# Research Papers — 2026-08 · bundle page 171 of 240 > Full-text markdown of papers #8501–8550 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/171 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/170.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/172.md) ### RobustDefect-LLM: Explainable and Robustness-Aware Industrial Surface Defect Classification with Decision Support and AI-Assisted Reporting Authors: Nazlıcan Düşünmez, Halûk Gümüşkaya Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08589v1 This paper presents RobustDefect-LLM, an industrial surface-defect inspection framework integrating deep-learning classification, operator-facing visual evidence, confidence-aware decision support, controlled AI-assisted reporting, traceable storage, and mobile interaction in a unified quality-control workflow. Here, robustness-aware denotes explicit evaluation under controlled image degradation and confidence-aware review routing, not an intrinsic robustness guarantee. Four transfer-learning-based convolutional neural networks, ResNet50, EfficientNet-B0, DenseNet121, and MobileNetV3-Large, were evaluated on 1,799 images from the six-class NEU-DET dataset using fixed training, validation, and held-out in-domain test partitions. MobileNetV3-Large achieved the highest numerical test accuracy (99.26%) and macro F1-score (0.9926), with a bootstrap 95% accuracy CI of 0.9815-1.0000. An exact paired McNemar test found no significant difference from DenseNet121 (p = 1.000). The selected model averaged 0.060 s per CPU forward pass (16.66 FPS). Under combined synthetic degradation, accuracy fell to 87.78% at mild intensity and below 40% at stronger intensities, revealing sensitivity to severe image-quality deterioration. Grad-CAM supplied visual evidence, while predictions with confidence below 0.90 or a top-2 margin below 0.10 were routed to HUMAN REVIEW. This conservative policy provided 12.22% automatic coverage and 100% observed selective accuracy among 33 eligible cases (95% CI: 89.43%-100.00%), while routing both observed classification errors to review. Under nominal controlled conditions, all 100 generated reports passed deterministic consistency checks, with a mean latency of 1.66 s. Results support the feasibility of the integrated workflow while emphasizing the need for calibration, repeated evaluation, and real-world industrial validation. --- ### LazyHMC: Hamiltonian Monte Carlo Simulation for Lazy, Infinite Dimensional Probabilistic Programs Authors: Maria-Nicoleta Crăciun, C. -H. Luke Ong, Tom Schrijvers, Sam Staton Published: 2026-08-09 Categories: stat.ML, cs.LG, cs.PL, stat.CO arXiv: https://arxiv.org/abs/2608.08588v1 Hamiltonian Monte Carlo (HMC) is a successful generic inference method in probabilistic programming, but in its ordinary formulation it needs gradients and finite-dimensional parameter spaces. In Haskell, lazy evaluation lets probabilistic programs express stochastic processes and other non-parametric Bayesian models over implicit infinite-dimensional spaces. This paper develops new formulations of gradient-based HMC for this infinite-dimensional setting, via lazy evaluation. For automatic differentiation, we provide an analysis based on a new notion of "piecewise analytic under cylindrical analytic partition" (PACAP), to show that even if a program is infinite-dimensional and defined lazily, the gradient of the likelihood function is finitely supported. For the Monte Carlo method itself, we develop several HMC variants and a No-U-Turn Sampler that operate over the infinite-dimensional parameter space but are still productive because of lazy evaluation. Experiments cover Gaussian mixture clustering, random walks, and piecewise-constant regression with Poisson-process changepoints. --- ### EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams Authors: Zixuan Chen, Jiakai Zhang, Junhao Dong, Guangcong Wang, Jianhuang Lai, Yew-Soon Ong, Xiaohua Xie Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08585v1 Event cameras, with high temporal resolution, high dynamic range, and asynchronous sensing characteristics, have shown great potential for dense 3D reconstruction. Traditional reconstruction methods based on off-the-shelf pose estimates achieve high efficiency but produce low-fidelity results, as inaccurate pose initialization introduces cumulative reconstruction errors. In contrast, recent SLAM-style methods stabilize joint pose-scene optimization through incremental tracking and mapping, yielding higher reconstruction fidelity at the expense of considerable computational overhead. To address this trade-off, this paper presents EvTrajGS, an accurate and efficient 3D Gaussian Splatting framework for unposed event streams. Our method enables reliable joint pose-scene optimization initialized from coarse pose priors, eliminating the need for computationally expensive SLAM-style pipelines. EvTrajGS parameterizes camera motion as a continuous-time trajectory initialized from discrete camera poses, providing a unified representation for pose refinement. We then aggregate adjacent trajectory states into a temporally coupled pose, promoting temporally consistent pose updates during joint optimization. Additionally, we introduce a loss-reweighted event sampling strategy to adaptively emphasize temporally under-reconstructed intervals. Extensive experiments on both synthetic and real-world datasets demonstrate that EvTrajGS outperforms state-of-the-art methods in terms of both geometric reconstruction quality and pose estimation accuracy, achieving 3.8 dB higher PSNR, 0.1 higher SSIM, and over 40\% lower ATE RMSE while retaining high computational efficiency. --- ### Where Is the Bee? Detecting Tiny Pollinators with a Single Collaborative-Head Transformer Authors: Junsu Kim, Seungryul Baek Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08580v2 The CVPPA@ECCV 2026 BuzzSpot Challenge asks us to detect bees, bumblebees, hoverflies, and moths in 1920x1080 field keyframes. Its annotations carry 2 difficulties: the median box occupies 0.16% of a frame, and bees account for 80% of the labels. To cope with the small boxes, we compare 10 recorded detector configurations on held-out keyframes; plain Co-DINO with a Swin-L backbone has the highest mAP in this comparison, so we select it. Training then addresses the bee dominance in 2 ways: fine-tuning on a crop-mosaic pool in which the combined annotation share of the 3 rare classes rises from 19.9% to 55.1%, and a class-weighted simplex equiangular tight frame (ETF) loss that pulls the projected states of matched decoder queries toward fixed class directions. The full schedule spans 12+3+2 epochs. Without inference-time ensembling or test-time augmentation, we rank first on FinalTest at 0.5062 mAP@(.5:.95). --- ### When Can Fraud Operations Authorize Automation? A Decision-Support Framework for Fresh Audit Evidence and Review Workload Authors: Jie Deng Published: 2026-08-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.08577v1 Fraud operations must allocate events among automatic approval, analyst review, and automatic blocking even though the labels needed to evaluate these actions are selective and delayed. Predictive scores order cases, but they do not show whether the evidence is current and representative enough to delegate an action to the model. We develop freshness-constrained audit capacity (FCAC), a decision-support framework that treats automation as an authorization decision constrained by action risk, evidence freshness, and shared review capacity. It evaluates candidate action regions from mature randomized audits and a prespecified temporal allowance. Supported regions are automated; unsupported regions remain in review. The resulting decision record reports evidence age, audit demand, total review workload, value exposure, and compatible temporal change. We show that current action risk is unidentified without restricting unobserved label evolution. Under representative randomized audits, label-independent evidence windows, and a prespecified condition linking historical and current action risk, we derive simultaneous finite-sample control of unsafe authorization. Chronological evaluations with simulated audits on IEEE-CIS, ULB-Worldline, and Elliptic++ yield zero-drift automation rates of 84.4%, 67.4%, and 81.3%, with total review workloads of 24.1%, 46.0%, and 43.1%. The experiments reveal an audit-capacity trade-off: sparse auditing delays authorization, whereas intensive auditing eventually increases workload. A separately specified BAF stress test further indicates that fallback thresholds must reflect candidate-specific evidence rather than a common fraction of the risk limit. These findings identify audit freshness and analyst capacity as joint design considerations for fraud decision support. --- ### CDGC-Net: 3D Medical Image Segmentation with Cooperative Dual-Scale Self-Attention and Grouped Channel Modeling Authors: Zheyang Jing, Qin Lu, Jianwang Li, Yujie Yang, Chen Yi, Shaofeng Jiang Published: 2026-08-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.08575v1 Accurate 3D medical image segmentation requires the integration of long-range anatomical context with fine boundary detail. Existing methods often model global and local features in separate modules or feature levels and perform channel recalibration independently. This may cause semantic mismatch between global context and local boundaries, insufficient channel relationship modeling, weak spatial-channel interaction, and redundant representations. We propose CDGC-Net, a 3D medical image segmentation network that combines cooperative dual-scale spatial attention with grouped hierarchical channel modeling. With-in each CDGC block, Cooperative Dual-Scale Self-Attention (CDSA) assigns attention heads to parallel local-window and global-sparse branches. The two branches capture fine spatial details and long-range anatomical context at the same feature level. Their outputs are concatenated into an $N\times C$ spatial representation and directly passed to Grouped Hierarchical Channel Attention (GHCA). GHCA organizes the channels into $r$ groups and models both within-group and cross-group dependencies. CDSA and GHCA reuse a shared key projection to maintain a consistent feature reference. Residual feature alignment subsequently integrates the refined features with the original representation. On the Synapse, ACDC, BraTS, and LA datasets, CDGC-Net achieved mean DSC values of 86.96\%, 92.91\%, 82.56\%, and 93.52\%, respectively, exceeding the next-highest reported values by 0.39, 0.47, 0.17, and 0.32 percentage points. CDGC-Net contains 25.83M parameters and 28.62G FLOPs for an input size of $64\times128\times128$, reducing these quantities by 39.87\% and 40.30\%, respectively, relative to UNETR++. These results indicate a favorable trade-off between segmentation accuracy and computational complexity. --- ### Robust Reputation-Driven Crowdsourced Federated Learning Authors: Mouhamed Amine Bouchiha, Gregory Blanc Published: 2026-08-09 Categories: cs.LG, cs.CR, cs.DC arXiv: https://arxiv.org/abs/2608.08574v2 Crowdsourced Federated Learning (CrowdFL) extends traditional federated learning by enabling open and heterogeneous participation through a crowdsourcing paradigm. In this setting, reputation-driven incentive mechanisms are commonly employed to guide worker selection and enhance trustworthiness. While such approaches improve participant reliability, existing frameworks largely overlook the quantification of their robustness against stealthy adversaries, particularly those capable of evading standard detection mechanisms. To fill this gap, this paper proposes R2CFL, a robust reputation-driven CrowdFL framework. R2CFL introduces a robust reputation model coupled with a nearest neighbor mixing (R2-NNM) defense mechanism that links reputation evolution with the filtering of updates during aggregation. The proposed mechanism prevents stealthy attackers from gradually accumulating trust and influencing future tasks. Experimental results demonstrate that R2-NNM matches or surpasses state-of-the-art Byzantine-robust and backdoor defense mechanisms against adaptive attackers. Furthermore, when integrated with existing detect-and-filter defenses, the proposed reputation model faithfully captures the statistical robustness of the underlying defense by producing reputation scores that closely reflect its true positive and false positive characteristics. --- ### FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Authors: Dongyi Lv, Fushun E, Aichen Cai, Liang Huang, Ya Zhang, Qiuyu Ding, Canhui Wu, Zhi Wang, Yuesong Zhang, Jiaqi Wang, Nan Duan Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08570v1 Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, and fine-tuning on the successful rollouts. However, even strong code agents repeatedly fail on a substantial fraction of such tasks, and standard RFT simply discards these failures. The discarded samples are precisely the hardest and most informative ones, drawn from verifiable instances that are costly to curate. Stronger base models may reduce the number of failures, but the remaining hard cases still define the frontier for further improvement. We propose FailForge, an agentic framework that converts failed rollouts into training signal. For each failed instance, an agent diagnoses the failure from error feedback and execution traces, distills the diagnosis into a concise and actionable skill, and injects the skill into the agent context for a guided second attempt. Trajectories that succeed under skill guidance are folded back into the RFT corpus. Crucially, the skill is removed at training time, so the model internalizes the recovered behavior rather than relying on external hints at inference. FailForge recovers over 26% of previously failed instances at marginal additional cost, and training Qwen3.5-4B on the augmented corpus improves the SWE-bench Verified resolve rate by 6.6 points over a strong RFT baseline, with gains concentrated on the hardest problems. --- ### VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference Authors: Wenxu Jia, Dongjie Fu, Xize Cheng, Fangming Feng, Linjun Li, Wenshi Chen, Yingming Li, Zhou Zhao, Tao Jin Published: 2026-08-09 Categories: cs.AI, cs.SD arXiv: https://arxiv.org/abs/2608.08569v1 Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks. Despite this progress, their long-context inference remains severely bottlenecked by prohibitive KV cache memory demands. Existing text-centric compression methods struggle here, often disrupting speech continuity or discarding crucial semantic cues. To address this, we propose VoxZip, a train-free, two-stage semantic-anchored KV cache compression framework. The first stage uses automatic speech recognition (ASR) transcriptions as explicit semantic anchors to temporally align, compress, and fuse audio tokens, significantly reducing the initial KV cache while elevating token information density. To further improve the compression ratio, the second stage employs a dynamic filtering strategy based on temporally decayed accumulated attention to evict non-essential tokens while mitigating early-token bias. Comprehensive evaluations on Qwen3-Omni across six diverse audio benchmarks demonstrate the superiority of our approach. VoxZip excels in long-audio reasoning and consistently maintains high-fidelity perception on short-form tasks. Notably, it sustains over 90\% of the uncompressed baseline performance even under an aggressive 20x KV cache compression in long-context scenarios. Furthermore, at a 4x compression ratio, VoxZip yields a 1.9x increase in inference throughput alongside a 3.3x reduction in peak memory overhead. Code and models will be available at https://github.com/MM-Speech/VoxZip. --- ### Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks Authors: Omer Yom-Tov, Avigdor Gal Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08567v2 A central obstacle in building graph foundation models is the input heterogeneity in terms of feature space dimensionality, semantics, and structure. Such heterogeneity limits the capability of graph neural networks to generalize to new graphs with unseen feature spaces. We address the transferability challenge with SIGIL, a framework that maps any attributed graph to a unified representation space of fixed dimension. Given a graph, SIGIL lifts it to a structural interaction graph, where nodes are the input feature dimensions and weighted, typed edges encode feature alignment across multiple orders of the graph's connectivity. A relational message-passing network embeds each feature dimension into a shared space, transforming the original node features, of arbitrary dimensionality, into representations transferable to any downstream graph. By construction, SIGIL is equivariant to permutations of nodes, feature dimensions, and labels. Additionally, when the input features are one-hot indicators of discrete relations, SIGIL recovers and strictly generalizes existing foundation models for knowledge graph reasoning. A single SIGIL model, pretrained on one graph, delivers strong fully-inductive link prediction. Also, SIGIL can be used to implement existing knowledge graph foundation models. As such, SIGIL unifies several existing regimes in graph foundation model design under a single framework --- ### On-Device Multi-Species Malaria Detection with Uncertainty-Calibrated Slide-Level Aggregation Authors: Idaya Seidu, Ahmed Tahiru Issah, Charles B. Delahunt, Carine Mukamakuza Published: 2026-08-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.08566v1 Malaria remains a leading cause of mortality in resource-limited settings, where expert microscopists are scarce. Automated diagnosis based on microscopy images thus has strong potential to improve care delivery. But for an algorithm to deploy, a necessary requirement is that it meet a suite of non-obvious (from a machine learning (ML) perspective) clinical constraints. Therefore, in close consultation with a national health center we developed a malaria diagnosis pipeline which addresses key requirements listed by the health care center but typically ignored in the ML malaria literature. In particular, it includes: (i) stopping criteria (to reduce image acquisition and time-to-result); (ii) human-in-the-loop functionality (for review and accountability); (iii) multi-species discrimination (since treatment varies by species); (iv) thick film detection (standard for microscopy); (v) computationally-efficient uncertainty calculations (to aid clinician review); and (vi) an edge device platform (since internet can be spotty in this catchment area). The mobile system performs all inference on-device using YOLOv13n deployed via TensorFlow Lite. It detects four species and white blood cells from Giemsa-stained thick blood smear images, aggregating per-image detections into slide-level parasitemia with World Health Organization (WHO)-standard quantification. This paper highlights these various clinical constraints and offers methods to address them. Evaluated on 2,739 annotated images across all four species, the system achieves mAP@0.5 of 0.863, per-image parasite count correlation of r = 0.812, slide-level r = 0.951 (soft counting, 10 images/slide), and runs entirely offline with a pipeline time of 10.27 +- 1.65 s per image. --- ### Deep probabilistic logic programming for diagnostic reasoning from incomplete information: A case study in stroke detection Authors: Felix Weitkämper, Monchito Avila, Elizabeth Nanjala, Siska, Grace Zawadi Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08561v1 In medical applications, raw data is frequently associated with significant privacy concerns, lending particular importance to the encoding of summary statistics from the literature. On the other hand, deep learning has become an invaluable tool for assessing symptoms based on visual or auditory sensor data. DeepProbLog allows for an extensible neuro-symbolic approach that accommodates connectionist components to analyse patient images within a transparent and rigorous probabilistic framework, namely probabilistic logic programming under the distribution semantics. Framed as a case study in stroke detection from multimodal data, this contribution explores the pathway from summary statistics available in the literature to a DeepProbLog-based diagnostic system. It suggests a workflow using established maximum entropy techniques to complete available probabilistic information and the probabilistic logic programming system ProbLog 2 to move from the entropy-maximising causal model to a discriminative neuro-symbolic model expressible within DeepProbLog. The relative performance of models derived from less complete data is analysed alongside the potential of the probabilistic inductive logic programming system ProbFOIL 2 for compressing large discriminative models, and the perspectives and implications of using DeepProbLog for diagnostic reasoning are discussed. --- ### Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation Authors: Lei Shu, Ying Jiang, Kui Wu, Yin Yang, Leonidas Guibas, Chenfanfu Jiang Published: 2026-08-09 Categories: cs.GR, cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.08559v1 Differentiable simulation is a key component in learning, control, and inverse problems, where gradients through nonlinear implicit solvers are required. Existing approaches either rely on unrolled automatic differentiation, whose memory grows with solver depth, or on equation-level implicit differentiation, which assembles global Jacobians and solves large sparse adjoint systems, discarding the locality of the forward solver -- and differentiating the converged equation rather than the finite computation that actually ran. We propose solver-level differentiation, which differentiates the executed solver itself. When a solver is composed of block implicit updates, its discrete adjoint is obtained by applying the corresponding adjoint updates in reverse order, yielding a reverse-sweep formulation whose backward pass mirrors the forward solver. From an operator perspective, the forward pass realizes an approximate inverse through ordered local solves, and the backward applies its transpose through reverse local adjoint solves, constructing no global system. We instantiate this idea on Vertex Block Descent, yielding a differentiable solver whose reverse colored Gauss-Seidel sweeps are composed entirely of local $3\times 3$ adjoint solves. The backward matches automatic differentiation through the identical executed forward to machine precision at every solver depth, where the equation-level adjoint is off by 37% after one sweep; in a controlled same-codebase, same-GPU comparison it is 33x faster and uses 71x less memory than unrolled automatic differentiation; and the same construction is exact on projective dynamics and extended position-based dynamics. We scale differentiable elastodynamics to $10^6$ contact-coupled soft bodies (8M vertices) on one GPU. Overall, this work highlights solver structure as a practical organizing principle for efficient differentiable simulation. --- ### OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories Authors: Changhao Xiang, Shilin Zhang, Zheng Ma, Kanzhi Cheng, Ruize Ma, Yi Feng, Jianbing Zhang, Zhi Wang, Zhen Wu, Xinyu Dai, Lewei Lu Published: 2026-08-09 Categories: cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.08557v2 Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capability from teacher-generated trajectories filtered for answer correctness, implicitly assuming that every successful demonstration provides effective supervision. We argue this assumption is flawed: a strong teacher often reaches the correct answer without needing its tool calls, and imitating such trajectories teaches a student that tool calls accompany correct answers, not that tool observations ground them. We present OpenVisTool, an open framework for constructing instructive visual tool-use trajectories that provide effective supervision for tool learning. The key insight is that a trajectory should be retained only if its answer is correct (outcome validity) and its tool observations causally contribute to that answer (causal utility). The framework operates in three stages: difficulty screening to select queries that are not reliably answerable without tools, domain-specific trajectory synthesis to elicit coherent tool-use trajectories, and supervision verification to jointly test both conditions. Rather than encouraging models to imitate tool calls, the resulting supervision teaches when and how visual evidence should be acquired. Using this framework, we construct OpenVisTool-42K, a dataset spanning five visual reasoning domains, together with OpenVisTool-Bench, a benchmark covering the same domains. Across four backbones (4B-27B), fine-tuning on OpenVisTool-42K consistently improves visual tool-use performance and yields gains on two out-of-distribution benchmarks; the larger models approach leading closed-source systems. The evidence suggests that effective visual tool use is learned from causally grounded supervision rather than tool-calling patterns. --- ### SC-Diff: Semantically Calibrated Diffusion for Visible-to-Infrared Image Translation Authors: Junyin Zhang, Siyu Huang, Jianxiong Ye, Haowei Gong, Ruicheng Zhang, Deyu Meng, Chenqiang Gao Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08555v1 Visible-to-infrared image translation provides a practical way to expand infrared training data using abundant visible images. Diffusion models are promising for this task because of their strong generative performance. However, existing diffusion-based methods typically use semantic priors only as external conditions, without explicitly regulating token interactions within the denoising network. Consequently, they struggle to preserve object locations, shapes, and semantic layouts required for reliable annotation reuse. We propose SC-Diff, a semantically calibrated latent diffusion framework that uses semantic priors for both conditional guidance and internal self-attention calibration. A pretrained SAM3 model with predefined text prompts first extracts category-specific semantic masks from visible images. These masks are merged into a semantic map and fused with the visible image as the input condition. The same map is converted into token-level semantic labels to calibrate self-attention in the denoising network. Based on these labels, we introduce Semantic-Guided Self-Attention Calibration (SGSC), which adaptively applies positive biases to query-key pairs of the same category. The query-wise calibration strength depends on the dispersion of attention across semantic categories and the attention assigned to the query's own category. The original attention scores further modulate the bias, giving greater calibration to same-category keys with stronger responses. This soft calibration reduces cross-category interference while retaining global contextual interactions, thereby improving semantic consistency in generated infrared images. Extensive experiments show that SC-Diff improves perceptual quality and produces more effective synthetic training data for downstream infrared object detection. --- ### Transfer Learning-Enabled Distortion Compensation for Amplitude-Phase-Time Block Modulation-Based Nonlinear Single-Carrier Wireless Communications Authors: Guoxing Duan, Min Fan, Cheng Yi, Bensheng Yang, Wei Xu, Haiming Wang, Xiaohu You Published: 2026-08-09 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2608.08554v1 Power amplifier (PA) nonlinearity and memory effects significantly limit the spectral compliance, reliability, and energy efficiency of communication systems. To address this, we propose a transfer-learning-enabled, fully digital transceiver-cooperative method for amplitude-phase-time block modulation (APTBM)-based nonlinear single-carrier transmission under adjacent channel leakage ratio (ACLR) constraints. At the transmitter, iterative clipping and filtering (ICAF) and static digital pre-distortion (SDPD) act jointly to reduce signal peaks and suppress spectral regrowth without requiring wideband feedback. At the receiver, the inherent amplitude-phase constraints of APTBM provide weakly supervised prior knowledge for offline inverse-model pretraining, which is followed by the online few-shot adaptation of a lightweight digital post-distortion (DPoD) network. Subsequently, a cascaded DPoD and clipping-noise cancellation scheme systematically compensates for residual distortions induced by both the PA and ICAF. Simulation and measurement results demonstrate reliable transmission at an input back-off of approximately 2 dB under a 30-dBc ACLR constraint. Furthermore, the proposed DPoD approach significantly reduces online training time and computational overhead, delivering a performance gain of over 2 dB compared to conventional learning-based DPoD schemes. --- ### MotionCraft: Latent World Modeling with Sparse Attention for Visual Upscaling Authors: Rong Fu, Chunlei Meng, Yangchen Zeng, Xiaowen Ma, Yongtai Liu, Wangyu Wu, Shuo Yin, Zijian Zhang, Sicheng Li, Yingrui Ji, Chenhao Wang, Simon Fong Published: 2026-08-09 Categories: cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2608.08553v1 Video super-resolution (VSR) aims to recover high-fidelity high-resolution videos from low-resolution inputs and is central to applications ranging from mobile capture to streaming and archival restoration. Existing approaches trade off among local-detail fidelity, long-range spatio-temporal modeling, perceptual realism, and efficiency: convolutional alignment techniques preserve local structure but suffer when motion is large or degradations are complex; transformer-based methods capture long-range dependencies yet require architectural or algorithmic adaptations to remain computationally feasible; and recent latent or diffusion-based generators synthesize rich texture but require specialized temporal constraints to maintain coherence. We present MotionCraft, a controllable VSR framework that formulates restoration as motion-aware latent state prediction inspired by world models and integrates adaptive sparse attention with an explicit user-accessible control interface. MotionCraft combines robust motion fusion, a Latent World Transformer that balances locality and targeted non-local interactions, and a compact conditional decoder to deliver temporally consistent, high-quality reconstructions under streaming constraints. Empirical evaluations show that MotionCraft achieves strong reconstruction and perceptual performance while enabling predictable trade-offs between temporal smoothness and reconstruction fidelity. --- ### Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies Authors: Prishita Ray Published: 2026-08-09 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2608.08545v1 Robust navigation policies for autonomous agents must generalize across continuously varying environmental conditions such as turn rates, obstacles, friction, pits, and slopes. Curriculum generation provides a principled mechanism for improving generalization by progressively adapting training environments, but designing such curricula in a sample-efficient and automated manner remains challenging. This paper proposes a reparameterized curriculum generation framework for structured continuous environment parameters using unidirectional gradient-based optimization. To improve robustness in multimodal observation spaces consisting of image-based and scalar inputs, a distribution-shift regularization objective is incorporated to encourage the learning of finer-grained latent representations. The proposed method is evaluated across two continuous-control OpenAI Gym environments: a 2D obstacle-based Car Racing variant and Bipedal Walker variant, where coupled environment parameters jointly influence policy performance. Across five random seeds, our method consistently outperforms vanilla policy training, random parameter sampling, manual curricula, frontier-based methods, Self-Paced Reinforcement Learning (SPRL), Absolute Learning Progress with Gaussian Mixture Models (ALP-GMM), and reverse curriculum learning baselines. Ablation studies further demonstrate the effectiveness of the reparameterized curriculum mechanism across both environments, while highlighting environment-dependent benefits of the auxiliary regularization objective. --- ### When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs Authors: Yu Ma, Hongli Shi, Jing Li, Xinran Xu, Weiwei Hou Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08542v1 Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, code, or domain specialists into a safety-aligned base using task arithmetic, TIES, or DARE. This convenience is known to carry a safety cost, but almost all of that evidence rests on static refusal tests: fixed harmful prompts scored for compliance. We argue this is misleading. Because safety alignment is "shallow," concentrated in the first few generated tokens, a merged model's static refusal can stay clean while a real adaptive attack still breaks it. We introduce SkillSafe-Bench, a controlled benchmark that scores skill-merged models on static refusal, adaptive jailbreak robustness, and capability retention under a conservative two-judge AND rule. Across six open-weight bases (five families, two scales), static safety does not predict robustness to attack: under a semantic template attack, safe-looking merges on the fragile bases (both Qwen scales and Gemma) are jailbroken 60-76% of the time while others (Llama, Phi-4) stay robust. We further show the static effect of merging is base-conditional, characterize same-recipe abliteration-style safety erosion through a data-free geometric signal (the overlap of a task vector with a safety subspace), and outline SubSafe-Merge, which projects this overlap away to remove that erosion at held capability. Adaptive evaluation is not optional for merged LLMs: the models that most need it look safe under static screening. --- ### Rethinking Attention Locality in Spiking Transformers Authors: Zeqi Zheng, Zizheng Zhu, Yuping Yan, Wenxuan Pan, Zhaofei Yu, Yaochu Jin Published: 2026-08-09 Categories: cs.CV, cs.NE arXiv: https://arxiv.org/abs/2608.08541v1 Spiking Transformers provide a promising paradigm for efficient visual processing with spike-driven computation, yet their Softmax-free Spiking Self-Attention (SSA) struggles to establish spatially localized token interactions. Although existing locality-enhanced SSA methods improve accuracy, it remains unclear whether they consistently induce spatial locality across layers and different Spiking Transformer architectures. Through Mean Attention Distance (MAD) analysis, we reveal that computational locality does not necessarily translate into spatial locality and show that uniformly applying the same locality enhancement overlooks architecture-dependent deployment requirements. Motivated by these observations, we propose Spatially Contiguous Local Attention with Boundary Continuity Pathway (SCLA-BCP). SCLA computes attention within non-overlapping regions of spatially adjacent tokens, while BCP facilitates cross-boundary information exchange through a lightweight convolutional pathway. Furthermore, we develop a hierarchical locality deployment strategy to effectively apply SCLA-BCP across the two major Spiking Transformer architectures. Extensive experiments on seven static and neuromorphic datasets covering classification, detection, and segmentation demonstrate consistent improvements with limited parameter and energy overhead. Notably, our approach improves mAP@50 by up to 9.50% on COCO 2017 and mIoU by up to 3.42% on ADE20K. Visualizations, MAD analysis, and ablation studies further validate its effectiveness. --- ### Can Graph Learning Learn Circuits? Authors: Chester Tan, Moritz Lampert, Courtney Maynard, Ankit Ramakrishnan, Tina Eliassi-Rad, Ingo Scholtes Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08536v1 Circuit localization is a mechanistic interpretability task whose goal is to identify a sparse subgraph of a transformer's computation graph sufficient to reproduce a particular behavior. Most established methods localize circuits independently for each model--task pair. We instead frame circuit localization as a graph machine learning problem in which the edges of a computation graph represent computational pathways, and graph neural networks (GNNs) model interactions among these pathways. We introduce Graph Circuit Learning (GCL), a supervised, amortized framework that trains a GNN across multiple model--task pairs and applies it to unseen cases. To provide sufficient data, we augment the InterpBench benchmark with additional cases derived from the TracrBench programs. Of the 14 evaluated GCL configurations, the highest scored a median edge AUROC of $0.902$ (interquartile interval $(0.861, 0.942)$) on the 16 original held-out InterpBench cases. This is close to the published InterpBench median of $0.910$ for EAP-IG while remaining below ACDC's $0.959$. Removing all message-passing edges reduces the median to $0.825$. We also adapt PGExplainer, a GNN explainability method, to circuit localization, obtaining a median edge AUROC of $0.858$ on the same cases. These preliminary results suggest that graph machine learning offers a natural and potentially powerful perspective on circuit localization, and we hope this perspective encourages closer exchange between the two communities. --- ### ERF-GS: Reconstructing Fast Motion from Disjoint Event-RGB Viewpoints Authors: Xiaoyang Bai, Zhenyang Li, Weiwei Xu, Edmund Y. Lam, Yifan Peng Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08531v1 Deep learning-driven representations such as neural radiance fields (NeRFs) and 3D Gaussian splatting (3DGS) have revolutionized the field of dynamic 3D scene reconstruction with improved visual precision and scalability. However, the reconstruction of fast-moving objects remains a challenge; existing methods based on conventional frame-based videos often struggle in scenarios such as sports events and animal videography. We propose an event-RGB fusion Gaussian splatting (ERF-GS) framework that integrates event information into both optimization and densification stages of the Gaussian splatting pipeline, taking advantage of novel event sensors with high frame-rate. Unlike many other event-assisted scene reconstruction methods, ERF-GS was developed using realistic simulation settings and realizes event-based learning detached from RGB inputs. This design enables its application beyond straightforward synthetic data into the realm of natural video with complex layout, low frame rates and severe motion blur. Our experiments show that ERF-GS outperforms both the 4DGS baseline and the concurrent E-D3DGS on different variants of the Neu3D and Nvidia datasets which include blurry RGB frames and disjoint RGB-event viewpoints. Our code is available at https://github.com/andrewbxy/ERF-GS. --- ### Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing Authors: Srinivasan Manoharan, Junhua Zhao, Fangbo Tu, Haifeng Wu, Jian Wan, Maliah Rajan M, Ashwin Hegde, Mithun Sasidharan, Kalyan Chakravarthi Podamekala Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08528v2 Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer wait time are included. We present Task-to-Model Optimization (T2MO), a data-driven methodology for optimizing model selection in production coding workflows. We treat each developer session as a task that can be discovered, classified, graded for difficulty, benchmarked in a production-like harness, and routed to the cheapest model able to complete it within quality and latency constraints. The framework is a nine-stage pipeline spanning telemetry instrumentation, taxonomy discovery, difficulty grading, benchmark construction, candidate evaluation, optimal mix derivation, forecasting and version planning, staged routing deployment, and continuous governance. Unlike token-centric routing rules, our objective is cost per completed task, with failure escalation priced in explicitly. We show that this expected-completion-cost objective weakly dominates token-cost minimization under escalation, and we derive the routing boundary, the minimum pass rate a cheaper model must reach on a given cell to be worth deploying. Decisions are organized as a two-level hierarchy of task category difficulty tier, and per-cell displacement opportunities are aggregated into a traffic-weighted savings waterfall that ranks replacement candidates by realized dollar impact. The framework supports developer guidance, spend forecasting, and a staged transition from static policies to shadow-mode classifiers, verified cascades, and ultimately an intelligent router. We describe the methodology, optimization objective, evaluation protocol, and governance loop in a form suitable for production deployment and future empirical study. --- ### Out-of-Distribution Federated Distillation with Domain-Aware Proxy Authors: Jiahao Xiao, Jiangming Liu Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08525v1 Federated Learning is a distributed machine learning paradigm that trains a global model by aggregating local clients without sharing private data of each client. Federated Distillation (FD) builds upon this paradigm by leveraging knowledge distillation to exchange soft predictions on proxy data instead of model parameters, enabling more efficient communication and supporting heterogeneous model collaboration. However, FD models trained on In-Distribution data are hardly adapted to Out-of-Distribution (OOD) scenarios. In this paper, we propose a domain-aware proxy selection framework to better adopt proxy data for OOD problems. The experimental results show that the proposed models effectively address the challenges of distribution shifts under OOD with and without proxy data by achieving average 82.9\% and 80.6\% over existing works on standard benchmarks. The codes and data are released in https://anonymous.4open.science/r/DPS-FD-8596. --- ### Discovering Diverse Planning Policies for Multimodal Embodied Agents with Quality-Diversity Optimization Authors: Pengfei Xu, Yong Liu, Xiaoya Nan, Qiang Yang, Peilan Xu Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08523v1 Multimodal embodied agents are increasingly required to solve long-horizon tasks by integrating visual observations, textual goals, and interaction history into closed-loop decision making. However, state-of-the-art large-model-based planners often rely on a single dominant planning style during execution. Once this execution mode becomes ineffective, the agent may remain stalled for many steps, repeatedly interacting with the environment without making meaningful progress. We address this limitation by proposing a Quality-Diversity (QD) framework for discovering diverse planning policies for multimodal embodied agents. The proposed method treats planning-policy templates as evolvable individuals and organizes them into a behavior-indexed archive rather than collapsing search to a single prompt style. In the offline stage, rollout trajectories are summarized into structured success and failure experiences, which guide policy variation through recombination and experience-guided mutation. The resulting policies are mapped into a behavior space defined by interaction intensity and goal-directedness, and the highest-quality policy in each niche is retained in the archive. In the online stage, the agent executes one policy at a time while monitoring task progress. When persistent stall is detected, the system rolls back to the latest checkpoint and switches to a behaviorally distinct archive policy to resume execution. Experiments on the ThreeDWorld transport benchmark show that the proposed framework improves both task success and interaction efficiency over representative baseline planners. These results suggest that discovering diverse policy repertoires is an effective way to support adaptive multimodal planning and online failure recovery. --- ### A Combined Feature-Based Framework for Disguise and Spoofing Detection in Face Recognition Systems Authors: Sangiya Pararajasingham Published: 2026-08-09 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.08521v2 Face recognition systems face two distinct, commonly-separated failure modes: spoofing, where an impostor presents a photograph or video of an authorized user, and disguise, where a legitimate user is rejected because their appearance differs from their enrolled template due to accessories, facial hair, illumination, or pose. This paper proposes and compares five combined feature-extraction and classification pipelines that address both problems within a single framework: PM (PCA and Minimum Euclidean Distance, MED), LPM (Local Binary Patterns with PCA and MED), HPM (Histogram of Oriented Gradients with PCA and MED), SM (Speeded-Up Robust Features with MED), and HM (Harris corner features with MED). Each pipeline follows a common two-phase process comprising pre-processing, feature extraction, feature filtering, and classification. The methods were trained on 115 subjects drawn from the FEI, Disguised Faces Database, and NUAA databases and evaluated on six test conditions covering mixed appearances, frontal faces, dark illumination, left- and right-turned poses, and photo-spoofing attempts. The HOG-based pipeline (HPM) achieved the most consistent performance across conditions, with 94.59% accuracy on mixed-appearance disguise, 81.5-93.2% across pose and illumination variants, and 91.67% on spoofing, while the LBP-based pipeline (LPM) achieved the second-highest spoofing-detection accuracy (93.2%), behind PM (96.67%), but weaker robustness to pose change. These results reveal a measurable trade-off between spoof sensitivity and disguise robustness among classical feature representations, motivating the deep-learning and cross-database extensions discussed in the concluding sections. --- ### eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models Authors: Ignacio Bugueno-Cordova, Fabian Valderrama, Rodrigo Verschae Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08519v1 Intensity-image reconstruction from event streams remains a challenging problem due to the binary, sparse, and asynchronous nature of event data. This work proposes eBIRD, an event-guided reconstruction framework that combines a DDPM with ControlNet-based conditioning. We analyze generic and specialized diffusion learning strategies for handwritten digit (N-MNIST) and face (RGBE-Gaze) reconstruction using 33ms event windows. On N-MNIST, the general model achieves the best reconstruction quality (MSE 0.0052, SSIM 0.8982, PSNR 23.34dB), whereas the specialized model performs best on RGBE-Gaze (MSE 0.0161, SSIM 0.7605, PSNR 19.08dB). These preliminary results suggest that controllable diffusion models are a promising approach for event-guided intensity-image reconstruction, while highlighting that the preferred learning strategy depends on the reconstruction domain. --- ### Reproducing and Stress-Testing Two Approaches to LLM Reasoning Reliability: Test-Time Probability Aggregation and Logic-Representation Editing Authors: Minhan Cho, Jimin Kweon Published: 2026-08-09 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.08514v1 We independently reproduce two recent methods for making large language model (LLM) reasoning more reliable, and stress-test them across domains and models (RPC across four new task domains with Qwen3-8B, LCF across four 7-8B models). The first, RPC, aggregates token probabilities and self-consistency at inference; the second, LCF, trains projectors that split hidden states into "content" and "logic" and edits the logic part toward a valid region. Validating such reliability claims matters because the original evaluations are run by each method's own authors and were never independently reproduced or stress-tested across models and domains, and LCF shipped no public code. We re-run RPC's published-path aggregation and re-implement LCF's projector, contrastive, and intervention pipeline, then extend both to text-to-SQL, legal extraction, fallacy identification, and precedent grading, and probe LCF's representation directly. RPC reproduces the original grid exactly on the authors' released reasoning paths; on four new domains its edge over self-consistency is never significant (ties or small mixed differences, paired p >= 0.28), and on BIRD, the one domain where we vary the budget, the edge grows with K as predicted but its largest gap (+2.5 accuracy at K=32, p=0.16) reverses to -0.25 when we enlarge the sample to n=200. LCF's logic-validity direction is real but weak (0.82 separability at the single best sub-layer versus 0.95 for a semantic-attribute control); its one positive effect (Qwen3 $Δ$Prob) is not significant (p=0.56), while it significantly reduces $Δ$Prob on two of the other three models. --- ### Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding Authors: Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Fahmid Hasan Chowdhury, Md Adnan Arefeen, Farig Sadeque, Md. Faizul Bari, Swakkhar Shatabda Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08512v3 Evolving documents, such as laws, tax codes, and software documentation, are amended, replaced, and sometimes reverted over time, so a question has different correct answers at different dates. In contrast to encyclopedic knowledge, where an old fact is simply overwritten, an amendment is itself an official text that states what it replaces and when it takes effect, and the earlier version stays correct for its validity period. The central challenge is therefore version resolution, that is, identifying the version in force on the queried date. Existing temporal QA datasets treat time only as an annotation, so version resolution stays untested. We present TIDE, an expert-verified benchmark of 3,050 QA pairs over 644 official customs instruments issued between 1969 and 2025 by the Government of Bangladesh, covering eight task types over deeply code-mixed documents that are heterogeneous in layout and dated in two calendars. In addition, we evaluate nine recent LLMs under a single protocol across parametric, gold-context, and retrieval access, scored by a three-judge LLM council with a hard date gate separating correct meaning from correct time. The best macro-averaged accuracy is only 68.5%. Resolving a version from an implicit date reaches 59.7%, and detecting that the supplied version does not govern the query reaches only 26.7%. Models are more likely to find correct versions than to reject incorrect ones, and they tend to follow a confident parametric answer over the supplied authoritative text. All code and data are available at https://github.com/icsetepa44/TIDE --- ### From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios Authors: Thai-Binh Nguyen, Zhaolin Li, Jan Niehues, Alexander Waibel Published: 2026-08-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08510v1 Humans have the remarkable ability to engage in spontaneous informal conversations and selectively attend to individual speakers while filtering out competing speech from nearby conversations. This "cocktail party" scenario still presents severe challenges to speech recognition systems. The CHiME-9 MCoRec task provides a testbed where systems must recognize groups of speakers and transcribe each of their conversations from audio-visual input. In this work, we analyze a diverse set of systems, representing different design directions for addressing the cocktail-party scenario, where the best system achieves up to 57% relative error reduction. We identify three main strategies: (1) explicit or implicit audio-visual target speech separation, (2) improved audio-visual speech recognition for each target speaker, and (3) the use of large language models to group speakers into conversations and enhance conversational consistency. Our analysis shows that these directions address complementary failure modes of the cocktail-party problem, and that high speech overlap alone does not explain performance differences, challenging the common assumption that overlap is the primary source of difficulty in cocktail-party recognition. --- ### Towards Adaptive Super-Resolution and Quality Assessment via Test-Time Adaptation Authors: Ajeet Kumar Verma Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08508v1 This paper presents doctoral research on adaptive video super-resolution and perceptual quality modeling under real-world conditions. Existing video super-resolution (VSR) methods struggle to generalize under unknown degradations arising from heterogeneous devices, codecs, and network environments. We address this challenge through test-time adaptation (TTA), a unified paradigm that improves robustness and perceptual quality without retraining or high-quality supervision. Specifically, we: 1) propose a TTA-based framework for no-reference video quality assessment (VQA), where adapted quality predictions provide perceptual guidance for VSR under unseen distortions; 2) develop a transformer-based architecture for screen-content super-resolution that preserves text clarity and structural fidelity; and 3) introduce a region-aware TTA strategy that selectively refines text and non-text regions without requiring high-resolution ground truth. Experimental results across diverse benchmarks demonstrate consistent improvements in perceptual quality and readability. We also outline ongoing work toward fully adaptive video enhancement systems capable of generalizing across unseen domains. --- ### Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs Authors: Mohanad Odema, Gabrielle De Micheli, Dayin Gou, Nilesh Malpeddi, Prathamesh Vaste, Jacob Song Published: 2026-08-09 Categories: cs.AI, cs.CL, cs.PF arXiv: https://arxiv.org/abs/2608.08506v1 Training-free low-rank compression frameworks have been gaining prominence for LLM compression given their effectiveness in reducing model parameter count while maintaining task-level accuracy. However, existing SOTA frameworks share two key limitations: (1) residual errors in calibration data activations accumulate across layers during compression, causing misalignment between representations simulated at compression time and those experienced at inference; (2) the assumption that layer importance distribution is preserved post-compression does not hold. Together, these two effects introduce misalignment in the compression process in relation to the deployed model. We study these effects and propose a simple, training-free methodology compatible with existing frameworks to mitigate them, comprising: (1) Layer-by-Layer Compression with Calibration Correction; (2) Iterative Compression with Rank Allocation Correction. Implemented atop an existing SOTA decomposition framework, and evaluated on Llama and Qwen3 models across various benchmarks and compression rates, our approach demonstrates up to ~1-2.5 accuracy point improvements over per-weight and joint decomposition baselines on zero-shot tasks. --- ### MathShikkha: A Controlled Study of Answer-Only and Chain-of-Thought Supervision for Bangla Mathematical Reasoning in Small Language Models Authors: Rahma Simin Ali, Jawad Hossain Published: 2026-08-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.08503v1 Mathematical reasoning remains challenging in low-resource languages such as Bangla. We study whether teacher-generated Bangla Chain-of-Thought (CoT) supervision provides benefits beyond ordinary supervised fine-tuning. We construct \textsc{MathShikkha}, a Bangla mathematical reasoning dataset with GPT-5.4-generated rationales, and fine-tune four 4B--7B student models under a matched protocol in which answer-only and CoT conditions share data splits, response-only loss masking, decoding, and scoring, differing only in the training target. In-domain, CoT provides no significant improvement over answer-only fine-tuning for three stronger backbones (paired bootstrap 95\% CIs include zero; exact McNemar $p \geq 0.17$), despite generating 15--52$\times$ more tokens, but significantly improves the weaker 4B model by 18.56 points ($p < 0.0001$). On the larger, contamination-audited BanglaMATH benchmark, this pattern reverses: CoT significantly outperforms answer-only supervision for all four models by 20.1--28.1 points (all $p < 0.0001$). Answer-only fine-tuning also reduces out-of-domain accuracy below the base model for three models, whereas CoT preserves or improves it for all four. A human study with two co-author annotators, external-expert adjudication, and Cohen's $κ= 0.76$--$1.00$ finds no significant CoT improvement over the base model on reasoning-content criteria; instead, its measurable effect is target-language adherence and producing inspectable reasoning. Overall, rationale supervision's value depends on backbone capability and distribution shift: in this setting, its main benefits are Bangla adherence, auditable reasoning, and out-of-domain robustness rather than improved in-domain reasoning validity. --- ### Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation Authors: Qiang Hu, Yuxuan Luo, Yingjie Guo, Hao Wang, Qimei Wang, Qiang Li, Zhiwei Wang Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08494v2 Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct Preference Optimization (DPO) has emerged as a promising post-training paradigm to enhance the performance of Supervised Fine-Tuned (SFT) MRG models, existing DPO-based MRG methods typically adopt a naive preference construction that directly pairs model-generated reports with ground truth reports. This strategy inadvertently entangles critical clinical findings with clinically irrelevant linguistic characteristics, and fundamentally lacks explicit vision-language alignment. To address these challenges, we propose DPO-Clin, a novel post-training framework that focuses preference optimization on clinical findings and cross-modal alignment. First, we introduce the Entity-level Clinical Diagnostic (ECD) module to perform a precise entity-level factual diagnosis. ECD guides the generation of linguistically-aligned report preference pairs, isolating clinical discrepancies from linguistic variations. Second, to achieve fine-grained cross-modal alignment, we develop M2DPO, a retrieval-augmented multi-modal DPO variant that enforces textual preference inversion triggered by visual context switches. Third, we locate correct yet highly uncertain predicted entities and apply counterfactual modifications to construct targeted preference data for latent risk mitigation, thereby further enhancing the model reliability. Extensive experiments on two public chest X-ray datasets (MIMIC-CXR and IU X-Ray) and an in-house endoscopy dataset demonstrate that DPO-Clin significantly improves the SFT baselines on clinical-aware metrics. Furthermore, it achieves superior performance over existing DPO-based MRG methods, exhibiting robust generalizability across distinct baseline architectures and diverse medical imaging modalities. --- ### TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models Authors: Yidong Wang, Yan Zhan, Ziteng Feng, Zhenyu Cui, Ziyi Zhou, Renzhao Liang, Jiaxuan Zhu, Zilei Yang, Yiran Zhao, Zhongkuan Mao, Bo Jia, Hanchu Ni et al. Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08491v1 Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-specific annotations. Existing open-source VLM reward judges like RoboReward adopt simple 1--5 trajectory progress scoring, lacking pairwise preferences for RLHF, DPO and Bradley-Terry frameworks, while failing to optimize video scene understanding. Augmenting RoboReward with pairwise comparison and video-QA supervision causes inconsistency between pairwise preferences and pointwise scores, introducing training noise and hurting downstream performance---an issue aggregation methods such as TrustJudge cannot resolve. To address this, we propose TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE). We construct a unified four-paradigm dataset with trajectory progress scoring (Score-A), video-QA answer quality scoring (Score-B), and their pairwise counterparts (Pair-A, Pair-B). Pairwise labels align better with human judgment than pointwise scores, inspiring us to calibrate pointwise scores to avoid score-pair reversals against pairwise preferences. POISE rectifies pointwise scores and eliminates cross-paradigm reversal conflicts unresolved by TrustJudge. Theoretically, POISE reduces score-pair reversal conflicts from 20.15% to 0%, whereas TrustJudge retains 20.46% conflicts on the same corpus. Evaluated on our benchmark, Qwen3-VL-4B trained with POISE achieves an overall reward score of 77.96%, nearly matching GPT-5-mini (78.09%, gap 0.13%) and outperforming the strongest RoboReward-4B baseline by 10.13%. It also lifts test-time score-pair consistency to 71.90%, exceeding RoboReward-4B (57.26%) and GPT-5-mini (68.09%). Integrating TrustJudge aggregation during inference boosts the overall score to 78.57%, surpassing the GPT-5-mini teacher model. --- ### No Unique Minimizer, No Problem: On the Consistency of Robust Neural Classifiers Authors: Subhabrata Majumdar, Anand Deo, Partha Pratim Saha, Abhik Ghosh Published: 2026-08-09 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.08489v1 Neural network classifiers trained by cross-entropy minimization are highly sensitive to label noise and adversarial contamination. While robust alternatives offer bounded influence and resistance to corruption, their statistical foundations in the deep learning setting are insufficient due to a fundamental difficulty: neural parameterizations are non-identifiable, so the population loss minimizer is an equivalence class of parameters, not a unique point. We develop a consistency theory for robust neural classifiers based on the S-divergence family that requires no identifiability assumption. Casting training as stochastic optimization over a non-identifiable parameter space, we prove that empirical S-divergence minimizers converge to the population-optimal equivalence class under mild regularity conditions, and verify these conditions for three architecture choices. We further establish that limit points of the robust training algorithm are stationary points of the empirical objective. Experiments on vision and language benchmark datasets confirm that S-divergence training maintains clean-data accuracy while exhibiting performance competitive with existing robust methods. --- ### RenderMatte: Exact-Alpha Rendering and Group-Relative Alignment for Image Matting Authors: Zecheng Ren, Yafei Hu, Jianing Zhao, Ruichen Cong, Qun Jin, Yiren Song Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08487v1 Image matting is an essential enabling technology for modern visual content production, where foreground extraction determines the realism and editability of downstream creation workflows. However, precise alpha estimation in open-world scenes remains challenging because real foregrounds exhibit highly diverse appearances and opacity patterns. This makes existing methods struggle with semantic ambiguity and fine-grained opacity variation, especially in sparse boundary regions that are fragile and difficult to supervise. To address this gap, we present RenderMatte, a trimap-guided matting framework that adapts FLUX.1 Kontext through full-parameter fine-tuning, leveraging image editing priors for structure-preserving alpha prediction. During supervised adaptation, an alpha-edge objective preserves the latent flow-matching signal while strengthening pixel-space boundary supervision. We further introduce group-relative alpha alignment for post-training. It compares multiple mattes sampled under the same trimap condition using matting-specific rewards for alpha accuracy, boundary fidelity, trimap compliance, and compositional consistency. To overcome the lack of precise edge annotations, we construct the RenderMatte dataset, a large-scale synthetic dataset combining 3D-rendered RGBA foregrounds with diverse multi-source assets. It features exact strand-level alpha annotations and diverse background composites. Experiments show state-of-the-art performance across all benchmarks, demonstrating a scalable path toward high-fidelity matting in open-world scenes. --- ### HoloAegis: Frozen Representation, Topological Inference --- Minimally Parametric Safety Manifolds and Their Capability Boundaries for LLM Guardrails Authors: Tak Ho Alex Li, Kaijie Liu, Lik-Hang Lee, Kin Chung Ho, Ping Shum, Michael K. Ng Published: 2026-08-09 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.08485v2 Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inference costs. We ask a complementary question: how far can safety be achieved through pure geometric reasoning over frozen representations, and where does it fail? We present HoloAegis, a minimally parametric topological inference framework that decouples representation from reasoning: an un-fine-tuned encoder maps text to the unit sphere S^{d-1}, and all decisions reduce to Gibbs-Boltzmann free-energy differences over pre-computed anchor centroids. We contribute a boundary-mapping study rather than a leaderboard claim. On a frozen three-benchmark protocol, HoloAegis (3.2 MB) statistically matches WildGuard-7B (14 GB) on toxicity (0.96 vs. 0.96), exceeds it on harmful behaviors (0.99 vs. 0.79), and cedes oversafety detection (0.62 vs. 0.98) -- while ShieldGemma-2B fails on indirect harms (0.34). These failure modes are complementary and mechanistically traceable: potential-difference scoring senses manifold clustering, whereas policy-conditioned LLM judging requires explicit taxonomy matching. We restate our Topological Boundary Stability conjecture in ratio form and validate it via reference-set bootstrap: anchor banks reduce score variance 4-15x and boundary displacement to approximately 0.44 + 0.23 sqrt(k/K) of the full-space estimator. Per-domain analysis further reveals that geometric separability tracks within-domain semantic homogeneity. Our results chart where geometric guardrails substitute for, and where they must defer to, LLM judges. --- ### SuperNeuroMAT: An Efficient Matrix-based Simulator for Spiking Neural Networks Authors: Prasanna Date, Kevin Zhu, Shruti Kulkarni, Ashish Gautam, Chathika Gunaratne, Robert Patton, Tyler Nitzsche, Ian Mulet, Zachary Johnson-Scott, Addison Helms, Duncan Rowden, Simon Weston et al. Published: 2026-08-09 Categories: cs.NE, cs.AI, cs.CE, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2608.08479v1 Spiking neural networks (SNNs) offer a promising pathway to energy-efficient AI and brain-inspired computing. However, their widespread adoption is hindered by a lack of fast, accessible, and versatile simulation frameworks. In this paper, we introduce SuperNeuroMAT, an open-source, scalable, and highly efficient Python-based SNN simulator. We devise a novel matrix-based approach to model the leaky integrate-and-fire (LIF) neuron dynamics and natively support dense and sparse execution modes. This enables fast simulation of approximately 10,000 neurons in dense mode and 100,000 neurons in sparse mode on standard laptops and desktops without requiring specialized hardware. We demonstrate that SuperNeuroMAT consistently outperforms four established SNN simulators---NEST, Brian2, BindsNET, and snnTorch---on two performance metrics (execution speed and peak resident memory) and across various network sizes and connection probabilities. Furthermore, we demonstrate SuperNeuroMAT's applicability across a diverse set of problems. SuperNeuroMAT can efficiently handle conventional machine learning benchmarks such as the Digits and citation network datasets as well as neuromorphic event-based vision tasks such as N-CARS and ASL-DVS. Moreover, it can be extended beyond machine learning workloads and facilitate general-purpose workloads. We validated this by implementing the neuromorphic shortest path algorithm and two arithmetic primitives (addition and multiplication). SuperNeuroMAT can be installed via the Python Package Index (PyPI), thereby lowering the barrier to entry into the field of neuromorphic computing and accelerating the broader development of neuromorphic algorithms. --- ### VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model, and What Limits Its Visual Grounding Authors: Juan S. Santillana Published: 2026-08-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08477v5 We build VectraYX-Vision-1B, a sub-2B Spanish/LATAM cybersecurity vision-language model for offline use, and measure what limits its visual grounding. A frozen 1.04B-parameter decoder is coupled to a frozen vision encoder through a trainable projector: first SigLIP, then the Qwen2-VL-2B tower with a projector shaped for llama.cpp's mmproj export. With SigLIP, after five fine-tuning defects were repaired, a nine-field extraction gate with a shuffled-image control passes the same 2/9 fields under every configuration that keeps the encoder and adds no text hint. A frozen-feature probe explains why. Transplanting the Qwen2-VL tower with its own merger reads an 8-nibble address SigLIP never read (0.00 to 0.81 exact match). On B8 (2,040 items, 34 fields, 16 templates, shuffled-image and best-constant controls), 9 fields pass on a Qwen-tower checkpoint, all within trained template-field pairs. Screenshot tool identification (B6) sat at exactly 0.000. That was not a perception ceiling. Stock Qwen2-VL-2B transcribes the same images at word recall 0.93 at our pixel budget (0.52 with our letterboxing). Training only the projector on B6's task format and render family lifts B6 tool identification to 0.96 and recall to 0.48-0.51. Perception of rendered text is therefore present and trainable in this frozen-backbone design. The evidence is narrow. B6 is nearly in-distribution for that projector, which also forgets part of B8 (mean field accuracy 0.53 to 0.29 on a retention check); runs are single-seed, and no checkpoint yet has both. We document four harness defects, retract an earlier B6 score, and release code, benchmarks and checkpoints. --- ### RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene Completion Authors: Meng Wang, Hongxia Yu, Wenzhe He, Xingdong Song, Huilong Pi, Jiapeng Zhang, Ruihui Li Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08476v1 Camera-based 3D semantic scene completion (SSC) provides comprehensive scene understanding for autonomous driving and robotics. However, existing methods often treat stereo depth estimates as deterministic geometric constraints, causing depth uncertainty and local correspondence errors to propagate directly into voxel representations. To address this issue, we propose RayLift, a framework that uses stereo geometry as a metric reference while incorporating complementary ray evidence to recover reliable 3D structures adaptively. RayLift first employs a Complementary Context Encoder that extracts geometry-aware priors from a frozen 3D vision foundation model, thereby enriching the scene context. It then introduces a Depth Ray Evidence Lifter module that jointly models geometric dissimilarity, depth confidence, and spatial uncertainty to adaptively sample and weight candidate surface locations along each camera ray. Finally, a Semantic-Aware Voxel Integrator injects the resulting ray evidence into voxel features by explicitly modeling their spatial support. Extensive experiments on SemanticKITTI and SSCBench-KITTI-360 demonstrate that RayLift achieves competitive performance and consistently outperforms existing methods. --- ### Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production Authors: Cong Ming, Jingyi Chen, Bin Liu, Qi Chu, Tao Gong, Nenghai Yu, Yingfei Xiang Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08471v1 Deployed LLM safety guardrails are predominantly static: trained once and frozen at release, while new jailbreak techniques and previously un-addressed harmful categories emerge within days, leaving the defense perpetually a step behind. We present SESG (Self-Evolving Safety Guardrails), a multi-agent system running in production. SESG monitors the live traffic behind a deployed guardrail and surfaces two classes of failure: jailbreaks novel in form and harmful categories novel in content. Once a failure is confirmed, a generation agent synthesizes paired training data targeted at it; a validation agent rebalances the batch toward the direction in which the deployed model errs, so that the model's own mistakes steer its training set; and a routing agent matches the training action to the diagnosed gap and returns the next version to production. Over six rounds of live evolution (V0 to V6), a 1.7B guardrail adapts to a new threat in 16-24 hours, with about 2 hours of human effort, versus the 40-90 hours of the manual process it replaces. On six emerging threats, it outperforms static guardrails from 0.6B to 9B and an adaptive baseline while preserving its general screening competence. Since April 2026, SESG has been the primary update pipeline of Sangfor's guardrail, autonomously closing 14 of 15 new threat scenarios in two months. We release 9 test sets for the 6 new threats at https://github.com/Trams1017/SESG. Warning: This paper contains examples that may be harmful or offensive. --- ### Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation Authors: Kaichen Zhang, Wei Huang, Keming Wu, Bo Li, Xiaojuan Qi Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08469v1 Existing streaming multimodal models process observations incrementally but still follow a turn-based prefill-then-decode pattern, making them non-duplex: new observations cannot naturally enter an active generation stream. Proactive alternatives use micro-turn polling or external response gates, which fragment continuous interaction, decouple response timing from language generation, and complicate KV-cache-friendly serving. We introduce Aero Realtime, a 4B streaming multimodal model with a duplex architecture for realtime generation. Aero Realtime aligns video, audio, and textual output on a shared temporal grid, where each approximately 80-ms audio slot predicts either a lexical token or a silence token. This allows input and output to advance together, enabling one autoregressive objective to learn both when to respond and what to generate. During inference, Aero Realtime appends only the newest multimodal slot, carries forward the previous output state, and reuses the KV cache for efficient incremental execution. We further provide a complete training and serving recipe, including realtime QA construction, slot-aligned supervision, hardware-aware distributed training, and resumable inference. On four NVIDIA A6000 workstation GPUs, Aero Realtime maintains 84-ms median and 173-ms P95 processing lag over 20 minutes of a continuously streamed video, remaining within 200~ms of the source timeline. These results demonstrate the feasibility of fully aligned input-output modeling for duplex, proactive, and hardware-aligned multimodal interaction. --- ### SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills Authors: Xinze Chen, Chi Zhang, Ping Ji, Yimin Liu Published: 2026-08-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.08468v1 Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, import anomaly, and capability mismatch dimensions. We construct an adversarial evaluation dataset of 2{,}266 skills spanning 16~attack types across code-level, system-level, and semantic-level threats, and evaluate on the full SkillMD-138K corpus. Our framework achieves an AUC of 0.93 and 5-fold cross-validated F1 of 73.4\%$\pm$0.5\%, with strong detection of data exfiltration (93\%) and steganographic payloads (93\%). Crucially, we identify fundamental blind spots: \emph{host destruction} attacks using common shell commands evade all five stages (0\% detection), and \emph{prompt injection} via natural-language manipulation achieves only 42\% detection. These findings establish that static analysis alone is insufficient for skill security, motivating defense-in-depth architectures that combine fast static pre-screening with semantic review. --- ### LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs Authors: Minhan Cho, Soyoung Park, Kihyeon Jeong, Byeongkyu Jeon, Daejin Choi, Jinyoung Han Published: 2026-08-09 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2608.08467v1 The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequently used reference data, such as identifier lookup tables, directly in the server instructions: the system-prompt text a server hands to the host application. When a query concerns an entry of the embedded table, the model can act on it immediately instead of re-discovering the same information through a search tool. We test whether client LLMs actually consume such instruction-embedded data, reporting a 54,000-trial study across 24 LLMs (9 Claude, 6 Gemini, 9 GPT) on a production legal-information MCP server. A diagnostic condition that removes the competing search tool shows that failures are dominated by behavioral preference rather than missing capability. With search unavailable, 23 of 24 models read the embedded data reliably (hit ratio at least 98%); with a search tool merely present, 9 models drop below 15%. A 2^3 factorial analysis of three instruction-level interventions reveals strong interaction effects: combining all three restores at least 86% for 20 of 24 models, but individual interventions can backfire for specific model families. Per-server prompt engineering is therefore a workaround rather than a fix; we argue that MCP host applications should provide an explicit mechanism that places server instructions ahead of tool selection in the client LLM's deliberation. --- ### Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses Authors: Tailin Zhou Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08466v1 Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the \emph{harness}---is typically treated as a fixed artifact after deployment. This work studies an alternative where the harness is \emph{task-specific and continuously evolvable}: each task family maintains its own harness, which is hot-swapped across iterations through a fixed task-injection seam and rewritten using environment feedback. We introduce \textbf{Hierarchical Self-Improvement (HSI)}, a framework in which a single frozen LLM $M$ operates across three hierarchical scopes: a task harness $H$ that executes tasks, an evolver that rewrites $H$, and a meta-evolver that rewrites the evolver's strategy code under a frozen outer anchor. A thinking-on/off design isolates the contribution of harness evolution by disabling reasoning during task execution while enabling it during self-modification. HSI is bounded by two factors: a \emph{feedback-fidelity bound}, since evolution requires informative reward signals to guide selection, and a \emph{backbone capability bound}, since harness redesign cannot overcome limitations of the frozen model. On BALROG with DeepSeek-V4-Flash-Preview as the frozen backbone, HSI achieves consistent gains over the initial harness on moderate-difficulty tasks ($+39.3$ on BabyAI, $+33.0$ on Crafter, $+25.0$ on TextWorld, and $+15.0$ on MiniHack, all in raw \% Progress), while obtaining strong held-out generalization on BabaIsAI sub-suites ($0.98$ best-test on BreakStop and $1.00$ on GoTo from a $20\%$ unseen split). On tasks beyond the backbone's capability (NLE), harness evolution provides no improvement. These results demonstrate task-specific harness evolution as a viable axis for improving frozen LLM agents under clear empirical limits. Code is available at https://github.com/TailinZhou/hsi. --- ### Halpern Iteration Achieves $\tilde{\mathcal{O}}(ε^{-1/p})$ $p$th-Order Oracle Complexity for Monotone Variational Inequalities Authors: Lesi Chen, Xinliang Zhang, Hengyu Wang, Chengchang Liu, Yongchao Chen, Jingzhao Zhang Published: 2026-08-09 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2608.08463v1 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 the rate of $\mathcal{O}(T^{-1.5})$. For convex-concave minimax optimization, a subset of MVI problems, Chen, Liu, Luo, and Zhang (COLT 2025) recently improved the complexity to $\tilde{\mathcal{O}}( T^{-1.75})$ . However, it is open whether the conjectured complexity for MVI can be improved. In this paper, by using a large-step inexact Halpern iteration, we propose a novel Halpern-NPE method that achieves an even faster rate of $\tilde{\mathcal{O}}(T^{-2})$ for solving MVIs. We also provide the $p$th-order generalization of our method. We first introduce an Anchored Tensor Method (ATM) that achieves the rate of $\mathcal{O}(T^{-(p-1)})$, and then combine it with the Halpern iteration to achieve a faster convergence rate of $\tilde{\mathcal{O}}(T^{-p})$. This improves all prior results for $p \ge 2$ and matches the classical extragradient method for $p=1$. --- ### InstructionCrafter: Generating Consistent and High-Fidelity Visual Instructions Authors: Shun Okamoto, Satoshi Iizuka, Kazuhiro Fukui Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08460v1 Given textual task instructions, generating step-by-step visual instructions as an image sequence requires the simultaneous satisfaction of multiple properties, specifically step faithfulness, cross-image consistency, and per-frame visual quality. Existing text-to-image generation approaches rarely meet all three properties, owing to independent sampling that breaks consistency, finetuning on low-quality video that degrades per-frame quality, and frozen backbones that lack multi-step understanding. In this work, we propose InstructionCrafter, a diffusion-based framework with the key idea of separating the optimization of temporal and instructional alignment from per-frame visual quality via (1) spatial-freeze training and (2) instruction-aware adapters. Built on a pretrained video diffusion backbone, InstructionCrafter freezes the spatial layers that control per-frame detail and updates only temporal and text-conditioning pathways to learn instruction semantics and inter-step relations, which preserves the generative prior for per-frame quality and reduces trainable parameters by about 50 percent compared with full finetuning. We also introduce two lightweight adapters that enhance the model's understanding of instructional context. The Consistent Adapter aggregates textual cues from the entire instruction sequence and from neighboring steps to keep object identity and attributes consistent across frames, and the Context-Aware Temporal Adapter converts cross-attention outputs into biases for temporal self-attention, explicitly propagating inter-frame relations. Extensive experiments on two benchmark datasets demonstrate state-of-the-art overall performance on step faithfulness, cross-image consistency, and per-frame visual quality while significantly reducing noise, blur, and spurious subtitles. Our code and trained models will be publicly available. --- ### Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction Authors: Zhuowen Liang, Zhengxuan Zhang, Jiayang Wang, Jiazhuo Chen, Nan Tang Published: 2026-08-09 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2608.08459v1 Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domains such as finance, healthcare, education, transportation, and enterprise operations, downstream workflows rely on normalized schemas, entity identities, keys, cross-table relationships, and integrity constraints for analytics, compliance, auditing, and SQL-backed decision making. Existing Document-to-Table benchmarks are insufficient for this setting: flattening evidence into single tables can duplicate entities, obscure many-to-many relationships, create sparse records, and avoid testing whether extracted facts form a valid database instance. This creates an urgent need to evaluate document understanding as database construction rather than field extraction. We introduce Doc2DB-Bench, a benchmark for Document-to-Database construction, containing 203 long-document instances across 42 schemas and seven domain groups, with 117 entity tables, 132 relationship tables, 7,341 rows, and 41,935 cells. Built through a controllable DB-to-Doc synthesis pipeline and organized by a taxonomy of intra-table extraction and inter-table reasoning, the generated documents undergo authenticity verification, proving indistinguishable from real-world references. Doc2DB-Bench thus provides a testbed for reliable, auditable, and relationally faithful LLM-based data systems. The benchmark is publicly available at https://github.com/SetonLiang/Doc2DB-Bench. --- ### What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files Authors: Chi Zhang, Yimin Liu, Xinze Chen, Ping Ji Published: 2026-08-09 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.08453v1 Under the current standard, Agent Skills are SKILL.md files that combine instructions with supporting resources, enabling Large Language Model (LLM) agents to reuse procedures beyond a single conversation. Yet many public skills appear to originate from a single task, repository, or conversation, even when they are shared as reusable components. We analyze this gap across 138,133 public SKILL.md files from 20,556 repositories using a two-tier defect taxonomy grounded in the official specification and best-practice guidance. We find that 91.8% of skills contain at least one detected defect, with stable estimates across lenient and strict thresholds (88.8-94.6%). The dominant failures are ordinary packaging problems rather than exotic attacks: weak routing metadata, bloated or non-actionable bodies, and poor resource organization. A deterministic routing stress test over 20,000 skills shows the functional impact: skills with valid routing metadata are retrieved more reliably from startup descriptions than skills with routing defects. Defect rates vary by platform and provenance: specification-aware skills contain fewer defects, while AI-marked skills show more safety and portability problems. Lightweight enforcement and repair experiments support a quality-assured generation workflow combining spec-aware prompting, lightweight linting, automated repair, and safety gating. ---