arXiv:2602.15341v3 Announce Type: replace
Abstract: We study monotonicity testing of real-valued functions on directed acyclic graphs (DAGs) with $n$ vertices. Let $m$ and $\ell$ be the numbers of edges in the transitive reduction and the transitive closure, respectively. For $1\le c\le d\le2$, define $u(c,d):=\min\left\{\frac12,\frac c3,\frac{c+d}{2}-1\right\}$. We show that every family of DAGs with $m=n^{c+o(1)}$ and $\ell=n^{d+o(1)}$ admits, for every fixed $\varepsilon\in(0,1)$, a non-adaptive tester with one-sided error that uses $O_\varepsilon(n^{u(c,d)+o(1)})$ queries. Conversely, we show that for every sufficiently small fixed $\varepsilon>0$ and every fixed $(c,d)$, there are families of DAGs satisfying $m=n^{c+o(1)}$ and $\ell=n^{d+o(1)}$ on which every randomized non-adaptive tester, even with two-sided error, requires $n^{u(c,d)-o(1)}$ queries, making the upper bound tight up to a factor $n^{o(1)}$. Our main technical contribution is a lower-bound technique based on Ruzsa--Szemer\'edi families of positive matchings.
Science Journals
arXiv:2511.01492v3 Announce Type: replace
Abstract: In uncertainty quantification for parametric partial differential equations (PDEs), it is common to model uncertain random field inputs using countably infinite sequences of independent and identically distributed random variables. The lognormal random field is a prime example of such a model. While there have been many studies assessing the error in the PDE response that occurs when an infinite-dimensional random field input is replaced with a finite-dimensional random field, there do not seem to be any analyses in the existing literature discussing the sharpness of these bounds. This work seeks to remedy the situation. Specifically, we investigate two model problems where the existing dimension truncation error rates can be shown to be sharp.
arXiv:2607.14288v1 Announce Type: new
Abstract: We study majority correctness when voting is preceded by sustained social interaction on a social network. Motivated by the Condorcet Jury Theorem, we consider a binary choice with an objectively correct alternative, where uninformed voters revise their vote intentions through repeated interaction in the presence of competing committed leaders (zealots). In this zealot--contrarian voter model, voters may either imitate or oppose the views they encounter. For fully mixed electorates, we characterize the long-run distribution of votes and the correlation structure induced among voters, and we show that Erd\H{o}s--R\'enyi networks exhibit the same majority-correctness behavior after an appropriate rescaling of leader influence. Building on these results, we establish a finite-electorate Condorcet-type guarantee: when post-deliberation individual correctness exceeds random choice, a strict majority is more likely to select the correct alternative than a randomly chosen voter. At the same time, we identify an aggregation failure: social interaction can reduce majority accuracy relative to a no-deliberation benchmark in which voters respond only to zealots. As the electorate size tends to infinity, this finite-electorate advantage disappears unless social updating is purely conformist, revealing a tipping point at full conformity: any persistent contrarian updating drives both individual and majority correctness to the random choice level of one half. Simulations on scale-free, ring, and small-world networks further show that topology matters because it shapes the vote correlations generated by social influence: hub-dominated structures generate stronger positive correlations and lower majority accuracy, whereas spatially structured networks generate weaker correlations, preserve a larger effective number of independent judgments, and improve majority accuracy.
arXiv:2607.14325v1 Announce Type: new
Abstract: Two-sided type systems, introduced in POPL'24, are an extension of the traditional notion of type system that allows for stating and deriving typing judgements in which (a) assumptions can be made about the types of arbitrary terms and not only variables, and (b) conclusions can be made about any number of type assignments, and not exactly one. In this work, we investigate the logical foundations of two-sided type systems in the sense of the propositions-as-types paradigm. We introduce new two-sided type systems 2$\lambda$Int and 2$\lambda$Int$^{\sim}$ that correspond with Wansing's bilateral logic 2Int and its extension with Nelson's strong negation respectively. Going beyond the propositional case, we introduce 2$\lambda$HOL as an extension of Guevers' $\lambda$HOL, and we show its expressive adequacy, its consistency and that it satisfies both the existence property and its dual.
arXiv:2607.15138v1 Announce Type: new
Abstract: A method is presented for the translation of acoustic field data from a source to a target region. Field data are represented as spherical harmonic expansions on spheres surrounding the source and target regions respectively and expansions are translated using a ``point and shoot'' method using the Kirchhoff-Helmholtz integral to carry out an axial translation from one sphere to the other. The principal motivation for the method is its use in a time-domain Fast Multipole Method, and test cases reflective of this application are presented. The method converges to six digits for appropriate values of parameters and computational effort scales approximately as $N^{2}$ where $N$ is the order of spherical harmonic expansion for the field data.
arXiv:2606.17288v2 Announce Type: replace
Abstract: Perfect resource placements in dense Eisenstein--Jacobi (EJ) networks partition the network into hexagonal radius-$t$ service cells. This paper studies local repair of such placements after resource failures. For one failed resource, we prove that one replacement cannot cover the failed hexagon and two always suffice, giving $\rho_{\mathrm{EJ}}(t)=2$ for all $t\ge1$. Among minimum-size repairs, the sharp minimum-overlap formula $\Omega_{\mathrm{EJ}}(t)=t^2$ follows from the three-strip geometry of EJ balls. For two failed resources, independent repair gives a four-replacement upper bound, but unlike the Gaussian case EJ repair is not always additive: two infinite neighboring displacement families admit three-replacement repairs, proved optimal by a two-ball impossibility argument. Additive behavior is established algebraically via endpoint-rigidity and diagonal-corridor theorems. For $q$ failed resources, independent canonical repair gives a universal $2q$ upper bound, exact when failed cells are pairwise more than $4t$ apart. Dense cluster subadditivity is proved for infinite four-fault and six-fault families with exact repair numbers four and five, giving savings of four and seven over independent repair. An exact inclusion--exclusion identity governs repeated coverage for arbitrary multi-fault repairs. An audit over 19,400 instances confirms widespread subadditivity. EJ local repair is structurally distinct from the Gaussian case: the one-fault overlap is quadratic, two-fault repair can be non-additive, and clustered repairs reuse replacement balls across multiple failed cells.
arXiv:2606.17386v2 Announce Type: replace
Abstract: End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all stages: collecting and labeling millions of driving frames is costly, and closed-loop RL on images is bottlenecked by the per-step cost of photorealistic rendering plus a forward pass through a large vision backbone. Self-play in vectorized simulators changes the economics: millions of rollout steps per second, and a state distribution naturally rich in collisions, near-misses, and recoveries that no driving log contains. Our approach exploits this asymmetry by decoupling learning to drive from learning to see. We pretrain a single policy by self-play, then align its latent space with a pretrained vision backbone, through the action KL divergence and a batch-relational low-rank structural loss. The action target comes from the self-play policy, so alignment never supervises against a logged trajectory: a paired dataset of (image, scene-state) frames suffices, with no need for the curated expert demonstrations that imitation pretraining is built on. On photorealistic 3D Gaussian splatting closed-loop scenarios, the resulting end-to-end policy matches or exceeds prior end-to-end methods.
arXiv:2606.19729v2 Announce Type: replace
Abstract: Planning under uncertainty is an essential capability for autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framework for such a capability. Although POMDP-based planning has advanced significantly, its application to real-world problems is often limited by the difficulty of obtaining faithful POMDP models. We present Vectorized Online planning wIth Learned diffusion model for POMDP Agents (VOiLA), a framework that learns task-agnostic POMDP models for online planning under uncertainty. VOiLA learns transition and observation samplers using conditional diffusion models and learns observation-likelihood models for particle-based belief updates. To enable efficient online planning, the diffusion samplers are distilled into compact feedforward generators and integrated with Vectorized Online POMDP Planner (VOPP), an online POMDP planner designed to leverage GPU parallelization. Experimental results indicate the distillation strategy reduces sampling cost by up to nearly three orders of magnitude, making learned generative POMDP models practical for online planning. Evaluation of VOiLA on three benchmark problems indicate that VOiLA achieves equal or better performance than Recurrent Soft Actor Critic while using less than 10% training data, and generalizes much better to unseen environment configurations. Physical robot evaluation indicates VOiLA uses the models learned using only simulated data and generates a policy that successfully accomplish the task in 10 of 10 runs.
arXiv:2606.19817v2 Announce Type: replace
Abstract: Synthetic images are increasingly used to augment scarce real data for object detection. However, not all synthetic sets help equally, and the only way to know a set's value is to train a detector on it, which is slow and demands dense annotation. We ask whether a training-free metric can instead rank candidate synthetic training sets by their downstream utility. Existing image-set metrics such as FID, KID, and MMD compare two feature distributions with a single global statistic, which we show is mis-specified for detection-data selection in two ways: it is blind to per-image composition (object count, box scale, class mix), and even at fixed composition its global averaging washes out the appearance differences that separate high-mAP pools from low-mAP ones. We propose Conditional-Composition Domain Match (CCDM), which converts any feature-space distance into a composition-stratified comparison, matching candidate and target within metadata-defined strata without training a detector. On COCO and VisDrone-DET, the best CCDM variant ranks 19 candidate training sets in strong agreement with YOLOv8 mAP (Spearman \r{ho} = 0.97 and 0.96), outperforming FID, KID, and MMD. Furthermore, CCDM holds when reference metadata comes from detector pseudo-labels rather than ground-truth boxes.
arXiv:2607.14394v1 Announce Type: new
Abstract: Fourier Neural Operators (FNOs) learn solution operators for partial differential equations and offer orders of magnitude speedup over traditional numerical solvers at inference time, which makes them attractive surrogates for high-resolution computational physics. Scaling FNOs to high-resolution spatial grids requires distributing the data across GPUs, but the distributed FFT at the core of each spectral layer requires multiple dense all-to-all collectives that communicate the full spatial tensor, only for most coefficients to be discarded immediately. We introduce the Distributed Truncated Spectral Transform (DTST), which reverses this order. Each GPU computes only a small subset of frequency modes used by the spectral convolution locally via a partial DFT, and two collectives combine the results with a payload that depends only on this mode count, not the spatial resolution. DTST produces spectral coefficients identical to the standard distributed FFT with truncation, while providing both spatial data parallelism and spectral weight model parallelism. We present DRIFT, a GPU implementation of DTST for distributed Fourier Neural Operators, using separable per-dimension basis matrices and efficient GPU-to-GPU communication. On a 3D+time FNO across 4--32 GPUs, on up to 8 nodes (4 GPUs/node), DRIFT achieves a forward-pass speedup of 38--64$\times$ and a 37$\times$ training speedup over the distributed FNO baseline, reducing communication time from 97\% to under 6\% of the forward-pass time, with growing speedups at higher resolution.
arXiv:2607.14504v1 Announce Type: new
Abstract: Physical reservoir computing has traditionally exploited the dynamics of physical systems for computation, enabling tasks such as inference, classification, and prediction. Here, we introduce a fundamentally different paradigm for exploiting physical reservoirs, termed "reservoir signal acquisition" (RSA), in which a physical reservoir serves as a dynamical measurement device rather than a computational engine. In RSA, the reservoir transforms an unknown broadband waveform into a diverse set of measurements, enabling waveform reconstruction from low-rate samples beyond the Nyquist limit of any individual acquisition channel. We show that exact reconstruction of arbitrary broadband signals is achieved when the number of measurement channels satisfies $M \geq N_R$, where $N_R$ is the undersampling ratio. Moreover, spectrally or temporally sparse signals can be recovered even when $M \ll N_R$, demonstrating a compressed-sensing capability that naturally emerges from the diversity of reservoir dynamics. We experimentally validate RSA using a silicon photonic reservoir circuit. With a data-driven calibration requiring no physical model of the device, we reconstruct radio-frequency signals up to 12.5 GHz using only low-rate analog-to-digital converters (ADCs), corresponding to four times the Nyquist frequency of each ADC. These results establish RSA as a new signal acquisition paradigm based on physical reservoirs, extending their role from computation to sub-Nyquist acquisition of broadband waveforms.
arXiv:2604.09091v2 Announce Type: replace
Abstract: The use of synthetic data in machine learning applications and research offers many benefits, including performance improvements through data augmentation and privacy preservation of original samples. This work proposes an efficient synthetic data generation method based on a fully connected neural network that transforms a high-dimensional random Gaussian distribution to approximate a target real-world dataset. The proposed solution combines data preprocessing designed for tabular data with distribution modeling and PCA dimensionality reduction to further enhance data privacy. The work also defines two dedicated randomized loss functions based on Wasserstein distance combined with feature Covariance and a randomized pairwise error reduction loss function. The experiments conducted on 25 diverse tabular real-world datasets confirm that the proposed solution obtains similarity and privacy scores relative to the state-of-the-art generative methods and achieves reference MMD scores orders of magnitude faster than modern deep learning solutions. The experiments involved analyzing distributional similarity, privacy protection, and the utility of synthetic data in classification tasks.
arXiv:2604.09567v2 Announce Type: replace
Abstract: Knowledge representation formalisms are aimed to represent general conceptual information and are typically used in the construction of the knowledge base of reasoning agent. A knowledge base can be thought of as representing the beliefs of such an agent. Like a child, a strong-AI (AGI) robot would have to learn through input and experiences, constantly progressing and advancing its abilities over time. Both with statistical AI generated by neural networks we need also the concept of \textsl{causality} of events traduced into directionality of logic entailments and deductions in order to give to robots the emulation of human intelligence. Moreover, by using the axioms we can guarantee the \textsl{controlled security} about robot's actions based on logic inferences.
For AGI robots we consider the 4-valued Belnap's bilattice of truth-values with knowledge ordering as well, where the value "unknown" is the bottom value, the sentences with this value are indeed unknown facts, that is, the missed knowledge in the AGI robots. Thus, these unknown facts are not part of the robot's knowledge database, and by learn through input and experiences, the robot's knowledge would be naturally expanded over time.
Consequently, this phenomena can be represented by the Closed Knowledge Assumption and Logic Inference provided by this paper.
Moreover, the truth-value "inconsistent", which is the top value in the knowledge ordering of Belnap's bilattice, is necessary for strong-AI robots to be able to support such inconsistent information and paradoxes, like Liar paradox, during deduction processes.
arXiv:2607.15048v1 Announce Type: new
Abstract: Road surface mapping plays a crucial role in autonomous driving, supporting high-definition map generation, lane-level perception, and automatic road annotation. Recent mesh-based road surface reconstruction methods have shown promising results, but they still suffer from limited reconstruction quality and high optimization cost, especially in large-scale driving scenarios. To address these limitations, we propose ROADGS-T, a robust and efficient large-scale road surface mapping framework based on adaptive meshgrid Gaussian representation. Specifically, we model the road surface by placing 2D Gaussian surfels on a meshgrid, where each surfel explicitly stores color, semantic, and geometric information. Compared with conventional mesh-based representations and 3D Gaussian primitives, the proposed meshgrid Gaussian representation better matches the thin-surface property of roads while significantly reducing redundant primitives and overlap during optimization. To further improve representation efficiency and structural fidelity, we introduce a road-structure-aware adaptive meshgrid strategy, which allocates denser Gaussian surfels to geometrically or semantically complex regions, such as lane markings, road boundaries, and height discontinuities, while maintaining a compact representation in flat road areas. Moreover, instead of relying on a single nearest vehicle pose, we design a trajectory-consistency-guided pose-robust refinement strategy, which estimates local surface priors from multiple neighboring poses and adaptively weights pose-guided height regularization according to their geometric consistency.
SCITUS: A Multi-Jurisdictional Framework for Adapting NIST AI RMF to the Canadian Regulatory Context
arXiv:2607.15051v1 Announce Type: new
Abstract: Canadian organizations deploying artificial intelligence systems face a fragmented regulatory landscape spanning federal requirements (the Treasury Board Directive on Automated Decision-Making) and divergent provincial regulations across Ontario, Quebec, Alberta, Manitoba, and British Columbia. The death of Bill C-27 (Artificial Intelligence and Data Act) in January 2025 - and the federal government's June 2026 confirmation that it will pursue targeted instruments rather than omnibus AI legislation - leaves organizations without unified compliance guidance. Global frameworks such as NIST AI RMF 1.0, the EU AI Act, and ISO/IEC 42001 provide valuable guidance but lack systematic methodologies for adaptation to multi-jurisdictional national contexts. We present SCITUS (Systematic Canadian Integration for Trustworthy and Unified Standards), a comprehensive framework adapting NIST AI RMF 1.0 to Canadian federal and provincial AI regulations simultaneously. SCITUS integrates seven trustworthy-AI characteristics enhanced for Canadian requirements, four core governance functions, a novel multi-jurisdictional compliance mapping methodology, and a versioned control catalog that has evolved from 31 controls (v1.0, June 2025) to 57 controls (v2.0, July 2026) in response to regulatory developments - including Canada's first regulatory findings on generative-AI training data - and the documented 2026 agentic-AI threat landscape. We demonstrate applicability through scenarios spanning federal government, provincial healthcare, and the private sector, and argue that systematic adaptation of NIST AI RMF to multi-jurisdictional requirements offers significant advantages over jurisdiction-by-jurisdiction compliance and provides a replicable model for other federal systems.
arXiv:2607.14499v1 Announce Type: new
Abstract: Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a framework that recasts evaluation as a three-party interaction between an evaluatee model, an automated examiner, and a grader. The examiner conducts multi-turn, semi-structured conversation guided by a graph-based representation of the task. By navigating state-space transitions, CEDI deploys diverse strategies, from clarification requests to adversarial probes, to elicit performance evidence. We apply CEDI to visual hallucinations. Empirical results across multiple models, diverse settings, datasets, and domains show that contextualized, interactive evaluations reveal not only significantly more hallucinations than conventional static evaluation but also ones that more closely resemble those arising in practical use cases. We further show that hallucinations often accumulate over long contexts, through self-reinforcing dialogue history, and models are particularly vulnerable to questions requiring premise rejection or refusal. Together, these findings highlight CEDI as a step toward realistic, systematic, and ecologically valid assessments of MLLMs' capabilities. Code is available at github.com/williamium3000/cedi.
arXiv:2607.14513v1 Announce Type: new
Abstract: Techniques for modeling 3D scenes from image collections, such as 3D Gaussian Splatting (3DGS), are capable of generating high-quality novel views by leveraging graphics primitives with view-dependent appearance. In 3DGS, spherical harmonic (SH) are employed to model view-dependent color, resulting in a large number of SH coefficients per primitive and large memory requirements. While compression approaches have been proposed to mitigate this problem, they do not exploit the capabilities of modern Graphics Processing Units (GPUs) for parallel decoding and rendering. In this paper, we propose a method for compressing SH color coefficients using texture compression schemes specifically designed for efficient parallel GPU decoding and supported by dedicated hardware acceleration. It is shown that those methods can compress color coefficients more effectively than 2D textures by exploiting the fact that primitives can be locally grouped and reordered according to color. Furthermore, we introduce a bit-rate control strategy that preserves random access, enabling large-scale parallelization without compromising rendering performance. Experimental results using BC1 and BC7 texture compression formats show that GPU-based decompression can be achieved with negligible or imperceptible degradation in the visual quality of rendered 3DGS scenes.
arXiv:2606.21005v2 Announce Type: replace
Abstract: Scientific discovery workflows often depend on structured curation from the literature. This is difficult for current agents because the key evidence is scattered across long text, dense tables, and figures, and the final records often require reasoning across multiple evidence fragments rather than copying a single span. We study scientific curation from multimodal sources and introduce Beaver, an agent harness that extracts structured information from scientific papers while preserving provenance to the supporting evidence. Beaver combines a frontier agent with multimodal evidence tooling, task scaffolding, and artifact-grounded autoresearch. These components turn curation into a staged, auditable workflow and enable an iterative evaluate--diagnose--revise loop, where persistent run artifacts expose stage-localized failures and guide harness updates. Experiments show that Beaver reaches 81.0 on Gold-Referenced Attribute Score (GRAS), an attribute-level measure of agreement with gold curated records, outperforming frontier agents by over 23 absolute points. Ablations show that task scaffolding, multimodal evidence tooling, and provenance traces each contribute meaningfully to performance, while attribute-level analysis shows the largest gains on high-value attributes that require cross-modal reasoning and normalization. These results show that, for scientific curation from papers with multimodal evidence, harness design is a central determinant of agent performance.
arXiv:2606.22030v2 Announce Type: replace
Abstract: We investigate when belief-based memory actually improves large language model (LLM) agents. Our vehicle is Nous, a long-term memory architecture that represents each entity-attribute pair as a categorical probability distribution updated through closed-form Bayesian inference, with information-theoretic surprise driving belief revision and entropy-based forgetting. A controlled ablation on the LoCoMo benchmark shows that Bayesian belief updating alone provides little benefit over naive last-write-wins because existing conversational memory benchmarks rarely contain contradictory or differently reliable evidence. We then introduce reliability-conditioned updating, estimating per-observation reliability from epistemic language, and show on a controlled contradiction benchmark that belief updating substantially outperforms last-write-wins and raw-memory retrieval when observations differ in trustworthiness. Because content-derived reliability is itself vulnerable to manipulation, we further propose provenance-capped belief updating, where trust is bounded by source provenance rather than textual confidence. Under controlled memory-poisoning experiments, this approach resists volumetric poisoning attacks while revealing the utility costs and implementation requirements of provenance-aware memory. Finally, we quantify a 27.5-point discrepancy between strict token-F1 and LLM-as-judge evaluation on identical outputs, highlighting important reproducibility concerns for long-term memory benchmarks. Our results suggest that probabilistic belief-based memory is most beneficial in environments requiring reasoning over conflicting and differently trustworthy evidence, rather than conventional conversational recall alone.
arXiv:2606.23040v2 Announce Type: replace
Abstract: Inductive proofs can be represented by proof schemata, a formalism that represents infinite sequences of proofs by recursive definitions. Since proof schemata avoid the explicit application of induction rules, they admit novel applications, one of which is the realization of Herbrand's theorem in the presence of induction. In this paper, we develop a new type of proof schema based on point transition systems. For skolemized proof schemata without quantified cuts, so-called Herbrand systems, that is, schemata of Herbrand instances of quantified formulas, can be computed. Herbrand systems also allow the representation of schemata of Herbrand sequents, thereby realizing Herbrand's theorem for proof schemata. We compare proof schemata with cyclic proofs and define a transformation from a large class of cyclic proofs to proof schemata. Finally, we show that proof schemata based on point transition systems are capable of proving the 2-Hydra statement, a well-known example that is provable by the cyclic proof system CLKID\omega but not in LKID.
arXiv:2606.25286v3 Announce Type: replace
Abstract: When institutions decide by consensus, the official record shows agreement but hides who shaped what was decided. We introduce a way to recover that hidden structure from the one trace consensus cannot suppress: the documentary record of what actors choose to work on. Adapting tools from economic complexity, we map a ``space of concerns'' in which issues lie close when the same actors repeatedly specialize in both -- turning a flat agenda into a measurable topology of attention. Across six decades of the Antarctic Treaty (6,591 documents, 66 actors), engagement is structured, local, and persistent, and the most specialized actors produce binding law at roughly five times the baseline rate. The approach generalizes to any document-rich consensus forum, showing that unanimity does not erase political structure -- it relocates it upstream, into the organization of attention.
arXiv:2606.27238v2 Announce Type: replace
Abstract: Production of useful chemicals using photoelectrochemical biohybrid devices offers an environmentally friendly alternative to existing energetically demanding processes. These devices exploit light-driven charge separation, e.g. by a photosystem, and require efficient electron transfer to a tailored redox enzyme cascade. Here we demonstrate that electron transfer efficiency can be increased by confining the photosystem with the redox protein inside a self-assembling, virus-based nanocontainer. The photosynthetic system from the phototrophic bacterium Cereibacter sphaeroides and cytochrome c were conjugated to a bacteriophage P22 scaffolding protein and co-incorporated into the 50 nm diameter virus shell in vitro. The porous shell confined the macromolecular components for efficient electron transfer while allowing free exchange of small electron mediators. Sustainable and accelerated light-driven electron transfer between the encapsulated components was confirmed by optical spectroscopy. This self-assembly system presents a versatile platform for developing nanoreactors that combine photosystems with complex redox pathways.
arXiv:2607.14522v1 Announce Type: new
Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develop a complete continuous-time RL framework for fine-tuning score-based discrete diffusion models. The proposed framework enables reward-driven optimization without requiring differentiability on the reward signals. In contrast to the existing GRPO-based approaches that only rely on terminal rewards, our formulation allows intermediate reward or advantage signals to be incorporated throughout the denoising trajectory. Importantly, when specialized to masked diffusion models (MDMs), our framework encompasses a rich class of policy parameterizations over the vocabulary simplex with analytically tractable probability ratios, providing a unified perspective on exploration and policy optimization in MDMs. For masked diffusion large language models (dLLMs), we further propose trajectory subsampling techniques to efficiently estimate computationally prohibitive trajectory likelihoods, reducing the computational cost of computing per-position probability ratios. We showcase the effectiveness of our methods on both low-dimensional entropy-regularized optimization problems and RL post-training of dLLMs on mathematical reasoning and coding tasks.
arXiv:2607.14534v1 Announce Type: new
Abstract: Industrial anomaly detection aims to identify and localize defective regions without relying on exhaustive annotations of all possible defect types. Although recent unsupervised methods have achieved strong performance, most are primarily designed for single-class settings and often struggle in multi-class scenarios, where diverse normal patterns may lead to over-generalization and reduce the discriminative capability between normal and anomalous regions. In this paper, we propose SwinAD, a reconstruction-based framework for multi-class unsupervised anomaly detection that leverages a frozen pretrained Swin Transformer V2 encoder and a feature diversity-preserving reconstruction decoder. The hierarchical encoder provides semantically rich multi-scale features, while stage-wise bottleneck modules with dropout prevent trivial identity mapping and encourage robust reconstruction of normal patterns. To further improve localization, we introduce a feature diversity-preserving reconstruction framework that maintains complementary reconstruction hypotheses instead of relying on a single decoding branch. The discrepancies between encoder features and the two reconstructed features are then aggregated across multiple scales to produce the final anomaly map. Experiments conducted on three industrial anomaly detection benchmarks, including MVTec AD, VisA, and Real-IAD, demonstrate that SwinAD achieves competitive image-level performance and strong pixel-level localization accuracy, with particularly notable improvements in pixel-level AP and 1 on MVTec AD. These results indicate that combining hierarchical Swin features with diverse multi-scale reconstruction substantially improve pixel-level localization in multi-class unsupervised anomaly setting.
arXiv:2603.20785v2 Announce Type: replace
Abstract: Reasoning-induced vision-language models (VLMs) advance image quality assessment (IQA) with textual reasoning, yet their scalar scores often lack sensitivity and collapse to a few values, so-called discrete collapse. We introduce ME-IQA, a plug-and-play, test-time memory-enhanced re-ranking framework. It (i) builds a memory bank and retrieves semantically and perceptually aligned neighbors using reasoning summaries, (ii) reframes the VLM as a probabilistic comparator to obtain pairwise preference probabilities and fuse this ordinal evidence with the initial score under Thurstone's Case V model, and (iii) performs gated reflection and consolidates memory to improve future decisions. This yields denser, distortion-sensitive predictions and mitigates discrete collapse. Experiments across multiple IQA benchmarks show consistent gains over strong reasoning-induced VLM baselines, existing non-reasoning IQA methods, and test-time scaling alternatives.