# Research Papers — 2026-09 · bundle page 122 of 266 > Full-text markdown of papers #6051–6100 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/122 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/121.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/123.md) ### ScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents Authors: ScholarSeed AI Team, Caoqinwei Gong, Xue Jiang, Wei Luo, Xiaoyu Qiu, Jiayi Sheng, Yi Wang, Zheng Yu, Ao Zhang, Haifan Zhang, Hanwei Zhang, Jihai Zhang et al. Published: 2026-09-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23735v2 Scientific agents support a range of literature-based research tasks, such as retrieval, question answering, evidence-grounded generation, and claim assessment. Most existing systems, however, are organized around individual tasks: the same papers are repeatedly retrieved, segmented, and interpreted, and the understanding built in one task is difficult to reuse in the next. We present ScholarStack, a layered research asset framework that compiles a paper collection into reusable, versioned, and provenance-preserving assets at three complementary levels: source-grounded paper-level statements, domain-level organization, and evidence-grounded cross-paper syntheses. A common access interface returns task-specific views at the evidence granularity each task requires, preserving study conditions, source traceability, and verification status. We instantiate the framework on four task families spanning ten task settings, comparing agents that use the compiled assets with task-specific baselines under matched base models. Quality gains concentrate on tasks that require cross-paper evidence, such as multi-paper question answering and literature review generation, and query-time token cost falls on every task where it is measured, with assets compiled once and reused across tasks. These results suggest that layered research assets can serve as shared infrastructure for scientific agents, shifting literature-based assistance from isolated document processing toward cumulative, evidence-grounded workflows. --- ### VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers Authors: Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23733v1 Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-view images. Despite their promising performance, these models scale quadratically with the number of input views due to their global attention mechanism, resulting in substantial latency for long sequence inputs. There have been some recent efforts to accelerate VGGT, but they primarily focus on reducing \emph{token redundancy} through token merging or key/value sparsification. Our work resolves this bottleneck from a different perspective by investigating \emph{architectural redundancy} in visual geometry transformers. We show that the multi-head attention modules in VGGT's global-attention layers contain substantial architectural redundancy, with only a subset of heads carrying critical geometric information. In light of this observation, we propose VGGT-Prime, a compute-adaptive mixture-of-heads model that resolves this redundancy to accelerate visual geometry transformers while maintaining competitive reconstruction quality. The key idea of VGGT-Prime is to estimate the appropriate computation level for each global-attention head using a lightweight router and then dynamically assign each head to different computation modes. Extensive experiments on multiple datasets demonstrate that VGGT-Prime can achieve an {$8\times$} inference speedup over VGGT while maintaining competitive performance on camera pose, depth, and point-cloud predictions. We further show that VGGT-Prime is complementary to existing acceleration methods, such as token merging, further improving inference speed by up to $14{\times}$ over VGGT. An overview of our work is available on our \href{https://vggt-prime.github.io}{project page}. --- ### Marginal Calibration Does Not Compose: Hidden Dependence in Modular Robot Navigation Authors: Rista Baral Published: 2026-09-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.23731v1 Robotic systems are typically composed of multiple independently developed modules that work together to perceive, predict, and act in the environment. Although each module may perform reliably in isolation, composing them does not necessarily preserve uncertainty calibration at the system level. In this work, we show that well-calibrated component interfaces do not necessarily produce calibrated downstream behavior after composition. Using a moving-obstacle prediction pipeline, we demonstrate that position and velocity estimators can each appear well calibrated individually, yet differences in how their error are correlated lead to substantially different estimates of future-state uncertainty. Consequently, assuming independence can make the system either overly confident or unnecessarily conservative, directly influencing downstream planning decisions and safety. Through simulations, we show that modeling the joint covariance restores downstream calibration and improves system performance, whereas dependence-robust uncertainty bounds enhance safety at the cost of increased conservatism. Our findings reveal a fundamental limitation of independently validating robotic modules and highlight the need for interfaces that communicate dependence information or support direct system-level calibration. --- ### GRACE: Grounded Adversarial Reasoning over Canadian Law Authors: Jiakang Xu, Wantong Huo, Udom Silparcha, Jonathan H. Chan Published: 2026-09-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.23726v1 Large language models have shown strong performance across a range of legal tasks, but existing benchmarks rarely evaluate the ability to take and defend a legal position, reason under incomplete information, or synthesize multiple statutory provisions. This gap is particularly pronounced for Canadian law, which remains underrepresented in legal NLP. We introduce GRACE (Grounded Reasoning Adversarial Canadian LEgal examples), a dataset of 1,915 question-reasoning-answer instances grounded in Canadian federal legislation. GRACE covers three reasoning modes: adversarial advocacy, uncertainty, and applied reasoning. We develop a pipeline that partitions raw statutory text, generates scenario-based questions and reasoning, and filters examples through model-free citation verification and LLM-based quality auditing. As a proof of concept, we fine-tune CLeAR-4B (Canadian Legal Adversarial Reasoning), a lightweight model for grounded legal reasoning, and evaluate it against the unmodified Qwen3-4B base model in open- and closed-book settings. CLeAR-4B substantially improves agreement with teacher outputs and statutory citation behavior when the relevant act text is provided, while its grounding degrades sharply when the statute is withheld. These results suggest that GRACE can support the development of lightweight legal models that reason more effectively from supplied statutory text. --- ### BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring Authors: Liuyang Song, Yi Zhang, Zhongyi Deng, Daqian Yang, Hongbo Zhang Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23717v1 Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which region or how those regions are arranged; a model can recognize every word and object yet prefer a compositionally incorrect caption. We argue that a frozen encoder retains this association structure, so the problem is to read it rather than to rebuild it beside the pretrained similarity. We introduce BindCLIP, a pairwise scorer built on one latent object: a balanced token--patch--depth optimal-transport coupling that places both candidate captions and several visual depths in a single plan. Semantic, entity, order, and spatial evidence are read as energies of this state, and exchanging the candidates permutes the plan, making the score exactly antisymmetric. A geometric refinement inside the coupling contracts moves that the candidates and the visual depths do not support. No task label, parser, relation inventory, or detector is used. One checkpoint and one inference path improve the official What'sUp, ARO, and SugarCrepe benchmarks over frozen global CLIP, with the strongest transfer on the relation splits. Controls rule out patch access and caption-length shortcuts, and an inference-time lesion localizes spatial arrangement to the coupling. --- ### STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification Authors: Yifan Xu, Yixuan Li, Xinzhuo Li, Yixin Gu, Yifan Shen, Lijun Yu, Haohan Wang Published: 2026-09-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.23716v1 Textual-gradient methods automate prompt optimization through natural-language feedback, but their iterative updates can be unstable. We identify two sources of this instability: noisy gradients produced from already-correct examples and over-specialization to hard cases that degrades performance on simpler inputs. We introduce STEVE, a stabilization framework with two coupled mechanisms. Error-Driven Refinement generates gradients only from incorrectly handled examples, concentrating updates on informative failures. Regularized Verification treats every update as provisional and accepts it only when improvement on hard cases does not cause unacceptable regression on a preservation set. Across ten reasoning benchmarks, three evaluator/optimizer models, and established prompt-optimization baselines, STEVE reduces degradation and produces more robust prompts. Additional evaluations with gpt-5.4-mini/gpt-5.4 on symbolic reasoning, GSM8K-Platinum, and DS-1000 show that these gains persist with newer models and larger test sets. STEVE therefore provides a practical way to improve the stability and effectiveness of textual-gradient prompt optimization. --- ### Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models Authors: Yahong Wang, Zhangkai Ni, Juncheng Wu, Yuyin Zhou, Ying Wen, Lianghua He Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23715v1 Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images. While token pruning has emerged as a promising approach to reduce the inference cost of MLLMs, existing methods typically reassign position embeddings to the retained tokens using either sparse or continuous position embeddings, each introducing distinct limitations. Sparse position embeddings tend to decrease the attention value allocated to visual tokens, thereby degrading the perception capability of MLLMs, whereas continuous position embeddings disrupt the original spatial correspondence of visual tokens, leading to weakened grounding capability. To mitigate this issue, we perform layer-wise analysis of the language decoder and observe that intermediate layers play a critical role for maintaining the grounding capability of MLLMs under token pruning. Based on this observation, we propose a layer-aware position embedding strategy, which switches to sparse position embeddings at grounding-sensitive layers while maintaining continuous position embeddings elsewhere. Extensive experiments across representative pruning methods and diverse benchmarks demonstrate that our approach improves the comprehensive multimodal performance of pruned MLLMs compared with standard sparse and continuous position embeddings. --- ### Infectious Bovine Pinkeye Detection Using Computer Vision and Imbalance-Aware Learning Authors: Michael Abalo, Jameson Brennan, Hossein Moradi Rekabdarkolaee Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23714v1 Infectious bovine pinkeye is a contagious ocular disease that adversely affects cattle health, welfare, and agricultural productivity. Conventional diagnosis relies primarily on clinical observation, which can be subjective, time-consuming, and difficult to implement efficiently in large herds or remote settings. This study evaluated and compared You Only Look Once (YOLO) v11 and YOLOv26 for automated bovine pinkeye classification and investigated the effects of class-balancing strategies on model performance. Five variants (n, s, m, l, and x) of each architecture were trained and evaluated using the original imbalanced dataset, Random Minority Oversampling (RMO), and an adapted Synthetic Minority Oversampling Technique (SMOTE). Both YOLOv11 and YOLOv26 demonstrated strong classification performance, although the effects of class balancing varied across model variants. For YOLOv11, RMO-s achieved an accuracy of 0.99, a macro F1-score of 0.98, and a true positive rate (TPR) of 1.00, with no false-negative classifications. RMO-m also achieved a TPR of 1.00 with no false negatives. For YOLOv26, the original l, RMO-m, and RMO-l variants each achieved an accuracy of 0.99 and a macro F1-score of 0.98, with RMO-l attaining a TPR of 1.00 and no false negatives. Overall, RMO generally provided greater improvements in minority-class detection than adapted SMOTE, whereas the strong performance of the original YOLOv26-l demonstrates that oversampling was not necessary for all model variants. These findings demonstrate the potential of YOLOv11 and YOLOv26 for automated detection of bovine pinkeye and support further evaluation for livestock health monitoring. --- ### Financial Language Models as Applied Artificial Intelligence Systems for News-Based Trading under Market Frictions Authors: Kemal Kirtac Published: 2026-09-20 Categories: cs.CL, cs.LG, q-fin.TR arXiv: https://arxiv.org/abs/2609.23703v1 Financial language models can transform unstructured firm-specific news into structured decision signals, but financial AI research lacks an integrated deployment framework for evaluating whether those signals remain useful in financial decision systems. Computer science research has developed strong methods for time-series forecasting, text classification, multimodal stock prediction, graph-based market modeling, and machine-learning operations, yet these streams do not provide a domain-specific protocol that jointly tests financial language-model outputs under event-time observability, probability calibration, execution timing, transaction costs, liquidity constraints, capacity limits, operational diagnostics, and statistical inference. We introduce MFAST, a Market-Friction-Aware Sentiment-to-Trading framework that converts timestamped financial text into auditable, reproducible, and market-feasible trading decisions. The application is news-based trading, where firm-specific text must be linked to securities before portfolio decisions can be evaluated. The framework links Refinitiv News Analytics to Center for Research in Security Prices (CRSP) equity data, restricts the primary out-of-sample evaluation to post-release news outside disclosed foundation-model data-freshness periods, and adds a public replication arm using open financial text and public price data. Results show that decoder-only language models outperform encoder baselines and dictionary sentiment in classification, calibration, return prediction, and net portfolio performance, while operational diagnostics reveal trade-offs among accuracy, latency, memory, throughput, and inference cost. The paper shows that credible evaluation of financial language models requires an end-to-end engineering approach combining language understanding, temporal discipline, market-friction-aware deployment, and reproducible validation. --- ### TEMPER: Temporal Encoder-Masked Probabilistic Ensemble Regressor for Time-Series Forecasting Authors: Giancarlo Vercellino Published: 2026-09-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.23701v1 Probabilistic forecasting requires accurate central predictions and calibrated uncertainty estimates. This paper presents TEMPER, the Temporal Encoder-Masked Probabilistic Ensemble Regressor, a univariate time-series forecasting algorithm that combines a temporal autoencoder, a differentiable masked neural decision forest, continuous ranked probability score (CRPS) training, and Gaussian-mixture post-processing. The R implementation is built on torch for R and returns horizon-wise density, distribution, quantile, and sampler functions. We evaluate TEMPER on three deterministic synthetic level series with trend, periodic, regime-switching, nonlinear-threshold, and heteroskedastic components. Across 96 rolling-origin forecasts at horizons t + 1, t + 5, t + 20, and t + 60, TEMPER obtains 2.824% mean CRPS normalized by origin level, 3.635% median absolute error, and 68.8% empirical 90% interval coverage after training with a 300-epoch cap and early-stopping patience of 100. A naive persistence bootstrap has the best aggregate CRPS, 2.763%, while TEMPER has the best median absolute error and the best CRPS at t+1 and t+5. The ablation study uses matched series-origin-horizon cells, horizon-wise CRPS deltas, endpoint sensitivity summaries, and a calibration-specific interval study. Relaxing the learned mask improves average CRPS by 0.472 percentage points on the ablation subset, mainly through long-horizon gains. A twofold interval inflation improves held-out coverage from 54.2% to 91.7% and gives the best 90% interval score among tested calibration rules. The results identify calibration, horizon-specific tuning, and component selection as the central research priorities. --- ### When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems Authors: Li Zhang, Yang Sun, Jie Shi Published: 2026-09-20 Categories: cs.CR, cs.AI, cs.OS arXiv: https://arxiv.org/abs/2609.23700v1 Large language model agents are now privileged principals that take consequential actions: editing code repositories, operating inboxes, completing purchases. Their authority is kernel-grade, but it comes without what classical systems security requires: a trusted mediator interposed on every access. Operating-system vendors are now rebuilding the platform around this de-facto agent kernel, inheriting complete mediation as a design problem. We systematize the security of such systems around a single distinction: a crossing mediated over provenance admits a deterministic check, while one over content semantics does not. A trust-boundary taxonomy locates where mediation must occur and isolates the central mediation gap at two kinds of semantic judgment: distinguishing data from instruction in untrusted input, and an authorized action from an unauthorized one. We argue that this gap leaves an irreducible residual of undetected attacks wherever inputs and actions are not restricted in advance to an enumerated set. The same distinction makes attack-success statistics actionable, placing each number on a spectrum from deployment debt (a sound deterministic mediator left unused) to a structural gap (no such mediator known). We systematize defenses across runtime monitoring, architectural separation, and authorization, and show that current evaluations tend to overstate deployed security through evaluation-validity failures. Finally, we carry that analysis forward beyond the de-facto kernel, to an architecture in which the model itself becomes the arbitration core, and derive the design constraints, open challenges, and research agenda for a security-first AI-native OS. --- ### Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation Authors: Jie Sun, Mao Zheng, Mingyang Song, Zeyuan Liu, Gengsheng Li, Houcheng Jiang, Yilin Cheng, Bichuan Feng, Yuchen Cai, Junfeng Fang, Xiang Wang Published: 2026-09-20 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.23697v1 Multi-teacher on-policy distillation allows a student to learn from complementary specialists on its own trajectories. Domain-routed approaches, however, select one teacher per example and keep it fixed throughout the response. This design both depends on labels that mixed training corpora often lack and cannot adapt teacher selection when the expertise required changes within a trajectory. We propose \textbf{TrustMOPD}, which replaces example-level teacher selection with label-free, token-level supervision allocation. At each student-generated prefix, TrustMOPD uses each specialist's RL-induced displacement from a shared pre-RL reference as a proxy for local reliability, calibrates these scores across teachers, and constructs a weighted distillation target. Across mathematics, code, and instruction following, TrustMOPD outperforms the strongest label-free baseline, increasing the recovery ratio from $54.4\%$ to $91.5\%$ on \textsc{SingleCap} and from $54.5\%$ to $98.0\%$ on \textsc{MultiCap}, while approaching label-based MOPD on \textsc{SingleCap}. Randomizing token-level weights independently of the student-generated prefix performs no better than uniform weighting, supporting the importance of conditioning supervision on the evolving generation context. --- ### PhysAI-Bench: A Benchmark for LLM-Based Agentic Decision-Making in Autonomous UAV-Centric Physical AI Authors: Mohamed Amine Ferrag, Merouane Debbah, Abderrahmane Lakas, Manu Perumkunnil, Norbert Tihanyi Published: 2026-09-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23695v1 Recent advances in Physical AI have accelerated the use of foundation models in autonomous systems such as unmanned aerial vehicles (UAVs), which must perceive, reason, plan, and act in dynamic environments. Existing benchmarks assess physical perception, intuitive physics, embodied navigation, and collaborative reasoning, but rarely evaluate the agentic decision-making required for reliable autonomy. We introduce \textit{PhysAI-Bench}, a benchmark for evaluating this capability. It contains 10,178 standardized decision instances automatically extracted from conversational traces of autonomous UAV missions. Each instance preserves mission context, temporal dependencies, physical constraints, Model Context Protocol (MCP) tool calls, Agent-to-Agent (A2A) interactions, sensor observations, and AI-native 6G network conditions, including latency, packet loss, throughput, edge load, and network slicing. We expose only information preceding each decision, preventing future-event leakage and approximating online decision-making. We evaluate 29 foundation models using a two-stage protocol. We select model-specific configurations from 12 combinations of zero-, three-, and five-shot prompting and four temperatures, tested in three runs on a 35-instance, human-verified development set. We then freeze each selected configuration and evaluate it in three runs on a fixed, episode-disjoint set of 500 instances. GPT-5.3 achieves the highest accuracy (52.00%), followed by GPT-5.2 (49.40%) and Grok~4.5 (49.07%). Few-shot prompting generally improves performance, while temperature has limited influence. The results demonstrate that reliable agentic decision-making in Physical AI remains an open challenge. The dataset is available at https://github.com/maferrag/physai-bench --- ### Tail-Weight Control and Localized Generalization in Nearly Low-Rank Adversarial Classification Authors: Kunyu Wang, Dehan Wang, Wenjun Chen Published: 2026-09-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.23688v3 Empirical ramp fitting can assign weight to pure-noise features even when the population optimum ignores them. We quantify this gap for norm-constrained adversarial classification with Gaussian signal and noise. The variance cost relative to normalized signed mean separates into two factors: selecting observations inside the active margin window and the curvature induced by the norm constraint. Changing the tail variance leaves the activewindow probability unchanged but changes the second factor. With positive attack budget and a signal-only predictor of risk below one half, we prove a uniform quadratic tail-deletion bound, including at zero tail variance. Sufficiently accurate approximate global empirical minimizers admit exact fixeddimensional asymptotic covariances in the low-risk regime with isotropic principal covariance. For positive tail variance at most principal variance, the product exceeds one; an additional moment condition transfers it to expected excess ramp and robust classification risks. A wide window analysis characterizes when this ordering reverses. Controlled experiments test the decomposition, and a separate contamination study examines its scope outside the Gaussian training model. --- ### A multi-temporal dataset for mapping burned areas in the Brazilian Cerrado using time series of remote sensing imagery Authors: Alisson Cleiton de Oliveira, Thales Sehn Körting Published: 2026-09-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.23687v1 This paper introduces a multi-temporal tabular dataset derived from satellite images to map burned areas in the Chapada dos Veadeiros National Park, in Goiás, Brazil, covering the years 2020 to 2022. The dataset contains blue, green, red, and near-infrared bands, as well as the BAI, EVI, GEMI, NDVI, and NDWI spectral indices from the WFI sensor on the CBERS-4A, CBERS-4, and AMAZONIA-1 satellites, organized into a regular grid. We applied the Random Forest classifier to develop and validate models based on samples labeled as totally burned, partially burned, and non-burned. Two classification approaches were tested: one combining burned and non-burned areas into binary classes and another distinguishing between totally burned (TB), partially burned (PB), and non-burned (NB) classes. Seven validation approaches assessed different post-classification combinations, focusing on accuracy, precision, recall, and intersection over union (IoU) metrics. Results showed higher IoU when TB, PB, and NB were used as individual classes and TB was reclassified as burned area (BA) while PB and NB were grouped as non-burned. Comparing the annual results of this approach to the MCD64A1 product, the errors of omission for the BA class were 22% in 2020, 28% in 2021 and 59% in 2022, while the errors of commission were 46%, 43% and 46%, respectively. The study highlights the utility of the WFI sensor for burned area mapping without inter-satellite spectral calibration and suggests further exploration with other machine learning algorithms to evaluate the dataset potential and limitations. --- ### One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting? Authors: Ziang Li, Yue Huang, Guoxu Zhou, Na Han, Jie Wen, Lunke Fei, Xiaozhao Fang Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23686v1 Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. We ask which of these roles can be adjusted separately. A supporting atomic-encoding study finds greater sensitivity to model width than to atom grouping on the evaluated grid. Our main finding is that a frozen parent's recursive trajectory is easier to fit than the observed future with lightweight parallel exits. Autoregressive Trajectory Distillation (ATD) turns this into selectable ATD-1/2/4/8 execution, with ATD-1 exactly recovering the parent. On a paired four-data-set comparison, ATD-8 reaches $5.54\times$ end-to-end speedup with stable quality across widths. Fewer calls do not automatically remove the parent's existing forecast error: ATD improves trajectory fidelity in all 21 seed runs but forecast accuracy in only 15 against matched clean-future supervision. We further find a correctable residual projection along a train-selected periodic history direction. Spectrum Tangent applies this correction without adding neural parameters or Transformer calls. At horizon 720, it reduces mean squared error (MSE) and mean absolute error (MAE) by 2.54% and 2.33% over seven data sets and two output widths, while remaining $3.24\times$ faster than recursive inference. Level and shape projections sometimes disagree. Trajectory compressibility, the fidelity-accuracy mismatch, and the correction recur across three public AR parents. Together these results separate representation, transition, and execution as AR design axes. Code is available at https://github.com/RowanFFF/ATD-Spectrum-Tangent. --- ### Smoothed Analysis of Inconsistent A* Authors: Zhiyang Chen, Hailong Yao Published: 2026-09-20 Categories: cs.DS, cs.AI arXiv: https://arxiv.org/abs/2609.23680v1 The A* search is a fundamental path-finding algorithm in artificial intelligence. While admissible and consistent heuristics guarantee efficient performance by expanding each state at most once, modern search applications frequently employ powerful but inconsistent heuristics derived from machine learning, randomized evaluations, etc. A long-standing theoretical barrier to using these inconsistent heuristics is the risk of catastrophic node re-expansion, which yields a worst-case exponential time complexity of $Ω(2^n)$. However, empirical observations contradict this pessimistic bound, demonstrating that inconsistent A* operates highly efficiently in practice. To bridge this significant gap between theory and practice, this paper presents the first smoothed analysis of the A* algorithm using inconsistent heuristics. We model typical real-world noise by applying slight random perturbations to the edge weights of worst-case search graphs. Our main result proves that the expected smoothed time complexity of inconsistent A* is bounded by a polynomial, specifically a total iteration number of $O(n^2 m κ)$, where $n$ is the number of nodes, $m$ is the number of edges, and $κ$ controls the scale of random perturbations. Furthermore, we also show that this result naturally extends to the functionally equivalent problem of Dijkstra's algorithm on negative-weight graphs. --- ### Mind the Gaps: A Curated Benchmark for Form Field Detection Authors: Iheb Brini, Omar Moured, Hamza Gbada, Elisa Barney Published: 2026-09-20 Categories: cs.CV, cs.DB arXiv: https://arxiv.org/abs/2609.23679v1 Form Field Detection (FFD) is a fundamental component of document understanding systems, enabling applications ranging from large-scale industrial digitization to accessible form interaction for automated analysis. Unlike conventional object detection tasks, FFD is inherently challenging because fields are often defined by layout structure and whitespace rather than visible foreground content. Existing large-scale datasets frequently rely on heuristic annotation pipelines, resulting in noisy and inconsistent labels that hinder reliable evaluation. In this work, we introduce mini-CommonForms, a carefully curated FFD benchmark with consistent, high-quality annotations, and present a detailed evaluation of state-of-the-art detection approaches. The benchmark is designed to support reproducible research in document automation and accessibility-oriented applications. Dataset and code are available at https://github.com/moured/mini-commonforms --- ### Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking Authors: Ji-Hoon Hwang, Jisung Bae, E-In Son, Dong-Wook Kim, Jung-Taak Kim, Seung-Woo Seo Published: 2026-09-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.23673v1 In vision-based off-road navigation, a robot needs to know not only which obstacles to avoid but also which terrain is better. The first is handled by freespace detection or semantic segmentation. The second is usually answered with a traversability score, but no universal ground truth exists for such a score, so perception falls back on a predefined value per semantic class or a freespace confidence. These scores say what a region is, not which region a robot should prefer. We therefore formulate this preference as visual traversability ranking, an ordering of visible terrain that can be supervised by comparisons between two regions. Standard annotations do not label preference, but they imply its direction. We present TravPro, which converts these annotations into ordered region pairs and fits a small readout on frozen vision--language model (VLM) patch tokens to these pairs. The tokens are clustered once into a fixed prototype bank, and the readout learns a preference score per prototype. The readout is then applied to every patch and serves as a teacher that turns sparse comparisons into dense preference pseudo-labels without pixel-wise annotation. An RGB student distills these maps into a dense terrain-preference map together with a non-ground mask that excludes obstacles and background from the ranking. On five unseen domains, TravPro reaches a mean pairwise accuracy of 0.915 against 0.783 for the strongest baseline, producing an ordering sensitive to surface condition that a per-class value cannot represent. The same VLM and the same supervision yield no such ordering when the VLM is prompted and the supervision is used as dense targets; what matters is how they are used. --- ### Fast Graph Laplacian Estimation using Effective Resistance Authors: Christoffer Kjellson, Claudio Altafini, Emma Tegling Published: 2026-09-20 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.23668v1 Inferring network topology from noisy node observations is a central problem in graph signal processing. In this paper, we consider Laplacian-constrained graph estimation for Gaussian Markov random fields, focusing on the underdetermined regime in which the number of samples is smaller than the number of graph nodes. Existing approaches often formulate the problem as a sparsity-regularized maximum-likelihood estimation problem. While effective, such methods typically require iterative optimization and are often computationally demanding, particularly under Laplacian constraints. Instead, we propose a non-iterative estimator of graph Laplacians that uses effective resistance for regularization, and evaluate the method using a simple sparsification procedure. Experiments show that with some trade-off in edge and weight recovery on the considered dataset, computational cost for moderately sized graphs can be substantially reduced. --- ### Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation Authors: Haoyue Liu, Ye Chen, Zhichao Wang, Xiaoyu Ma, Haoran Shou, Xiaoying Tang Published: 2026-09-20 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.23665v1 Constraint-following music generation asks a score to satisfy several user-specified properties at once, each checkable programmatically (key, meter, length, range, final note, rhythm, motion and form), yet no existing benchmark isolates this capability. We construct MusicConstraintBench, 2,180 items over eight constraint families, on which current models fail once a few constraints are combined. The natural remedy is reinforcement learning with these verifiers as reward, yet we observe that a reward paid only when every property holds leaves most training groups without a learning signal: over the first 50 updates, 0.550 of rollout groups score identically and receive no gradient, even though a failing score typically misses only one requested property. Under the joint criterion, rollouts for a prompt tend to fail together, so a binary reward cannot separate a nearly correct score from a malformed one. We therefore introduce MusicRLVR, which pays graded per-property credit behind a hard validation gate that rejects malformed outputs, plus a joint-satisfaction bonus, requiring no human annotation, learned reward model, or music-domain fine-tuning. On MusicConstraintBench, MusicRLVR lifts Qwen3-4B-Instruct from 0.160 to 0.807 on mixed constraints and leads every zero-shot baseline including Llama-3.1-70B at 0.380. It also generalises to property combinations unseen in training and to out-of-range parameter values, showing that verifiable rewards need not presuppose a target output. --- ### ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift Authors: Kemal Kirtac, Carsten Maple Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23659v1 Ethereum decentralized finance (DeFi) provides a public, time-stamped record of transaction-level event streams, but the same public symbols can create strong machine-learning shortcuts. We introduce ETH-TraceBench, a benchmark for evaluating Ethereum DeFi representations under temporal, protocol, pool/infrastructure, and symbolic shift. The raw event universe covers January 2021-December 2025 and contains 1.35 billion transactions with logs and 5.01 billion raw log rows. Model evaluation uses a fixed 911,267-instance supervised sample, training on 2021-2024, selecting models on 2025H1, and testing on 2025H2. Simple models perform strongly on the aggregate temporal test: TraceStats-GB reaches 0.953 macro-F1 and TopicEmitterHashMLP 0.959 on the canonical DEX test set. Performance drops sharply under protocol novelty, with macro-F1 of 0.794, 0.743, and 0.766 for TraceStats-GB, TopicEmitterTrace-SGD, and TopicEmitterHashMLP, while strict unseen-pool scores remain 0.927, 0.897, and 0.935. Uniswap v4 and Ekubo v1, both absent from supervised training, are materially harder than the full test. Jointly masking emitter and topic identity reduces DEX macro-F1 to 0.916 and liquidation macro-F1 to 0.774 for TopicEmitterTrace-SGD. A standard Transformer over log-index-ordered events provides no consistent advantage over a deterministic shuffle of the same events, indicating that high aggregate scores can arise without sophisticated chronological modeling. A natural-prevalence audit estimates 2025H2 DEX prevalence among logged Ethereum transactions at about 22.5%, and a deterministic 400-transaction audit finds complete agreement with task label sources and independently re-queried raw-log counts. ETH-TraceBench therefore treats difficult transfer and controlled-input conditions, rather than a single aggregate score, as the main evaluation target. --- ### Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms Authors: Yueyan Li, Haibo Wang, Caixia Yuan, Xiaojie Wang Published: 2026-09-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.23658v1 Despite impressive visual quality, state-of-the-art video diffusion models often generate content that violates real-world physical laws. While existing solutions rely on external priors or specialized data, we investigate the root cause by exploring the internal mechanisms of these models. Specifically, we present the first interpretability study on the ''motion planning'' process of text-to-video diffusion models, revealing how motion trajectories form during early denoising stages. Building upon the ''first shape, then details'' finding, we combine cross-attention trajectory patterns with causal head contributions to identify a specific subset of attention heads driving motion planning. Further, our self-attention analysis shows that Rotary Position Embedding (RoPE) induces excessive spatial attention decay. This causes early candidate regions to prematurely lock into physically implausible positions, suppressing reasonable trajectories in adjacent frames and triggering generation failure modes. To address this fundamental flaw, we propose a lightweight architectural modification that scales the frequency of RoPE across different denoising steps. This strategy reduces excessive attention decay, helping the model explore better candidate regions to establish coherent physical motion. Finally, training-free and training-based experiments confirm the effectiveness of our approach in enhancing the physical commonsense of generated videos. --- ### Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains Authors: Kiran Naseer, Samreen Azhar, Dwarikanath Mahapatra Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23655v1 Imbalanced gradient magnitudes between the visual and language pathways of a vision-language model are often treated as a defect to be corrected. We test that premise for one family of correction, deliberately excluding adaptive, signal-driven schemes (e.g. BalGrad, OGM, PMR, CGGM), which are a mechanistically distinct class outside this study's scope. Measuring the language-to-visual gradient-norm ratio, reported in parameter-normalised form, across nine fine-tuning conditions, three seeds, and three captioning datasets spanning distinct physical domain shifts -- underwater, aerial, radiological -- we find imbalance magnitude varies markedly across domains with no predictable ordering. A plain learning-rate reduction cuts imbalance substantially and lands within a few BLEU points of the best method on every dataset. Staged freezing reduces the ratio on every domain yet never ranks first; a schedule-only control isolates freezing as the cause on one dataset but not the other two. Forcing the two gradient groups to equal magnitude drives per-parameter imbalance close to zero on every domain, yet is both the best result in the study and the worst placement among full fine-tuning methods, on different datasets, with identical settings. Reductions in gradient-norm ratio do not consistently predict captioning performance across domains, and how a given level of balance is reached matters as much as the level itself. As a secondary finding, a commonly reused LoRA configuration applied to BLIP silently adapts zero visual parameters; correcting it improves BLEU-4 on all three datasets. --- ### Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models Authors: Shuaijun Liu, Feiyang You, Chengyu Wu, Shuyang Hao, Chenglong Zhang, Jingyao Cai, Xingwei Chen, Ningxin Su Published: 2026-09-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.23650v1 Vision-language-action (VLA) models have achieved strong performance in embodied manipulation, but still lack a clear mechanism to balance behavioral stability with task-semantic sensitivity. We identify two complementary failure modes. Under task-preserving changes, where task semantics remain unchanged but scene appearance varies (e.g., style, illumination, clutter, or paraphrasing), policies often exhibit unnecessary action drift. Conversely, under semantic-breaking changes, where key task semantics such as the target object or constraint are altered, policies frequently fail to produce sufficiently distinct behaviors and instead follow the original trajectory. To address this gap, we propose BAS-VLA, a task-semantic action calibration framework built on top of a frozen base VLA. BAS-VLA adopts a breaking-centered calibration core as the default path, and introduces a selective evidence-gated preserving auxiliary that activates only when nuisance variation is detected while task semantics remain consistent. On the OpenPI-pi0.5 / LIBERO-Object Milk-Swap benchmark, BAS-VLA maintains high success on clean (98.0%) and semantics-preserving conditions (97.5%), while reducing clean-criterion success to 0.0% under deliberate target-object swaps, demonstrating strong stale-task suppression and task-semantic separation. On validated style-preserving shifts, it improves success from 42% to 70% without degrading clean performance. These results highlight that reliable VLA behavior requires moving beyond appearance robustness toward explicit task-semantic action calibration. --- ### Beyond Relevance: Structured Semantic Supervision for Product Search with LLM-Augmented Annotations Authors: Girish A. Koushik, Swapnil Bhosale, Samarth Agrawal, Hadeel Sadany, Constantin Orasan, Xiatian Zhu, Diptesh Kanojia Published: 2026-09-20 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2609.23646v1 E-commerce search requires distinguishing products that are merely related to a query from those that directly satisfy the user's shopping intent. We augment query-product pairs with structured LLM-generated query and product attributes and human-validated relevance, explanations, and centrality judgments, and evaluate these signals using a simple dual-encoder retriever and MLP re-ranker. On an augmented subset of ESCI, a human-feature oracle reaches $0.9382$ nDCG@10, while a human-free trained $Q+P$ configuration reaches $0.9258$. Synthetic approximations of the human signals reach $0.9150$ overall but provide substantial gains for difficult, low-performing queries. Ablations show that most of the oracle improvement comes from post-edited explanations and annotator comments rather than the scalar centrality feature, suggesting that LLMs are most useful for exposing and approximating structured semantic supervision rather than replacing human judgment directly. --- ### Spiking Neural Network Actor-Critic Proximal Policy Optimization Control for Autonomous UAV Navigation Through Constrained Openings in Civil Infrastructure and Buildings Authors: Francis Noah Walugembe, Maciej Wielgosz, Tomaž Goričan, Matej Mertik Published: 2026-09-20 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.23643v1 Autonomous navigation of unmanned aerial vehicles in constrained three-dimensional environments has been a challenge in the robotics domain. The application of autonomous unmanned aerial vehicles in civil infrastructure inspection involves the use of such vehicles in bridge inspection, tunnel inspection, and structural inspection. The use of deep reinforcement learning in the autonomous navigation of unmanned aerial vehicles has been successful in constrained environments. However, the computational cost of the algorithm limits the application of the algorithm in the autonomous navigation of unmanned aerial vehicles. This paper proposes the use of the spiking neural network-based Proximal Policy Optimization algorithm in the autonomous navigation of unmanned aerial vehicles in constrained sequential environments. The proposed algorithm integrates the use of spike-based actor-critic reinforcement learning with the Proximal Policy Optimization algorithm. The proposed algorithm uses the stochastic Gaussian policy in the autonomous navigation of unmanned aerial vehicles. The proposed algorithm was implemented in the autonomous navigation of unmanned aerial vehicles in constrained 3D environments. The proposed algorithm was successful in completing 1913 episodes out of more than 3000. The proposed algorithm was successful in passing an average of 2.10 windows per episode. The proposed algorithm was successful in achieving a success rate of 63.77%. The proposed algorithm was successful in achieving success rates of more than 90% in the later stages of the algorithm. --- ### Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment Authors: Suqin Yuan, Runqi Lin, Muyang Li, Guanzhe Hong, Jindong Gu, Lei Feng, Chris Russell, Tongliang Liu Published: 2026-09-20 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.23640v1 Human-feedback alignment has made language models useful assistants and is commonly described as aligning them with humans. However, the responses people prefer from an AI need not be the responses they themselves would give. We distinguish alignment with human preferences from alignment with human behavior, and show that alignment with human preferences can make model behavior less human-like even when both preferences and responses come entirely from humans. We call this the Turing-test gap. We show that preference alignment preserves the human response distribution only under a restrictive condition, and find no consistent evidence that real human preferences satisfy it. Empirically, the loss of human-response likelihood increases with the strength of preference weighting, regardless of its direction, and the gap also appears under standard DPO. These results establish human-likeness as an explicit dimension of alignment rather than something assumed to follow from preference alignment. --- ### Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion Authors: Kazuma Fujiwara, Takuya Funatomi, Kazuya Kitano, Yuki Fujimura, Yasuhiro Mukaigawa Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23619v1 Snapshot hyperspectral imaging avoids sequential scanning, but systems that jointly achieve stable reconstruction, low cost, and compact optics remain limited. We present a snapshot hyperspectral imaging system based on angular-to-spectral diversity conversion. A tapered kaleidoscope creates replicated views with distinct incidence directions, and a directly attached birefringent filter converts them into view-channel-dependent spectral transmittances, yielding complementary measurements that better condition the inverse problem for more stable single-shot spectral reconstruction. The system preserves a simple pixel-wise linear model for fast non-learning-based reconstruction and uses only off-the-shelf components without relay optics or cascaded modules. We select the birefringent filter configuration using a condition-number-based criterion and validate the system on both synthetic and real data. --- ### Beyond UV Mapping: Mesh Texture Compression via Surface-Aligned Texture Fields Authors: Jianqiang Wang, Junhui Hou, Siyu Ren, Weiyao Lin, Wenping Wang Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23606v1 Mesh texture compression typically relies on 2D UV atlases, whose chart discontinuities and mapping overhead can limit coding efficiency. To tackle this challenge, we introduce TexF, a surface-aligned texture field that organizes texture attributes in sparse voxels derived from the mesh surface. This representation supports high-resolution textures while preserving local 3D correlations for compression and enabling direct surface queries. For bitstream compression, TexF reuses established 3D attribute codecs, with voxel locations reconstructed from the decoded mesh without separate transmission. For GPU-resident compression, we develop 3DNTC, which combines quantized hash features with a lightweight decoder for random-access reconstruction at surface positions. Differentiable rendering enables image-space refinement of both voxel attributes and compressed neural fields. Experiments on the MPEG and AOM mesh compression benchmarks demonstrate improved average rate-distortion performance over representative UV-based methods for both bitstream and GPU-resident compression. 3DNTC also supports real-time rendering. --- ### PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding Authors: Siru Zhong, Qiongyan Wang, Xiaohui Lv, Yuzheng Zhuang, Shuai Tao, Wulong Liu, Haohuan Fu, Yuxuan Liang Published: 2026-09-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.23601v1 Long-video understanding must capture transient visual evidence under strict token budgets, yet existing methods compress frames, append memory tokens, or alter internal key-value (KV) caches. We introduce Prefix-Steered Recurrent Memory (PREM), a memory-token-free framework for frozen vision-language models (VLMs). PREM separates video ingestion from query answering: a recurrent writer distills visual streams into a compact 256 KiB multi-slot associative state, while a question-conditioned readout adds memory-derived key/value (K/V) steering modulations to existing non-visual prompt prefixes during prefill. This enables write-once, query-many inference without extra prompt tokens or decoding recurrence. Across six long-video benchmarks in offline and streaming end-of-stream settings, PREM consistently outperforms frozen baselines at every evaluated visual budget. Under a constrained budget of 16 frames, PREM improves macro-average accuracy by 3.06% on Qwen2.5-VL-3B, with gains of 11.0% on action antonym identification and 9.9% on localized needle retrieval. These gains require tuning 0.24% of backbone parameters at 0.03 GiB of peak GPU memory overhead. --- ### PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models Authors: Weihan Cai, Hao Tan, Xinping Gao, Shibiao Xu, Jun Wan Published: 2026-09-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.23600v1 Prompt learning efficiently adapts vision-language models (VLMs) to downstream tasks, but gains on seen classes often come at the expense of generalization to unseen classes. To address this limitation, we propose prompt ensembling with training-free routing (PETR), whose key innovation is a carefully designed dual-prompt architecture: two complementary prompts are learned from different data and objectives to emphasize seen class discrimination and unseen-class generalization, respectively. During training, both prompts are fine-tuned using a shared frozen CLIP backbone, and statistical information is collected from the training set logits. At inference time, we determine the similarity of each test sample to seen data, and route the sample to the most appropriate prompt branch. To the best of our knowledge, this is the first prompt tuning framework that performs training-free adaptive routing based on statistical similarity. This design provides an interpretable routing signal and avoids common MoE-style routing pathologies, such as router training instability and load imbalance. Extensive experiments on 11 benchmark datasets demonstrate that our framework consistently outperforms previous methods on both seen and unseen classes, achieving new state-of-the-art results. --- ### StyleAT: Defending Face Recognition Against Semantic Attacks Authors: Ben Shapira, Roi Cohen, Shang-Tse Chen, Mahmood Sharif Published: 2026-09-20 Categories: cs.CV, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.23596v1 With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models remain acutely vulnerable to adversarial semantic edits. I.e., adversarially produced semantic alterations to the input, such as slight aging or pose changes, can induce misclassifications. Certain existing attacks are powerful, but they can be computationally costly, rendering them inadequate for developing defenses (e.g., through adversarial training). To fill the gap, we introduce BoundStyle, a potent semantic attack operating in StyleGAN's rich latent space to maximize misclassification rates. Notably, BoundStyle achieves high attack success rates while being ${\sim}{\times}9.5$ faster than existing state-of-the-art attacks, making it suitable for adversarial training. Building on BoundStyle, we develop StyleAT, an efficient adversarial training scheme that incorporates low-budget attack variants yet defends against stronger and unseen semantic attacks. We evaluate on two datasets unseen during training and seven models, and find that StyleAT boosts robust accuracy against state-of-the-art attacks and outperforms common defenses in various settings. --- ### Bilinear Optimization Divergence: Diagnosing Factor-Constrained LoRA Continual Learning Authors: YongShun Wang, JianLin Su, Yong Ma Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23594v1 Orthogonality in a LoRA factor does not by itself specify what the composed update protects: the answer depends on the task-start state, the parameterization, and the realized optimizer displacement. We formalize this question through Bilinear Optimization Divergence (BOD), an anchor-relative diagnostic of effective-update response on selected historical features. The finite-step analysis distinguishes two cases. In a shared adapter, protecting the routing displacement leaves a learned-anchor residual through the changing companion factor. In a fresh zero-output block, a feasible routing state can protect the composed update while both current factors remain trainable. These conditions yield Semi-Frozen Orthogonal Routing (SFOR) for shared adapters and current-block hard protection for cumulative O-LoRA; Weight Residual Projection (WRP) enforces the required displacement after the optimizer step. Controlled two-task traces verify the predicted residual paths, reducing normalized historical response from 19.12% to 0.005% in the shared family and from 7.72% to 0.002% in the cumulative family. Four-task experiments on Qwen3-8B characterize the resulting trade-offs: SFOR improves backward transfer (BWT) from -2.47 to -0.86 with nearly unchanged average accuracy (AA), while O-LoRA hard protection improves three-order mean AA from 80.27% to 81.30% and forgetting measure (FM) from 2.20 to 0.43. Component controls also show that stricter feasibility need not improve final task performance. Together, the analysis and evidence provide an architecture-conditioned account of which constraint to enforce, how to enforce it, and how to interpret its empirical value. --- ### Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing Authors: Xingyu Lin, Dehui Du Published: 2026-09-20 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2609.23592v1 End-to-end document parsers increasingly offer an optional reasoning mode for complex pages. On a 180-page entropy-stratified discovery sample with one frozen 4B checkpoint, complexity is the wrong decision variable. Reasoning lowers mean quality by 2.21 Overall at 1.54x tokens; a preregistered input-only model cannot predict its signed benefit (held-out AUROC 0.47, indistinguishable from chance). The benefit concentrates on pages whose ordinary pass has already collapsed, and they do not look complex: shared collapses have lower layout entropy than healthy ones yet consume 19x the tokens as degenerate repetition that doubling the budget does not cure. Switching modes rarely repairs them: 83% recur under reasoning. We instead detect collapse from the ordinary-pass trace, decompose the page by projection, and re-parse each region. Repair gains 1.40 Overall (95% CI (0.68, 2.16)) at 1.13x tokens, replicates across three checkpoints, and, with all parameters frozen, gains 2.41 (CI (1.64, 3.46)) on the remaining 1,175 benchmark pages. --- ### Cost-Aware Reinforcement Learning with Action Masking and Projection for Battery Energy Storage Dispatch under Suppressed-Spread Market Shifts Authors: Kuanlin Chen, Chen-Wei Kuo, Cheng-En Ou Published: 2026-09-20 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2609.23590v1 Battery energy storage system (BESS) dispatch must preserve operational feasibility while declining price spreads reduce the margin available to pay for cycling. We study a proximal policy optimization (PPO) controller whose pre-selection physical action mask and emergency projection are separated from a causal, forecast-informed economic advisory. All forecast-dependent methods receive the same causal 24-step forecast and grid-side settlement. Across five PPO seeds, advice-on net profit is 30.59 and 18.04 USD per 336-hour T1 and T2 window, versus 36.77 and 22.94 USD for proxy-cost MPC; PPO remains below this reference in both periods. Advice raises T2 profit from 16.45 to 18.04 USD while reducing throughput, but is immaterial in T1. On disjoint weekly blocks, PPO is stable under daily, weekly, and blended seasonal forecasts, weakens under persistence, and remains below proxy-cost MPC. Paired diagnostics localize changes to the observed 5-10 USD/MWh regime with mixed SoC-dependent effects. An M0-M6 ablation shows that mask removal sends thousands of infeasible requests to projection, while removing both physical layers exposes ramp violations. The evidence separates economic screening from feasibility enforcement without claiming formal safety, lifecycle-optimal aging, or RL dominance. --- ### Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models Authors: Jiaheng Dong, Xiaofeng Yu, Jean Honorio, Abhirup Ghosh, Hong Jia, Ting Dang Published: 2026-09-20 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2609.23589v1 Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio representations into a large language model (LLM) backbone to enable multimodal reasoning. Recent test-time reinforcement learning (TTRL) methods further improve LLM reasoning capability by leveraging unlabelled test data after pre-training. However, the importance of the perceptual capability of LALMs remains underexplored, particularly how much acoustic evidence is integrated and relied upon during reasoning, and how this contributes to final task performance. This gap limits the development of effective post-training methods like TTRL for audio reasoning. In this work, we first analyse how audio information is integrated and utilised during reasoning process. We quantify layer-wise perceptual reliance and show that stronger acoustic reliance is associated with higher accuracy and a larger performance gain attributable to the audio input. Building on this, we propose Perception-Grounded TTRL (PG-TTRL), which aligns label-free test-time optimisation with perceptually grounded reasoning, encouraging the model to structure its reasoning more strongly on the audio input. Experiments across LALMs and benchmarks show that PG-TTRL consistently improves reasoning performance over both the base models and standard TTRL, showing the value of perceptual-grounding optimisation for test-time audio reasoning. --- ### On the Efficiency-Safety Dilemma in Large Reasoning Models Authors: Yifei Yang, Zouying Cao, Xingrui Wang, Xiao Zhou, Yuexian Li, Dongjie Yang, Hai Zhao Published: 2026-09-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.23587v1 Large reasoning models (LRMs) incur high inference costs, often mitigated by efficiency techniques like quantization and pruning. However, the impact of these techniques on model adversarial robustness remains largely unexplored. This study provides the first comprehensive analysis of the interplay between efficiency, jailbreak vulnerability, and reasoning in LRMs. We find that while efficiency methods seemingly reduce the success rate of jailbreak attacks, this improvement is often superficial. It largely arises from degraded reasoning capabilities leading to "attempted but failed" malicious responses, rather than an increase in genuine alignment. Mechanistic analysis of representational drift confirms this, revealing a strict coupling between reasoning capability loss and the model's inability to maintain malicious semantic trajectories. Additionally, we identify quantization with pruning as the optimal strategy to balance efficiency and robustness. These findings clarify the distinction between true safety alignment and capability-induced failure, providing an empirical foundation for LRM deployment. --- ### An Efficient and Effective Watermarking Scheme for the Protection of the Intellectual Property Rights of Video Generative Models Authors: Wenhong Huang, Jianwei Fei, Benedetta Tondi, Bin Ma, Fangjun Huang Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23586v1 The rapid development of video generative models (VGMs) has enabled the generation of highly realistic synthetic videos, raising concerns about the intellectual property rights (IPR) of these models. In particular, two closely related forensic tasks remain largely unaddressed: synthetic video verification (determining whether a video was generated by a protected VGM) and model ownership verification (determining whether a suspect VGM is an unauthorized copy of a protected VGM). In this paper, we propose a new in-generation watermarking scheme that can address the two verification tasks. First, a novel video watermarking network named VidMark is presented, which incorporates a two-scale discrete wavelet transform (DWT) decomposition and a global temporal attention block (GTAB) to enhance watermark robustness and imperceptibility. Second, we present a decoder-guided fine-tuning procedure. By leveraging the frozen VidMark decoder, this process enables VGMs to synthesize videos carrying an imperceptible, robust, and model-specific watermark. Finally, two verification frameworks are established to perform synthetic video verification and model ownership verification. Extensive experiments on representative VGMs demonstrate that the proposed scheme achieves over 99% watermark extraction accuracy and 100% verification accuracy on both tasks, with negligible impact on video generation quality. Furthermore, the watermarks exhibit strong robustness against a comprehensive range of video-level and model-level attacks. --- ### Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only Quantization Authors: Kuanlin Chen, Chen-Wei Kuo, Cheng-En Ou Published: 2026-09-20 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.23585v1 Sink-aware deployment may identify important first-token attention heads before a model is quantized, then reuse that map at the edge. We test when this shortcut is safe for 4-bit NF4 weight-only post-training quantization (PTQ). Our Sink Topology Consistency (STC) metrics separate global rank preservation, top-$k$ set overlap, and layerwise sink-mass shift, and distinguish per-input sensitivity from calibration-map transfer. Across Qwen2.5-0.5B, Qwen2.5-1.5B, and Llama-3.2-1B, global bf16-to-4-bit ranks remain high at 4,096 tokens ($ρ_s \geq 0.980$), yet top-$k$ Jaccard overlap is only 0.619-0.793, corresponding to 76.5-88.5% membership retention. The global statistic also masks local failures: terminal Qwen layers shift by 6.2-7.9x their model means, whereas Llama-3.2-1B shows low, nearly uniform drift. Under a C4-to-LongBench shift, cross-domain overlap degrades more than the within-domain precision comparison for both Qwen models, but not for Llama-3.2-1B. Matched-domain 4-bit recalibration reaches 90% of a split-half stability plateau at the smallest tested $n=8$ for both Qwen models and $n=32$ for Llama-3.2-1B, though not as a sharp threshold; for the two Qwen models, updating only selected layers does not reach the full-map stability criterion. On Jetson Orin NX, the 16-sample workload takes seconds for the two models with valid on-device sink measurements. The practical message is precise: global rankings often transfer, but discrete head sets, layer-local policies, and cross-domain calibration should be revalidated after quantization. --- ### ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders Authors: Kuanlin Chen, Chen-Wei Kuo Published: 2026-09-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.23582v1 Maintenance work orders must often be processed offline on embedded hardware, yet downstream software requires predictable structured output. We present ARID (Aviation-inspired Routing for Industrial Deployment), which extracts component, failure mode, symptom, and maintenance action into fixed-schema JSON on an 8 GB NVIDIA Jetson Orin NX. ARID combines conservative dual-teacher filtering, targeted noise-aware synthesis, one routing decision per work order, 4-bit inference, and grammar-constrained decoding. From 2,326 unlabeled OMIn records, it retains 716 training pairs and adds 99 topology-constrained records targeting action extraction. On 300 human-labeled records, ARID reaches 84.8% token-F1 on the reference stack and 82.9% on the deployed Jetson. Resident serving achieves 5,310/5,656 ms P50/P99 at 12.5 W. On zero-shot MaintNet transfer, semantic F1 falls to 46.4% while parser success remains at least 99.8%, showing that output validity transfers but field semantics do not. --- ### PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models Authors: Qi Qin, Erbo Li, Ting Wei, Zizhou Huang, Zixuan Qin, Wu Wang, Yifan Sun Published: 2026-09-20 Categories: stat.ML, cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2609.23574v1 In high-dimensional tabular learning, feature screening provides a lightweight, model-agnostic way to remove irrelevant features before model fitting. However, scoring raw values directly can miss nonlinear or distributional structure. We introduce PACE (Plug-and-Play Contextual Embedding), which inserts a frozen tabular foundation model (TFM) column encoder before an existing feature-scoring rule, expanding each feature into a higher-dimensional contextual representation. Across controlled studies, PACE improves raw-space screening of complex nonlinear dependence with only modest additional encoding cost. These gains translate to downstream prediction on TALENT datasets: PACE-DC improves binary AUC by 0.077 and multiclass macro-AUC by 0.064, with a median normalized RMSE improvement of 0.063 across ten learners. Matched random-weight and random-feature controls show that PACE gains from pretrained structure beyond generic dimensional expansion. PACE further achieves favorable performance--time trade-offs against task-fitted selectors and attribution-based methods, positioning pretrained column geometry as a reusable upstream primitive for tabular learning. --- ### Error-Supervised Synthetic Learner Writing for Automated Essay Scoring Authors: Duy Anh Nguyen Published: 2026-09-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.23573v1 Synthetic essays can help reduce dependence on human-written data in Automated Essay Scoring (AES). However, they often lack realistic errors, limiting their ability to represent authentic human writing, particularly when the target texts are intended to resemble those produced by language learners. In this study, we present a simple approach that introduces error supervision into synthetic essay generation. Specifically, we fine-tune an LLM generator on error-annotated texts of the kind commonly used in Grammatical Error Detection (GED). To assess the utility of the proposed approach, we fine-tune and evaluate AES scorers under three data conditions: authentic essays, synthetic essays generated conventionally, and synthetic essays generated using our proposed approach. The results show that in the larger-data settings, the proposed approach outperforms the conventional synthetic baseline in 11 out of 12 dataset-metric comparisons, with performance in some cases approaching that of models trained on authentic essays. Despite these gains, performance under extremely low-resource settings remains mixed, with advantages over the conventional baseline only becoming more apparent at 200 training essays, although not consistently across datasets. Qualitative and quantitative analyses further show that the proposed approach produces learner-like errors whose distributions broadly resemble those observed in authentic essays. --- ### VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks Authors: Liyang Fan, Yingcheng Shi, Yongbin Li, Chenghao Sun, Xin Chen, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye Published: 2026-09-20 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2609.23570v1 Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluations do not show whether those systems improve executable repository work. Repository benchmarks test code changes but do not isolate memory, while memory benchmarks score recall without measuring downstream coding outcomes. We introduce VibeMemBench, a benchmark for evaluating memory systems on 111 coding targets from 90 SWE-rebench V2 repositories and 3,634 history trajectories from the target repositories. The targets follow the SWE benchmark style and cover bug fixes, feature requests, interface changes, and configuration work. An agent edits each target codebase under a declared memory condition. Executable tests decide task resolution. Each target is retained only when injected history experience improves its executable outcome in a reference setting, so every target carries a prior experience whose usefulness is verified by execution in that setting. The frozen verified experience is then transferred to five held-out solvers. Direct injection raises observed task resolution on four of them by 1.1 to 4.5 percentage points while lowering agent steps on all five. Yet when four existing memory systems must construct and retrieve experience from the same history, eleven of twelve solver and system pairings fail to exceed the matched memory-off baseline. VibeMemBench exposes the gap between the useful experience that repository history holds and the experience existing memory systems deliver for repository coding tasks. --- ### Contributions to the hierarchy of probabilistic languages Authors: Lothar Sebastian Krapp, Remo Nitschke Published: 2026-09-20 Categories: cs.FL, cs.CL, math.LO, math.PR arXiv: https://arxiv.org/abs/2609.23567v1 We reconsider the theory of probabilistic formal languages generated by n-gram models and by probabilistic context-free grammars (PCFGs). The expected hierarchy of probabilistic grammars is established by proving that every probabilistic language generated by an n-gram model is also generated by some PCFG, while some probabilistic languages generated by PCFGs cannot be generated by any $n$-gram model. We introduce the notion of fully connected PCFGs, namely PCFGs in Chomsky normal form where every production rule only involving non-terminals has non-zero probability. Our main result shows that any probabilistic language generated by an $n$-gram model differs from any probabilistic language generated by a fully connected PCFG. Therefore, the class of probabilistic languages generated by $n$-gram models is not a subset of the class generated by fully connected PCFGs. --- ### G6D: Geometric Learning-Free RGB-D 6D Pose Solver for Robotic Manipulation Authors: Yixuan Liang, William Chen, Yunan Wang, Jizhou Yan, Zhao Jin, Changling Liu, Chuxiong Hu Published: 2026-09-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.23566v1 6D object pose estimation is fundamental to robotic manipulation and automation. Recent zero-shot methods have significantly improved generalization to unseen objects, but most still rely on large-scale pretrained models with substantial GPU computation and memory demands. These requirements complicate deployment on robotic platforms where perception, planning, and control share limited computational resources, while learned intermediate representations offer limited geometric interpretability for task-specific adaptation. To address these limitations, we propose G6D, a learning-free, geometry-driven RGB-D 6D pose solver. Given an RGB-D observation, an object instance mask, camera intrinsics, and a CAD model, G6D generates pose hypotheses through template-based geometric matching and refines them using silhouette and depth consistency, forming a purely geometry-driven pose estimation paradigm. This paradigm requires neither pretrained visual models nor target-specific training and preserves interpretable geometric representations throughout pose estimation. Moreover, adjustable hypothesis counts provide flexible accuracy-computation trade-offs, while a CPU-only configuration supports deployment without GPU resources. Experiments on LineMOD and five BOP19 datasets demonstrate advanced performance. Real-world pick-and-place experiments further demonstrate G6D's applicability to robotic manipulation. The complete project is publicly available at https://ai4control.github.io/G6D-Project-Page . --- ### MaskVLA: Visual Masking Against Trajectory Overfitting of Vision-Language-Action Model Authors: Yuxuan Jiang, Jiaying Huang, Ge Wang, Shenhao Yan, Jiahao Yang, Chengsi Yao, Qi Liu, Qing Zhao, Shuguang Cui, Yiming Zhao, Yatong Han, Zhen Li Published: 2026-09-20 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.23565v1 Vision-Language-Action (VLA) models integrate vision-language understanding with executable robot actions, enabling end-to-end learning for robot control. However, our empirical analysis reveals that existing models exhibit severe trajectory overfitting when finetuned on limited datasets. To guide the model in effectively utilizing wrist camera information, we propose MaskVLA, a masking-based fine-tuning strategy. By randomly masking a small portion of the main camera's visual information, the model is guided to autonomously learn more fine-grained, task-relevant, and effective visual features. This process leads to the emergence of robust policies, thereby enhancing the model's capability to tackle complex manipulation tasks and improving its generalization performance. Our method has been comprehensively evaluated on RoboTwin 2.0, achieving an average success rate improvement of 23.2% and 16.8% compared to $π_0$ and OpenVLA-OFT, respectively. Furthermore, experiments on real-world ALOHA robots also demonstrate the effectiveness of our approach. --- ### Transferring Visual Explanations: How Cross-Architecture Knowledge Distillation Affects Model Interpretability Authors: Aleks Czufarow, Ihor Babin Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23561v1 Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical in safety-critical domains such as autonomous driving and medicine. This study investigates whether Knowledge Distillation transfers the spatial feature attribution of a large teacher network to a compact student. To assess the influence of the KD scheme on interpretability, we distill a ResNet-152 teacher into a ResNet-34 student on ImageNet-1K across five configurations by systematically varying the distillation temperature and soft-label loss weight. Models are evaluated on top-1 accuracy, along with two interpretability metrics: Relevance Mass Accuracy and Relevance Rank Accuracy. These metrics are computed via Grad-CAM heatmaps benchmarked against ground-truth object masks. Our results show that top-1 accuracy ranges from 71.6% to 74.0%. For Grad-CAM, RMA ranges from 7.7% to 9.7% and RRA from 7.3% to 10.1%; for Guided Grad-CAM, RMA ranges from 16.1% to 18.6% and RRA from 15.9% to 21.5%. Interpretability proves far more sensitive to the soft-label weight than to the temperature: keeping the student anchored to hard labels preserves both accuracy and coarse localization, whereas weighting the teacher heavily degrades both. Fine-grained attribution, however, fell below the undistilled baseline in every configuration tested, indicating that logit distillation transmits where a model attends more readily than the pixel-level structure of that attention. We evaluate 12 cross-architecture combinations of convolutional and transformer-based models, revealing that the inheritance of fine-grained spatial reasoning is fundamentally bottlenecked by the student's intrinsic structural biases. To our knowledge, this is the first application of this interpretability-aware evaluation framework - previously used for neural network pruning - to KD. --- ### Optimal High-Order Methods for Solving Monotone Variational Inequalities Authors: Xinliang Zhang, Lesi Chen, Linxuan Pan, Chengchang Liu, Junchi Yang, Jingzhao Zhang Published: 2026-09-20 Categories: math.OC, cs.GT, stat.ML arXiv: https://arxiv.org/abs/2609.23557v1 We study second- and higher-order methods for solving smooth monotone variational inequalities (MVI). Monteiro and Svaiter (SIAM J. Optim., 2012) showed that a second-order method, NPE, converges at a rate of $\mathcal{O}(T^{-1.5})$. For convex-concave minimax optimization, a subclass of MVI problems, Chen, Liu, Luo, and Zhang (COLT 2025) recently improved this rate to $\tilde{\mathcal{O}}( T^{-1.75})$. However, the result has a substantial gap compared to the lower bound of $Ω(T^{-2.5})$ established by Chen et al. (2026). In this paper, we propose a novel second-order method that achieves the optimal rate of $\mathcal{O}(T^{-2.5})$. Our algorithm also extends to higher-order methods: for any integer $ p \ge 1$, we obtain a $p$th-order method with a convergence rate of $\mathcal{O}(T^{-(3p-1)/2})$, matching the known lower bounds and therefore establishing optimal rates across all orders. --- ### Resolution-Flexible Decoding for Hybrid Neural Video Representations Authors: Taiga Hayami, Masaya Takabe, Hiroshi Watanabe Published: 2026-09-20 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.23555v1 Neural video representations (NVRs) represent videos using neural network parameters and, in hybrid formulations, frame-wise latent embeddings. Although hybrid NVRs can improve reconstruction quality by using content-adaptive latent embeddings, their latent spatial sizes and decoder upsampling schedules are tied to the target frame resolution. For high-resolution videos, this dependency may require large and non-uniform upsampling factors and can affect the parameter allocation between the latent embeddings and the decoder. In this paper, we propose a resolution-flexible decoder framework for hybrid NVRs. The decoder is constructed from uniform \(2\times\) upsampling stages, whose target feature sizes are obtained by tracing the spatial resolution backward from the final output resolution. After each upsampling stage, the feature map is aligned with the target size by minimal padding or cropping when necessary. To support this progressive decoding process, we further use intermediate reconstruction supervision and a reconstruction-difficulty-aware frame sampling strategy based on recent frame-wise losses. The framework preserves the basic representation format of hybrid NVRs and can therefore be applied to different backbones. Experiments on the UVG dataset show that the proposed approach improves reconstruction quality over the corresponding NVR baselines. ---