deductive validity.
arXiv:2607.11711v1 Announce Type: new
Abstract: Correlation-consistent Gaussian basis sets are central to systematic molecular quantum chemistry, but their direct use in periodic solids is often limited by severe linear dependence from diffuse atomically optimized primitives. This problem is particularly acute for metallic and metal-containing systems, where reliable complete-basis-set (CBS) extrapolation is needed for correlated-wavefunction benchmarks. We introduce material-constrained atomic optimization (MCAO), a basis-set optimization framework that preserves the atomic and correlation-consistent character of Gaussian basis sets while penalizing large overlap-matrix condition numbers in representative solids. As a proof of concept, we generate Dunning-style MCAO-cc-pVXZ basis sets (X = D, T, Q) for Cu with all-electron, scalar-relativistic all-electron, effective core potential (ECP), and pseudopotential treatments. The resulting basis sets remain numerically stable for Cu solids and surfaces while reproducing molecular Cu dimer energetics and plane-wave reference properties of bulk Cu. CBS-extrapolated random-phase approximation calculations further enable a controlled assessment of pseudopotential, relativistic, and basis-set errors in bulk Cu and CO adsorption on Cu(111), providing scalar-relativistic all-electron Gaussian-basis benchmarks for the CO adsorption puzzle.
arXiv:2607.11274v1 Announce Type: new
Abstract: Sustainability refers to a system's ability to maintain its functionality and endure over time. Hence, sustainability is a highly desirable property of software systems, including Self-Adaptive Systems (SASs). SASs can change (adapt) their behavior at runtime to continue achieving their objectives despite external or internal impacts. SASs' intended long-term system behavior can be expressed through a sustainability-driven visual modeling notation called Decision Maps (DMs). Although DMs have been proven helpful, they lack adequate modeling support for safety and security concerns. We address this limitation by extending the current notation for sustainability-driven modeling of SASs to better accommodate the unique characteristics of safety and security scenarios. First, we introduce an additional modeling dimension to account for safety incidents. Second, we adopt a fine-grained divide-and-conquer approach, modeling from distinct temporal security viewpoints ("security modes") to address security. We employ the extended DM notation in a real-world use case scenario provided by our industry partner to assess its feasibility and suitability for practitioners. Our results indicate that our modeling notation helps capture security and safety scenarios more accurately and provides holistic support for the self-adaptation life cycle phases.
arXiv:2607.11732v1 Announce Type: new
Abstract: Referring Camouflaged Object Detection (Ref-COD) requires segmenting hidden targets guided by reference cues. While supervised methods are annotation-heavy and training-free approaches via sparse point-prompting are sensitive to localization errors, we propose GFR-SAM, a robust three-stage training-free framework. GFR-SAM shifts the paradigm from fragile point-matching to a "Generate-Filter-Refine" pipeline. First, we introduce In-Context Exemplar-guided Segmentation, empowering SAM3 with cross-image inference to generate candidate masks via holistic visual exemplars, bypassing its native intra-image constraints. Second, a Region-Global Contrastive Filtering module ranks candidates through DINOv3-based prototypical alignment, effectively suppressing background distractors. Finally, a Geometric-Semantic Refinement module synergizes bounding box and text prompts to recover fine-grained boundaries and enhance instance recall. Evaluated on the R2C7K benchmark, GFR-SAM outperforms existing training-free methods by 8.7\% in weighted F-measure ($F_\beta^w$) and competes with supervised state-of-the-art counterparts. Ultimately, this work underscores the potential of unlocking SAM3's latent capability for cross-image In-Context prompting, establishing a robust, training-free paradigm that effectively bridges the gap between general-purpose foundation models and specialized, label-intensive perception tasks without the need for task-specific fine-tuning.
arXiv:2607.10174v1 Announce Type: new
Abstract: With the proliferation of Virtual Reality (VR) markets, VR applications are rapidly expanding in scale and complexity, thereby driving an urgent need for assuring VR software quality. Different from traditional mobile applications and computer software, VR testing faces unique challenges due to diverse interactions with virtual objects, complex 3D virtual environments, and intricate sequences to complete tasks. All of these emerging challenges hinder existing VR testing tools from effectively and systematically testing VR applications.
In this paper, we present VRExplorer, a novel model-based testing tool to effectively interact with diverse virtual objects and explore complex VR scenes. Particularly, we design the Entity, Action, and Task (EAT) framework for modeling diverse VR interactions in a generic way. Built upon the EAT framework, we then present the VRExplorer agent, which can achieve effective scene exploration by incorporating meticulously designed path-finding algorithms into Unity's NavMesh. Moreover, the VRExplorer agent can also systematically execute interaction decisions on top of the Probabilistic Finite State Machine (PFSM).
Experimental evaluation on 11 representative VR projects shows that VRExplorer consistently outperforms the state-of-the-art (SOTA) approach VRGuide by achieving significantly higher coverage and better efficiency. Specifically, VRExplorer yields up to 122.8% and 52.8% improvements over VRGuide in terms of executable lines of code (ELOC) coverage and method (function) coverage, respectively. Furthermore, ablation results also verify the essential contributions of each designed module. More importantly, our VRExplorer has successfully detected two functional bugs and one non-functional bug from real-world projects.
arXiv:2607.10179v1 Announce Type: new
Abstract: Patent databases represent one of the largest public archives of technical knowledge, yet much of this knowledge remains difficult to identify, interpret, and reuse once patent rights expire or lapse. This paper proposes an AI-enabled framework for discovering expired and lapsing patents, identifying technology trends, and translating patent disclosures into business pathways. We use pathways to mean structured commercialization routes such as SaaS products, services, licensing packages, consulting playbooks, training offerings, data products, or internal process tools. The framework treats patent expiry as both a business signal and an archival transition, not primarily as a legal problem. Legal status remains important, but it is one risk-screening input alongside customer need, implementation feasibility, channel access, and market timing. We describe a system architecture that combines patent metadata, maintenance-fee records, legal-status indicators, semantic search, patent-family analysis, market signals, and generative AI workflows. A proof of concept parses all 378 records in an official weekly CIPO ST.96 archive, identifies 20 expired, lapsed, or near-expiry candidates, tests the stability of the transparent scoring model, and uses a locally hosted Qwen3.6 model to populate structured review packets. The evaluation demonstrates reproducible ingestion, stable rankings under weight perturbation, and schema-conformant model output, while also exposing incomplete legal-status coverage and the need for register and expert review. We argue that AI can function as a discovery and translation layer for dormant technical knowledge, but that such systems must explicitly represent legal uncertainty, data limitations, and commercialization risk.
arXiv:2607.11736v1 Announce Type: new
Abstract: Language models are increasingly used for moral decision-making across diverse linguistic and cultural contexts, yet existing work overlooks multilinguality on three aspects: 1) multilingual evaluation benchmarks use direct translation, failing to adapt culture-specific items; 2) inference-time methods for moral reasoning rely on static, English-centric scaffolds and lack grounding in moral theory; 3) training methods for moral decision-making typically require expensive supervision from stronger models or human annotators. We address these gaps with three contributions. First, we introduce MCLASH, a multilingual moral decision-making benchmark to capture culturally situated moral intuitions and social norms across languages. Second, we propose MET (Multilingual Ethics with Theory-grounded reasoning), a two-step prompting method built on expert-curated, theory-based grounds drawn from psychology and philosophy: the model first selects situation- and culture-specific grounds, then reasons over them in the native language of the user. Third, we introduce MET-D (MET-Distillation), which enhances the second step through a self-distillation training stage that requires no external supervision. MET-D improves macro-F1 over the base model on all three models of different sizes and families (Qwen3-4B, Qwen3-8B, Gemma3-4B), by an average of 3.71 points on MCLASH and 4.23 on MMoralExceptQA, with a peak MCLASH gain of 12.94 points for Malay on Qwen3-8B. We further reveal that MET-D increases native-language reasoning by 62.13 points on average, and that beneficial grounds differ systematically across cultures. Together, these contributions open the path for culture-aligned, theory-grounded multilingual moral reasoning.
arXiv:2607.10469v1 Announce Type: new
Abstract: Across a range of fast growing urban markets, private developers are constructing a version of the smart city that operates largely outside the purview of municipal government, often at the explicit invitation of city officials seeking to shift the cost and complexity of digital infrastructure onto private capital. Gated residential and mixed use developments are increasingly marketed not merely on the basis of security and amenity, but on their smartness: integrated home automation, app mediated access control, and centralized energy and resource management, among other features. We refer to this phenomenon as the smart compound. Despite its rapid proliferation, it has received comparatively little sustained scholarly attention: the literatures on smart cities and on gated communities have developed largely independently of one another, even as developers are, in practice, merging the two. This paper introduces the smart compound as an emerging real estate and urban development phenomenon, considers the opportunities and risks it presents, and examines how questions of data governance differ when smart urban infrastructure is built and owned privately rather than publicly. It concludes with a set of research questions intended to orient researchers, planners, and regulators toward a phenomenon whose growth is outpacing the scholarship meant to account for it.
arXiv:2607.11314v1 Announce Type: new
Abstract: The promise of AI literacy ``for all'' confronts a structural challenge embedded in how nations organise secondary computer science education. In most systems, a general-track subject -- Digital Literacy, ICT, TIC, or SNT -- bears the weight of universal AI literacy, while a specialist Informatics course serves STEM pathways separately. Yet the content and depth of the general track are shaped by governance decisions made largely with reference to the specialist one. This paper presents a comparative analysis of curricula and examination frameworks across fifteen countries, identifying two structural challenges. First, in several systems a significant portion of students completes secondary education without any formal programming exposure. Second, among those who do receive CS education, a \emph{Syntax Ceiling} emerges: Python-based instruction reaches most students, while the algorithmic depth associated with C++ remains concentrated in elite STEM tracks. Drawing on reform cases spanning centralised mandates (France, China, Japan), assessment-driven systems (Poland, Romania, South Korea), and recent universal reforms (Switzerland, Kazakhstan), we show that governance structures and high-stakes examinations are the primary drivers of both challenges -- and that specialist and general-track language choices are rarely independent, linked through shared teacher pipelines that curriculum policy seldom acknowledges. Achieving genuine AI literacy for all requires confronting not just curriculum content, but the access architectures and resource constraints that determine who receives it -- and at what depth.
arXiv:2607.10948v1 Announce Type: new
Abstract: Optimal Transmission Switching (OTS) reduces generation cost by strategically opening transmission lines, but its mixed-integer linear program (MILP) formulation scales poorly for large-scale transmission networks. Reinforcement learning (RL) offers a computationally efficient alternative, but existing RL-based OTS approaches rely on soft penalties that permit physical constraint violations. This paper presents a comparison between an RL framework and an MILP-based optimization method for OTS. Case studies were carried out on the IEEE RTS-96 24-bus system; results show that the agent was able to produce near-optimal solutions at low switching budgets and tended to yield suboptimal solutions at high switching budgets. However, the RL agent was able to generate feasible solutions two-to-three orders of magnitude faster than the optimization solver.
arXiv:2607.11050v1 Announce Type: new
Abstract: We describe an $\widetilde{\Omega}(1/d^4)$-improvement over threshold rounding schemes for a broad class of Boolean MAX 2-CSP instances in which every variable appears in at most $d$ constraints. In the case of MAX 2-SAT, we improve the ratio further and obtain an $(\beta_\star + \widetilde{\Omega}(1/d^2))$-factor approximation algorithm for bounded-degree MAX 2-SAT instances, where $\beta_\star$ is the UGC-optimal approximation ratio for MAX 2-SAT achieved by the LLZ algorithm. Our result generalizes an $(\alpha_{GW} + \widetilde{\Omega}(1/d^2))$-factor approximation algorithm for MAX CUT on graphs with degrees bounded by $d$, due to Hsieh and Kothari. Together with the state-of-the-art approximability results for MAX DI-CUT and MAX 2-AND, our result suggests that similar improvements exist for bounded-degree instances of these problems as well.
arXiv:2607.11339v1 Announce Type: new
Abstract: Recent text-to-CAD approaches have shown promising results by leveraging large language models, but they often struggle with maintaining structural consistency in complex designs and accurately grounding geometric parameters. To address these issues, we propose HierCAD, a hierarchical text-to-CAD framework that improves both structural reasoning and parameter prediction. HierCAD reformulates CAD generation as progressive reasoning by decomposing CAD construction trees into object-level procedural reasoning and part-level topology reasoning trajectories. To further improve generation fidelity, we introduce a unified Structure Alignment and Parameter Grounding (SAPG) learning strategy. Structure alignment aligns topology reasoning trajectories with their corresponding parametric CAD spans, while parameter grounding mitigates shortcut learning through structure-preserving parameter perturbations and ranking-based supervision. Experiments demonstrate that HierCAD outperforms prior state-of-the-art methods on both CAD sequence generation and reconstructed CAD model evaluation. Our code is available at https://github.com/Collab-Gen/HierCAD.
arXiv:2607.02772v2 Announce Type: replace
Abstract: Since 2020, the Linux Foundation and the multi-organization Inclusive Naming Initiative (INI) have encouraged open-source projects to replace non-inclusive terms such as master/slave and whitelist/blacklist. Although these recommendations have been widely adopted, there is limited empirical evidence on their long-term adoption across Linux Foundation (LF) projects or their implications for AI-assisted software development. In this paper, we present NISCAN, a multilingual static-analysis framework that detects non-inclusive terminology across source code and related software artifacts using the INI vocabulary. Using NISCAN, we conduct the first ecosystem-scale study of inclusive naming across 461 Linux Foundation repositories. Our analysis shows that non-inclusive terminology has declined by approximately 47% since 2020, yet adoption remains incomplete: 62.7% of repositories still contain at least one Tier-1 non-inclusive identifier, while most remaining terminology resides outside source code in documentation, comments, configuration files, and other software artifacts. We further show that repository size, programming language, project functionality, and ecosystem are stronger predictors of term inclusiveness in LF repositories rather than foundation governance. To examine the implications for AI-assisted software development, we conduct a case study evaluating whether large language models (LLMs) can reconstruct legacy non-inclusive identifiers from surrounding program context. The results show that historical naming decisions remain embedded in model predictions even after identifiers have been renamed. Overall, our study findings provide the first ecosystem-scale assessment of inclusive naming adoption within the Linux Foundation and highlight the importance of addressing terminology residue to support responsible naming and ethically sourced code generation.
arXiv:2607.03481v2 Announce Type: replace
Abstract: Modernizing cancer registries with deep learning is opening new opportunities to automate labor-intensive tasks such as the coding of pathology reports. However, progress is constrained by the scarcity of report-level human-annotated training data. Cancer registries generate substantial volumes of expert-assigned labels as a routine product of their operations, but these exist at the patient level and are not linked to the individual pathology reports that informed them, limiting their direct use for training models. We develop an efficient framework for training deep learning classifiers by leveraging these operationally-generated labels without requiring per-report human annotation, demonstrated for tumor group classification at the BC Cancer Registry. We use Attention-Based Multiple Instance Learning (ABMIL) to recover the lost link between patient-level labels and the reports that informed them, leveraging the attention the model places on each report to distil a large, noisily-labeled corpus into a compact, high-quality per-report training dataset. A classifier fine-tuned on a distilled dataset achieved a macro F1 of 0.83, outperforming established baselines across most tumor groups. By turning routine operational labels into high-quality training data without additional annotation or large-scale computing infrastructure, ABMIL offers a practical and accessible route to automating cancer registry workflows.
arXiv:2607.11060v1 Announce Type: new
Abstract: In mountainous regions where traction loads constitute a significant portion of a long-chain weak power grid (PG) with sustainable energy, the interaction between the traction power supply system and the PG becomes increasingly evident. The integrated power flow calculation (PFC) method and its linearized model are quite important for the PG - traction network (TN) joint planning. However, existing research on the port load characteristics of the EMUs and the connection angle characteristics of traction transformers is insufficient, and there is a lack of effective methods for PFC or linearized PFC in systems that couple the PG with the traction network. To fill this gap, this paper proposes an integrated PFC model for the AT TN - PG coupled system, along with a linearized method. Firstly, according to the relationship of the phases between the PG and the AT traction network, the node admittance matrix of the coupled system has been constructed. Then, the issue of power injection equations being unable to deal with the EMUs port load is resolved by merging the contact line node and the rail node. Subsequently, the integrated PFC equations for the coupling system are established. Next, a hybrid phase linear decoupled power flow model for the coupling system is developed, employing the correspondence between the phases of the PG and the TN, as well as the phase angle differences among various nodes and branches. Numerical simulations conducted in a specific region demonstrate the necessity of an integrated PFC for the coupled system and validate both the accuracy and efficiency of the linearized model.
arXiv:2607.11578v1 Announce Type: new
Abstract: Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less than 10\% of clinical recordings. We present DiffEEG, a 9.6M-parameter self-supervised foundation model that addresses both limitations through denoising diffusion pre-training and reinforcement learning (RL)-based fine-tuning. Pre-trained on 1.3M unlabeled segments from the Temple University Hospital Seizure Corpus (TUHSZ), DiffEEG learns generic neural representations via a 1D U-Net with multi-head self-attention. For downstream adaptation, a reinforced decision layer employs policy gradient optimization to directly maximize F1-score, prioritizing sensitivity to rare seizure events over overall accuracy. Under strict patient-wise evaluation (279 patients, Leave-One-Fold-Out), DiffEEG achieves 61\% accuracy and 59\% F1 for 4-class seizure subtyping, and 81\% accuracy with 85\% weighted F1 for binary detection, maintaining clinically viable seizure recall (59\%) despite extreme imbalance (6.7\% prevalence). Segment-level evaluation establishes an upper bound of 97.6\% accuracy, confirming strong architectural capacity. DiffEEG demonstrates that diffusion-based pre-training combined with metric-aware reinforcement learning enables clinically deployable seizure monitoring with minimal labeled data requirements.
arXiv:2607.11589v1 Announce Type: new
Abstract: The axion is a theoretical particle that could resolve multiple fundamental problems, most notably the strong Charge-conjugation-parity-symmetry (CP) problem in quantum chromodynamics and the nature of dark matter.To date, however, the axion has never been detected in any free-space experiment. In this work, we designed and constructed a laser-based system that generates a three-dimensional, closed trapping potential field with a null central region. Owing to its spindle-like geometry, we term this configuration an optical spindle trap (OST). Along the propagation axis, the photon population evolves in a distinct manner from the left to the right terminus of the trap: it first diminishes and then recovers to its baseline value.This behavior is analogous to the photon axion photon conversion process sought in light shining through wall experiments(LSW)1-3, in which a measured photon deficit would constitute evidence for axion conversion. The photon population was monitored with a single-photon counter (SPC) operated well below its saturation threshold, and the observed behavior was corroborated by charge-coupled device (CCD) imaging at extremely low optical powers, thereby excluding detector artefacts as the origin of the photon deficit.Under the constraint of energy conservation, the missing photons are attributed to conversion into axions that remain undetectable by both the SPC and the CCD. The underlying conversion mechanism is ascribed to spin-coupled axion photon interactions. This tens-of-millimeter-scale optical spindle trap thus provides a viable free-space axion source, generated by a table-top laser, for the study of the strong CP problem and axion-like dark matter candidates.
arXiv:2607.11500v1 Announce Type: new
Abstract: Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization across videos. To amortize this optimization, we propose HyperGS, a feedforward, optimization-free approach that directly predicts Gaussian representations from any video in a single forward pass, speeding up encoding and decoding by orders of magnitude while generalizing to out-of-distribution videos at higher resolutions. In HyperGS, we design a factorized spatiotemporal Transformer to extract tokens from video, and a learnable query-based Transformer to obtain 8-parameter Gaussian representations for each video frame. We find that naively predicting Gaussians across diverse videos induces a needle-like degeneration that collapses training, and address this with a rank-based geometric regularizer whose strength adapts dynamically to stabilize optimization. HyperGS achieves encoding at $10^4$--$10^5\times$ the speed of per-video Gaussian optimization at matched reconstruction quality while generalizing zero-shot to $720p$ video, enabling higher-resolution rendering without re-encoding. HyperGS improves PSNR by +2.9--3.1 dB over the prior video encoders on K400, SSv2, and UCF101 at a smaller video representation size. By predicting explicit 2D Gaussians in a single forward pass, HyperGS combines the fast, flexible rendering of Gaussian Splatting with the speed and generalization of feedforward prediction, advancing Gaussians as a practical direction for fast and generalizable video representation.
arXiv:2607.11508v1 Announce Type: new
Abstract: Causal discovery, the process of recovering underlying causal structures from observational data, is a fundamental pursuit across scientific disciplines. Over the past decades, numerous algorithms have been developed to tackle this challenge through workflows tailored to the specific causal mechanisms underlying each type of dataset, demonstrating effectiveness across a wide range of applications. However, as the volume and heterogeneity of real-world data continue to grow, this dataset-specific approach inevitably leads to a fragmented, test-driven paradigm that struggles to scale to the demands of modern scientific discovery. To address this, we formulate the Causal Discovery Foundation Model (CDFM) as a unified, general-purpose framework for zero-shot structural inference. To ensure reliable generalization across unknown domains, we first investigate the theoretical boundaries of causal identifiability, revealing the indispensable role of causal prior mechanisms in this process. Building on these insights, we formulate a principled variational framework that treats unknown causal mechanisms as latent variables and mathematically decomposes the intractable marginal likelihood into distinct, tractable learning modules. The variational decomposition provides a conceptual design principle for the architecture design of CDFM, while comprehensive causal knowledge guides the large-scale synthesis of our pretraining data. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries. Extensive experiments demonstrate that CDFM consistently outperforms traditional algorithms, driving a paradigm shift toward a general-purpose causal discovery foundation model.
arXiv:2607.11811v1 Announce Type: new
Abstract: Randomised testing is a widely-used approach to software validation, yet its theoretical foundations remain thin. In particular, the fundamental question of what it means for a set of inputs to be \emph{generable} has gone unanswered in both the literature and folklore. We present the first complexity-theoretic foundations for random generators in software testing. We model generators as Turing transducers that consume random bits and produce string-encoded outputs, and show that the theoretically generable languages coincide exactly with the recursively enumerable languages. This has direct implications for testing at the boundaries of decidability, such as compiler testing. For \emph{efficient} generation, we show that the polynomial-time generable languages lie within \textit{NP}, that certain \textit{NP}-complete languages admit efficient generators, and that -- under standard cryptographic assumptions -- there are languages in \textit{P} for which no efficient generator exists: the complexity of efficienct generation and of efficient decision are not the same. We show space-bounded complexity is the natural framework for generators producing \emph{correlated} samples, capturing methodologies such as coverage-guided fuzzing and symbolic execution. Beyond classification, we characterise efficient generability: a language has a polynomial-time generator iff it admits a \emph{certificate scheme} over a verifier -- so witness planting, the folklore technique behind generators to test SAT solvers, is in a sense the only route to efficient generation. On the design of property-based testing libraries, we prove no library can compositionally derive efficient generators from logical predicates involving conjunction or negation, under standard assumptions. However, restricted classes like \textit{NL} (equivalently, linear Datalog predicates) would admit such a compilation.
arXiv:2607.10538v1 Announce Type: new
Abstract: The open-sourcing of powerful image generation models has created a vibrant ecosystem where creators curate and combine a vast array of community-contributed models. This practice stands in sharp contrast to using closed-source tools like Midjourney. Yet, little is known about these emerging creative workflows. To bridge this gap, this paper presents the first large-scale empirical study of creator model usage behavior within this open-source image generation ecosystem. We construct a novel dataset of 6 million images with their embedded generation metadata -- a detailed recipe of the creation process, including the models used and the prompts. By linking the usage of 22.4K base models and 154K LoRA models to the images, our findings underscore the ecosystem's unique strengths and its inherent obstacles. This provides valuable insights for making this ecosystem more sustainable and innovative. Moreover, we make our dataset publicly available, providing creators with practical references for producing better artworks and researchers to facilitate further studies.