# Research Papers — 2026-07 · bundle page 74 of 222 > Full-text markdown of papers #3651–3700 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/74 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/73.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/75.md) ### User-Centric Modeling of Transactional Sequences with Explainable State Space Models Authors: Ivan Palagin Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20228v1 We propose a hybrid approach for user-centric modeling of transactional event sequences that combines contrastive representation learning (CoLES) with State Space Models (SSMs). While contrastive methods yield high-quality compressed user representations, existing encoders -- RNNs and Transformers -- suffer from vanishing gradients or quadratic complexity, respectively. Mamba, a selective SSM, efficiently handles long-range dependencies but remains underexplored for personalized user analysis. We investigate two integration strategies: (1)~initializing the Mamba hidden state with a CoLES embedding, and (2)~prepending the projected CoLES embedding as a prefix token to the input sequence. Both approaches supply the model with an informative user prior from the first step. Experiments on three public datasets -- Age (multiclass age-group prediction), MBD (multi-label product acquisition), and Taobao (binary purchase prediction) -- demonstrate consistent improvements over standalone Mamba and CoLES with a linear classifier, with the hybrid models converging 2--3$\times$ faster than the plain SSM baseline. Explainability analysis via discretization-step maps and Integrated Gradients reveals selective event filtering on behavior-rich datasets and identifies the most informative transaction features. --- ### DQAOA-GPT: AI-Accelerated Distributed Quantum Optimization for Combinatorial Problems Authors: Seongmin Kim, Abhinav Rijal, Yuri Alexeev, Nora Bauer, Martin Roetteler, Mina Yoon, George Siopsis, In-Saeng Suh Published: 2026-07-22 Categories: quant-ph, cs.AI, cs.DC, math.OC arXiv: https://arxiv.org/abs/2607.20225v1 While combinatorial optimization problems are central to many scientific and engineering applications, their solution remains challenging due to exponentially large search spaces. Variational quantum algorithms offer a promising route for tackling such problems, yet their practical performance is limited by repeated quantum circuit evaluations and classical parameter updates. In this work, we introduce DQAOA-GPT, a hybrid framework that integrates the distributed quantum approximate optimization algorithm (DQAOA), which decomposes a large optimization problem into smaller sub-problems, with GPT-based quantum circuit generation for solving those sub-problems. Rather than relying on iterative variational optimization, the proposed approach uses a trained generative model to directly generate high-quality quantum circuits for the decomposed sub-problems. As a benchmark, we evaluate DQAOA-GPT against conventional DQAOA on dense HUBO optimization problems with up to 100 decision variables. The results demonstrate that DQAOA-GPT significantly reduces computational cost while maintaining competitive solution quality, with larger acceleration observed for larger sub-problem sizes. Although this work focuses on benchmark-scale validation, the framework provides a promising foundation for larger-scale combinatorial optimization in hybrid HPC-QC environments through increased GPU resources and parallel computing capability. --- ### HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering Authors: Abdessalam Bouchekif, Mohammed-En-Nadhir Zighem, Salah Eddine Bekhouche, Hichem Telli, Somaya Eltanbouly, Shahd Gaben, Heba Sbahi, Samer Rashwani, Mutaz Al-Khatib, Emad Mohamed, Mohammed Ghaly, Abdenour Hadid Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20219v2 Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing hallucination benchmarks often provide response-level labels, with limited support for identifying the exact erroneous content, explaining why it is incorrect, or selecting the correct factual answer. We introduce HalluTruthQA, a fine-grained benchmark for hallucination evaluation in Arabic question answering. The benchmark contains 2,400 expert-curated examples across four knowledge-intensive domains: Islamic knowledge, history, science, and geography. Each example pairs an Arabic question and a model-generated answer with a verified reference answer, a binary hallucination label, and six candidate answers for factual verification. Hallucinated answers additionally include character-level erroneous spans, human-written explanations, and macro- and micro-level hallucination types. We evaluate four open-source LLMs, ALLaM-7B, Falcon-H1R-7B, Qwen3-32B, and SILMA, in a zero-shot setting across hallucination detection, span-level localization, factual verification, and explanation evaluation. Results show that these tasks capture different abilities: no single model performs best across all tasks. The best scores are 0.880 Macro-F1 for detection, 0.516 F1-Sp for localization, 0.852 LO-Score for factual verification, and 0.644 for explanation evaluation. These findings show that hallucination evaluation should move beyond response-level detection toward the localization, verification, and explanation of factual errors. --- ### Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis Authors: Adel ElZemity, Shujun Li, Budi Arief Published: 2026-07-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.20216v1 Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models (LLMs) demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight frontier models motivate exploration of open-weight alternatives. However, many open-weight models are large, demanding significant compute resources and incurring non-trivial hosting costs that place them beyond reach for resource-constrained deployments. This paper investigates whether orchestrated ensembles of small language models (SLMs) can match or exceed single LLM performance on structured questions about malware detonation reports. We established baselines by testing eleven open-weight SLMs, three cyber security pre-trained models, and six frontier LLMs on Meta's CyberSecEval Malware Analysis benchmark. We then designed and evaluated four orchestration architectures: (i) a multi-agent pipeline that decomposes analysis into structured evidence-collection and reasoning stages, (ii) an adversarial debate framework in which two agents iteratively critique each other's reasoning, (iii) a hierarchical consultation system that pairs a general-purpose SLM with a cyber-specialised expert model, and (iv) a hybrid architecture that combines evidence-grounded pipelines with adversarial debate reasoning. The hybrid system (Qwen3-4B with Foundation-Sec-8B) achieved 35.30% overall accuracy, exceeding the strongest cyber-specialised baseline (22.54%) and the strongest ungrounded frontier baseline (34.77%); when given the same evidence pipeline, grounded Gemini remained the strongest configuration at 38.22%. These findings show that evidence-grounded orchestration can substantially improve the performance of collaborative SLMs for supporting interpretation of malware detonation reports. --- ### ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers Authors: Mahdi Heidari, Mohammad Mahdi Rahimi, Jaekyun Moon Published: 2026-07-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.20214v1 The quadratic $N\times N$ attention score matrix remains a central obstacle to extending Transformers to longer input lengths. Existing efficient attention methods usually reduce this bottleneck by either imposing sparsity, so that each query attends to only a small subset of keys, or by using low-rank/kernel sketches, so that global interactions are compressed into a lower-dimensional representation. We propose \emph{ELSAA}, an efficient low-rank and sparse approximation of attention. Importantly, ELSAA does \emph{not} decompose the learned projection or output matrices of the Transformer into sparse and low-rank factors. Instead, after dense projections produce $Q,K,V$, ELSAA approximates the induced attention score operator itself: a sparse branch captures selected high-similarity interactions, while a low-rank branch summarizes diffuse global interactions. Since the two branches can be normalized over supports with very different denominator mass, ELSAA introduces a denominator-aware fusion term that scales the sparse branch according to its estimated attention mass relative to the low-rank branch. This gives a practical framework for constructing low-rank and sparse attention outputs without materializing the full quadratic score matrix, aiming to enable longer-context training while preserving both sharp token-level interactions and broad contextual mixing. --- ### surprisal is Not a Theory Authors: Andrés Buxó-Lugo, Aniello De Santo, Morgan Grobol, Ryan J. Hubbard, Cassandra L. Jacobs Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20208v2 Surprisal Theory is often characterized as a computational-level explanation per (Marr, 1982). We argue in this work that, even though a computational level narrative has been used to support "representation-agnostic research" within computational psycholinguistics, the movement toward black box systems embodied by large language models (LLMs) does not exempt modelers using the surprisal metric from the representational decisions required by computational-level characterizations. In fact, we argue that the uncritical use of LLM-surprisal obfuscates the representational and algorithmic-level commitments of different models. In three analyses, we show that the choice of algorithm and model architecture play significant roles in the computation of language model probabilities. We advise that researchers who wish to test Surprisal Theory re-evaluate the practice of treating large language model probabilities as interchangeable --- ### surprisal is Not a Theory Authors: Andrés Buxó-Lugo, Aniello De Santo, Morgan Grobol, Ryan J. Hubbard, Cassandra L. Jacobs Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20208v1 Surprisal Theory is often characterized as a computational-level explanation per (Marr, 1982). We argue in this work that, even though a computational level narrative has been used to support "representation-agnostic research" within computational psycholinguistics, the movement toward black box systems embodied by large language models (LLMs) does not exempt modelers using the surprisal metric from the representational decisions required by computational-level characterizations. In fact, we argue that the uncritical use of LLM-surprisal obfuscates the representational and algorithmic-level commitments of different models. In three analyses, we show that the choice of algorithm and model architecture play significant roles in the computation of language model probabilities. We advise that researchers who wish to test Surprisal Theory re-evaluate the practice of treating large language model probabilities as interchangeable --- ### Statistical Inference for Rank Allocation in Low-Rank Adaptation Authors: Yihang Gao, Vincent Y. F. Tan Published: 2026-07-22 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2607.20205v1 Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large language models. Since different modules and layers may contribute unequally to downstream adaptation, allocating rank resources under a fixed parameter budget is an important problem for balancing efficiency, expressiveness, and generalization. Existing adaptive rank methods address this problem mainly through carefully designed importance scores constructed from gradient-derived sensitivity and uncertainty measures, without an explicit statistical interpretation. In this paper, we formulate LoRA rank allocation as a statistical hypothesis testing problem and propose StatLoRA, a statistical inference-based rank allocation method. StatLoRA associates each LoRA component with a test statistic and uses estimated p-values to determine which components should be retained or pruned under a prescribed rank budget. The proposed testing procedure is supported by our central limit theory for stochastic optimizer trajectories. In particular, we establish asymptotic normality for a broad class of commonly used optimizers in deep learning, including AdamW, and derive the corresponding asymptotic distributions for the proposed component scores used in hypothesis testing. We evaluate StatLoRA on LoRA fine-tuning of DeBERTaV3-base, BART-Large, and Qwen2.5-7B across natural language understanding, natural language generation, and question answering tasks. Experiments show that StatLoRA achieves comparable or better performance than vanilla LoRA, AdaLoRA, and IGU-LoRA under matched rank budgets. Sensitivity analyses and empirical diagnostics further support the stability of the proposed hypothesis-testing-based allocation rule and provide empirical evidence for the asymptotic theory of component scores. --- ### The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networks Authors: Antonio Di Cecco Published: 2026-07-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.20201v1 Additive models buy interpretability by forbidding feature interactions, a constraint that neural instantiations enforce architecturally. We introduce the quadrilateral loss, a differentiable penalty that treats additivity as a measurable behavior instead: a second-order mixed difference on pairs of training points swapping one coordinate, which vanishes if and only if the coordinate carries no interaction, remains informative for piecewise-linear networks, and equals in expectation the per-coordinate interaction mass of the interventional Shapley-GAM. The loss turns additivity into a dial - most learned interactions prove removable almost for free, and on small datasets a moderate penalty improves accuracy and additivity simultaneously - and into an online observable: its per-feature surrender curves show, across seeds and datasets, that pre-regularization interaction magnitude barely predicts what a regularized model retains, undermining post-hoc interaction rankings. Against this instrument we compare routes to exact additivity, spanning structural masks, behavioral penalties (optionally crystallized into exact structure), weight decay, backfitting, the shared-section model, and bagged boosted stumps: constraining behavior before structure dominates weight-space constraints, rankings reverse between data regimes, and converging routes agree on the shape functions themselves. Three silent failure modes we document share one anatomy: guarantees imported into settings that quietly void their preconditions. --- ### RS-RIE-Bench: Benchmarking Reasoning-Guided Remote Sensing Image Editing Authors: Zihan Qin, Boao Xu, Zhao Dong, Yingping Sun, Ziheng Jiao, Junying Wang, Hongwei Wang Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20197v1 Remote sensing image editing aims to modify remote sensing images according to natural language instructions while preserving geographic rules and sensor observation characteristics. Existing benchmarks mainly target natural images or general visual scenes, and thus may not fully capture the reasoning, regional control, and sensor-consistency abilities required in remote sensing editing. To fill this gap, we introduce RS-RIE-Bench, the first benchmark for reasoning-guided remote sensing image editing. RS-RIE-Bench organizes tasks into three categories: temporal reasoning, causal reasoning, and spatial reasoning. These categories capture temporal evolution, causal consequence, and spatial imaging consistency in remote sensing scenes. The evaluation protocol covers three dimensions: target region plausibility, non-target region preservation, and image quality consistency. We further demonstrate the feasibility of MLLM-based evaluation through cross-judge consistency analysis and stratified expert review. Systematic evaluation on eight open-source and closed-source image editing models shows that current models still have clear limitations in reasoning-guided remote sensing editing. Even the strongest model achieves only 24.28\% overall accuracy under the strict joint-satisfaction criterion, while the mean relaxed joint-4 success rate across all eight models is 32.23\%. Causal reasoning and spatial reasoning remain especially challenging, and several open-source models are close to zero in some categories. These results show that RS-RIE-Bench can effectively reveal the limitations of current models in geographic reasoning, regional control, and sensor-consistent generation. It also provides a standardized benchmark and a clear research direction for future remote sensing intelligent editing models. --- ### OLEDLM: A Unified Language Model for OLED Molecular Design Authors: Fukang Wen, Yuchong Tang, Jingyuan Li, Beichen Wang, Yixuan Jiang, Xiaoyi Jiang, Yaxuan Liu, Shunyu Wang, Zuoqiang Shi, Yi Zhu, Yanan Zhu, Pipi Hu Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20194v1 The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints, and a scarcity of labeled data. Although the question of OLED generation is important, few models have been trained effectively for this specific domain. We propose an inverse molecular design framework based on causal language models: given target optoelectronic properties (e.g., excitation energy, oscillator strength), our model directly generates OLED SMILES sequences satisfying the specified constraints. We employ a multi-stage strategy: first, we establish a foundational chemical language model using a LLaMA-style transformer architecture. To the best of our knowledge, this represents the first successful adaptation of LLMs specifically for the OLED domain, bridging the gap between generic molecular generation and the stringent structural requirements of optoelectronic materials. Second, we fine-tune property predictors based on a BERT model pre-trained on our large-scale OLED dataset. Then, we perform Reinforcement Learning on our fine-tuned model, leveraging our property predictor, for better SMILES generation. Finally, through DFT verification, we demonstrate that our framework can efficiently navigate the OLED chemical space, generating novel candidates with high structural validity and optimized optoelectronic properties. --- ### On Optimization Complexity of Second-Order Certified Unlearning Authors: Nikita Doikov, Anastasia Koloskova Published: 2026-07-22 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2607.20192v1 We study machine unlearning: the removal of memorized training data from a trained model. Specifically, we investigate the algorithmic complexity of certified unlearning from an optimization perspective. We formalize the goal of an unlearning algorithm as simultaneously achieving certified unlearning and optimization accuracy. Utilizing the notion of uniformly convex regularizers, we prove new bounds on the distance between initial and unlearned models using a novel substitute for generalization error. Thus we theoretically demonstrate that if the removed data is well-predicted by the unlearned model, the corresponding optimization problem is simple. Furthermore, we develop a new second-order unlearning algorithm with an anisotropic Gaussian mechanism and state-of-the-art global convergence. We prove fast rates for our method in achieving certified unlearning for linear models with quasi-self-concordant losses. As a direct application, our theory covers unlearning for logistic and exponential regressions and shows a provable benefit of utilizing second-order information compared to first-order unlearning methods. --- ### PerceptDrive: Perception Prior World-Action Modeling with Adaptive Expert Routing for End-to-End Autonomous Driving Authors: Yushan Liu, Tianxiong Lv, Bohua Wang, Hangqi Fan, Chenxu Zhao, He Zheng, Xuchang Zhong, Yifan Xie, Congyang Zhao, Zhihao Liao, Leigang Luo, Yang Cai et al. Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20175v1 Frozen perception foundation models encode rich geometric, semantic, and dynamic knowledge. Yet narrow conditioning interfaces may attenuate task-relevant cues, while static fusion cannot adjust expert contributions to each scene. We cast this challenge as the prior-to-plan transfer problem and introduce PerceptDrive, a perception prior world-action modeling framework with adaptive expert routing. PerceptDrive feeds teacher-distilled priors from a frozen, driving-adapted provider and dense observation latents from a frozen self-supervised video encoder into a trainable expert-routed world-action model. Expert-specific query branches process these signals, while a prior-retention objective anchors each branch to its prior. A router predicts soft gates from a shared scene representation and combines the expert conditions before trajectory generation. During training, privileged rule-based sub-metric estimates for branch-specific trajectory drafts provide soft-gate distillation targets. The predicted action-free future latent conditions a flow-matching actor. At inference, privileged components are absent; with one front-facing camera, PerceptDrive generates one trajectory per planning step without test-time scoring, reranking, or search. Experiments show that PerceptDrive achieves state-of-the-art performance with 90.4 PDMS on NAVSIM v1 and 90.2 EPDMS on NAVSIM v2, outperforming existing methods. Ablations confirm complementary gains from prior retention and scene-conditioned routing, alongside differential reliance on the three priors. These results demonstrate that preserving and adaptively routing perception priors improves direct planning without test-time candidate selection. --- ### StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation Authors: Zejing Rao, Haoxian Zhang, Xiaoqiang Liu, Yiping Meng, Guoxin Zhang, Pengfei Wan, Fan Tang, Tong-Yee Lee Published: 2026-07-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.20174v1 Existing human--object interaction (HOI) video generation methods are largely limited to offline short-video generation with complex driving conditions, making them unsuitable for real-time interactive applications. We present \emph{StreamHOI}, a low-latency streaming framework for long-duration HOI video generation. Instead of converting heavily conditioned HOI pipelines into streaming systems, we study how an image-to-video streaming generator should organize historical memory to preserve interactions under bounded latency. We find that the standard sink-local memory design faces a trade-off in streaming HOI generation, and different transformer blocks show different historical-memory preferences for HOI regions and surrounding regions. To match memory composition with block behavior, StreamHOI performs offline HOI-aware block profiling and applies bias-guided memory-specialized training to adapt the generator to block-specific memory layouts. We further introduce a memory distance scaling module to strengthen long-range access to early interaction states. Extensive comparisons with both long-video baselines and recent HOI generation methods demonstrate that StreamHOI achieves strong interaction plausibility, object fidelity, human quality and efficiency, reaching 17.6 FPS with 0.75s first-chunk latency. --- ### Instance Hardness-Based Relevance for Imbalanced Regression Authors: Vitor M. Leitao, Juscimara G. Avelino, George D. C. Cavalcanti, Rafael M. O. Cruz Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20173v2 Imbalanced regression problems arise when the target variable has an asymmetric distribution, resulting in underrepresented value ranges in the dataset. Traditional approaches for identifying rare instances rely on a relevance function that assigns higher importance to specific regions of the target distribution. However, the effectiveness of imbalance-aware learning methods depends strongly on how relevance is defined. In more complex scenarios, such as bimodal distributions, traditional relevance functions struggle to capture rarity, as they assign fixed relevance values based solely on target values, thereby compromising the distinction between truly rare and normal instances. To address these limitations, this study proposes an Instance Hardness-based relevance function (InHaR) for identifying rare instances in regression problems. Unlike traditional relevance functions, the proposed approach incorporates learning difficulty, allowing rarity to be inferred not only from the target distribution but also from the difficulty of instances for the learning algorithm. This property is particularly important in bimodal scenarios, where rarity cannot be accurately inferred from target values alone. Experimental results demonstrate that the InHaR correctly identifies rare regions under bimodal distributions and, when used to guide resampling strategies such as Random Oversampling (RO) and Gaussian Noise (GN), leads to significant improvements in predictive performance compared to traditional relevance-based approaches. The code, dataset, and further details about the proposed method are publicly available at https://github.com/VitorLeitao/instance-hardness-Imbalanced-regression. --- ### Guarantees by Construction for Learned Finite Volume Schemes on Steady Supersonic Flow Authors: Denis Gueyffier Published: 2026-07-22 Categories: physics.flu-dyn, cs.LG, math.NA arXiv: https://arxiv.org/abs/2607.20171v3 A second order finite volume scheme rests on two local quantities: a gradient reconstructed in each cell, and a limiter which scales it down where the reconstruction would overshoot. Both are set by fixed formulas, and on coarse unstructured meshes a small network can supply better values. But a network is free to output anything, and the usual safeguard is a penalty in the training loss, which discourages inadmissible states without preventing them. We replace the penalty by a hard constraint. The network still sets both quantities, and every value it can produce lies inside safe bounds: its stencil weights cannot cancel a neighbour, and its limiter is capped by the local flow. The flux, the wall treatment and the time step are not learned and carry their own guarantees. Admissibility therefore holds for every value of the weights rather than as an outcome of training, and no negative density or pressure occurred in any computation reported here. Because the scheme is safe whatever the network does, we could ask what the network contributes. We test it on supersonic channel flow over an obstacle, including the forward facing step of Woodward and Colella. Learning lowers the error by 38% on an unseen geometry and 29% on an unseen obstacle topology, measured against the same scheme with the network switched off. The method aims at the accuracy of a fine mesh for the cost of a coarse one, and refining once improves the error fourfold while multiplying the run time by eight. Learning secures half of this improvement for a sixth of this time. All of this comes from one of the two quantities the network sets. The gradient reconstruction reproduces the full effect on its own, and the limiter accounts for about a tenth as much. This also explains why the gain fades beyond the Mach numbers the weights were trained on. --- ### Quantum Kernels and the Cross-Section of Stock Returns: Anatomy of a Vanishing Advantage Authors: Junchi Shen Published: 2026-07-22 Categories: q-fin.PR, quant-ph, stat.ML arXiv: https://arxiv.org/abs/2607.20168v1 Do quantum kernels improve cross-sectional stock return prediction? We run a controlled horse race on the Chinese A-share market in which a quantum fidelity kernel, a projected quantum kernel, and a classical RBF control share identical training subsamples, solver, and tuning budgets, so that only the kernel is exchanged. On the main evaluation -- a point-in-time universe and 170 walk-forward windows (2012-2025) -- no quantum advantage exists: the fidelity kernel is indistinguishable from its RBF control ($Δ$IC $=+0.005$, $p=0.42$), and a $2\times2$ design crossing kernel type with training budget (a Nystrom extension to the full ~38,000-observation windows) shows quantum kernels matching, but never beating, equal-budget linear models; after family-wise correction no pairwise difference among eleven models is significant, with point estimates favoring penalized linear regressions throughout. We then document how the opposite conclusion arises: a 60-window evaluation on a universe screened with full-sample information makes the same quantum kernel appear dominant on stability criteria and significantly better than neural baselines. Interaction characteristics from the anomalies literature help nothing, quantum or classical; a widened bandwidth grid reveals an interior optimum rather than the near-classical endpoint a coarse grid suggests; and the geometric difference, while large throughout ($g \gg 1$), does not predict out-of-sample gains ($ρ=-0.20$). We propose protocol standards -- kernel-swap controls, budget-equalized comparisons, point-in-time universes, and multiplicity-robust inference -- for empirical claims of quantum advantage in finance. --- ### Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning Authors: Siqian Tong, Xuan Li, Chaozhuo Li, Baolong Bi, Yiwei Wang, Yujun Cai, Shenghua Liu, Chengpeng Hao Published: 2026-07-22 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2607.20166v1 Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e.g., recognizing event order, repetitions and duration). Existing post-training methods heavily rely on expensive external labels or provide only coarse semantic signals. To bridge this gap, we introduce Audio-Zero, the first label-free self-evolution framework in the field of LALMs that improves fine-grained auditory perception and reasoning. Audio-Zero constructs an auditory self-play game from unlabeled audio contrast pairs: most players hear a reference audio, while one odd listener hears a subtle variant. The model first generates clues describing what it hears and then identifies the odd listener by reasoning over inconsistencies among clues. Since the odd listener is known by construction, the game provides verifiable rewards without any annotated answers. Experiments with Qwen2-Audio-7B-Instruct and Qwen2.5-Omni-7B on TREA, MMAU Test-mini and MMAR show that Audio-Zero improves fine-grained audio reasoning while preserving broad audio understanding. Evolutionary and diagnostic analyses further reveal that increasingly fine-grained auditory descriptions emerge naturally from game pressure. --- ### Plausibility-Driven Prioritization of Candidate Biomedical Annotations Authors: Emanuele Cavalleri, Miad Alavinezhad, Dario Malchiodi, Marco Mesiti Published: 2026-07-22 Categories: q-bio.QM, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2607.20163v2 The rapid growth of biomedical knowledge has made the validation of automatically generated biological annotations a major bottleneck in biomedical curation. While computational methods can rapidly produce large numbers of candidate annotations, determining which are biologically valid still requires costly expert review. Prioritizing these candidates before manual curation has therefore become a fundamental challenge. Machine learning techniques can support this process by exploiting biomedical knowledge graphs (bioKGs), which capture biological entities and their functional associations. In this work, we propose a framework that leverages bioKGs to estimate the plausibility of candidate annotations and guide expert curation. Starting from knowledge graph embeddings, we train relation-specific binary classifiers using a community-based negative sampling strategy to obtain reliable confidence estimates. We then introduce a family of plausibility measures that combine classifier confidence, classifier reliability, and the semantic context provided by alternative relationships involving the same pair of biological entities. Unlike conventional confidence estimation, the proposed approach explicitly accounts for multiple biologically meaningful relations that may coexist between the same entities. Experimental results on five large bioKGs demonstrate that the proposed negative sampling strategy consistently improves classifier robustness, increasing balanced accuracy by an average of 5.8%. Moreover, the plausibility measures outperform classifier confidence alone, enabling more effective prioritization of candidate annotations for expert review. Overall, our results show that the use of bioKGs improves the efficiency of AI-assisted biomedical curation while preserving expert control over the final annotation assessment. --- ### Self-organizing Architecture of Receptron Units: a Hardware-Aware Framework for Edge Intelligence Authors: Stefano Radice, Ludovico Casaccia, Riccaro Emanuele Beccalli, Bruno Paroli, Paolo Milani Published: 2026-07-22 Categories: cs.LG, cs.ET arXiv: https://arxiv.org/abs/2607.20162v1 The growing demand for intelligent processing at the edge of IoT networks is constrained by the severe computational and memory limitations of microcontroller units, which render impractical conventional deep learning approaches. We propose a neuromorphicinspired classifier based on the Receptron model, a single-unit architecture capable of implementing non-linearly separable decision boundaries, without resorting to multi-layer networks. The model is designed for direct deployment on mid-range MCUs, while supporting continuous on-device adaptation. Experimental evaluation on basic dataset benchmarks yields cross-validated accuracies compatible with standard machine learning method baselines. These results position the Receptron as a viable and interpretable alternative for resource-constrained neuromorphic edge systems operating in dynamic, non-stationary environments. --- ### SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction Authors: Sriprabha Ramanarayanan, Rahul G. S., Mohammad Al Fahim, Keerthi Ram, Ramesh Venkatesan, Mohanasankar Sivaprakasam Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20159v1 Attention Mechanism (AM) selectively focuses on essential information for imaging tasks and captures relationships between distant pixel neighborhoods to compute feature representations. Accelerated MRI reconstruction benefits from AM, as the imaging process involves Fourier domain measurements that influence image representation non-locally. However, AM-based models are more adept at capturing low-frequency information with limited capacity for high-frequency representations, restricting models to smooth reconstruction. Additionally, AM-based models need mode-specific retraining for multimodal MRI data, as their knowledge is restricted to local contextual variations that may be inadequate to capture transferable features across heterogeneous domains. To address these challenges, we propose a neuromodulation-based discriminative multi-spectral AM for scalable MRI reconstruction that can (i) propagate context-aware high-frequency details for high-quality reconstruction, and (ii) capture features reusable across deviated unseen domains in multimodal MRI. The proposed network consists of a spectral filtering CNN to capture mode-specific transferable features and a dynamic high-pass kernel generation transformer focusing on high-frequency details. We evaluate our model on comparative studies in supervised and self-supervised learning, diffusion model-based training, closed-set and open-set generalization under heterogeneous MRI data, and interpretation-based analysis. Our method offers scalable, high-quality reconstruction with best improvement margins of ~1 dB in PSNR and ~0.01 in SSIM under unseen scenarios. Code: https://github.com/sriprabhar/SHFormer --- ### Local Stability and Gaussian Smoothing of Quantized Neural Networks Authors: Sergey Salishev, Anton Makarov, Oleg Granichin Published: 2026-07-22 Categories: cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2607.20153v1 We study Gaussian averaging as a smooth surrogate for quantized neural models. Under bounded local oscillation, we derive a local dimension-dependent bound on |f-g|, linking Gaussian smoothing to the stability analysis of discontinuous networks. We compute closed-form Gaussian averages of the rectified linear unit (ReLU) and sign activation functions, and illustrate the mechanism on a high-dimensional binary perceptron, where layer-preactivation aggregation under an explicit quantization-noise surrogate yields the Gaussian envelope used in inference-side smoothing and training-side smooth surrogate gradients. --- ### Active Inference as a Convex Markov Decision Process Authors: Nikola Milosevic, Nicolás Hinrichs, Nico Scherf Published: 2026-07-22 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2607.20152v2 Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization and show that, for closed-loop control policies, EFE minimization can be formulated as a convex Markov decision process (MDP). This perspective reveals that policy-dependent reward prediction errors transmit natural gradients of the expected free energy backwards in time rather than up a hierarchy. Finally, we show that coupling world-model learning with policy optimization gives active inference the structure of performative reinforcement learning. Together this places EFE minimization within modern reinforcement learning and optimization theory and opens a route toward principled algorithms for active inference. --- ### Active Inference as a Convex Markov Decision Process Authors: Nikola Milosevic, Nicolás Hinrichs, Nico Scherf Published: 2026-07-22 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2607.20152v1 Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization and show that, for closed-loop control policies, EFE minimization can be formulated as a convex Markov decision process (MDP). In this formulation, the pragmatic terms are linear in the predictive state marginals and therefore equivalent to reward maximization in a latent MDP, while the epistemic value introduces a nonlinear component that distinguishes EFE minimization from standard reinforcement learning. This perspective further reveals the epistemic drive of active inference as a policy-dependent (performative) reward. We analyze finite-horizon, discounted, and average-reward formulations of EFE and derive a mirror descent (MD) algorithm that locally linearizes the objective around the current state marginals, yielding a policy-dependent reward that is compatible with actor-critic methods and dynamic programming. Finally, we argue that coupling world-model learning with policy optimization gives active inference the structure of performative reinforcement learning, providing a route toward grounding active inference within modern reinforcement learning and optimization theory, including convergence analysis and principled policy improvement guarantees. --- ### Multi-stage Dynamic Selection for Cross-Project Defect Prediction Authors: Juscimara G. Avelino, Juscelino S. A. Junior, George D. C. Cavalcanti, Rafael M. O. Cruz Published: 2026-07-22 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2607.20151v2 Cross-Project Defect Prediction (CPDP) involves building models using data from external projects, called training projects, to predict modules from the target project. However, traditional CPDP methods suffer from the distribution shift between training and target projects that affects the model's performance. This paper proposes a novel CPDP framework that addresses this issue by proposing a two-stage multiple classifier system (MCS) selection scheme: one working at the project level and another at the module level. In the first stage, the framework evaluates multiple possible MCS configurations to find one that covers and generalizes well across multiple training projects. Consequently, the proposal is likely to obtain a diverse set of classifiers, each specialized in tackling software modules with distinct characteristics. The second selection stage operates at test time, selecting the most competent classifiers to predict each new module in the target project. Unlike previous approaches that apply the same classifiers to the entire target project, the proposed framework performs module-level model selection. This way, the system is more robust to changes in distributions between training and target projects because the selected set of classifiers is module-dependent. Our experimental results using 82 projects from four different CPDP benchmark datasets demonstrate that the proposed approach outperforms the state-of-the-art CPDP methods in most scenarios. The code, dataset, and further details about the proposed method are publicly available at https://github.com/jsaj/Multi_DES. --- ### Gotta Catch them all: the modes of Sycophancy Authors: Shreyans Jain, Alexandra Yost, Amirali Abdullah Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20146v1 Large language models often align with users' beliefs at the expense of factual accuracy, a behavior known as sycophancy. Prior mechanistic studies largely treat sycophancy as a single behavioral dimension that can be uniformly amplified or suppressed. We challenge this assumption by analyzing three hypothesized modes of sycophancy across 948 social pressure situations. Although the modes produce highly similar outputs, with a text-only classifier achieving just 57.8 percent accuracy, their internal representations are perfectly linearly separable from layer 14 onward. We further find the modes emerge at different processing stages, rely on distinct attention circuitry, and fire strongest on different inputs. These results show that sycophancy is not a monolithic tendency, but a structured family of representationally and computationally distinct modes, motivating more precise measurement and intervention. --- ### SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Authors: Dongfang Li, Xiaodong Luo, Ruoyu Sun, Xuhui Chen, Linyuan Qiu, Jian Meng, Zhengxuan Lu, Yiting Wang, Yucheng Xie, Tao Guo, Tianxiang Fang, Jing Li et al. Published: 2026-07-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20145v3 Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While most large-scale LLM training systems are built around GPU-based clusters, this report presents an end-to-end optimization practice on the Ascend NPU SuperPOD. Using the DeepSeek-V4 model family as the target workload, we develop a hierarchical optimization framework spanning model-level parallelism, computation-communication orchestration, and low-level kernel execution. The resulting system achieves 34.22% Model FLOPs Utilization (MFU) with a 2.93x improvement over the open-source baseline recipe while maintaining training stability. Building on this optimized infrastructure, we further establish a CPT and SFT workflow for complex Operations Research (OR) tasks. We refer to the integrated framework as SLAI T-Rex. Using DeepSeek-V4-Flash, we develop OR-oriented CPT and SFT data pipelines that combine collected domain resources with solver-verified synthetic optimization documents. The resulting dataset contains 10K high-quality SFT samples spanning four task categories and three problem representations. The specialized model achieves the highest average zero-shot Pass@1 score among the evaluated models, reaching 71.81% and outperforming GPT-5.4-Mini and the base DeepSeek-V4-Flash model by 3.98 and 11.27 percentage points, respectively. Overall, this work demonstrates a full-stack pathway from efficient trillion-parameter model post-training on Ascend infra to domain-specialized Flash models for solver-grounded mathematical modeling, advancing frontier-model systems for complex reasoning. --- ### SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Authors: Dongfang Li, Xiaodong Luo, Ruoyu Sun, Xuhui Chen, Linyuan Qiu, Jian Meng, Zhengxuan Lu, Yiting Wang, Yucheng Xie, Tao Guo, Tianxiang Fang, Jing Li et al. Published: 2026-07-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20145v2 Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While most large-scale LLM training systems are built around GPU-based clusters, this report presents an end-to-end optimization practice on the Ascend NPU SuperPOD. Using the DeepSeek-V4 model family as the target workload, we develop a hierarchical optimization framework spanning model-level parallelism, computation-communication orchestration, and low-level kernel execution. The resulting system achieves 34.22% Model FLOPs Utilization (MFU) with a 2.93x improvement over the open-source baseline recipe while maintaining training stability. Building on this optimized infrastructure, we further establish a CPT and SFT workflow for complex Operations Research (OR) tasks. We refer to the integrated framework as SLAI T-Rex. Using DeepSeek-V4-Flash, we develop OR-oriented CPT and SFT data pipelines that combine collected domain resources with solver-verified synthetic optimization documents. The resulting dataset contains 10K high-quality SFT samples spanning four task categories and three problem representations. The specialized model achieves the highest average zero-shot Pass@1 score among the evaluated models, reaching 71.81% and outperforming GPT-5.4-Mini and the base DeepSeek-V4-Flash model by 3.98 and 11.27 percentage points, respectively. Overall, this work demonstrates a full-stack pathway from efficient trillion-parameter model post-training on Ascend infra to domain-specialized Flash models for solver-grounded mathematical modeling, advancing frontier-model systems for complex reasoning. --- ### Real-Time EEG Cap Electrode Detection for Guided Point-of-Care Placement Authors: William Lehn-Schiøler, Mads Sverker Nilsson, Nicki Skafte Detlefsen Published: 2026-07-22 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2607.20142v1 We present a two-stage vision system that detects EEG cap electrodes in a live webcam stream and validates their anatomical placement in real time. A single-class YOLO detector localises electrodes; a geometric stage assigns each detection to a named 10-20 role from facial landmarks. Evaluating under subject-disjoint leave-one-subject-out (LOSO) cross-validation across five subjects wearing the clinically-validated Small/Medium/Large caps, the detector attains mAP@.5 = 0.94 +/- 0.07 across five held-out folds (0.96 pooled). A dedicated leave-one-cap-out axis, holding out every frame of a cap regardless of subject, leaves Medium and Large mAP@.5 within 0.01 of LOSO (0.97, 0.97) while Small drops to 0.72 +/- 0.28, a gap confounded with subject familiarity rather than cap style. Geometric augmentation (rotation, perspective, mixup) improves in-plane-roll robustness and temporal-electrode recall at no inference cost, and a landmark-driven head crop extends the usable distance range, lifting mAP@.5 from 0.23 to 0.45 at 0.6 x apparent scale. A compact mobile-candidate backbone (YOLOv10n) keeps the detector at real-time throughput (19 FPS) on a commodity CPU at 640 px. --- ### Formal Foundations for Known Good Reliable Die Screening in Chiplet-Based AI Systems-on-Chip Authors: Prashanthi Metku, Chandra Gandu Published: 2026-07-22 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2607.20141v1 The rapid growth of chiplet-based artificial intelligence systems-on-chip (SoCs) has exposed a fundamental gap in semiconductor test methodology. Existing Known Good Die (KGD) screening guarantees pre-assembly functional correctness, yet it offers no probabilistic assurance of post-assembly reliability lifetime. To address this limitation, the present work formalizes the transition from KGD to Known Good Reliable Die (KGRD) screening as a constrained inference problem over incomplete pre-assembly observability. Building upon this formulation, four interlocking contributions are presented: (i) a Bayesian probabilistic risk model that maps pre-assembly telemetry to post-assembly failure likelihood with a quantified observability bias bound; (ii) a safety-gated decision architecture that provides a provable post-assembly failure probability guarantee; (iii) uncertainty-aware disposition boundaries derived from Bayes-optimal decision theory; and (iv) a constrained closed-loop feedback mechanism that delivers consistent model improvement without violating reliability constraints. A Monte Carlo simulation study on N = 4,000 synthetic dies verifies all four theoretical properties and confirms that the safety guarantee holds uniformly across the full range of tested gate threshold. --- ### CURED: Creating, Understanding, and Repairing Errors Demonstrator Authors: Nicholas Chandler, Sebastian Jäger, Philipp Jung, Felix Bießmann Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20140v1 Detecting and cleaning errors in tabular data is a prerequisite for data intense software applications. Recent research at the intersection of Machine Learning (ML) and Database Management Systems (DBMS) highlights the potential of statistical learning algorithms for error detection and cleaning. This paper combines our recent work on ML-based data cleaning and error models in a unified demonstrator. The web application allows users to upload tabular data, perturb the data with realistic data dependent errors and use modern ML methods to clean and understand error mechanisms in data. Our demonstrator helps to bridge the gap between theoretical advancements and intuitive practical insights in the context of error models and data cleaning algorithms for tabular data. The demonstrator is available at https://cured.demo.calgo-lab.de/ --- ### PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping Authors: Busra Bulut, Maik Dannecker, Thomas Sanchez, Sara Neves Silva, Steven Jia, Jean-Baptiste Ledoux, Leo Pomar, Joanna Sichitiu, Yvan Gomez, Meriam Koob, Vincent Dunet, Maria Deprez et al. Published: 2026-07-22 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2607.20136v2 Slice-to-volume reconstruction (SVR) is the standard method for obtaining high-resolution (HR) 3D fetal brain volumes from motion-corrupted 2D MRI slice stacks acquired in multiple orientations. Existing SVR methods are optimized and validated only for clinical-range echo times (TEs), limiting their use at non-clinical TEs and making them incompatible with quantitative T2 mapping, a protocol- and center-independent biomarker of fetal brain maturation requiring HR reconstructions across multiple TEs. We present PRIME-SVR, the first implicit neural representation (INR) framework for joint HR reconstruction from multi-echo MRI. A single fully connected network models a continuous function from spatial coordinates to signal intensities across TEs, while a second network estimates slice-specific acquisition degradations. Cross-TE coherence is enforced via a Bloch equation-derived regularization penalizing deviations from expected T2 decay, with adaptive weighting that strengthens coupling for degraded stacks. The method is fully self-supervised. We validate PRIME-SVR on 39 in vivo fetal acquisitions (13 subjects x 3 TEs) from two centers, two vendors, and two field strengths (1.5 T and 0.55 T). Compared to state-of-the-art SVR, PRIME-SVR improves reconstruction sharpness by 47%, anatomical accuracy by 30%, and cross-TE structural consistency by 14%. It enables reconstruction at late TEs previously inaccessible to SVR, yielding the first 0.8 mm isotropic T2 maps at 0.55 T and the first T2 maps derived from INR-based SVR. PRIME-SVR also accelerates quantitative imaging by reducing the data needed for multi-TE reconstruction, cutting acquisition from 15 to 10 minutes while keeping T2 accuracy within 1.7% in white and deep gray matter, or to 5 minutes with a mean T2 error of 2.3% for high-quality acquisitions. --- ### PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping Authors: Busra Bulut, Maik Dannecker, Thomas Sanchez, Sara Neves Silva, Steven Jia, Jean-Baptiste Ledoux, Leo Pomar, Joanna Sichitiu, Yvan Gomez, Meriam Koob, Vincent Dunet, Maria Deprez et al. Published: 2026-07-22 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2607.20136v1 Slice-to-volume reconstruction (SVR) is the standard method for obtaining high-resolution (HR) 3D fetal brain volumes from motion-corrupted 2D MRI slice stacks acquired in multiple orientations. Existing SVR methods are optimized and validated only for clinical-range echo times (TEs), limiting their use at non-clinical TEs and making them incompatible with quantitative T2 mapping, a protocol- and center-independent biomarker of fetal brain maturation requiring HR reconstructions across multiple TEs. We present PRIME-SVR, the first implicit neural representation (INR) framework for joint HR reconstruction from multi-echo MRI. A single fully connected network models a continuous function from spatial coordinates to signal intensities across TEs, while a second network estimates slice-specific acquisition degradations. Cross-TE coherence is enforced via a Bloch equation-derived regularization penalizing deviations from expected T2 decay, with adaptive weighting that strengthens coupling for degraded stacks. The method is fully self-supervised. We validate PRIME-SVR on 39 in vivo fetal acquisitions (13 subjects x 3 TEs) from two centers, two vendors, and two field strengths (1.5 T and 0.55 T). Compared to state-of-the-art SVR, PRIME-SVR improves reconstruction sharpness by 47%, anatomical accuracy by 30%, and cross-TE structural consistency by 14%. It enables reconstruction at late TEs previously inaccessible to SVR, yielding the first 0.8 mm isotropic T2 maps at 0.55 T and the first T2 maps derived from INR-based SVR. PRIME-SVR also accelerates quantitative imaging by reducing the data needed for multi-TE reconstruction, cutting acquisition from 15 to 10 minutes while keeping T2 accuracy within 1.7% in white and deep gray matter, or to 5 minutes with a mean T2 error of 2.3% for high-quality acquisitions. --- ### CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning Authors: El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane Published: 2026-07-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20129v2 Quantized small reasoning models can enter repetitive or otherwise unproductive trajectories, yet standard decoding does not adapt to the trajectory as it unfolds. We study MGT-B, a fixed, weight-preserving controller that converts overlapping windows of uncertainty, repetition, and local-change features into position-conditional empirical tail probabilities. It accumulates mixture betting factors with a CUSUM-shaped reset, and, after an alarm, restores a coherent earlier token and key-value-cache state before constrained re-decoding. On MATH-500, a paired three-seed evaluation over 1,500 generations per method raises exact-normalized accuracy from 54.73% for vanilla decoding to 56.40% (+1.67 percentage points; problem-clustered bootstrap 95% CI (+0.47, +2.80)), while a prospectively profiled random-intervention control reaches 54.60%. The gain is positive in all three seeds and costs 5.14% more sampled tokens. Seed-0 ablations show that rollback alone does not explain the result and that an isolated repetition penalty is harmful. Five-sample self-consistency reaches 70.0% but uses about 4.84x as many tokens as MGT-B. On the harder, non-overlapping Omni-MATH evaluation, however, MGT-B obtains 16.60% versus 16.67% for vanilla (-0.07 points; clustered 95% CI (-0.33, +0.20)) with 2.10% more sampled tokens. Thus, MGT-B provides a modest, reproducible local improvement on MATH-500 in the studied configuration, but the effect does not transfer to Omni-MATH and should not be interpreted as a general improvement in mathematical reasoning. --- ### CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning Authors: El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane Published: 2026-07-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20129v1 Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops. Building on an earlier token-level e-CUSUM controller, we develop MGT-B (Monitoring-Guided Test-time Backtracking), a revised external controller that maps overlapping windows of pre-sampling uncertainty and degeneration features to position-conditional empirical tail probabilities, accumulates mixture betting factors with a CUSUM-shaped reset, and responds to an alarm by estimating a rollback point, restoring token and key-value-cache state, and performing constrained re-decoding. To audit whether the effect persists on problem identities first observed after the manual choice of log threshold h = 10, we retrospectively exclude 260 IDs present in pre-threshold artifacts and retain the chronologically first post-threshold pair for each remaining ID, yielding a 240-pair chronology-audit set. On this set, accuracy changes from 82/240 to 88/240 (+2.50 percentage points; 13 corrections, 7 regressions; exact McNemar p = 0.2632; paired bootstrap 95% interval (-1.25, +6.25)). A broader 467-pair historical-coverage set of seed-matched pairs changes accuracy from 146/467 to 167/467 (+4.50 points; McNemar p = 0.000753), but includes 200 seed-1 IDs available before or during threshold selection and is reported only as an exploratory estimate. All 316 no-alarm outputs in the 467-pair set are identical to vanilla, while the 151 alarmed trajectories contain 29 corrections and 8 regressions. Neither analysis is confirmatory, and the empirical factors are not established as a valid e-process or e-detector. The results support a selective monitoring-and-repair mechanism for the studied MATH-500 setting, rather than a general or theoretically certified reasoning improvement. --- ### Back to Back with a Copy: A Computational Analysis of AI-Generated Visual Contemporary Art Pastiches Authors: Anca Dinu, Andreiana Mihail, Andra-Maria Florescu, Claudiu Creanga, Liviu Dinu Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20127v1 The aim of this paper is twofold. First, it investigates whether newer generative models are getting better at pastiching contemporary artworks. Second, it explores the consistency of the multidimensional nature of stylistic evaluation across different LLMs. Building on previous work, we analyze stylistic similarity between AI generated pastiches and the original artworks of twelve contemporary artists. We used five complementary computer vision models to capture texture, color, semantics, composition, and perceptual features through cosine distance in high-dimensional embedding spaces. The distances obtained show that the newer image generation model that we used has produced pastiches with improved semantic alignment and greater diversity than the model used in previous work. However, it was slightly less performant on shallow features such as color, texture, and perceptual adherence. Our findings confirm that artistic style is inherently multidimensional, and measuring it does not depend on any spatial architecture. These quantitative findings are contextualized through feedback from human evaluators, which are the artists themselves. --- ### HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation Authors: Jinliang Shen, Lianghao Su, Zheming Li, Kang He, ZiLiang Lai, Yanbing Jiang, Chengru Song Published: 2026-07-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.20125v1 Autoregressive (AR) video diffusion models have become a promising paradigm for long and streaming video synthesis, but the continuously growing Key-Value (KV) cache makes attention the dominant inference cost, especially at high resolution where each frame contributes many tokens. Existing remedies either evict the cache with coarse heuristics that cause inter-frame flickering, or require model re-training. We propose HeadCast, a training-free, plug-and-play acceleration framework built on the observation that a pre-trained AR model's attention heads exhibit stable, heterogeneous behaviors. After a short warm-up, HeadCast performs a one-time classification at the maximum-noise step that sorts every head into one of four archetypes: Sink, Dummy, Spatial, and Global, and restructures the monolithic KV cache into head-specific pathways. Crucially, it retains the Global heads that preserve the long-range temporal consistency aggressive eviction destroys. Because the Spatial pathway operates on a fixed-size grid, its savings grow with resolution: across state-of-the-art AR models, HeadCast accelerates inference by up to 1.62x at 720P and 1.95x at 1080P, while keeping VBench quality on par with full attention and largely flicker-free. Code is available at https://github.com/sjlgaga/HeadCast . --- ### Autonomous Collaborative Learning Among an Ensemble of Tsetlin Machines with Consensus-Based Inference Authors: Yehuda Rudin, Osnat Keren, Michal Yemini, Alexander Fish Published: 2026-07-22 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2607.20124v1 Tsetlin Machine (TM) is a rule-based machine-learning algorithm comprising collectives of two-action Tsetlin Automata (TAs) that cooperatively form conjunctive logical clauses from Boolean inputs through stochastic feedback. Although few recent studies have examined TM Federated Learning, the broader area of distributed and decentralized TM learning has not received much attention in the existing literature and warrants further exploration. In this work, we propose a paradigm for decentralized collaborative learning under a vertical feature-partitioning setting among an ensemble of Tsetlin Machines using consensus-based inference. Within this decentralized paradigm, each agent maintains its own private TM model, and there is no exchange of raw data among agents. Inference combines individual agents model predictions into a global consensus. The paradigm accommodates heterogeneous TM-based agents with differing data acquisition means, local data distributions, or computational resources, thereby facilitating the integration and fusion of information in settings such as multi-modal sensing environments. Experiments conducted using two-dimensional grid and connected graph network topologies demonstrate that the classification accuracies achieved are comparable to those of centralized models. --- ### OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills Authors: Qiyuan Liu, Tingfeng Hui, Kun Zhan, Kaike Zhang, Ning Miao Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20121v2 LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that only emerge during actual execution. In this work, we conduct a systematic investigation into how well current agent systems recognize and avoid such risks. To support quantitative and qualitative evaluation, we construct OpenSkillRisk, a dedicated safety benchmark containing 263 risky skills collected from public skill marketplaces. We classify these skills into seven categories based on their threat types and pair each skill with a standardized user task and a corresponding sandbox for controlled evaluation. Distinct from prior benchmarks, OpenSkillRisk not only covers more realistic and diverse unsafe scenarios, but also provides a fine-grained analysis to diagnose the behavioral patterns of agents in such scenarios. We conduct comprehensive experiments covering three mainstream CLI agent frameworks and thirteen state-of-the-art LLMs. Experimental results show that no tested system handles risky skills reliably: even the safest configurations still execute unsafe actions in about 17% of cases. Context-dependent and system-level risks are especially difficult for current agent systems to avoid. Our behavioral analysis reveals three recurring failure patterns: agents may fail to recognize the risk, recognize it but fail to intervene before acting, or follow skill instructions beyond the user's intended scope. These findings highlight the need to improve both risk reasoning in LLMs and execution control in agent frameworks. --- ### Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparison Authors: Shijie Zhong, Jiangfeng Fu Published: 2026-07-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.20119v1 We introduce the Directional Kernel Mean Difference (DKMD), a signed statistic for univariate distribution comparison that preserves the direction of distributional shifts. Unlike the squared Maximum Mean Discrepancy (MMD), which discards directional information by squaring the RKHS distance, DKMD integrates the difference of kernel mean embeddings against a fixed odd weighting function. This construction yields three structural properties: antisymmetry, immunity to symmetric distributional differences, and directional monotonicity under stochastic dominance. We derive a data-driven Riemann estimator that ensures asymptotic consistency with the continuous formulation, strictly preserving the theoretical guarantees of the signed statistic in empirical evaluations. To overcome the quadratic computational cost of kernel methods, we develop an $O(N \log N)$ prefix--suffix scanning algorithm that exploits the total order of the real line while requiring only $O(N)$ memory. Experiments on synthetic benchmarks demonstrate that DKMD correctly isolates directional shifts from symmetric perturbations, remains robust to heavy-tailed outliers that can flip the sign of the mean difference, and scales to millions of samples in seconds. --- ### RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs Authors: Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao, Bingliang Hu, Geng Zhang Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20116v2 Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, differences in acquisition time and imaging platform between UAV and reference imagery introduce substantial cross-domain appearance and viewpoint shifts, challenging robust six-degree-of-freedom (6-DoF) pose estimation. To mitigate these shifts, we render UAV-viewpoint references from Google 3D Tiles across locations, altitudes, and orientations. A two-stage strategy adapts SALAD with pose-near positives and geographically distant hard negatives; local geometric consistency then re-ranks the Top-K candidates. We further propose Retrieval-In-Matching (RIM), which freezes the adapted DINOv2-B retriever and distills a local-descriptor decoder from its token field and a shallow VGG19 detail stream. One query-side DINOv2-B backbone forward therefore supports both SALAD retrieval and local description, eliminating a second foundation-model backbone while preserving the retrieval descriptors by construction. We evaluate RIM zero-shot on the reconstructed EPFL Urbanscape and self-collected Chang'an Park datasets, both geographically disjoint from the training data. RIM outperforms ten retrieval baselines. Under the full 3D distance metric at 25/50 m, it improves Recall@1 over SALAD by 8.55/13.77 percentage points on EPFL and 4.45/8.94 points on Park. At Top-K=5, the measured online query path through retrieval, candidate matching, and robust geometric verification takes 90.8 ms: 1.2 times faster than the strongest separate sparse-matching baseline and over 30 times faster than RoMa, while maintaining comparable re-ranking accuracy. These results demonstrate an efficient UAV global visual localization pipeline under unreliable satellite navigation. The source code is available at https://github.com/curious-energy/RIM. --- ### RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs Authors: Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao, Bingliang Hu, Geng Zhang Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20116v1 Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, acquisition-time and imaging-platform differences between UAV and reference imagery induce substantial cross-domain appearance and viewpoint shifts, challenging robust six-degree-of-freedom (6-DoF) pose estimation. We address these shifts by sampling UAV-viewpoint reference views from Google 3D Tiles across locations, altitudes, and orientations. A two-stage cross-domain fine-tuning recipe adapts SALAD using pose-near positives and geographically distant hard negatives, while local geometric consistency re-ranks the Top-K candidates. We further propose Retrieval-In-Matching (RIM), which freezes the adapted DINOv2-B retriever and distils a local-descriptor decoder that reuses its token field alongside a shallow VGG19 detail stream. One query-side DINOv2-B forward thus serves both SALAD retrieval and local description, eliminating a second foundation-model backbone while preserving retrieval descriptors by construction. We evaluate RIM zero-shot on the reconstructed EPFL Urbanscape and self-collected Chang'an Park datasets, both geographically disjoint from the training data. RIM outperforms ten recent retrieval baseline families. At 25/50 m under the full 3D distance metric, it improves Recall@1 over SALAD by 8.55/13.77 percentage points on EPFL and 4.45/8.94 points on Park. At Top-K=5, the complete measured localization query, including retrieval, candidate matching, and robust geometric verification, takes 67.9 ms end-to-end: 1.8 times faster than the strongest separate sparse-matching baseline and over 40 times faster than RoMa, while achieving comparable re-ranking accuracy. These results establish an efficient and deployable pipeline for UAV global visual localization in GNSS-challenged environments. --- ### Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing Authors: Langchen Huang, Sebastian Padó, Franziska Weeber Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20115v1 Large language models (LLMs) are known to be sensitive to prompt and input formulations. However, existing studies have focused on lexical realization and largely ignored constructional choice. This paper studies whether linguistic construction can systematically shift LLM decisions and where these shifts can be causally localized inside the model. We use political stance judgment as a meaning-sensitive case study and extend an English political statements dataset, resulting in six controlled linguistic rewrite types that preserve or invert the meaning of a statement. Experiments on four open-weight models show that stance instability affect both meaning-preserving and meaning-inversing rewrites. Because output shifts reveal that rewrites affect stance, but not where in the model, we apply activation patching, where activations from the original statement are substituted into the forward pass for the rewritten statement and measure which components recover the original stance distribution. The results show that mid-to-late decoder layers, especially block outputs at the final prompt position, provide the strongest restoration signal. --- ### Two-Step Occupation Coding Authors: Alexander M. Esser, Jens Dörpinghaus Published: 2026-07-22 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.20101v1 Occupation coding links job titles in free text to occupational taxonomies and is a core task in labor market research. Existing approaches typically address this problem in a single end-to-end step, jointly identifying job titles and assigning occupational codes. This paper presents a novel two-step approach that separates these tasks. In the first step, a domain-specific Named Entity Recognition (NER) model identifies occupational titles in continuous text, even under noise such as OCR errors. In the second step, the extracted job titles are mapped to a taxonomy, enabling the classifier to focus exclusively on this mapping. We demonstrate that this separation improves accuracy, robustness, and interpretability compared to single-step approaches. The method has been developed for German documents but is transferable to other languages. We further introduce a margin-based confidence criterion for occupation coding, replacing common absolute thresholds. To support reproducibility, we publish the source code and evaluation scripts. --- ### ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models Authors: Karan Goyal, Afreen Hossain, Debojyoti Das, Vishal Bhutani Published: 2026-07-22 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20092v1 Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is relevant, true, or even meaningful. Recently, it has been identified and given a mechanistic account in unimodal language models. Whether and how it manifests in vision-language models (VLMs) is, by contrast, largely unexamined, and the field lacks a purpose-built instrument with which to investigate it. We take the position that studying contextual entrainment in VLMs requires more than porting an existing text-only benchmark to the multimodal setting: it requires a taxonomically structured, dual-modality instrument whose conditions are constructed around the item at hand (the depicted image in the textual stream, the textual query in the visual stream). We argue that the move to VLMs is substantive rather than incremental. It makes entrainment a dual phenomenon, drivable independently by textual and by visual context, and it opens a veracity distinction (context that is false of the depicted scene yet possible in the world) that has no counterpart in the unimodal, world-knowledge-only formulation of prior work. To make this position concrete and actionable, we introduce ENTRAP-VL (ENTRainment Assessment Probe for Vision and Language), a manually curated dataset of 1,500 items across eight categories, organized by a taxonomy that spans two axes, i.e., the association of context with the item and its relationship to truth, and split into a textual-entrainment stream (eight context conditions) and a visual-entrainment stream (three context conditions). We do not claim to measure entrainment in any particular model; we provide the instrument, the taxonomy that motivates it, and the evaluation protocols it enables, so that the community can investigate the phenomenon rigorously. We will release the dataset and its documentation publicly. --- ### Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results Authors: Yanyu Chen, Yue Li, Yongyi Cui, Dongsheng Shi, Lichang Dai Published: 2026-07-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20090v1 Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content. Blanket refusal discards valid evidence, whereas uncritical adoption yields incorrect or unsafe answers. The ability to selectively adopt relevant information while rejecting deceptive or harmful content is therefore critical for reliable deployment in real-world retrieval settings. We introduce SelectBench, a controlled benchmark and training set for selective evidence adoption, and post-train Qwen3.5-4B directly with DAPO using either deterministic rule rewards or a frozen semantic judge. On the corrected 325-example SelectBench-v2 test set, strict success rises from 22.46% for the original checkpoint to 25.54% with DAPO-Rule and 26.46% with DAPO-DeepSeek. Both trained policies reduce forbidden-content adoption and produce shorter, more focused responses, yet prompt-injection following does not improve. The paired gains are modest and fail to survive Holm correction, suggesting that stronger reward shaping or additional training iterations may be needed for more robust gains. DAPO-DeepSeek exhibits no material degradation on MMLU or clean HotpotQA, indicating that the post-training procedure preserves general capabilities. These results demonstrate a directional improvement in selective evidence use, while identifying injection resistance and statistical robustness as important remaining challenges for future work. --- ### Development of an automated, reliable, and clinically meaningful artificial intelligence (AI) tool for diagnosing cardiac disease from conventional cardiovascular magnetic resonance (CMR) images Authors: Sina Amirrajab, Volker Vehof, Michael Bietenbeck, Nuriye Akyol, Redouane Bouras, Khuraman Isgandarova, Alexandru Zlibut, Philipp Stalling, Ali Yilmaz Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20087v1 Aims: Cardiovascular magnetic resonance (CMR) imaging enables non-invasive assessment of myocardial structure, function, and pathology, but requires substantial experience in interpretation of CMR images that could be supported by artificial intelligence (AI)-based models. However, use of AI models for enhanced CMR reading is limited by labor-intensive data curation, suboptimal model performance, and unclear implementation pathways. Methods and results: We developed an automated data curation pipeline for CMR-based cardiovascular disease (CVD) diagnosis, integrating open-source locally-run large language models (LLMs) to extract diagnostic labels from narrative CMR reports and preprocessing multimodal imaging data, including cine and late-gadolinium-enhancement (LGE) CMR sequences. Three vision foundation models (DINO, VST, UMedPT) were fine-tuned across these modalities in a two-stage approach. The dataset comprised hypertrophic cardiomyopathy (HCM), dilated cardiomyopathy (DCM), ischemic cardiomyopathy (ICM), cardiac amyloidosis (CA), and normal controls (NOR). A total of 988 curated cases were randomly divided into 742 for training and 246 for validation. Fine-tuned AI-models achieved high discriminative diagnostic performance on an independent test set comprising 1067 patients , with individual AUC-ROC values of up to 0.937 for the correct diagnosis of HCM and 0.945 for cardiac amyloidosis. Ensemble strategies combining multiple models and modalities further improved AI-based diagnostic accuracy and robustness, achieving the highest overall diagnostic performance for HCM (AUC=0.959, CI (0.936-0.978)), CA (AUC=0.966, CI (0.939-0.986)), NOR (AUC=0.872, CI (0.852-0.894)), DCM (AUC=0.848, CI (0.808-0.885)) and ICM (AUC=0.840, CI (0.809-0.868)). All training and inference code, along with the trained model weights, are publicly available on https://github.com/sinaamirrajab/CMR_CVD. --- ### Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting Authors: Mahesh Godavarti Published: 2026-07-22 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2607.20086v1 State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks. We study cumsum-composable phase transport, a streaming-native temporal layer for keyword spotting. Each layer projects acoustic frames to complex channels, transports them by learned unitary rotations, accumulates a finite window using prefix differences, and applies a gated residual update. The same prefix representation gives exact batched training with ordinary cumulative sums and exact online inference with one prefix update per frame. Unitary transport is the key constraint: inverse rotations have norm one, keeping prefix terms well conditioned while memory is supplied by windows or block readouts. On Google Speech Commands v2 with 12 labels, mel+cumsum models retain competitive accuracy with compact baselines. The strongest single-seed run reaches 97.3\% test accuracy; a 51.6K-parameter tied model also reaches 97.3\%, and a 24.8K tied model reaches 96.8\% versus 97.1\% for a 25.6K MelCNNMaxPool baseline. In a matched cumsum-versus-scan benchmark, cumsum+window gives comparable accuracy, 94.82\% versus 94.33\%, while training 1.07x faster and reducing single-example latency from 7.09 ms to 5.01 ms on a Tesla T4. These results support cumsum phase transport as a simple low-cost temporal primitive for streaming keyword spotting. --- ### Non--negative matrix factorization using the \textit{R} package \textsf{nnmf} Authors: Volkan Sevinç, Nikolas Kontemeniotis, Theodoros Perdikis, Michail Tsagris Published: 2026-07-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.20084v1 Non--negative matrix factorization (NMF) has become an established dimensionality reduction technique for extracting latent structures from non--negative data and has found widespread applications in fields such as bioinformatics, text mining, image analysis, and recommender systems. As the popularity of NMF has increased, numerous \textit{R} packages implementing different optimization strategies and computational frameworks have been developed. Despite their widespread availability, comprehensive evaluations of these implementations under real--world data conditions remain limited. Consequently, researchers often lack objective guidance when selecting an appropriate package for practical applications. This study introduces a new \textit{R} package for NMF and offers asystematic performance comparison with two widely available \textit{R} packages for NMF analysis. Rather than relying on simulated datasets, the evaluation is conducted using real--world data to better reflect the complexity, heterogeneity, and noise characteristics encountered in practical analytical settings. The packages are assessed using a consistent experimental framework, with emphasis on computational efficiency, convergence behavior, reconstruction accuracy, memory utilization, and the stability of the resulting matrix factorization. --- ### Co-Evolving LLM Evaluators and Policies via DynamicRubric Authors: Beining Wang, Weihang Su, Hongtao Tian, Hao Kong, Tao Yang, Ting Yao, Qingyi Pan, Yueyue Wu, Qingyao Ai, Min Zhang, Yiqun Liu Published: 2026-07-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.20083v2 Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models. As policies improve, these sampled responses become close in quality. These close candidates create a bottleneck for policy optimization: collapsed relative evaluator score gaps yield weak or misleading policy supervision. We theoretically characterize why these gaps matter through a probability allocation view, showing that the directional gain of shifting probability mass from one response to another is exactly the evaluator score gap between them. This identifies relative score gaps as the policy optimization signals that guide updates. Motivated by this view, we propose DynamicRubric, a response-set-conditioned evaluator--policy co-evolution framework that generates weighted binary rubric items for each candidate set and aggregates the resulting judgments into response-level scores. In our experiments with 8B backbones, DynamicRubric improves evaluator performance and provides stronger policy supervision than baselines using a 70B reward model or a 235B static rubric generator. DynamicRubric-optimized policies also show gains on verifiable reasoning and coding tasks. A DynamicRubric-optimized model is fully deployed in WeChat Search's AI answering scenario, where it serves all online traffic across tens of millions of requests per day and improves key online metrics. These results suggest a principle for evaluator-guided post-training: evaluators should evolve with the policies they supervise. ---