arXiv:2602.22845v2 Announce Type: replace
Abstract: Measuring the phase of light is fundamental to optical imaging, sensing, and signal processing applications. Conventional optical phase measurements rely on multipath configurations, bulky interferometric setups, and computationally intensive data pipelines, limiting scalability, robustness, and practicality. We introduce a technique that allows for reference-free in-line phase retrieval of abrupt phase transitions in optical pulses directly from spectral measurements. Theory, simulations, and experiments concurrently explain the effect as a result of a Kerr-mediated interference between a projected linear wave component and the high-intensity residual of the phase-altered pulse. Utilizing this phenomenon, we demonstrate algorithm-free phase measurements of up to {\pi}/385 sensitivity and shot-to-shot signal prominence at 13 dB above noise at 80 MHz rates and 50 pJ pulse energies. This approach offers new paths toward the use of femtosecond pulses as broadband data carriers for optical communications, information processing, and direct high-throughput phase imaging.
Science Journals
arXiv:2606.05974v1 Announce Type: cross
Abstract: Since the initial disclosure of the extraordinary piezoelectric coefficients of Potassium sodium niobate (KNN) in near-equimolar bulk ceramics, its development trajectory has resembled a rollercoaster, with its integration into microelectronics severely lagging due to thermodynamic stability issues and poor planar process compatibility. In this work, we revisit the bulk-derived phase diagram for the specific case of thin films integrated on silicon. By systematically investigating Mn-doped K1-xNaxNbO3 films grown on 8-inch wafers, we demonstrate that the optimal stoichiometry for thin films fundamentally diverges from the bulk equimolar standard. A Na-rich composition (> 70 at.%) is required to overcome substrate-induced constraints, effectively suppressing pyrochlore formation and chemical phase segregation while promoting dense columnar growth with a complete (001) out-of-plane polar orientation. Consequently, Na-rich films deliver outstanding functional properties, reaching remanent polarizations up to 14 uC cm-2, with piezoelectric coefficients of d33f= 79 pm/V and e31f = 10 C/m2. Supported by Density Functional Theory simulations, we correlate this enhancement with improved stability and a strain-driven structural reorientation toward a lower-symmetry monoclinic phase with tilted polarization. By redefining the phase engineering rules for wafer-scale thin films, our results establish a clear route toward KNN integration in microsystems.
arXiv:2508.19006v2 Announce Type: replace-cross
Abstract: This study investigates the pre-trained RNN attention models with the mainstream attention mechanisms, such as additive attention, Luong's three attentions, global self-attention and sliding window sparse attention, for the empirical asset pricing research on the top 420 large-cap US stocks. This is the first paper on the large-scale state-of-the-art (SOTA) attention mechanisms applied in the asset pricing context. They overcome the limitations of the traditional machine learning-based asset pricing, such as mis-capturing the temporal dependency and short memory. Moreover, the enforced causal masks in the attention mechanisms address the future data leaking issue ignored by the more advanced attention-based models, such as the classic Transformer. The proposed attention models also consider the temporal sparsity characteristic of asset pricing data and mitigate potential overfitting issues by deploying the simplified model structures. This provides some insights for future empirical economic research. All models are examined in three periods, which cover pre-COVID-19, COVID-19 and one year post-COVID-19, for testing the stability of these models under extreme market conditions. The study finds that in value-weighted portfolio back testing, the global self-attention model and the sliding window sparse attention model exhibit excellent capabilities in deriving the absolute returns and hedging downside risks, while they achieve an annualized Sortino ratio of 2.0 and 1.80 respectively in the period with COVID-19 in the static transaction cost scenario. Moreover, the sliding window sparse attention model performs more stably than the global self-attention model from the perspective of absolute portfolio returns with respect to the size of stocks' market capitalization.
arXiv:2506.03232v2 Announce Type: replace-cross
Abstract: Spreadsheet tools are widely accessible to and commonly used by K-12 students and teachers. While spreadsheets are not ideal for many types of statistical analysis, they have an important role in data collection and organization. From a pedagogical standpoint, spreadsheets make data visible and easy to interact with, facilitating student engagement in data exploration, analysis, and computation. Though not suitable for all tasks, spreadsheets can facilitate learning and practicing data and computing skills for K-12 students. This paper 1) demonstrates the potential utility of spreadsheets in K-12; 2) reviews prior frameworks and standards that are relevant for K-12 data tools; and 3) proposes data-driven data skills to help develop data acumen and computational fluency. We provide some example activities, identify challenges and barriers to adoption, suggest pedagogical approaches to ease the learning curve for instructors and students, and discuss the need for professional development to facilitate deeper use of spreadsheets for data science and STEM disciplines.
arXiv:2604.00555v5 Announce Type: replace
Abstract: Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level. We present a neurosymbolic architecture implemented within the Foundation AgenticOS (FAOS) platform that addresses these limitations through ontology-constrained neural reasoning. We introduce a three-layer ontological framework--Role, Domain, and Interaction ontologies--grounding LLM-based enterprise agents. We formalize asymmetric neurosymbolic coupling: current enterprise systems constrain agent inputs (context assembly, tool discovery, governance thresholds) but not outputs, and we propose mechanisms extending this coupling to output-side validation (response checking, reasoning verification, compliance enforcement). A controlled experiment (1,800 runs across five industries and three LLMs: Claude Sonnet 4, Qwen 2.5 72B, Gemma 4 26B) finds ontology-coupled agents significantly outperform ungrounded agents on Metric Accuracy (p < .001) and Role Consistency (p < .001) across all three models with large effect sizes (Kendall's W = .46-.64). Improvements are greatest where LLM parametric knowledge is weakest--particularly in Vietnam-localized domains, where ontology lift is 2x that of English domains. Contributions: (1) a formal three-layer enterprise ontology model; (2) a taxonomy of neurosymbolic coupling patterns; (3) ontology-constrained tool discovery via SQL-pushdown scoring; (4) a proposed framework for output-side ontological validation; (5) empirical evidence for the inverse parametric knowledge effect--ontological grounding value is inversely proportional to LLM training-data coverage of the domain; (6) cross-model replication establishing model-independence; (7) a production system serving 22 industry verticals with 650+ agents.
arXiv:2606.06262v1 Announce Type: new
Abstract: Climate change and extreme weather are increasing the vulnerability of power systems globally, particularly in emerging economies such as Indonesia. Yet, existing studies often assess these impacts in isolation, focusing on individual components or specific hazards, leaving system-level implications under-examined. To address this gap, we develop an integrated, spatially explicit approach to assess an energy system's climate-related vulnerabilities and their impacts, and apply the approach to Indonesia. We quantify climate-based vulnerabilities in generation and transmission infrastructure as well as in demand by distinguishing stressors (temperature rise) and shocks (disruptive hazards due to sea-level rise, flooding, and landslides). Through geospatial data analysis, derating models, and regression analysis, we examine existing and planned assets and demand under historical and future climate conditions. Results indicate that both existing and planned generation are likely to experience stress, which implies a reduction in usable capacity, even as electricity demand increases due to temperature rise, and transmission assets face potential disruption from climate change-induced shocks. Together, these effects erode reserve margins by up to 36 percentage points under the 10-year plan, indicating a substantial reduction in system resilience. The largest system, Jawa-Madura-Bali, experiences a 20.8 percentage point decline, leaving a remaining margin of 26.5%, below the 10-year planning threshold. Importantly, the findings suggest that a growing share of future capacity expansion may be absorbed by climate-induced losses, implying that adaptation-related investments may increasingly be required simply to maintain existing supply levels rather than meet future requirements. We conclude that there is an urgent need to embed climate considerations more explicitly into power sector planning.
arXiv:2606.06254v1 Announce Type: new
Abstract: Large code language models (CodeLLMs) can generate and rewrite programs, enabling functionality-preserving code mutation that may be used to create diverse malware variants and evade signature-based detection. A key security question is whether this mutation capability survives model compression, which would make deployment feasible under limited hardware budgets. We propose SecRL-Prune, a structured pruning framework for CodeLLMs that operates on feed-forward (MLP/FFN) channels. Starting from a pretrained teacher, it learns a layer-wise pruning policy with reinforcement learning using a teacher-student KL-divergence reward. To improve efficiency, we cache the teacher's top-P predictions once and compare the pruned student against this compact target, avoiding simultaneous teacher-student residency in GPU memory. We evaluate SecRL-Prune on HumanEval using pass@k for execution correctness and var@k for code diversity across three 7B CodeLLMs at 10-30% compression. SecRL-Prune consistently preserves higher pass@k and var@k than recent structured pruning baselines under aggressive pruning. In a case study on real malware samples, semantics-preserving mutations from 20%-pruned models substantially reduced detections. These results show that code mutation capability can survive significant structured pruning, highlighting the security relevance of compressed CodeLLMs.
arXiv:2606.06252v1 Announce Type: new
Abstract: Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations to reduce token overhead and avoid a discrete communication bottleneck. However, this shift also removes a key advantage of textual reasoning: intermediate states are no longer inspectable, making it difficult to determine whether a latent state still preserves the constraints of the original query. As a result, latent reasoning typically operates in an open loop, where a latent state is produced and consumed without an input-anchored fidelity check. We propose ReLAT (Reconstruction-Guided Latent Reasoning At Test Time), a self-supervised test-time training method that closes this loop using the query itself as the reference. Our key observation is that if a latent state faithfully represents a query, the query should be recoverable from it; if the query cannot be recovered, the latent state has lost task-relevant information. ReLAT operationalizes this principle by constructing a differentiable Question -> Latent Thought -> Question cycle and optimizing query reconstruction loss through the latent thought before answer generation. This anchors opaque latent computation to the problem specification it is supposed to represent. Across mathematical reasoning, knowledge QA, and code generation benchmarks on the Qwen family, ReLAT consistently improves over single-model inference, text-based collaboration, open-loop latent collaboration, and alternative test-time training objectives. On Qwen3-8B, ReLAT raises AIME 2024 accuracy from 56.7% to 73.3%, a 16.6-point gain over the strongest open-loop latent baseline.
arXiv:2604.15596v4 Announce Type: replace
Abstract: Algorithmic predictions are increasingly used to inform the allocation of scarce resources. The promise of these methods is that, through machine learning, they can better identify the people who would benefit most from interventions. Recently, however, several works have called this assumption into question by demonstrating the existence of settings where simple, unit-level allocation strategies can meet or even exceed the performance of those based on individual-level targeting. Separately, other works have objected to individual-level targeting on privacy grounds, leading to an unusual situation where a single solution, unit-level targeting, is recommended for reasons of both privacy and utility. Motivated by the desire to fully understand the interplay of privacy and targeting levels, we initiate the study of aid allocation systems that satisfy differential privacy, synthesizing existing works on private optimization with the economic models of aid allocation used in the non-private literature. To this end, we investigate private variants of both individual and unit-level allocation strategies in both stochastic and distribution-free settings under a range of constraints on data availability. Through this analysis, we provide clean, interpretable bounds characterizing the tradeoffs between privacy, efficiency, and targeting precision in allocation.
arXiv:2606.06188v1 Announce Type: new
Abstract: Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reasoning dynamics remains underexplored. We bridge this gap by demonstrating that the l2 norm of hidden states serves as an endogenous signal of the model's reasoning intensity. Using Sparse Autoencoders (SAEs) as a diagnostic probe, we observe that LLMs' internal reasoning is marked by a sharp increase in reasoning feature activations concentrated in late layers. Motivated by this pattern, we establish a formal link between reasoning intensity and the model's latent geometry and theoretically prove that the l2 norm of hidden states bounds the activation strength of SAE reasoning features. Empirical correlation analysis and causal interventions further validate the l2 norm as a faithful indicator, where heightened norms consistently correspond to critical reasoning steps. We then introduce three test-time scaling techniques guided by l2 norms: (i) Adaptive Layer-wise Reasoning Recursion, (ii) Endogenous Reasoning State Steering, and (iii) l2-guided Response Selection, which requires no additional training or data and is compatible with advanced inference engines. Experiments across model architectures and benchmarks show that l2-norm-based techniques significantly improve reasoning performance, offering a principled yet simple lens to perceive and control LLM latent reasoning dynamics. Our code is available at https://github.com/zjy1298/The-Tell-Tale-Norm.
arXiv:2606.04672v2 Announce Type: replace
Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global structural patterns. To mitigate this, we derive a parameter-efficient state-space modeling framework for continuous-time dynamic graphs (CTDG-SSM) from first principles. We first introduce continuous-time Topology-Aware higher order polynomial projection operator (CTT-HiPPO), a novel memory-based reformulation of HiPPO to jointly encode temporal dynamics and graph structure. The solution from CTT-HiPPO is obtained by projecting the classical HiPPO solution through a polynomial of the Laplacian matrix, yielding topology-aware memory updates that admit an equivalent state-space formulation for CTDGs (CTDG-SSM). Then a computationally efficient discrete formulation is obtained using the zero-order hold approach for model implementation.
Across benchmarks on dynamic link prediction, dynamic node classification, and sequence classification, CTDG-SSM achieves state-of-the-art performance. Notably, it achieves large performance gains on datasets that require long range temporal (LRT) and spatial reasoning.
arXiv:2101.05057v4 Announce Type: replace
Abstract: We study synchronizing partial DFAs, which extend the classical concept of synchronizing complete DFAs and are a special case of synchronizing unambiguous NFAs. A partial DFA is called synchronizing if it has a word (called a \emph{reset word}) whose action brings a non-empty subset of states to a unique state and is undefined for all other states. The class of strongly connected partial DFAs is precisely the class of DFAs recognizing the Kleene star of prefix codes. While in the general case the problem of checking whether a partial DFA is synchronizing is PSPACE-complete, we show that in the strongly connected case, this problem can be efficiently reduced to the same problem for a complete DFA. Using combinatorial, algebraic, and formal languages methods, we develop techniques that relate main synchronization problems for strongly connected partial DFAs to the same problems for complete DFAs. In particular, this includes the \v{C}ern\'{y} and the rank conjectures, the problem of finding a reset word, and upper bounds on the length of the shortest reset words of literal automata of finite prefix codes. We conclude that solving fundamental synchronization problems is equally hard in both models, as an essential improvement of the results for one model implies an improvement for the other.
arXiv:2606.05351v1 Announce Type: cross
Abstract: We present a novel nonlinear dynamical model, the generalized Allee-logistic (GAL) map given by $x_{t+1} = r x_t (1 - x_t) G(x_t)$ where $G(x_t) = m (x_t - h) + 1 - m$ incorporates the Allee effect with magnitude $m$ and threshold $h$. The case $m = 0$ yields the logistic map with a continuous transition to extinction. Conversely, $m = 1$ recovers a previously studied model that undergoes only a discontinuous extinction-to-active transition. Between these extremes, the GAL map exhibits nontrivial phenomena, including tricriticality with a closed-form expression for the tricritical point and a universal crossover function. Under a small external input, we verify Widom-like relations. We also note that the Allee effect disfavors the onset of chaos. Our work establishes additional bridges between analytically tractable chaotic maps, nonequilibrium tricriticality, and Allee effects.
arXiv:2602.02241v2 Announce Type: replace
Abstract: Entropic optimal transport (EOT) in continuous spaces with quadratic cost is a classical tool for solving the domain translation problem. In practice, recent approaches optimize a weak dual EOT objective depending on a single potential, but doing so is computationally not efficient due to the intractable log-partition term. Existing methods typically resolve this obstacle in one of two ways: by significantly restricting the transport family to obtain closed-form normalization (via Gaussian-mixture parameterizations), or by using general neural parameterizations that require simulation-based training procedures. We propose Variational Entropic Optimal Transport (VarEOT), based on an exact variational reformulation of the log-partition $\log \mathbb{E}[\exp(\cdot)]$ as a tractable minimization over an auxiliary log-normalizer. This yields a differentiable learning objective optimized with stochastic gradients and avoids the necessity of MCMC simulations during the training. We provide theoretical guarantees, including finite-sample generalization bounds and approximation results under universal function approximation. Experiments on synthetic data and unpaired image-to-image translation demonstrate competitive or improved translation quality, while comparisons within the solvers that use the same weak dual EOT objective support the benefit of the proposed optimization principle. The code for our solver can be found at https://github.com/DrEternity/VarEOT .
arXiv:2602.00911v2 Announce Type: replace
Abstract: The unit of collaboration in federated learning determines what guarantees are even expressible. Flat units like weights, prompts, raw examples, carry no type signature on which privacy, conflict resolution, or cross-model transfer can dispatch as well-defined operations. We propose typed federated artifacts: schema validated objects whose declared field structure makes per field differential privacy, schema aware merging, and cross architectural transfer first-class operations rather than heuristic approximations. We instantiate this as SYNAPSE, a compendium for federated tool routing across clients with frozen, heterogeneous LLMs and no shared data or weights which is a setting flat units cannot handle without either leaking gradients or discarding structure. The compendium admits a typed merge operator with field wise conflict resolution, a formal DP guarantee on numeric metadata, and conditional retrieval distortion and routing-stability results empirically characterized on five distributions, including one where the contraction premise fails. A single compendium transfers across four LLM families (LLaMA 3.18B,LLaMA 3.2-3B, Mistral 7B, GPT 4o) with approximately 2 pt loss, a capability weight-sharing federation cannot provide without architectural matching.
arXiv:2606.05699v1 Announce Type: new
Abstract: Bimanual dexterous tool use remains challenging for robots due to high-dimensional hand configurations and complex hand-tool-object dynamics and contact. Most existing control policies depend on future configuration references provided from demonstrations, while future action-conditioned world models require slow online planning over high-dimensional action sequences. A significant challenge is generating a dynamically consistent future reference trajectory without relying on privileged states from demonstrations or slow counterfactual planning. We propose DexFuture, a hierarchical system that couples a high-level Future-State Visuomotor Target Predictor with a low-level Target-Conditioned Structured Dexterous Policy. Conditioned on egocentric RGB, proprioceptive and geometric history, the high-level predictor constructs structured hand-tool-object visuomotor embeddings and uses a horizon-conditioned transformer to generate a multi-step future target trajectory. Then, the low-level policy tracks them with a target-conditioned per-link transformer. This hierarchy decouples coarse future reference generation from fine-grained action control, and slow long-horizon semantic prediction from high-frequency execution. On OakInk2 bimanual tool-use tasks, DexFuture achieves 90% of the privileged-oracle performance, compared to 7% for a no-reference policy. DexFuture operates at 60 Hz, approximately 250 times faster than DexWM-style Cross-Entropy Method (CEM) planning with a future action-conditioned world model.
arXiv:2601.22580v2 Announce Type: replace
Abstract: The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture ensures training stability at the cost of potential performance degradation in deep models, while the ``PostNorm'' architecture offers strong performance but suffers from severe training instability. In this work, we propose SpanNorm, a novel technique designed to resolve this dilemma by integrating the strengths of both paradigms. Structurally, SpanNorm establishes a clean residual connection that spans the entire transformer block to stabilize signal propagation, while employing a PostNorm-style computation that normalizes the aggregated output to enhance model performance. We provide a theoretical analysis demonstrating that SpanNorm, combined with a principled scaling strategy, maintains bounded signal variance throughout the network, preventing the gradient issues that plague PostNorm models, and also alleviating the representation collapse of PreNorm. Empirically, SpanNorm consistently outperforms standard normalization schemes in both dense and Mixture-of-Experts (MoE) scenarios, paving the way for more powerful and stable Transformer architectures.
arXiv:2601.21288v2 Announce Type: replace
Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high inference latency, while conventional supervised fine-tuning (SFT) often struggles to bridge the capability gaps of small models. To address these limitations, we propose Drive-KD, a framework that decomposes autonomous driving into a "perception-reasoning-planning" triad and transfers these capabilities via knowledge distillation. We identify layer-specific attention as the distillation signal to construct capability-specific single-teacher models that outperform baselines. Moreover, we unify these single-teacher settings into a multi-teacher distillation framework and introduce asymmetric gradient projection to mitigate cross-capability gradient conflicts. Extensive evaluations validate the generalization of our method across diverse model families and scales. Experiments show that our distilled InternVL3-1B model, with ~42 times less GPU memory and ~11.4 times higher throughput, achieves better overall performance than the pretrained 78B model from the same family on DriveBench, and surpasses GPT-5.1 on the planning dimension, providing insights toward efficient autonomous driving VLMs.
arXiv:2606.06246v1 Announce Type: cross
Abstract: We consider Bayesian discrimination among multiple quantum states and establish a dimension-free one-shot upper bound on the minimum probability of error in terms of the sum of pairwise errors. This resolves a conjecture of Audenaert and Mosonyi [J. Math. Phys. 55 (2014)] and improves the multiple quantum Chernoff bound of Li [Ann. Statist. 44 (2016)] by removing its dimension-dependent prefactor. In the asymptotic many-copy regime, our bound proves the achievability of the multiple quantum Chernoff distance for arbitrary separable Hilbert spaces, thereby settling the previously open infinite-dimensional case, and further yields constant-factor sharp asymptotics for the optimal error probability.
In binary quantum hypothesis testing, we prove that the minimum error probability is characterized, up to universal constants, by a trace harmonic-mean quantity. Consequently, the optimal binary quantum error probability is within a factor of two of the optimal classical error probability for the associated Nussbaum-Szko{\l}a distributions, complementing the lower bound of Nussbaum and Szko{\l}a [Ann. Statist. 37 (2009)].
arXiv:2606.05982v1 Announce Type: new
Abstract: Uncertainty quantification in neural networks prediction is a main issue for usual applications. Our approach seeks at reducing computation costs by directly evaluating uncertainty using PDE's information on the asymptotic variance, rather than the deep ensemble method which may be seen as a Monte Carlo estimation of the prediction, requiring the training of multiple networks. We thus study the law of the limiting process describing the random fluctuations around the mean-field limit of wide two-layer neural networks trained by stochastic gradient descent in a weak-noise regime. Building on a recent trajectorial central limit theorem, in which this limit is characterized as the weak solution of a linear stochastic evolution equation, we identify its law explicitly. More precisely, we show that it is a centered Gaussian process in the dual of a weighted Sobolev space, and we derive a closed covariance representation for the finite-dimensional distributions obtained by testing it against smooth functions. This covariance is expressed through the solution of a backward transport equation with a nonlocal source term, whose coefficients are driven by the mean-field trajectory. As a consequence, by testing against the activation function at a fixed input, we obtain an expression for the limiting variance of the corresponding network-output fluctuations. We illustrate this result numerically on a one-dimensional regression example.
arXiv:2606.06178v1 Announce Type: new
Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense. LLM routing aims to mitigate expenses while maintaining performance by sending queries to the most suitable model. However, existing methods cannot perform well for different user cost-performance preferences. To address this gap, we introduce a novel perceptive LLM routing paradigm for personalized and user-centric cost-performance optimization, which efficiently learns users' implicit preferences through little interaction. To handle the challenge of heterogeneous user needs, we formulate preference profiles as a set of distinct tasks in contextual bandit and propose MetaRouter, a meta-learning framework designed for preference-aware LLM routing. Experimental results show that MetaRouter outperforms strong baselines on both in-distribution and out-of-distribution tasks. Furthermore, it exhibits high efficiency in learning user preferences, robustness to changes in the routable LLMs, and scalability to multi-model routing.
arXiv:2606.06071v1 Announce Type: new
Abstract: This paper studies the weak convergence order of structure-preserving stochastic theta methods for a class of index-$1$ stochastic differential algebraic equations with time-dependent singular matrices. The singular matrix is allowed to vary in time but preserves a fixed differential-algebraic splitting, thereby extending the constant singular-matrix setting while retaining the projector structure required for constraint preservation. By exploiting the index-$1$ algebraic-differential decomposition of the exact solution, we establish an abstract weak convergence theorem for constraint-preserving one-step approximations and apply it to the stochastic theta method with $\theta \in (0,1]$. Under global Lipschitz, linear growth, and suitable smoothness assumptions, the considered method is proved to be well posed, to preserve the algebraic constraints at all time levels, and to converge with weak order one. Numerical experiments are finally presented to confirm the structure-preserving property and the theoretical convergence order.
arXiv:2606.06020v1 Announce Type: new
Abstract: To address the limited diversity and data scarcity in Pedestrian Attribute Recognition (PAR), we explore image synthesis using diffusion models guided by attribute-based prompts. While this enables the controlled generation of pedestrian images, it faces two critical challenges: (i) the domain gap between high-quality pre-training data and low-resolution, non-standard surveillance crops, and (ii) the need for reliable attribute verification to prevent generative hallucinations. In this paper, we introduce a robust generate-score-autolabel pipeline called ReSAGE-PAR (REpresentational Similarity Assessment for Generative Expansion in PAR) that bridges this domain gap and enables scalable, high-fidelity dataset expansion. First, we adapt pre-trained diffusion models to native PAR resolutions using a tailored LoRA-based Image-to-Image approach. Second, we extract vision-language alignment scores between the generated images and their conditioning prompts, utilizing a comprehensive prompting strategy that includes label-consistent and inconsistent complements. Finally, we formulate a Bayesian classifier that converts these continuous scores into reliable binary pseudo-labels. Extensive evaluations demonstrate the effectiveness of ReSAGE-PAR in preserving spatial priors and verifying attributes. When integrated into PAR training, ReSAGE-PAR consistently yields significant improvements-achieving gains of up to 8.7% on standard backbones and pushing state-of-the-art frameworks to new performance levels. This proves its value as an architecture-agnostic solution for scalable PAR enhancement. The complete codebase for ReSAGE-PAR is publicly available at http://www-vpu.eps.uam.es/publications/ReSAGE-PAR.
arXiv:2606.05518v1 Announce Type: new
Abstract: Tackling complex coding tasks often requires autonomous agents and iterative repair pipelines. These increasingly rely on large amounts of test-time computation, often spending many decoding and repair steps before discovering whether a program compiles, runs, or validates. Executable parallel-code translation is an effective setting for earlier guidance because success is behavioral rather than textual. However, most guidance methods act only after complete programs or textual traces are decoded. This motivates the question: can latent reasoning provide an earlier intervention point, before the model commits to code?
We study a test-time latent guidance method for this setting that trains a smaller Process Reward Model (PRM) over continuous latent prefixes and uses it to select among alternate hidden-state trajectories before final code decoding, separately from but compatible with post-decoding optimization. On a 76-task ParaTrans benchmark evaluation, latent PRM guidance improves mean validation rate from 32.89% with unguided latent reasoning to 42.1%, outperforming fine-tuned and vanilla baselines in the same setting. These gains persist under the same three-iteration repair loop. These results provide bounded evidence that useful alternative latent continuations exist and that PRM-scored latent branch selection can improve executable outcomes in this setting without retraining the main generative model.
arXiv:2606.06013v1 Announce Type: new
Abstract: Cheating poses a significant threat to the Multiplayer Online Games (MOG) industry by degrading player satisfaction and undermining the fairness in competitive gaming. Despite efforts to develop mitigation techniques, cheating remains difficult to detect and prevent in practice. In particular, a class of cheats based on network flow disruption remains unsolvable. To find out how to detect such attacks we need access to representative labelled data. However, no such dataset exists.
To address this gap, we leverage an experimental framework that combines a multiplayer online game with a plug-in capable of both reproducing cheating attacks and collecting logs at two levels: network and application-layer.
This paper presents a dataset compiling records of game sessions played by both real players and automated game clients, with cheating actions explicitly logged. To the best of our knowledge, this is the first dataset that provides logs of network flow disruption cheats. While it includes such network-based cheats, it is not limited to them and also contains records of more commonly studied cheats, such as aimbots and wallhacks. This dataset can be used by researchers in academia and industry seeking to develop cheating detection mechanisms for online games. Furthermore, it is designed to be evolutive and can be enriched by others creating their own data traces with the proposed framework.