# Research Papers — 2026-08 · bundle page 123 of 240 > Full-text markdown of papers #6101–6150 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/123 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/122.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/124.md) ### Online Convex Optimization with Dueling Feedback Authors: Yiyang Lu, Hareshkumar Jadav, Mohammad Pedramfar, Ranveer Singh, Vaneet Aggarwal Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15050v3 Noisy binary comparison between two candidates is a common interface between human and learning systems, especially in modern large language model (LLM) post-training alignment. We study online convex optimization with dueling (pairwise comparison) feedback, where the learner observes only a binary preference between two queried points. We consider adversarial sequences of convex losses and measure regret with the loss at both queried points, under a comparison link with a known nonzero slope at the origin. We propose a simple reduction that converts dueling feedback into approximate gradients, enabling the use of standard first-order methods. We show that regret guarantees transfer under this reduction, yielding $\mathcal O(T^{3/4})$ static and adaptive regret, and $\mathcal O(T^{3/4}\sqrt{1+P_T/D})$ dynamic regret with unknown comparator path length $P_T$. For strongly convex losses, the static and adaptive bounds improve to $\widetilde{\mathcal O}(T^{2/3})$. For smooth losses, we presents unified dueling ellipsoidal FTRL, and proves $\widetilde{\mathcal O}(T^{2/3})$ static regret, which improves to $\widetilde{\mathcal O}(\sqrt T)$ under additional strong convexity. --- ### Certifying Compressed Language Models: An Audit and a Statistical Toolkit Authors: Amogh Singh Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15046v1 A fraction of a point of benchmark accuracy is the usual evidence that a compressed model is equivalent to its original. That quantity is least informative when two models are most alike: a net delta is what survives cancellation between opposing per-item changes, and cancellation is most complete in the regime equivalence claims occupy. Across an atlas of 1,707 paired model-by-task cells mined from public per-item evaluation dumps (1.3B-405B), churn runs roughly five times the net accuracy delta, and cells scoring identically to their baseline still disagree on individual items. In a preregistered audit of 17 equivalence claims from three registered frames (method papers, model cards, vendor documentation), 16 are eligible. None states a prospective numerical equivalence margin, and none releases task-matched per-item outputs, though 3 release outputs for other tasks only; 5 report too little to assess numerically, so a reader cannot check them at any sample size. We audit evidential sufficiency, not truth: no claim is called false. We supply the missing instrument: paired equivalence testing at a declared margin, with certification tables giving the items an evaluation needs, computed from disagreement observed under compression, not from independent-binomial variance. A controlled experiment pairs GPTQ and AWQ on byte-identical calibration samples across five seeds. Under the frozen eight-cell decision rule H3 is supported: changing the calibration draw was sufficient to reverse the observed method ordering in 5 of 8 confirmatory cells. The reporting standard we propose is five lines: declare a margin, run the paired test, report churn beside net delta, cite the sample size you met, release per-item outputs. It applies to any comparison between two models alike enough to be worth comparing. All per-item outputs, protocols and code are released. --- ### MOSS-VL Technical Report Authors: Pengyu Wang, Chenkun Tan, Shaojun Zhou, Qirui Zhou, Yanxin Chen, Xingyang He, Huazheng Zeng, Jijun Cheng, Chenghao Wang, Xiaomeng Qian, Pengfei Wang, Zhan Huang et al. Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15045v1 We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability. It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention, so the model can naturally see incoming frames while generating; a synthesized interaction corpus supervises when to speak, when to stay silent, and when to revise; and a staged curriculum concentrates all real-time-specific training in one light final stage over a strong offline foundation. Offline, MOSS-VL-Instruct is competitive at comparable scale and leads temporal-reasoning video sets. Across four streaming benchmarks, MOSS-VL-Realtime posts the best average on three (second on the fourth) among open-source streaming models, sweeping the three subsets that squarely test proactive behavior -- 66.0 vs. 37.5 for the best baseline on OmniMMI Proactive Alerting. With 11.3B parameters but visual tokens outside the decoded sequence, MOSS-VL widens its time-to-first-token advantage over same-backbone Qwen3-VL-8B from 2.8x to 5.1x as visual context grows. We release all five checkpoints, the training curriculum, and the real-time inference code at https://github.com/OpenMOSS/MOSS-VL. --- ### SCOPE: Score-Isolated Agentic Optimization for Video World Models Authors: Yuhua Jiang, Jiaming Wang, Qingbin Liu, Feifei Gao Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15043v1 Video world models are increasingly used as simulators for planning and embodied decision making, yet improving them at inference time introduces a subtle evaluation problem: prompts, samplers, verifiers, and selectors may evolve together, making it difficult to attribute gains or prevent held-out feedback from shaping the final policy. We introduce \scope (\emph{\scopefullname}), a framework for auditable inference-time adaptation of frozen video world models. \scope represents external controls as a typed state, updates this state only through bounded changes supported by development evidence, and freezes the resulting policy before held-out evaluation. On Physics-IQ benchmark, \scope improves over the exact frozen base by $+14.24$ (95\% CI $(+8.10,+21.23)$). Controlled ablations further identify gains from scene specification, sampling, and learned selection, while the margin over the strongest matched agentic baseline remains unresolved. Cross-backbone and prospective evaluations reveal a complementary result: useful inference-time updates exist, but their benefits do not transfer uniformly across models and settings. Together, these findings suggest that reliable inference-time adaptation requires not only better proposals, but also a principled mechanism for deciding which updates should become part of the deployed system. Code is available at https://github.com/YuhuaJiang2002/SCOPE. --- ### Uncovering Hidden Leptonic Correlations with Flow Matching and Autoencoders Authors: Haruto Kitagawa, Satsuki Nishimura, Hajime Otsuka Published: 2026-08-15 Categories: hep-ph, cs.LG, hep-th arXiv: https://arxiv.org/abs/2608.15042v1 We perform a global search for values of the Yukawa matrices and Majorana masses in the Type-I seesaw mechanism. Using flow matching, which is a generative artificial intelligence (generative AI) method, we generate a broad set of solutions reproducing the experimentally measured values of the neutrino mass-squared differences and the mixing angles. Then, a machine learning method known as an autoencoder is applied to uncover non-trivial correlations among physical quantities in the lepton sector. Our analysis reveals new non-linear relations involving neutrino masses and CP phases. These findings may contribute to elucidating the origins of the mass hierarchies and mixing patterns among generation structure. --- ### LLM-Based Hierarchical Coordinated Control with Continuation-Aware Policy Learning Authors: Changhong He, Jinda Gao, Xinkuan Liu, Le Zhang, Xizi Luo, Yu Mei Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15041v1 Coordinating multiple interacting units in complex engineering systems is challenging when system interactions are difficult to model, operational information is heterogeneous, and low-level actions must satisfy strict constraints. We propose an LLM-based hierarchical framework in which the LLM coordinates interacting units based on heterogeneous operational context, while task-specific controllers or optimizers generate executable and constraint-aware actions. We further introduce Continuation-Aware GRPO to capture the consequences of coordination decisions over subsequent control intervals. Rather than judging a decision only by its immediate outcome, the method also evaluates how the system evolves afterward under the current policy. We validate the framework on multi-ramp traffic control and virtual power plant (VPP) energy management, using simplified system models for training and more realistic simulators for evaluation. Across both tasks, the proposed method consistently outperforms direct task-specific control and optimization, end-to-end reinforcement learning, rule-based and RL-based hierarchical coordination, and prompting-only LLM coordinators, demonstrating the value of heterogeneous-context reasoning, hierarchical execution, and continuation-aware policy learning. --- ### Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift Authors: Ashish Anand Shukla, Rini Smita Thakur, Aryan Das, Vinod K. Kurmi Published: 2026-08-15 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2608.15037v1 Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference. We address these failures with PRISM (Prototype-Rectified Iterative Self-supervised Manifold Denoising), a training-free, source-free TTA framework grounded in the Affine Noise Hypothesis: severe acoustic noise induces a low-rank affine shift in the multimodal latent space, with more than 90% of distortion energy confined to the leading 60 principal components. PRISM estimates and reverses this distortion from an unlabeled target batch using frozen text prototypes as geometric anchors via three closed-form geometric corrections compiled into a single static projection matrix by Affine Bias Regression. At inference, adaptation reduces to one matrix-vector multiplication in 0.0009 ms, making it substantially faster than gradient-based TTA while requiring no additional training. On UrbanSound8K, PRISM improves over the zero-shot baseline by 12.94 percentage points and surpasses an oracle-assisted TTA baseline by 9.41 percentage points, despite never observing its privileged augmented noise prompts. We further identify the Polyphonic Trap, a principled failure mode of subspace deflation for broadband classes, and resolve it via Confidence-Aware Regression (CAR), recovering up to 8.16 percentage points for the worst-affected class. --- ### Lipschitz Bandits with Arbitrary Feedback Delays Authors: Yuhao Liu, Yu Chen, Longbo Huang Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15036v1 The Lipschitz bandit problem extends the traditional multi-armed bandit framework to continuous action spaces by assuming that the reward functions satisfy a Lipschitz condition. This work investigates Lipschitz bandits under arbitrary feedback delays, where reward signals are not received immediately upon taking an action but after an arbitrarily chosen delay. We consider both stochastic and adversarial reward settings, proposing an elimination-based algorithm and an EXP3-based algorithm, respectively. For both settings, our algorithms achieve a regret bound of $\tilde{O}\left(T^{\frac{d_z+1}{d_z+2}}+\sqrt{D}\right)$ over a time horizon $T$ with total delay $D$, where the main difference between settings lies in the definition of the zooming dimension $d_z$. Our bounds match existing delay-free regret guarantees for Lipschitz bandits and characterize the additional $\tilde{O}(\sqrt{D})$ impact introduced by feedback delays. --- ### Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints Authors: Bruno Chicelli, Henrique Alves, Rodrigo Anselmo, Joshua Weinberg, Felipe Lemos, Jan Baryla Published: 2026-08-15 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.15032v1 Converting a set of architectural blueprints into a complete material quantity takeoff requires visual perception across drawing sheets, dimensional and multi-hop reasoning, and grounding in construction conventions that the drawings never state. We present Handoff-H1, a takeoff system built from three layers: purpose-built computer-vision models that extract primitives; tool-using agents equipped with image operations and in-house visual-task tools, including CV-model-backed counting, detection and plan decomposition; and a persistent, hierarchically structured project foundation, grounded in a curated construction knowledge base. We evaluate on the Construction Blueprint Takeoff Benchmark: 10 real residential blueprint sets paired with consensus-validated expert takeoffs - 2,009 verified line items, restricted for scoring to the 1,348 primary-tier materials that drive an estimate - scored per trade by an LLM judge on material coverage and quantity Precision@25% (P@.25) and combined into a weighted composite. Under identical scoring from the raw PDF, seven frontier and open-weight models span composites of 35-61, and independent professional estimators - scored against the same reconciled gold standard - post 77.6% (65.5% coverage, 87.9% P@.25). Handoff-H1, working end-to-end from the raw PDF, reaches 81.6% (86.1% coverage, 78.8% P@.25): roughly 20 points above the strongest frontier agent, and above the independent estimators by pairing near-human quantity precision with coverage they do not reach. The evaluation harness is public for the open harbor framework; the blueprint sets and ground truth are available upon request for research use. --- ### Generation of Synthetic Fingerphotos with GANs Authors: Conor Miller-Lynch, Sandip Purnapatra, Syed Konain Abbas, Lambert Igene, Faraz Hussain, Soumyabrata Dey, Stephanie Schuckers Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15029v1 Contactless fingerprinting is an emerging approach to biometric authentication that allows users to scan their fingerprints without touching a scanner. Due to the limited amount of contactless fingerprint data available and the security risks associated with sharing real individuals' fingerprints, it is valuable to explore methods of generating synthetic data that can be used in place of - or in conjunction with - real data to develop and evaluate contactless fingerprinting systems. In this paper, we present and evaluate synthetic fingerphotos generated using StyleGAN2-ADA and StyleGAN3, existing image generation architectures. We evaluate the realism, privacy preservation, and variety of the synthetic fingerphotos by comparing their biometric feature statistics to those of real fingerphotos, computing match scores between real and synthetic fingerphotos, and computing match scores between different synthetic fingerphotos. This paper provides a quantitative comparison point for future evaluations of synthetic fingerphotos. The evaluation code is made available at https://github.com/cmillerlynch/fingerphoto-gan. --- ### Closed-Form Nonlocal Shrinkage for Multiplicative Image Denoising and SAR Despeckling Authors: Xuran Hu, Mingzhe Zhu, Djordje Stanković, Yujie Zhu, Zhenpeng Feng, Yifang Ban, Ljubiša Stanković Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15028v2 Multiplicative noise poses a challenge in coherent and signal-dependent imaging owing to its intensity-dependent variance and frequently non-Gaussian distribution. We propose a deterministic nonlocal estimator that combines a logarithmic Yeo--Johnson transformation, patch grouping, an adaptive singular basis, and sparse shrinkage. The orthonormal group dictionary makes the weighted Lasso separable and yields an exact coefficient-wise soft-threshold solution. This solution replaces the iterative inner solver and expresses patch reliability and atom importance through a single threshold field. Since the dictionary is estimated from the noisy group, we introduce a random-matrix correction governed by the group aspect ratio $γ=p^2/K$. The correction links patch size, group size, and shrinkage strength. Experiments cover gamma-corrupted images from three standard benchmarks and real synthetic aperture radar (SAR) imagery from five sensors. The method gives the best result in 18 of 24 PSNR/SSIM comparisons with twelve published methods and the lowest mean ratio-image deviation across six real SAR configurations. These results support geometry-calibrated nonlocal modeling for structure-preserving image restoration, with SAR despeckling serving as a demanding application. Code is available \href{https://github.com/Teriri1999/Geometry-Calibrated-Closed-Form-Shrinkage-for-SAR-Despeckling}{here}. --- ### MotionGS-SLAM: Event-Modulated Gaussian Splatting for Motion-Blur Robust SLAM Authors: Zhiqiang Hu, Shouren Huang, Masatoshi Ishikawa Published: 2026-08-15 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.15024v1 Current Vision-based SLAM systems fail catastrophically when motion blur corrupts the visual input, as they attempt the ill-posed inverse problem of recovering sharp content from degraded observations. We present MotionGS-SLAM, which fundamentally reimagines motion blur handling through a paradigm shift: rather than removing blur artifacts, we reformulate the challenge as a well-constrained forward problem that generatively models blur formation within the rendering pipeline. By leveraging event cameras' microsecond temporal resolution and immunity to motion blur, we introduce a novel event-modulated Gaussian kernel that dynamically adapts each Gaussian's rasterization based on precise motion cues. Our dual-modulation mechanism transforms 2D Gaussian projections from isotropic dots into anisotropic, motion-aligned elliptical brush strokes (spatial modulation) while adaptively varying exposure integral sampling density based on local velocity (temporal modulation). This physics-based approach enables joint optimization of intra-exposure camera trajectories and 3D scene geometry through blur-aware photometric and event-based constraints. Extensive experiments demonstrate significant improvements over state-of-the-art methods in trajectory accuracy and map quality under severe high-motion conditions. --- ### Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form Authors: Parsa Mazaheri Published: 2026-08-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.15022v1 Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly. What causes a representation to enter that form is open, and the word workspace invites an admission story: a gate that decides what gets in. Testing it on open-weight models with Jacobian lenses, over a benchmark whose five arms share an identical context, we find no gate where it predicts one. Demand raises a concept's lens visibility beyond what applying an operator to a supplied value produces: +0.050 (+0.045, +0.057) in percentile rank on our primary checkpoint, positive on all four we measure, though that arm answers at ceiling and the accuracymatched contrast is stronger under that readout. At the same time one shared linear map decodes the variable from every arm, the control included, at 6.4-9.0x its selection-corrected floor. What produces the later readable form at the queried position is attention-mediated gathering inside a mid-depth window: separating patch depth from readout depth puts transport there at least 17x above anywhere shallower under non-saturating readouts, with no tested MLP output contributing positively inside it. Under the saturating percentile rank the same grid does not localise the window, which is a fact about that measure. An arm that needs the variable for nothing concentrates sevenfold less, so the window is demand-specific. That window has two measured edges, a survival failure below and destruction above, and it falls at the same fractional depth in a 64-layer hybrid and a 62-layer dense model from another family. We localise where the variable is installed and read, not the route from the passage, which transports nothing. But the readout is not a calibrated measure of use: three components move it to within 12% of one another and differ 7.4x in what they do to the answer. --- ### DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest Authors: Alibek Kamiluly, Milana Muratova, Yash Patel, Fan Li Published: 2026-08-15 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.15019v1 Breast mass segmentation is an important step in computer-aided mammography, but it remains difficult because masses can have low contrast, irregular shapes, and boundaries that blend with surrounding breast tissue. To address this problem, we present DualMiT-Net, a dual-branch network that uses both a focused view of the mass and a wider view of the surrounding tissue. The local branch uses a Mix Transformer (MiT-B5) encoder to learn mass shape, texture, and boundary information, while the global branch uses an EfficientNet-B5 encoder to learn surrounding breast context. Features from the two branches are shared at the deeper encoder levels and are then progressively fused in a single decoder. A spatial gate controls how much global information is added during decoding. We also evaluated four input representations and selected a percentile-windowed mammogram combined with a Gabor texture response. The model was trained and evaluated on the mass subset of the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) using a patient-level split. Across three training runs, DualMiT-Net with exponential moving average weights achieved a mean Dice coefficient of 0.9375 and a mean Intersection over Union of 0.8834. It also achieved better Dice and IoU scores than six standard encoder-decoder baselines trained using the same data and training settings. These results show that combining local mass information with wider breast context can provide accurate and consistent breast mass segmentation. --- ### S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices Authors: Haochen Huang, Shengxuan Qiu, Meng Li Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15018v2 Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and Mixture-of-Experts (MoE) have been proposed to improve inference efficiency, naively combining them often incurs excessive verification overhead and poor expert reuse, limiting their effectiveness in memory-bound edge settings. In this work, we propose S2-MoE, an efficient self-speculative decoding framework for MoE inference on edge devices. S2-MoE reduces redundant verification through routing-aware adaptive speculative expansion, improves verification efficiency with reuse-aware expert gating, and aligns draft and target execution via shared context. Implemented in llama$.$cpp, S2-MoE achieves up to $5.3\times$ speedup (about $2.0\times$ on average) over standard autoregressive decoding across diverse MoE models and datasets on edge devices. Code is available at https://github.com/angerybob/S2-MoE. --- ### Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference Authors: Yiran Gao, Juntao Chen, Tao Li Published: 2026-08-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.15016v1 Network incident response remains slow and labor-intensive as the defender must infer multi-stage attacks from partial observations and translate recovery decisions into reliable system commands. Decision-theoretic planners provide principled optimization but typically rely on abstract states and predefined actions, while large language model (LLM) agents can reason over operational context but may hallucinate attacks and responses. Toward automating response planning, we present a hierarchical agentic response framework that integrates LLM-based attack inference, rollout planning, and digital-twin validation. A fine-tuned LLM infers the attack progression and affected hosts from security alerts and system measurements. An emulated network digital twin replays the inferred attack and returns discrepancies between predicted and observed effects to calibrate the inference. A separately fine-tuned planning agent uses the rollout planning method to prioritize affected components at the tactical layer. At the operational layer, the planning agent proposes high-level recovery actions, and an execution agent translates selected actions into recovery and verification commands that are validated in the digital twin. We evaluate the framework on a 33-component enterprise-network testbed under three multi-stage attack scenarios. The results show that our framework outperforms frontier-LLM baselines in recovery success rate by 18--31%. --- ### SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system Authors: Yuhan Meng, Shaofei Li, Jionghao Huang, Jiandong Jin, Puyi Wang, Hanlin Jiang, Anis Yusof, Peng Jiang, Zhenkai Liang, Yao Guo, Ding Li Published: 2026-08-15 Categories: cs.CR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.15012v1 The rapid advancement of large language models (LLMs) has created a growing asymmetry in cybersecurity, where attack accelerates toward autonomous execution while defense remains predominantly human-intensive. Despite substantial prior work across cyber ranges, AI-driven attack, and AI-driven defense, this asymmetry persists. We trace it to a deeper root cause, that evolution itself has stalled on both sides at three layers. To overcome this, we propose co-evolution as the integrating insight, where attack and defense AI agents autonomously and safely drive each other's evolution through adversarial confrontation. Based on this insight, we present \sysevolve, comprising three co-designed components, \sysfield, \sysspear, and \sysarmor. \sysfield constructs realistic multi-host ranges. \sysspear generates efficient, safe attack schemes. \sysarmor performs real-time, interpretable defense. Together they form a self-driven adversarial loop restoring evolution at all three layers. In evaluation, \sysfield achieves zero-loss collection at 2.1\% overhead and orchestrates 257 CVEs into 1,148 ranges, \sysspear improves attack success by over 25\% over baseline LLMs, and \sysarmor achieves 10--1000$\times$ greater precision than prior systems and detects real APT attacks in production at Huawei and Sangfor. Our evaluation also reveals three findings about LLM agent capabilities. First, multi-step composition and larger topologies expose agent capability gaps hidden by single-step evaluations. Second, the bottleneck lies after initial access in post-compromise state utilization. Third, LLM agents are susceptible to environmental interference. When decoy endpoints are deployed in the range, agent timeouts triple and downstream completion disappears despite the success rates of initial accesses are unchanged. --- ### ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning Authors: Xingzheng Wu, Cheng Zhang, Guihao Yan, Xifeng Hu, Zhi Liu, Qing Cai Published: 2026-08-15 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.15009v1 Embodied intelligent ultrasound scanning enables the automation and standardization of the ultrasound examination process by integrating perception, decision-making, and execution capabilities. However, existing methods suffer from loosely coupled modeling between force and ultrasound modalities and lack awareness of scanning stages, which limits their ability to capture dynamic probe-tissue interactions. To address these issues, we propose ForceU-VLA, a force-aware Vision-Language-Action model for autonomous embodied ultrasound scanning, which leverages force signals and ultrasound image feedback throughout the scanning process to enable accurate and high-quality ultrasound acquisition. Firstly, we propose a Force-Ultrasound Synergistic Fusion Module (FUSFM) that synergistically fuses ultrasound visual and force-feedback information to provide stable, reliable guidance for probe motion. Secondly, a Stage-Adaptive Modulation Mechanism (SAMM) is proposed to accommodate the task requirements across different scanning stages by adaptively modulating multimodal features to enhance their representation quality. Additionally, we introduce ForceU-VLA-Data, a real-world, force-aware embodied ultrasound dataset that integrates visual, force, and action signals, including data from two organs across five representative clinical scanning views, and comprising 450 expert-collected trajectories with approximately 100,000 synchronized multimodal frames. Extensive experimental results demonstrate that ForceU-VLA significantly improves contact stability and probe pressure regulation in embodied ultrasound scanning, thereby effectively enhancing task execution quality and overall system reliability. The source code is available at https://github.com/VMVLab/ForceU-VLA. --- ### Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents Authors: Wei-Chieh Huang, Weizhi Zhang, Yuchen Wu, Yankai Chen, Eric Hanchen Jiang, Wooseong Yang, Yiwei Yang, Henry Peng Zou, Hanrong Zhang, Ying Nian Wu, Haolun Wu, Kai-Wei Chang et al. Published: 2026-08-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15008v1 Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely the underlying medium in which memory is represented and stored, should be used under different operating regimes. We present a controlled harness evaluation of memory substrates for memory-augmented agents, covering dense and sparse indices, text records, structural stores, hierarchical stores, refinement-based memories, parametric updates, and activation-compatible context mechanisms. Across three backbone models and four benchmark suites spanning user-centric question answering and agent-centric decision-making, we instrument 26 performance and efficiency metrics under a unified harness. Our results show that no single substrate consistently dominates: broad retrieval benefits long-context factual QA, while excessive retrieval can harm sequential decision-making by shifting attention away from action-critical context. Scalability introduces a further routing axis, as substrates that perform well at moderate history lengths can become costly or brittle at longer horizons. These findings motivate substrate routing as a necessary component of adaptive agent memory systems and provide empirical guidance for designing efficient, reliable, and regime-aware long-term memory for LLM agents. Code will be made available upon acceptance. --- ### MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems Authors: Penghao Yin, Haomin Wang, Qihong Tang, Xiaoye Qu, Hongjie Zhang, Xiao-Ping Zhang Published: 2026-08-15 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2608.15006v1 Although visual reasoning is crucial for solving complex geometry tasks, existing vision-language models rely heavily on text-only reasoning. Some recent methods introduce intermediate visual states to facilitate reasoning, but they are often hindered by inaccurate geometric representations and low rendering fidelity, ultimately leading to unreliable outputs. To address these limitations, we propose MetaReason, a framework for multimodal reasoning in plane geometry that leverages structured meta-information to enable accurate auxiliary-line construction. The framework first parses geometric images into meta-information, performs controllable edits with predefined tools to synthesize high-fidelity visual states, and then conducts reasoning based on these augmented views. To support this framework, we construct TutorGeo, a comprehensive dataset containing 17k image-to-meta conversion samples, 60k text-only reasoning traces, and 60k interleaved multimodal reasoning traces. Using this dataset, we combine supervised fine-tuning and reinforcement learning to develop robust multimodal reasoning capabilities. We also introduce ExamGeo, a benchmark derived from real-world examination problems that enables systematic evaluation across varying difficulty levels. Experimental results demonstrate that MetaReason significantly outperforms existing open-source models and achieves competitive performance against proprietary models. --- ### FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making Authors: Pramit Dutta, Jenita Manokaran, Richa Mittal, Ryan Appleby, Eranga Ukwatta Published: 2026-08-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.15004v1 Lung cancer remains one of the leading causes of cancer-related mortality worldwide, and Computed Tomography (CT) is a primary imaging tool for screening and followup assessment. After pulmonary nodule detection, radiologists manually assess anatomical location, diameter, margin characteristics, and attenuation type to support risk assessment and clinical decision-making. However, this post-detection workflow is time-consuming and can be affected by inter-observer variability. Existing Artificial Intelligence methods often focus on isolated tasks, limiting their use as a unified, clinically grounded interpretation framework. This study presents FZ-VLM, a two-stage Florence-Zephyr Vision Language Model framework for unified structured pulmonary nodule characterization in lung CT. The framework uses a fine-tuned Florence-2 model to extract radiological attributes from expert-annotated 2D axial CT slices, while a Zephyr-7B model uses these attributes to generate nodule descriptions, follow-up recommendations, and longitudinal analyses. Results showed that the Stage 1 model achieved 77.18\% accuracy for anatomical location, 67.96\% accuracy for margin characteristics, and 79.13\% accuracy for attenuation type, with a Mean Absolute Error of 2.58 mm for diameter estimation, outperforming evaluated GPT-4-based baselines as well as the human baseline. Expert radiologist evaluation of Stage 2 showed 93.9\% accuracy, 98.6\% completeness score, 76.1\% clinical relevance, and an overall score of 89.5\%. Safety analysis showed that most outputs were clinically safe, although some follow-up recommendations still required expert review. To the best of our knowledge, this study presents the first two-stage Vision-Language Model framework for structured nodule characterization and clinical decision-making. --- ### NPU Offloading of a Frozen Visual Encoder for Robot Policy Training Authors: Hyojun Yun, Seungjae Won, Hyungpil Moon Published: 2026-08-15 Categories: cs.RO, cs.AR, cs.LG arXiv: https://arxiv.org/abs/2608.15002v1 When a robot policy is trained for a new task or dataset, its visual encoder can be frozen and only its action generation module trained, reducing training cost. Freezing removes the encoder's backward pass, but its forward pass must still run at every training step because the input images change, so it keeps consuming GPU compute. We therefore ask whether moving this computation to a low power AI accelerator such as an NPU can reduce total energy despite the added data transfer and longer training time, and how it affects policy performance. We built an asynchronous training pipeline that uses both a GPU and an NPU for the AR-Actor specialist. The frozen visual encoder runs in A8W8 INT8 on a Mobilint Aries2 NPU, while the FP32 action expert is trained on an NVIDIA GeForce RTX 5060 Ti GPU. We compared a GPU-only baseline with four conditions, L1 to L4, which gradually extend NPU offloading from one to four Transformer encoder layers. Each condition was trained for 30,000 steps with three random seeds. We measured GPU board power for the GPU-only condition and combined GPU and NPU board power for the NPU conditions. Energy per sample decreased by 17.1% in L1, which offloaded ResNet18 and the first encoder layer, and by 27.9% in L4, which offloaded ResNet18 and all four encoder layers. In contrast, training time per sample increased by 15.2% in L1 and 37.7% in L4, and peak allocated GPU memory decreased by 19.8 to 20.7%. The 15 resulting policies were each evaluated with the same 300 environment seeds, for a total of 4,500 simulator rollouts. The combined success rate was 93.33% for GPU-only and 91.44 to 92.89% for the NPU conditions. These results show that NPU offloading of a frozen visual encoder can reduce training energy, but it increases training time and lowers policy success rate by 0.44 to 1.89 percentage points compared with GPU-only training. --- ### Spinning Conformal Correlators from Neural Networks Authors: Manas Dogra, James Halverson, Joydeep Naskar Published: 2026-08-15 Categories: hep-th, cs.LG arXiv: https://arxiv.org/abs/2608.15001v1 We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in examples, building on scalar conformal field techniques introduced in \cite{Halverson:2024axc}. For a particular ensemble of i.i.d. neurons we recover the 4d Maxwell CFT in the infinite-width limit. --- ### RamseyGadgets: A Graph Construction Dataset for LLMs Authors: Zohair Raza Hassan, Deepak Pandita Published: 2026-08-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.14999v1 Constructing special graphs is an important task within graph theory and computer science. Many popular graph constructions are the result of a comprehensive exploration of relevant graphs and human ingenuity. Given the rise of generative AI usage in mathematics, it is natural to test whether LLMs are able to construct graphs with specified properties using their reasoning capabilities. Unfortunately, many natural graph construction problems, such as finding extremal Ramsey-good graphs (i.e., avoiding specific monochromatic subgraphs), have been explored extensively in the literature, making it difficult to ascertain whether a construction is the product of an LLM's reasoning capabilities or its recollection from training data. In this work, we introduce \textbf{RamseyGadgets}, a novel dataset of 70 underexplored graph construction problems that require finding Ramsey-good graphs with special properties (e.g., containing an edge with a fixed color). These problems have reasonably sized solutions (at most 10 vertices) that can be verified by SAT solvers, making them suitable for automatic evaluation. Our dataset is easily expandable, as one can simply change the monochromatic subgraphs being avoided to obtain a new set of problems. We evaluate the performance of five open-source LLMs on our dataset and report the results. Our findings show that LLMs achieve only 37.70% accuracy on the hard-tier problems in our dataset, with Gemma-4-31B achieving the highest performance out of the five. We also showcase how our dataset allows us to ascertain what kind of hints help LLMs perform better at this task. --- ### PAS-QFL: Personalized Ansatz Selection for Quantum Federated Learning under Client Data Heterogeneity Authors: Jindi Wu, Qun Li Published: 2026-08-15 Categories: quant-ph, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2608.14995v1 Quantum federated learning (QFL) lets multiple quantum clients collaboratively train quantum neural networks (QNNs) without sharing private local data. However, existing QFL methods commonly assume that all clients use the same ansatz, overlooking how heterogeneous client data affects ansatz suitability. Under class-imbalanced non-IID data, different clients may favor different ansatz structures, so a fixed ansatz can lead to unstable and unfair performance across clients. In this paper, we propose PAS-QFL, a Personalized Ansatz Selection framework for QFL under client data heterogeneity. Rather than treating the ansatz as a monolithic structure, PAS-QFL decomposes each client QNN into a globally shared ansatz and a client-specific private ansatz, and personalizes the structure of the private ansatz rather than only its parameters. The shared ansatz is placed first and selected by a stability-aware cross-client criterion so that its parameters can be reliably aggregated, while the private ansatz serves as a personalized decision head, selected per client by local Macro-F1 to adapt the shared representation to its local data. During training, each client updates both its shared and private parameters locally but uploads only the shared parameters, so federated aggregation stays well-defined while each client keeps its own private structure. PAS-QFL uses Macro-F1 as the primary selection metric to avoid misleading accuracy under class imbalance. Experiments on heterogeneous QFL tasks show that PAS-QFL improves average Macro-F1 over the existing fixed-ansatz QFL baselines, demonstrating the value of personalizing the ansatz structure for practical QFL. --- ### Registration-Free Hyperspectral Reconstruction from RGB via a Permutation-Invariant Gram-Matrix Principle Authors: Jiangsan Zhao, Masayuki Hirafuji, Seishi Ninomiya, Jakob Geipel, Wei Guo Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.14994v1 Reconstructing a spatially and spectrally high-resolution hyperspectral image (HR-HSI) from a low-resolution HSI (LR-HSI) and a high-resolution RGB image (HR-RGB) usually assumes precise registration and a known camera response function (CRF). Both assumptions are difficult to satisfy with different sensors. We remove both through a permutation-invariant supervision principle: the Gram matrix of an unmixed abundance map depends on shared material composition but not on pixel ordering. Matching abundance Gram matrices therefore allows RGB-to-HSI mapping to be learned without spatial correspondence and without a predefined CRF. Under a full random permutation of HR-RGB pixels, a state-of-the-art fusion method collapses, whereas our reconstruction is unchanged after inverse reindexing for evaluation. Building on this principle, a residual spectral super-resolution function maps HR-RGB directly to HR-HSI without registration, known CRF, or paired supervision. Across indoor, natural-scene, and remote-sensing benchmarks, the method achieves accuracy comparable to approaches that require these assumptions while remaining robust when they are violated. Loss ablations further show that reconstruction accuracy is largely insensitive to the specific discrepancy used to match the Gram matrices, indicating that performance arises primarily from the permutation-invariant principle rather than loss tuning. --- ### Does a Tool Result Carry More Authority Than Plain Text? Three Prospective Studies of False-Claim Adoption in a Synthetic Assignment Task with Claude Opus 5 Authors: Justin Bronder Published: 2026-08-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.14992v1 Language-model systems increasingly read from stores they also write to, so a claim that was merely written earlier can return looking retrieved. We tested whether the message package carrying an unsupported assignment changes which answer a model gives in a synthetic lookup task. Claude Opus 5 selected a color code for a named item or abstained. In an exploratory four-arm study, false-code adoption was 0/24 with no target claim, 0/22 scorable trials when a prior assistant assertion named the target, 14/24 when a tool-result record named it, and 15/24 when that result used a ten-field metadata wrapper that marked it unchecked. The tool-result arm selected the record's code in 11/12 supported trials and 14/24 unsupported trials, ruling out a fixed output-token bias while leaving substantial planted-token heterogeneity. A document-preregistered replication reproduced the tool-result versus assistant-assertion gap, 7/24 against 0/24, one-sided Fisher exact p = 0.0047. The tool-result rate nevertheless fell from 14/24 to 7/24 across runs made four days apart. A second preregistered study gave the earlier comparison a live text control: both records were announced in advance and placed in the same final user turn, then target binding was swapped between the linked tool result and later inline JSON. Inline text was sufficient for false-code adoption in 60/60 trials; the tool-result condition produced 57/60, so the registered result-first superiority criterion failed, p = 1. The result does not show that tool results have no effect. It shows that native tool-result placement was not necessary and that this experiment did not find greater behavioral weight for the result package than for announced inline text. The findings concern a single model on one synthetic task template, accessed through one API. --- ### Risk-Adaptive Edge--Cloud Visual Reasoning for Communication-Efficient Autonomous Driving Authors: Meng Ma, Shuyang Li, Naigang Wang, Ruimin Ke Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.14991v1 Cloud-hosted vision-language models (VLMs) offer greater contextual reasoning capabilities than smaller onboard models, but frequent visual uploads increase communication overhead and add network and inference latency to tactical decisions. We present a risk-adaptive edge-cloud architecture in which onboard traffic assessment determines when cloud reasoning is requested. An onboard VLM and a lightweight detector capture temporal traffic conditions and path-relative hazards for conservative local response and selective cloud access. The cloud model provides tactical advice, while validation, vehicle control, and automatic emergency braking remain local. In CARLA experiments, our method matched the task success rate of periodic cloud access while reducing cloud requests by 54.1% and recording fewer automatic emergency braking (AEB) activations. In a delayed-roadwork ablation, semantic events triggered requests before the next scheduled audit. Across three emulated network profiles, the method continued to reduce cloud traffic, although lane changes took longer than with periodic access. Onboard traffic assessment therefore served as a practical trigger for selective VLM inference in these experiments. --- ### GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation Authors: Zhiqiang Hu, Shouren Huang, Masatoshi Ishikawa Published: 2026-08-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.14986v1 Long-horizon robotic manipulation fundamentally relies on persistent spatial memory. However, existing 3D memory systems function merely as passive recorders: they store observations using fixed, hand-crafted rules, treating every scene element--whether a critical grasp target or an irrelevant background wall--with equal importance. In this paper, we propose a paradigm shift from passive storage to active, task-driven spatial memory. We argue that a robot's memory should not simply record what it sees, but actively learn how to remember--discovering which objects to track precisely, how aggressively to update them, and what to discard, all learned end-to-end without hand-designed rules. Crucially, this active paradigm is realized by unifying memory update and readout as two sides of the same cognitive process, enabling bidirectional flow where task needs shape update strategies and vice versa. To instantiate this vision, we introduce GaussMemory, which leverages 3D Gaussian Splatting as a persistent geometric substrate. On LIBERO, GaussMemory outperforms MemoryVLA on Goal and Long-10; on VLABench, it surpasses $π_0$-FAST by +5.2% (Track 1) and +6.0% (Track 6). --- ### Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games? Authors: Wenji Fu Published: 2026-08-15 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.14982v1 Transformers applied to spatial imperfect-information games must represent map geometry while tracking hidden entities through time. We ask whether geometry-aware positional encodings improve these capabilities, without claiming a new positional encoding. We construct a four-level benchmark on a hexagonal naval pursuit game: controlled geometry and topology probes, an exact-Bayes hidden-target tracking task, offline policy imitation at 1k and 10k games, and 7,200 fixed-seed games against three legacy opponents. Across matched Transformer backbones, HexRoPE reduces exact-belief posterior cross-entropy relative to no positional encoding by 0.278 on D6-transformed test orbits and 0.329 on a larger map; both hierarchical-bootstrap confidence intervals exclude zero, and both Holm-adjusted p-values are below 0.001. At 1k games, HexRoPE improves policy action accuracy by 4.63 percentage points over no encoding and 2.05 points over rectangular relative bias; the gains shrink to 1.55 and 0.41 points at 10k games. However, HexRoPE does not improve aggregate gameplay win rate: its paired effect over no encoding is -1.56 percentage points (95% CI (-4.50, 1.17)). Rectangular relative bias is strongest on D6 belief consistency but fails sharply when extrapolating from radius 3 to radius 4, while graph bias provides only a small blocked-edge gain. The results show that geometric inductive bias improves belief estimation and data-efficient imitation, but those representation gains do not automatically produce stronger closed-loop play. --- ### Benchmarking Frontier Text-to-Image Models on Image-Description Prompts Authors: Sajjad Abdoli, Ghassan Al-Sumaidaee, Ahmed Rashad Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.14976v1 Text-to-image models are typically reported on average-case prompts, which understates the gap between systems on compositionally demanding requests involving precise object counts, multi-object attribute binding, legible embedded text, and explicit spatial constraints. We evaluate four production text-to-image systems: Hunyuan 3.0, Gemini 3 Pro Image ("Nano Banana Pro"), Black Forest Labs FLUX.2, and Ideogram 3.0. The evaluation uses the 48 hardest prompts drawn from the DataSeeds.AI Sample Dataset (DSD), selected through an automated complexity-scoring pass over the full corpus. Every generated image is graded using an independent-judge rubric. GPT-5.4-Pro authors an atomic, weighted, mutually exclusive and collectively exhaustive (MECE) evaluation rubric, while Gemini 3.1 Pro Preview independently determines whether each criterion is satisfied. Gemini 3 Pro Image ranks first with a score of 84.8/100, narrowly ahead of FLUX.2 at 82.3/100. Ideogram 3.0 and Hunyuan 3.0 score 65.7/100 and 63.3/100, respectively. Failure analysis shows that the leading systems primarily lose points through object miscounting and geometric artifacts, whereas the trailing systems more frequently produce garbled text. Ideogram 3.0 also frequently omits requested elements. Full per-sample rubrics, scores, and failure annotations are available from the authors upon request. --- ### Demand-Driven Vertiport Siting and Discrete-Event Fleet Simulation for On-Demand Urban Air Mobility Network Design Authors: Hossein Z. Saghazadeh, Yonas Ayalew, Reza Ahmari, Parham Kebria, Abdollah Homaifar Published: 2026-08-15 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2608.14974v1 This paper presents a demand-driven framework for on-demand Urban Air Mobility (UAM) network design that links vertiport siting, fleet simulation, and door-to-door travel-time feasibility. Demand is estimated from commuter and passenger activity data, converted into spatial trip-end points, and clustered using K-means to generate candidate vertiport locations. Candidate networks are screened using range and minimum station-spacing constraints, then evaluated with a discrete-event simulation that models multi-vehicle dispatch, deadhead relocation, battery swaps, and service regularity. Flight time and energy consumption are computed using a point-mass eVTOL performance model. In a Greater Los Angeles case study, the preferred design expands from four stations and four eVTOLs at low demand to sixteen stations and twelve eVTOLs at the highest tested demand level. Results show that larger fleets improve completion time and vehicle-arrival regularity but do not eliminate deadhead flights, indicating that spatial demand imbalance remains an operational burden. The travel-time savings analysis further suggests that UAM is most defensible for longer or congestion-heavy trips where sufficient non-flight time remains after accounting for flight time. --- ### A Physiology-Informed Digital Twin Framework for Simulating Liver Health Progression Authors: Sumaiya Afroz Mila, Sandip Ray Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.14969v1 We present a physiology-informed digital twin of the human liver designed for longitudinal simulation of liver function and early-stage disease progression. The model, referred to as HEPATWIN, integrates key hepatic processes, including carbohydrate, lipid, and protein metabolism, bilirubin conjugation, bile production, and detoxification, within a unified systems-level framework to generate clinically observable biomarker trajectories. Unlike purely data-driven approaches, HEPATWIN incorporates mechanistic representations of liver physiology and patient-specific inputs such as diet, activity, and baseline biomarkers to simulate disease evolution over time. To ensure consistency with clinical progression patterns, we introduce a stage-transition-driven calibration mechanism that aligns simulated outputs with population-level biomarker distributions across disease stages, including NAFLD, fibrosis, and cirrhosis. Validation using the NIDDK NAFLD dataset demonstrates that HEPATWIN produces longitudinal biomarker estimates within clinically acceptable ranges and can forecast trajectories over multi-year horizons. Furthermore, simulated biomarkers retain sufficient clinical signal to support downstream NASH detection with competitive performance relative to models using ground-truth laboratory data. These results highlight the potential of physiology-informed digital twins for personalized, non-invasive diagnosis and prediction of organ health in general and liver health monitoring in particular. --- ### A Deep Learning Model for Spatially Clustered Data via Differentiable Cluster Assignment Authors: Kexuan Li, Weidong Ma Published: 2026-08-15 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.14968v1 We consider nonparametric regression when the association between a response and its covariates changes across an unknown partition of a spatial domain. The proposed estimator learns the partition and the cluster-specific regression functions jointly. A neural network depending only on location determines cluster membership, while separate neural networks describe the covariate--response relationship within the clusters. An annealed softmax relaxation permits gradient-based estimation of the otherwise discrete assignments. Graph-Laplacian and occupancy penalties are used to discourage fragmented regions and degenerate solutions. We establish identifiability up to label permutation, bound partition error under a margin condition, and decompose prediction risk into regression and assignment components. The resulting rate agrees with that of an oracle estimator when the partition is estimated sufficiently accurately. Simulations show that joint estimation is useful when regression surfaces change abruptly across spatial boundaries, including settings with nonlinear effects, unequal region sizes, preferential sampling, and spatially correlated errors. Finally, a real data analysis is provided to demonstrate the validity and effectiveness of the proposed method. --- ### Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning Authors: Joanikij Chulev, Hendrik Baier Published: 2026-08-15 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.14963v1 Pareto Conditioned Networks learn multiple multi-objective reinforcement learning behaviours by conditioning a single policy on a desired return command. However, the local mapping from command and state to action remains opaque. We propose command-space counterfactual explanations for PCNs: given a fixed state, original command, and foil action, we search, in a black-box setting, for a minimally changed desired-return command under which the same trained policy would choose the foil. Our contributions are threefold. First, we formulate PCN explanations as return-command interventions, using a return-only PCN variant that avoids the added ambiguity of horizon-conditioning. Second, we adapt adversarial machine learning methods to reinforcement-learning explanations. Third, we introduce a boundary-seeded directional search that improves over purely local optimization in the command-action landscape, resulting in our proposed approach CF-ZOO. The resulting explanations are actionable and intuitively expressed in the user's own preferences: "If your trade-off had shifted slightly towards X, the agent would have chosen Y." --- ### LLM-based Framework for Generating and Verifying Parallel DEVS Statecharts Authors: Vamsi Krishna Vasa, Hessam S. Sarjoughian, Edward J. Yellig Published: 2026-08-15 Categories: cs.LG, cs.LO arXiv: https://arxiv.org/abs/2608.14956v1 The development of models demands sound modeling and simulation knowledge as well as domain knowledge. Every model should accurately represent a system's dynamics and be verifiable. Toward this objective, this research introduces an agentic PDEVS-LLM framework to assist human modelers in generating and verifying PDEVS statecharts for behavior modeling of atomic Parallel Discrete Event System Specification (PDEVS) models. The framework supports (re)generating plausible facts from a system description prompt using the agentic LLM used for generating plausible facts. Inconsistencies in plausible facts lead to incorrect PDEVS statecharts having logical structure and behavioral inaccuracies. A controlled-correction mechanism is developed to verify the logical consistency of the plausible facts. The agentic LLM is used to generate key behavioral conditions from the system description prompt. The plausible facts are then verified against the behavioral conditions using propositional logic entailment for a finite number of times. The verification results enable the generation of modification prompts that can reduce errors in generated plausible facts, resulting in more accurate PDEVS statecharts. To verify a statechart's logical correctness, its Timed Automata counterpart is manually created and verified for deadlock and reachability properties. The human modeler may regenerate plausible facts and PDEVS statecharts iteratively and incrementally. A basic correctness metric is introduced to quantify the completeness and accuracy of the expected behavioral traits of the PDEVS statechart models. A collection of example systems with varying levels of complexity is developed to demonstrate the capabilities and limitations of LLMs. The evaluation of the proposed verification mechanism shows a substantial improvement in the logical consistency of generated statecharts. --- ### Generative data assimilation highlights fronts as key regulators of ocean energy cascade Authors: Scott A. Martin, Georgy E. Manucharyan, Patrice Klein Published: 2026-08-15 Categories: physics.ao-ph, cs.AI arXiv: https://arxiv.org/abs/2608.14955v1 Mesoscale eddies are fundamental to the ocean circulation, yet the extent to which submesoscale motions, a few kilometers across, influence mesoscale eddy energetics through a kinetic energy cascade remains uncertain. High-resolution simulations predict that submesoscale fronts are key regulators of the cascade, transferring energy both downscale towards dissipation and upscale to sustain and shape the seasonality of mesoscale eddies. Testing these predictions has remained difficult because existing observations and state estimates cannot resolve submesoscale currents over sufficiently broad domains. Here we map the ocean's submesoscale energy cascade by combining multi-source satellite observations with a generative deep learning framework, reconstructing gap-free, kilometer-scale surface currents with physically plausible dynamics learned from simulations. Applying this to the eddy-rich Agulhas Current system, we find that submesoscales energize the mesoscale through an upscale energy cascade above 10 km, contributing to the seasonality of mesoscale eddies. Below 10 km, convergence at submesoscale fronts drives a downscale cascade towards dissipation. Both upscale and downscale pathways concentrate within fronts, where cross-scale transfer is up to an order of magnitude more efficient. Despite their limited extent, fronts account for a substantial fraction of the domain-integrated cascade, establishing them as key regulators of the cascade and targets for next-generation eddy parameterizations. --- ### T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework Authors: Zahra Fazel, Sunanda Gamage, Shayan Shirahmad Gale Bagi, Amir H. Ashouri, Tomasz S. Czajkowski, Bryan Chan, Reza Azimi, Yaoqing Gao Published: 2026-08-15 Categories: cs.AI, cs.CL, cs.LG, cs.PF, cs.PL arXiv: https://arxiv.org/abs/2608.14953v1 Recent advances in Large Language Models (LLMs) have opened opportunities to apply high-level code transformations to the field of code optimization, and it has since emerged as one of the most fundamental tasks for LLMs to perform; however, at present, LLMs struggle to apply wide-ranging code optimization tasks due to both the complexity of the code and the inability to independently verify the correctness of the transformations. In this paper, we present the Trusted LLM (T-LLM) Compiler, which proposes an advancement in compiler technology through a collaborative effort involving high-level LLM code transformations, traditional compilers, and verification tools. Experimental results reveal that it can significantly improve code correctness when tested on a set of PolyBench/C benchmarks. Our approach facilitates iterative code optimization efforts with verification strategies that enable corrective actions. Through this approach, T-LLM Compiler achieves code optimization accuracy of up to 83.3% and a speedup of up to 16.1\% on the PolyBench/C benchmarks, with the transformed code reaching an average of 26.7% speedup wrt standard baselines. Additionally, we release the project's source code to the open-source community. --- ### Evidence of Absence: Cross-Modal Abductive Risk Perception to Sustain World Models When Vision Fails Authors: Cong Xu, Ravi Sankar Published: 2026-08-15 Categories: cs.RO, cs.CV, eess.SP arXiv: https://arxiv.org/abs/2608.14952v1 A structured world-state (entities, relations, context, and predictive cues) is designed to preserve prediction-critical content when perception degrades, but it presumes observations to populate it; when the primary visual modality is occluded or degraded, those observations may be missing. We address how to sustain the world model from a complementary modality by treating the absence of expected co-evidence as evidence of a hidden cause. The abductive framework is modality-agnostic; this article instantiates it acoustically. A microphone-array front-end estimates the bearing of engine and tire sources and extracts approach-rate evidence (Doppler when a stable tone exists, a broadband looming readout otherwise); the event "signature present, visual co-evidence absent" then triggers abductive inference of a hidden road user, emitting a calibrated risk advisory rather than a control command. Recoverability of the hidden state is analyzed as an identifiability question separating shared from modality-unique information, and cueing is cast as Neyman-Pearson detection under an explicit false-alarm budget. On real occluded-approach recordings at blind junctions, the method warns a mean 1.7 seconds before line-of-sight entry, matches the sustained-window variant of the published acoustic baseline's detection rate with 42% fewer false alarms, localizes to 3.4 degrees median once in view, is well calibrated (expected calibration error 0.034), and keeps hazard awareness above 0.87 under staged vision degradation that collapses a vision-only channel to 0.03. We also measure the method's limits: calibration transfers to an unseen junction almost losslessly, the signature classifier does not, and moving-ego noise is the binding deployment constraint. --- ### PathFinder: Joint Decompositions of Linked Multimodal Datasets Authors: Ying-Qiu Zheng, Alex Fung, Stephen M Smith, Rogier B Mars, Saad Jbabdi Published: 2026-08-15 Categories: cs.LG, eess.IV, q-bio.QM, stat.ML arXiv: https://arxiv.org/abs/2608.14951v1 Low-rank matrix decompositions can uncover patterns and structure in data and have a number of different applications across many disciplines. Extensions to "joint" low-rank decompositions have been proposed to link datasets from different modalities. While these methods enable the discovery of common patterns across modalities, they require that all the multimodal data share one or more dimensions. We propose a new analysis method, PathFinder, that enables co-analysis of datasets that do not necessarily all share a dimension. The key insight is that as long as pairs or subgroups of matrices do share some dimension, and that there are one or more paths that link across the data matrices, a global joint decomposition can be sought out. This enables the joint estimation of common patterns across different modalities, species, or scales, where a one-to-one mapping across all data along some dimension is not necessarily available. We show that PathFinder is a general umbrella under which many matrix decomposition methods fall as special cases. It can be used to discover common patterns across disparate datasets and to make predictions for missing data or modalities. --- ### DA-RAC: Distance-Aware Calibration of LLM Judges for Trustworthy AI Auditing Authors: Cheng Wu, Vishal Anand, Jaya Krishna Mandivarapu, Xiya Liu, Rui Zhuang Published: 2026-08-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.14950v1 Generative AI systems are increasingly producing real-world artifacts, however their efficacy and validity are often evaluated via context-free LLM-scoring. These judges can be miscalibrated by irrelevant in-context reference examples, creating false confidence and allowing low-quality or harmful outputs to pass evaluation. We study this failure mode as context-induced miscalibration and introduce DA-RAC, a distance-aware reference-anchored calibration method for LLM judges. DA-RAC retrieves semantically and structurally similar labeled anchors for each judgement scenario, weights them by distance, and exposes neighborhood difficulty as a calibration and triage signal. On multi-run LLM-judge evaluation benchmarks, it improves calibration and reduces false-pass risk relative to zero-shot, chain-of-thought evaluation, and static-anchor baselines. Mechanistic analysis shows that judge scores vary systematically with anchor distance, while static references can induce misleading decision boundaries. Thus LLM-judgement requires not only better models, but also calibrated, auditable reference selection, especially when automated evaluation is used to support high-impact AI generated artifacts. Judgments should be grounded in relevant, inspectable, and contestable interpretive artifacts. --- ### RETRACE: Resilience-Guided Trait-Conditioned Craving Estimation from Wearable Physiology in Opioid Use Disorder Authors: Yi Xiao, Harshit Sharma, Dessa Bergen-Cico, Asif Salekin Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.14947v2 Detecting opioid craving from wearable physiological signals is critical yet difficult, with the potential to support proactive interventions for individuals with opioid use disorder (OUD). This challenge is especially pronounced under subject-independent evaluation because craving is subjective, heterogeneous, and often physiologically entangled with stress. Our empirical analysis shows that stress elicits strong and reproducible autonomic responses, while craving-related signals are weaker, sparse, and largely embedded within stress-related physiology. We further show that psychological resilience, which shapes stress regulation and craving vulnerability, is not reliably observable from short-term wearable windows, but can be captured through reusable subject-level proxies, including post-stress heart-rate recovery and autobiographical memory recall. Motivated by these findings, we introduce RETRACE, a resilience-guided trait-conditioned framework for subject-independent craving estimation from wearable physiology. RETRACE reframes craving detection as trait-conditioned physiological interpretation: rather than assuming the same physiological pattern has the same meaning across individuals, it uses resilience-related subject context to guide inference. Technically, RETRACE introduces a novel dual-encoder design that separates generalizable stress physiology from subject-specific craving interpretation. It combines a frozen stress-pretrained encoder with resilience-conditioned craving encoder, using feature-level gating and representation-level fusion to enable lightweight personalization without target-user craving labels or per-user retraining. We evaluate RETRACE on a novel multimodal OUD dataset containing wearable physiology, stress and craving annotations, and autobiographical narratives. Under LOSO setup, RETRACE achieves up to 7% absolute improvement over the strongest baseline. --- ### On the Effect of Bit-Level Parameter Perturbations in Machine Learning and Deep Learning Models Authors: Akanksha Raghapur, Mark Stamp Published: 2026-08-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26280v1 In this chapter, we investigate how classical machine learning models respond to small, targeted modifications in their parameters. We compare and contrast these results to analogous experiments on deep learning models. For classical learning models, we consider Hidden Markov Models (HMM) and Support Vector Machines (SVM), and for comparison, we conduct analogous experiments involving Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM) networks. When applied to the Drebin Android malware dataset, our results show that classical models are brittle, in the sense that a limited set of selected parameters can have a dramatic effect on model behavior. In a related set of experiments, we investigate the steganographic capacity of these same learning models, that is, the proportion of bits in model parameters that can be overwritten without having a significant adverse affect on a model. We find that classical models offer limited steganographic capacity due to their compact, parameter-efficient, and relatively sensitive parameter structure. In contrast, neural networks are parameter-redundant, enabling higher steganographic capacity, where modifications can be distributed across many parameters with minimal impact on performance. These results highlight differences in how classical and neural models respond to parameter changes, with clear implications for both robustness and hidden information embedding. Overall, this work provides a framework for understanding parameter sensitivity and steganographic capacity across different classes of learning models. --- ### FISSION: Label Augmentation for Bot Detection Authors: Sen Yang, Ignacy Nieweglowski, Aviv Yaish Published: 2026-08-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.26279v1 Bot accounts and coordinated influence operations are often discovered via heuristic methods, leaving a dearth of reliable ground-truth labels for training detection systems. To address this challenge, we study a natural question: can we generate labels to assist in learning embeddings in which bots and accounts from the same coordinated operation are close? We present FISSION, a method to generate labels by splitting each account's activity into positively labeled sub-accounts. Given this label source, we train detection models which preserve behavioral regularities recurring across positive sub-accounts. We evaluate FISSION and show it outperforms prior methods in detecting Wikipedia sockpuppets and Twitter/X bots. --- ### JAMPR+/L2D: scalable neural heuristic for constrained vehicle routing problems in dynamic environment Authors: Andrew Soroka, Alex Meshcheryakov Published: 2026-08-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26275v1 The vehicle routing problems with real-world constraints (we consider vehicles capacity limits, time windows constrains, pickup-and-delivery multi-depo --- CPDPTW) pose significant computational challenges. While classical exact and heuristic methods remain effective to solve problems of small/medium size ($N\lesssim100$), they often lack adaptability and scalability for larger logistics tasks. In this work, we show how JAMPR+/L2D RL deep learning model, proposed in to solve large CPDPTW problems can be adopted in the case of substantial changes of graph distance matrix. We test performance of JAMPR+/L2D model for medium-sized CVRP and VRPTW problems on CVRPLIB benchmarks: JAMPR+/L2D outperforms the state-of-the-art heuristic HGS in over 85\% of instances, achieving improvement in objective gap. We show that the JAMPR+/L2D model trained on CPDPTW problem, generalizes well for tasks with simpler constraints (CVRP, VRPTW), for different problem sizes and for moderate changes in distance matrixes. For more substantial changes in distance matrixes, we propose here to make fast finetuning of JAMPR+: on ORTEC data (for CPDPTW) the proposed strategy remarkably reduces the objective gap without full model retraining, what will give both accuracy and rapid inference of the model in the practical routing scenarios with distance matrix changes. --- ### Sample-Smooth Spaces: A Convenient Category for Differentiable Probabilistic Programming Authors: Patrick Forré Published: 2026-08-14 Categories: math.CT, cs.LG, cs.LO, cs.PL, math.PR arXiv: https://arxiv.org/abs/2609.26270v1 We introduce the category $\mathbf{SSS}$ of sample-smooth spaces over a mixed site. The test objects are the products $Ω_n := \mathbb{R}^n \times Ω$ of a Cartesian space with the universal Hilbert cube $Ω$ carrying all universally measurable sets, and a space is a set with a family of admissible plots $Ω_n \to \mathcal{X}$ closed under precomposition. Smoothness and measurability are then not two structures glued along an axiom, but one structure over one site. The site has finite non-empty products, because $Ω$ absorbs its own square; its Karoubi envelope contains every $\mathbb{R}^n$; and it has mixed morphisms $ω\mapsto (W(ω),Φ(ω))$, which turn measurability of a smooth family from an axiom into a consequence. $\mathbf{SSS}$ is a concrete quasitopos: complete, cocomplete, cartesian closed and locally cartesian closed, with a classifier for embeddings. Morphisms of Cartesian spaces are exactly the $C^\infty$ maps and manifolds embed full and faithfully, both without Boman's theorem. Every object has tangent and cotangent spaces, every morphism a differential. The modalities sit in an adjoint string $Π\dashv \flat \dashv \natural \dashv \sharp \dashv Λ$, making $\mathbf{SSS}$ cohesive over quasi-universal spaces. The point is the probability monad. Defining the plots of $\mathsf{P}(\mathcal{X})$ as push-forwards of $\mathcal{X}$-plots at every test object, $\mathsf{P}$ is an unconditional strong commutative affine monad on all of $\mathbf{SSS}$ -- functor, unit, product of kernels, multiplication and the monad laws are each one line of seed splitting -- and its Kleisli category, of differentiable simulators, is a Markov category. The reparametrisation trick holds by construction: every Kleisli morphism is plot-wise a sampler, stably under composition. A reflection theorem locates the whole gain in a single plot family. --- ### Decoupling Is Not Identification: Supervised Evidential Learning in Next-Token Prediction Authors: Ge Wang Published: 2026-08-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.26268v1 A next-token probability says what a model predicts, not how much training support lies behind it. A Dirichlet head can represent this distinction by separating mean $m$ from concentration $S$, but decoupling does not identify what $S$ means. Here we propose an Evidential Next-Token Prediction (ENTOP) framework to audit this gap on character-level Moby-Dick, using exact 8-gram count as a reproducible lexical-support label and withholding count regression from 20% of context types. Standard implicit evidential training carries essentially no count signal beyond confidence on held-out-label types (partial Spearman $ρ= 0.001 \pm 0.014$), whereas explicit supervision generalizes ($ρ= 0.201 \pm 0.010$; matched-pair win $= 0.822 \pm 0.021$). CE predictive entropy is at chance for unseen 8-grams (AUROC $= 0.490 \pm 0.004$), while supervised vacuity reaches $0.772 \pm 0.003$, comparable with an indexed CE-representation baseline ($0.769$) but below the tautological corpus oracle ($1.000$). Neither longest-suffix nor representation-distance strata explain where amortization succeeds. Increasing count weight under the digamma objective improves support fit only by sacrificing prediction. A constant predictor wins natural log-RMSE, and vacuity does not improve error deferral. These results motivate a minimum evidence protocol---confidence control, matched pairs, held-out labels, a constant baseline, and a decision test---and show that concentration can pass identification while failing calibration and utility. --- ### A Multi-Timestep LSTM Ensemble regressor for Enhanced Short-Term Runoff Prediction Authors: Hamid Saadatfar, AmirHossein Eshghi, Behnaz Behdani Published: 2026-08-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.26244v1 Accurately forecasting river runoff is key to managing water resources, controlling floods, and planning agriculture. This study examines the Ajichay River in northwest Iran, a major tributary of Lake Urmia that has experienced increasing water-related stress in recent years. We introduce a daily runoff prediction model based on Long Short-Term Memory (LSTM) networks. The model combines five LSTM units, each trained on different time intervals ranging from 2 to 6 days, to better capture variations in river flow patterns. To improve performance, each model was fine-tuned using Particle Swarm Optimization (PSO), a population-based optimization algorithm. The proposed approach was evaluated on unseen data from 2017-2018 using $R^2$, RMSE, and MSE as performance metrics. The results showed strong predictive accuracy, with $R^2$ values ranging from 74.95% to 91.42%. In addition, multiple feature-importance methods were applied to identify the most influential variables, providing further insight into the factors that drive runoff variations. --- ### Partially Observed Sparse Graphs: The Unknown Sampling Rate is a Tail Index Authors: Jian Xu, Delu Zeng, John Paisley, Qibin Zhao Published: 2026-08-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26199v1 A large graph is often available only in part: a crawl stopped by its budget, a panel, a partial dump. When the sampled fraction $s$ is known by design the total edge count follows from $\hat e=e_s/s^2$ and no model is needed. We treat the case where $s$ is unknown and the population size is known. Our main result is a reduction: under a sparse exchangeable (graphex) model the expected non-isolated fraction obeys $n_s/n_1\to s^{1+σ}$, so the sampling rate becomes estimable once the tail index $σ$ is, and substituting it back gives $e_s(n_1/n_s)^{2/(1+σ)}$ -- the same estimator, with the design quantity inferred. Estimating global edge cardinality in a sparse graph is therefore, in expectation, tail-index estimation, and the quadratic graphon estimator is the case $σ=0$: it fails by an identity rather than by a fit ($260\%$ median error against $27\%$). We bound the finite-size error of the substitution and show the reduction is \emph{modular} in the tail-index estimator --- filled with a published closed-form one it reaches $21.7\%$ over $13$ networks and $39$ sampling budgets with no fitting at all. Fitting a full graphex additionally returns the degree distribution at any size and a generative object, in a representation where sparsity is a coordinate and the interpolation path is dictated rather than chosen. Two limits are exact: rank-one graphexes have transitivity fixed by the degree profile, so high-clustering graphs lie outside the class; and under snowball or random-walk crawls every method here fails, the design-based oracle worst of all ($7.8\%$ to $588\%$). --- ### Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation Authors: Jian Xu, Delu Zeng, John Paisley Published: 2026-08-14 Categories: cs.LG, cs.GR, cs.SD arXiv: https://arxiv.org/abs/2609.22361v3 Joint audio--video (AV) generators are trained on data in which \emph{what an event looks like} and \emph{what it sounds like} are spuriously correlated. We present a \emph{controlled causal study} of the resulting failure mode. In an AV structural causal model where the audio is, by construction, independent of the video's nuisance appearance, models that let audio read video directly---through cross-attention or a shared latent---learn a \emph{visual shortcut}: they predict sound from appearance rather than the causal event and, when the appearance--event correlation is broken at test time, synthesize the wrong event's sound. Crucially, the popular remedy of routing both modalities through a \emph{shared common-cause latent} does \emph{not} fix this---a bottleneck, an unsupervised shared/private factorization, and a faithful shared-prior model all grab the appearance proxy and fail like the direct model. Blocking the shortcut instead requires an \emph{intervention on the nuisance}: under the stated assumptions we prove that counterfactual invariance is necessary and sufficient to identify the causal predictor, and we verify the mechanism from feature-vector SCMs to procedural pixel video, real images with spectrogram audio, moving real digits, and a conditional generator. On a \emph{real, pretrained} V2A generator (MMAudio), an input-intervention test shows the model is far from invariant to sound-irrelevant edits, though a generic-noise control reveals it is broadly input-brittle rather than specifically colour-shortcutting---clean isolation of the shortcut needs the controlled confounds our synthetic studies provide. We characterize \emph{when} the shortcut occurs, compare the objective against supervised counterfactual augmentation, and isolate the \emph{unknown-nuisance} regime---where the intervention cannot be applied---as the central open problem. ---