# Research Papers — 2026-09 · bundle page 176 of 266 > Full-text markdown of papers #8751–8800 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/176 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/175.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/177.md) ### Question's Gambit: The First Move Matters in Agentic Deep Search Authors: Radin Hamidi Rad, Amin Bigdeli, Negar Arabzadeh, Sajad Ebrahimi, Charles L. A. Clarke, Benjamin C. M. Fung, Ebrahim Bagheri Published: 2026-09-13 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.14412v1 Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmarks such as BrowseComp-Plus shows that well-configured lexical retrieval can surface high-quality evidence, yet agents may still fail to connect documents carrying evidence to the gold documents. We identify a deep research agent's first retrieval move as an important design decision for this setting. We introduce Question's Gambit, a first-move retrieval module that decomposes the question into a set of clues, reformulates them into complementary searches, consolidates the retrieved results, and reranks the candidate pool before the agent begins its iterative search-and-reasoning process. This produces an opening context designed to support both clue aggregation and final-answer verification. We further evaluate on MultiHop-RAG to test whether these benefits transfer beyond BrowseComp-Plus to a more conventional multi-hop question structure. Experiments on BrowseComp-Plus show that Question's Gambit improves retrieval recall and downstream agent accuracy over strong baselines, improving answer accuracy from 83.1% to 90.5% with gpt-5.5 over Pi-Serini, the strongest reported agentic baseline. Our results confirm that effective agentic deep research depends not only on the tools available inside the loop, but also on the quality of the first move. We published our implementation publicly at https://github.com/radinhamidi/Question-s-Gambit. --- ### Dynamic Learning Solutions: A System for Personalized Educational Video Generation Authors: Siddhanth Sridhar, Shreya Chaurasia, Baddela Sai Yaswantha Reddy, Deepak Parmar, Shylaja S S Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14408v1 We present an automated pipeline that converts NCERT textbooks into interactive video explanations that respond directly to user queries. A user uploads a PDF and asks a question; the system then generates a video-based explanation as output, handling both text and visual elements from the PDF for multi-modal retrieval and response generation. The pipeline combines a Retrieval-Augmented Generation (RAG) model with generative multimedia components. The RAG stage is optimized for the structure of NCERT textbooks and performs best on content from those books. Given a user query, the RAG model retrieves relevant content from the PDF and generates a multi-scene script containing narrative explanations and structured visual prompts aligned with the textbook's explanatory style. These prompts are passed to a Stable Diffusion module, implemented layer by layer for interpretability and control, which generates contextually relevant images. The images are then processed by DynamiCrafter to produce animated sequences. Finally, a Google Text-to-Speech module generates synchronized narration, aligning speech with the visual scenes through time-based control. The result is a coherent video explanation integrating animation, narration, and textbook-aligned visuals, transforming static educational material into an engaging learning experience. By combining multi-modal document retrieval, generative visual models, animation frameworks, and speech synthesis, this pipeline demonstrates a scalable approach to delivering interactive, personalized digital education content. --- ### Neural Modal Decomposition: Architectural Priors from Observables Authors: Juho Park, Kaushik Sengupta Published: 2026-09-13 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2609.14402v1 Many engineering building blocks behave as multi-port linear time-invariant systems. RF cavities, photonic devices, and superconducting quantum chips, despite their different underlying physics, all share a common mathematical structure for their port-level response. Each entry of the response matrix is a sum of contributions from a small number of intrinsic resonant modes, the pole-residue form. A model capable of predicting such responses for arbitrary geometries and arbitrary port configurations, while simultaneously extracting the underlying eigenmode structure, would therefore establish a foundational design principle spanning all these domains. We propose a neural framework that learns this modal decomposition end-to-end, supervised only by system-level observables and without supervising the modal parameters themselves. The architecture decomposes into a port-independent pole predictor and two port-dependent coupling predictors whose outputs are combined entry-wise, separating intrinsic from port-dependent features. This factorization yields a single trained model that generalizes to port counts unseen during training, dissolving the $\mathcal{O}(N^2)$ scaling barrier of direct regression. Despite no modal supervision, the freely-parameterized poles converge to physically meaningful eigenmodes, verified by cross-validation against the AAA rational approximation algorithm. We instantiate the framework in radio-frequency electromagnetic surrogate modeling. A model trained only on 2-port data accurately predicts $N$-port responses unseen during training. --- ### Policy Loopholes in Agent Evaluation: When Policy Ambiguity Masquerades as Agent Error Authors: Hongliu Cao Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14400v1 Agent benchmarks evaluate policy compliance but assume each policy determines a unique correct action. Natural-language policies can violate this assumption through silence, ambiguity, or contradiction, admitting multiple defensible readings that a single gold trajectory cannot capture. Auditing two $τ^2$-bench domains, we develop a taxonomy of such policy loopholes and show that affected tasks produce unreliable scores: they lower scores across different models in different ways and make every model less consistent across repeated trials. A cross-domain comparison reveals that exploitability requires both policy ambiguity and tool permissiveness: when policy complexity exceeds what tools can enforce, agents resolve gaps inconsistently and scores become unreliable. Policy specification quality sets the ceiling on evaluation quality. Benchmark developers should audit policies before collecting gold annotations. --- ### MOSCOPT: Mixture-of-Skills Collective Optimization for LLM Agents Authors: Zhenyu Zhang, Jiudong Yang Published: 2026-09-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.14399v2 Natural language prompts and skills serve as the strategic backbone of LLM-based agents. Recent advances in prompt and skill optimization have achieved notable gains, yet all existing methods optimize a \emph{single} text template---missing the synergy among multiple complementary strategies. We propose MOSCOPT, a text-native, parameter-free algorithm that jointly optimizes a pool of $N$ skills and a gating skill $G$ that dynamically selects $K$ skills per step. To effectively optimize the skills, we build the EditAdam with internally maintained dual states. Through the three-phase interleaved updates with EditAdam, the system monotonically improves without gradient or parameter tuning. Extensive experiments and detailed ablations across 5 benchmarks and 3 target LLMs demonstrate that MOSCOPT consistently outperforms all baselines, and confirm that both the mixture-of-skills architecture with selective activation and the collective evolution with three-phase interleaving are essential to its superior performance. Code is released https://github.com/zhangzhenyu13/SummerClaw/tree/master/summerclaw/agent_trainer/algorithms/moscopt. --- ### Newton Deep Unfolding for Compressed Sensing Authors: Changhua He, Xianchao Xiu Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14391v1 Compressed sensing (CS) reconstructs images from highly limited measurements, but existing deep unfolding methods are typically driven by first-order optimization and weakly exploit the optimization states generated during reconstruction. To address these limitations, we propose a Newton deep unfolding network (NDU-Net), which, to the best of our knowledge, is the first deep unfolding framework that leverages second-order optimization for CS reconstruction. Specifically, NDU-Net introduces a Newton update (NU) module to estimate Newton-type update directions and generate optimization states that characterize the current reconstruction process. Furthermore, a Newton-guided multi-scale prior (MP) module is designed to incorporate these optimization states into multi-scale feature restoration, thereby enabling the learned prior to adapt to the current reconstruction stage. Experimental results under different CS ratios confirm that our proposed NDU-Net achieves promising reconstruction performance and exhibits enhanced robustness. Our code is available at https://github.com/xianchaoxiu/DNU-Net. --- ### Formal Properties of Language as Constraints on Neural Dynamics Authors: Elliot Murphy Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14384v1 What must a neural system be capable of to implement language? Current research annotates stimuli with linguistic variables and tests which electrodes, voxels, or language-model layers predict neural activity. Yet predictive success leaves mechanisms under-constrained. Here, we show that algebraic properties of language specify invariants that mechanisms must preserve: non-associative hierarchical grouping, commutativity, recursive closure, access to substructures, and structured workspace transitions. We term this the Neural Admissibility Program (NAP). Syntactic structure building is analyzed algebraically, with candidate mechanisms offered for each requirement: content-addressable workspace memory, graph-structured transient dynamics scheduling structure-building operations (e.g. stable heteroclinic channels), and a phase-coupled sealing operation recording grouping. Simulations show that a corrected Marcolli-Berwick entropy-optimized binding gate preserves grouping only within a narrow commitment band. As an alternative, we propose a novel neural binding operation we term 'Meld': two constituent populations converge through shared synapses, integrate sublinearly, and saturate. Meld is, to our knowledge, the closest neurally plausible composition law to syntactic Merge. It preserves every NAP invariant, uses known cortical operations, and recovers hierarchical structure at every tested depth and temperature. It predicts that effective population dimensionality separates alternative bracketings and that the composite depends on constituent disagreement. Importantly, the laws decoding bracketing most accurately are a priori inadmissible, showing that decoding accuracy alone cannot adjudicate between mechanisms. By specifying how neural dynamics can remain faithful to linguistic structure, the NAP changes the criterion by which neural implementations of cognition are evaluated. --- ### Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detection Authors: Sam Williams, Yuan Xiang Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14383v1 Real-time pedestrian detection in driving scenes is constrained by three coupled failure modes: tiny targets lose discriminative evidence, occlusion weakens geometric support, and weather or illumination changes distort appearance statistics. We formulate the detector through a unified \emph{contour-guided spectral routing} view rather than treating frequency processing, attention, and boundary reasoning as independent add-ons. The detector routes information in a prescribed order: spatial evidence is first augmented with global spectral context, deep representations then exchange spatial and spectral cues, and cross-scale fusion is finally conditioned on boundary--semantic disagreement. This ordering yields a compact representation pipeline in which low-frequency context stabilizes global structure while high-frequency evidence protects small-object contours. We further retain a wavelet-subband training transformation that perturbs low- and high-frequency coefficients independently, targeting appearance shifts caused by fog, rain, snow, and low illumination. The formulation exposes a single routing variable at each stage and distinguishes reusable signal transforms from the task-specific policy that decides where each signal is injected. On CityPersons, the proposed detector obtains 70.4 AP$_{50}$ and 44.2 AP$_{50:95}$, compared with 68.1 and 42.2 for RT-DETR, while the full wavelet-augmented configuration reaches 71.1 and 44.6. --- ### Rethinking Camouflage Image Generation towards a Training-Free Paradigm Authors: Haodong Yang, Zhongling Huang, Gong Cheng Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14377v1 Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background contexts. Achieving this objective requires jointly satisfying three coupled requirements: foreground preservation to retain target integrity, semantic compatibility to select plausible concealment contexts, and appearance assimilation to reduce visual discrepancies. Recent approaches predominantly rely on task-specific training on camouflage datasets to address these requirements, incurring substantial computational cost and limiting generalization beyond the training domain. To address these limitations, we formulate training-free CIG as a concealment-oriented paradigm that preserves the target while reducing its perceptual separability from the synthesized surroundings, rather than maintaining its visual prominence, without parameter updates. We instantiate this paradigm with FreeCam based on a frozen inpainting diffusion framework to preserve the foreground. Within this framework, a Contextual Reasoning Module exploits frozen multimodal priors to infer an environment favorable to concealment, thereby promoting semantic compatibility, while an Intrinsic Appearance Module extracts low-level color and texture cues from the foreground to guide background synthesis toward appearance assimilation. Extensive experiments demonstrate that FreeCam achieves state-of-the-art generation quality and camouflage effectiveness without task-specific training, while its generated images provide synthetic supervision for camouflaged object detection and reduce target detectability under general object detectors. --- ### LLaTSA: Large Language Model-Aligned General-Purpose Transient Stability Analysis Authors: Chao Shen, Hongwei Zhen, Junyan Shao, Zhenghao Yang, Yifan Zhang, Mingyang Sun Published: 2026-09-13 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2609.14374v1 Dynamic trajectory prediction has become an important paradigm for data-driven transient stability analysis (TSA), yet most existing predictors remain system-specific and require substantial retraining when network configurations, generation mixes, or state-variable sets change. Uni-TSA introduced a general-purpose TSA framework that combines channel-independent modeling with a pretrained large language model (LLM) predictor. Nevertheless, its application to heterogeneous systems is limited by ambiguity in short observations, a mismatch between numerical trajectories and LLM embeddings, neglected coupling among state variables, and the high inference cost of dense backbones. This paper proposes LLaTSA, an LLM-aligned framework for general-purpose trajectory-based TSA. LLaTSA first incorporates operating conditions, disturbance attributes, and state-variable identity through a structured textual prefix. It then aligns normalized temporal patches with a TSA-related vocabulary before processing them with a pretrained sparse decoder-only mixture-of-experts (MoE) backbone. A state-variable coupling module captures coordinated post-fault evolution, while teacher forcing and rollout-based training support iterative long-horizon prediction. Case studies on multiple test systems demonstrate accurate trajectory prediction, reliable stability discrimination, and effective adaptation across unseen scenarios. --- ### Robust small-molecule identification from incomplete, degraded, and inconsistent spectra using multimodal mixed-condition training Authors: Bowen Gao, Lei Zhu, Yiying Wang, Wenjie Yu Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14360v2 Reliable small-molecule identification often requires complementary evidence from multiple spectroscopic measurements. In practice, however, spectra may be unavailable, degraded by measurement-related variations, or even incorrectly associated with a sample, thereby hindering accurate molecular identification. Herein, we propose a multimodal mixed-condition training strategy that accommodates missing, degraded, and mismatched measurements for small-molecule structure identification. The strategy incorporates chemical and spectroscopic knowledge through predefined missing-input configurations, modality-specific spectral perturbations, and chemically informed spectrum replacements. Models were trained on 635,441 samples comprising mass spectrometry (MS), infrared (IR), and nuclear magnetic resonance (NMR) simulated spectra from the Multimodal Spectroscopic Dataset (MSSD). They were then systematically evaluated on 79,462 held-out samples across 30 views designed to represent variations in spectra. A controlled comparison of complete-input and mixed-condition training under concatenation and mixture-of-experts (MoE) fusion showed that the training strategy was the principal source of improvement. For MoE, mixed-condition training increased the mean reciprocal rank (MRR) by 6.08% (from 0.9203 to 0.9763) and the top-1 molecular identification rate by 7.67% (from 89.50% to 96.36%). Notably, under single-modality inputs, IR MRR increased 2.15-fold (from 0.4337 to 0.9307), while MS MRR increased 2.31-fold (from 0.3711 to 0.8575). With the proposed strategy, complete-input performance remained high, while sample-level mismatch detection also improved. Together, these results highlight the potential of multimodal mixed-condition training for practical molecular identification by explicitly addressing incomplete, degraded, and mismatched measurements encountered in real-world analysis. --- ### Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents Authors: Zhangjie Fu, Jiazhen Yan, Yuanwen Chen, Xinquan Yu, Yanzhe Li, Hui Jiang, Lei Gao, Chenfu Bao Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14352v1 AI-generated image detection has attracted increasing attention, but existing evaluations mainly focus on natural images, leaving AI-generated document images largely underexplored. This omission is concerning because documents often appear in sensitive real-world scenarios, such as invoices, expense reports, certificates, and medical records. In this paper, we first construct a controlled diagnostic benchmark, AIGDoc-Pilot, and reveal that existing detectors suffer substantial performance degradation on AI-generated document images, with the mean AUC dropping by more than 7%. Based on this, we further reveal two document-specific properties behind this gap: generation artifacts exhibit strong spatial inconsistency across local regions, and text density significantly affects real-synthetic separability, where text-dense regions offer stronger discriminative evidence. Motivated by these findings, we construct AIGDoc, a larger document-centric dataset containing diverse real-world documents and AI-generated counterparts produced by multiple advanced generation and editing models. Extensive experiments on AIGDoc demonstrate that existing detectors still struggle to reliably identify AI-generated documents, while document-based training partially narrows the gap. Together, these results offer valuable insights for developing dependable and generalizable detectors in document-centric scenarios. The code and datasets will be made publicly available upon acceptance of the paper. --- ### Two-Stage Mixture-of-LoRA for Multi-Task Medical Vision-Language Learning Authors: Zhanghao Chen, Yuanyuan Li, Zhenyu Lu, Shuo Gao, Guangquan Zhou, Yikun Zhang Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14350v1 Medical vision-language models (VLMs) allow a single model to perform clinical image analysis tasks ranging from diagnosis classification to report generation. However, joint adaptation is challenged by heterogeneous output formats, conflicting task gradients, and imbalanced training data. Hence, we present \textbf{Two-Stage Mixture-of-LoRA}, a framework built on MedGemma-1.5-4B. The framework uses a shared-specific Mixture-of-LoRA architecture comprising one shared LoRA and six task-specific expert LoRAs, together with a two-stage training procedure. In Stage 1, we jointly train the shared LoRA and all task-specific expert LoRAs on all tasks. In Stage 2, we first freeze the backbone, the shared LoRA, and all non-target experts, and refine one task expert at a time. Classification and regression then receive an additional modality-balanced continuation, in which smaller modality groups are repeated to match the largest group. In the FLARE 2026 Task 3 test sets, the proposed method achieves 0.85 balanced accuracy for classification, 0.48 micro-F1 for multi-label classification, 0.79 detection F1, and 17.39 regression MAE. Code is available at https://github.com/YuanYL03/MICCAI-FLARE-2026-Challenge-Task3-2D. --- ### Multi4D: an end-to-end neural network for structural determination at complex material interfaces Authors: Haoran Zhang, Zian Mao, Shufen Chu, Xiaoya He, Yuyan Guan, Antong Yang, Mingze Li, Xiaoqin Zeng, Yujun Xie Published: 2026-09-13 Categories: cond-mat.mtrl-sci, cs.CV arXiv: https://arxiv.org/abs/2609.14348v1 Heterogeneous interfaces dictate the performance and degradation of functional materials, making it essential to link local structural variations with macroscopic failure mechanisms to guide future materials design. Yet structural heterogeneity, phase overlap, and local disorder produce highly convoluted diffraction signatures, making extended transition regions difficult to interpret at atomic resolution across large fields of view. Here, we introduce Multi4D, a physics-informed neural network framework for automated multi-component crystallographic identification using four-dimensional scanning transmission electron microscopy (4D-STEM). By combining a latent-space Diffusion Transformer for physics-constrained style translation with a rotation-invariant convolutional neural network for orientation-agnostic classification, this approach translates multi-components diffraction datasets into deterministic crystallographic maps with 98.82% accuracy. In addition, we introduce Diffraction-Inferred Structural Complexity as an information-theoretic entropy metric derived from classifier predictive uncertainty that quantifies local structural ambiguity. We apply Multi4D to generate high-fidelity structural maps of complex superconducting heterostructures, corroded alloy surfaces, and degraded solid-state battery interfaces down to single-nanometer spatial resolution. This framework establishes a statistically robust analytical paradigm for automated microscopy, facilitating both industrial quality control and the data-driven discovery of interfacial design principles. --- ### Mobile CT Services for Rural, Regional, and Remote Areas: Current Practice and Future Integration with Telehealth and Regulatory-Authorised AI Authors: Zhicheng Lu, Md Zahid Islam, M Mamun Huda, Kristie Sweeney, Shayne Chau, Oliver Mulcock, Corey Hemopo, Catherine Keniry, Mohammad Ali Moni Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14347v1 Computed tomography (CT) plays an essential role in clinical workflow to improve patient outcomes. However, access to CT imaging and specialist interpretation remains limited, particularly in rural, regional, remote (RRR), and other resource-limited settings. Recent advances in mobile CT, telehealth, and artificial intelligence (AI) provide opportunities to extend advanced imaging services to populations in RRR settings. This review examines: 1) mobile CT systems deployed in trucks, trailers, ambulances, and other mobile platforms; 2) telehealth technologies supporting CT-based healthcare; and 3) AI for CT that has received regulatory authorisation or is currently deployed in clinical practice. Applications are evaluated across four clinical functions: screening and diagnosis, patient monitoring, risk prediction, and intervention or therapeutic decision support. The review covers neurological, thoracic, cardiovascular, abdominal, oncological, musculoskeletal, and interventional imaging, with particular attention to stroke, cancer, and other image-guided treatment. Other factors such as regulatory status, deployment status, and estimated technology readiness (TRL) level are compared. Current evidence indicates that mobile CT, telehealth, and AI for conventional CT are individually relatively mature, but fully integration of these technologies remains less widely deployed and validated in the clinical settings. Key barriers include regulatory variation, domain shift, connectivity requirements, cost, workflow integration, cybersecurity, and limited evidence of patient-level benefit. Future research should prioritise prospective, multicentre evaluation of integrated CT systems in real-world and underserved clinical settings. --- ### AURA: Unified Multimodal Framework for Conversational Music Editing Authors: Quoc-Huy Trinh, Minh-Van Nguyen, Debesh Jha Published: 2026-09-13 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2609.14344v1 Instruction-guided music editors typically process each request independently, limiting their ability to support workflows in which users progressively refine a track. We introduce AURA, a unified multimodal framework for conversational music editing. AURA uses a multimodal large language model to interpret the complete dialogue history, an optional image, and reference audio, distilling the editing intent into compact concept tokens. A concept-to-audio module injects these tokens and frame-aligned reference features into a frozen MusicGen backbone, enabling precise edits while preserving unaffected content. AURA optimizes only 91M parameters while retaining 1.9B frozen backbone parameters. Experiments on Slakh2100 and MoisesDB demonstrate substantial improvements in edit correctness and content preservation over existing instruction-guided methods, including a 4-5 times reduction in FAD for out-of-domain addition and removal. --- ### Communication-Efficient LLM Adaptation over Decentralized GPU Meshes Authors: Sameera Ramasinghe, Shamane Siriwardhana, Thalaiyasingam Ajanthan, Hadi Mohaghegh Dolatabadi, Chamin P Hewa Koneputugodage, Gil Avraham, Violetta Shevchenko, James Snewin, Karol Pajak, Harry Xi, Alexander Long Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14339v1 Decentralized training enables large-model training over low-end GPUs and internet-grade connections, but communication along both data-parallel and pipeline-parallel axes becomes the primary bottleneck. We study post-pretraining adaptation in this setting. We propose an asynchronous two-circuit system: a fast compressed training circuit drives throughput using activation masking for pipeline-parallel (PP) transfer and compressed data-parallel (DP) synchronization, while a slow anchor circuit runs occasional unmasked forward--backward passes off the critical path. Then, we introduce a spectral correction optimizer that uses these delayed anchor priors to denoise masked gradients without blocking the fast stream. Although prior work has found aggressive activation compression unreliable, we show that masking supports post-pretraining adaptation at high compression rates when anchored this way. Pipeline-parallel compression alone yields up to a $9\times$ throughput gain, and combining it with data-parallel compression increases beyond $40\times$ over internet-grade $\sim 200$Mbps connections, while matching dense uncompressed performance across domain adaptation and continual pretraining. --- ### Nonparametric Variance-Penalized Actor-Critic: Statistical Inference for Risk-Sensitive Reinforcement Learning Authors: Saunak Kumar Panda, Tong Li, Yisha Xiang, Ruiqi Liu Published: 2026-09-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.14327v1 Variance penalization is a principled approach to risk-sensitive reinforcement learning (RL) that explicitly trades expected return for policy stability. Existing methods require a dedicated second critic to estimate return variance online, adding architectural complexity and compounding estimation error during learning. We propose a nonparametric variance-penalized actor-critic (VPAC) framework that replaces the variance critic with statistically grounded online estimators based on bootstrapping and random scaling, techniques drawn from the statistical inference literature for stochastic approximation. These estimators require no auxiliary network, maintain a single-critic architecture, and produce variance penalties that are bounded by construction, enabling clean convergence analysis. We establish almost-sure convergence for both a variance-penalized Q-learning algorithm and a two-timescale actor-critic variant via the ordinary differential equation (ODE) method, requiring only that variance estimates remain bounded rather than consistent. Empirically, we evaluate across discrete and continuous stochastic environments, demonstrating that the proposed methods match or exceed the variance reduction achieved by the existing dual-critic VPAC baseline while eliminating the overhead of a second critic. We further validate on a high-temperature superconductor (HTS) manufacturing case study, where VPAC-RS (Random Scaling) achieves a 74% reduction in steady-state critical current variability and a 63% reduction in episode return standard deviation, translating directly to improved yield consistency. Our results establish nonparametric statistical inference as a practical and theoretically sound alternative to auxiliary critics for risk-sensitive RL. --- ### AI Assisted Workflow Optimization and Automation Authors: Zhen Zhong Published: 2026-09-13 Categories: cs.SE, cs.CE, cs.LG, q-fin.RM arXiv: https://arxiv.org/abs/2609.14323v1 Against the backdrop of digital transformation and stricter regulation, enterprise compliance work demands higher efficiency and accuracy. The auxiliary compliance process has become an important entry point for optimizing the compliance system due to its strong transactional nature and high degree of repetition. This study focuses on the process characteristics of auxiliary compliance work, sorts out its structural composition and organizational mechanism, proposes an optimization path with process reengineering, system modeling, and technology integration as the core, and focuses on exploring the collaborative application of key technologies such as RPA, rule engine, and semantic recognition in process automation. Research suggests that the systematic optimization and intelligent upgrading of auxiliary processes will help build a modern compliance operation system that is responsive, efficient, structurally clear, and risk controllable. --- ### SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization Authors: Zian Liu, Yiwen Hu, Zican Dong, Tian Xie, Wayne Xin Zhao, Yucheng Ding, Ran Tao, Bryan Dai Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14320v1 Recently, linear attention layers have been increasingly adopted to replace softmax attention at scale for long-context modeling. However, existing context extension approaches typically apply continued pretraining directly without modifying these layers, overlooking the spectral properties of linear attention state dynamics. In this work, we study long-context extension of Gated DeltaNet (GDN) from a spectral perspective of transition matrix and identify two essential factors governing long-range information retrieval: (1) a sufficiently broad slow spectral band aligned with the target dependency length, and (2) the preservation of fast-decaying modes for state clearing and context switching. Based on this observation, we propose SpectralShift, a spectral reparameterization approach for long-context continual pretraining of GDNs. Specifically, SpectralShift reparameterizes the alpha projections initialization to reshape the decay spectrum by enhancing slow propagation capacity, and further introduces a learning-rate scaling for alpha projections to facilitate long-context training. Experiments show that SpectralShift consistently improves long-context capabilities over training, providing an effective and efficient solution for extending context windows of linear attention models. The code has been open-sourced at https://github.com/RUCAIBox/GDN-SpectralShift. --- ### Learning Continuous Source Responses For Generalizable AI-Generated Image Detection Authors: Manni Cui, Ruiqi Liu, Zijian Yu, Hao Tan, Zibo Wei, Zian Wang, Ziheng Qin, Huijia Zhu, Weiqiang Wang, Jun Lan, Shu Wu Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14316v1 Advances in image generation have made synthetic images increasingly difficult to distinguish from real photographs, raising concerns about the trustworthiness of visual media. Existing AI-generated image detectors often perform well on in-domain data, but their robustness and cross-generator generalization remain limited. These limitations are commonly attributed to overfitting to shortcut cues. Although many methods seek to suppress shortcut learning, most retain binary classification as the training task without reconsidering how the task itself shapes the learned representations. We introduce CuRe, a framework for learning Continuous Source Responses that revisits authenticity detection from the perspective of the training task. CuRe reformulates backbone adaptation as regression of real-generated mixing ratios, providing finer supervision that encourages the model to capture authenticity-related variation beyond binary endpoint separation. We further select a compact source-response subspace to suppress nuisance variation and limit the final classifier's access to potential shortcut cues. Across ten public benchmarks, CuRe achieves an average balanced accuracy of 89.7%, exceeding the second-best method by 5.2 percentage points. Further experiments demonstrate consistent generalization gains across visual backbones and strong robustness to common image degradations. Code is available at https://github.com/manic-cui/CuRe --- ### S3-Tracker: Self-Supervised Surgical Tissue Tracking With Contrastive Random Walks Authors: Jiaming Zhang, Zijian Wu, Mehran Armand, Septimiu Salcudean Published: 2026-09-13 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.14313v1 Robust point tracking in endoscopic videos is essential for computer-assisted intervention and autonomous robotic surgery, enabling continuous registration between intraoperative video and preoperative imaging despite soft tissue deformation. However, supervised tracking methods depend on large annotated datasets, while surgical conditions make reliable trajectory annotation challenging. We propose a self-supervised Track-Any-Point approach that learns from unlabeled surgical videos by establishing global pixel correspondences and inferring point trajectories through contrastive random walks. Trained without annotations, our method achieves performance comparable to existing semi-supervised approaches while implicitly handling tissue deformation. These findings demonstrate the feasibility of self-supervised point tracking in surgical environments and its potential to reduce reliance on annotated data. --- ### DTI-Guided Volumetric Spherical Harmonics Regression for Single-to-Multi-Shell dMRI Synthesis Authors: Binghua Li, Christina Andica, Tong Liang, Ziqing Chang, Chao Li, Wataru Uchida, Kaito Takabayashi, Qibin Zhao, Toshihisa Tanaka, Zhe Sun, Shigeki Aoki Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14312v1 Multi-shell diffusion MRI (dMRI) unlocks more expressive microstructural modeling than single-shell scans, yet its longer acquisition time hinders deployment in large-scale cohorts and time-constrained clinical settings. Synthesizing an unobserved shell from a single-shell input is fundamentally ill-posed and further complicated by protocol mismatch, where source and target gradient direction sets may not align. We propose DTI-SHNet, a single-to-multi-shell synthesis framework that operates in the real symmetric spherical harmonics (SH) coefficient domain and performs spatially aware volumetric regression. Given a source shell, we estimate diffusion tensor imaging (DTI) and use direction-agnostic parametric maps along with a brain mask as conditioning priors to guide a 3D U-Net regressor from source-shell to target-shell SH coefficients. To couple coefficient accuracy with signal fidelity, we introduce a signal consistency regularization that reconstructs signals on randomly sampled canonical directions from predicted coefficients and enforces agreement in the signal domain. Experiments on UK Biobank and Cam-CAN data for b=1000 to b=2000 dMRI synthesis show that DTI-SHNet achieves competitive visual quality compared to advanced methods, while better preserving downstream diffusion measures. Our code is available at https://github.com/xiaovhua/dti-shnet. --- ### Robust low-rank tensor completion via factorized weighted tensor schatten-p norm minimization Authors: Binghao Wang, Feng Zhang, Wendong Wang, Jianjun Wang Published: 2026-09-13 Categories: cs.CV, math.OC arXiv: https://arxiv.org/abs/2609.14307v1 Low-rank tensor factorization provides a flexible framework for completing multidimensional data from incomplete and corrupted observations. However, unweighted spectral regularizers impose a common shrinkage profile across singular components, which may excessively attenuate dominant low-rank components, and factorized variants either lack component-specific weighting or require costly singular value decompositions (SVDs). This paper proposes two weighted Schatten-$p$ tensor factorization models, termed \WSpTFI{} and \WSpTFII{}, under the tensor-tensor product (t-product) framework to address these limitations. \WSpTFI{} is motivated by a factorized weighted tensor Schatten-$p$ norm identity and permits flexible, possibly asymmetric factor exponents. \WSpTFII{} constructs a regularizer from transform-domain column-pair energies, yielding SVD-free main factor updates and a column-pruning mechanism for reducing redundant rank components. This paper further develops an iteratively reweighted alternating direction method of multipliers (ADMM)-type scheme for \WSpTFI{} and an iteratively reweighted least squares (IRLS)--block successive upper-bound minimization (BSUM) scheme for \WSpTFII{}. Theoretical analysis establishes the weighted factorization relation and provides a conditional limiting Karush--Kuhn--Tucker (KKT) characterization for \WSpTFI{}. For \WSpTFII{}, the actual damped quadratic block updates yield a quantitative sufficient-decrease mechanism for the fixed-$δ$ smoothed factor objective. This implies asymptotic regularity, and every accumulation point of the fixed-dimensional tail is stationary. Experiments on synthetic tensor completion, color-image restoration, hyperspectral inpainting, and printed-circuit-board defect detection demonstrate competitive reconstruction quality and robustness under various degradation conditions. --- ### E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning Authors: Xiaoya Wang, Yutong Xu, Junjie Wang Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14302v1 Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucination evaluations are mostly claim-centric; they assess whether generated statements are supported, but not whether evidence remains traceable through rationale, confidence, and final action. We introduce E2A-Bench, a 969-query benchmark for financial chart reasoning, constructed from 323 HS300 constituents under three input modalities with deterministic OHLCV-derived evidence anchors. E2A-Bench evaluates grounding, reasoning-action consistency, evidence-confidence calibration, and directional coverage through UCR, RCI, ECI, and NDR, where NDR measures coverage-aware evidence-to-action reliability rather than realized trading performance. Evaluating 20 VLMs reveals three failures hidden by scalar hallucination scores: the lowest-UCR model ranks near the bottom by NDR due to only 6.4% directional coverage; oracle-aided verification reduces unsupported claims but can collapse coverage; and financial fine-tuning amplifies the BUY:SELL ratio by factors of 4.21 to 4.68 across strict base-fine-tuned pairs. These results show that financial VLM evaluation should trace the full evidence-to-action chain rather than rely on a single hallucination score. Code and data: https://github.com/wanng-ide/E2A-Bench --- ### Learning Source Acquisition Policies by Offline Planning Authors: Ziqi Zhao, Run Xu, Qingjian Ni Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14299v1 Predicting under an acquisition budget requires choosing feature groups whose value can depend on later queries. O-MPAC transfers finite-horizon risk-cost targets from complete training records into a shared source-action scorer. At inference time, the scorer uses partial observations and source metadata, re-scores after each query, and applies a hard cost mask. We analyze how tied teacher targets and the remaining planning horizon affect the learned decisions. Uniform supervision over tied minima preserves the target distribution under source relabeling. In a five-seed routing experiment, it achieves 0.965 accuracy under both original and context-last orders. On six real tasks, validation selects H1 without action cross-entropy in all thirty splits. O-MPAC has the highest mean budget-integrated accuracy on five tasks against source-adapted GDFS, DIME, AACO+NN and a static policy. --- ### Fusing Spectral Signatures and Activation Clustering for Backdoor Detection in Healthcare Imaging Models: Method, Implementation, and Evaluation Authors: Suresh Tamang Published: 2026-09-13 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.14290v1 Machine learning models are increasingly deployed in healthcare imaging pipelines for diagnostic support, and training-time attacks against them are a named sector-level concern: healthcare-sector guidance identifies model poisoning and adversarial attacks as threats requiring dedicated defenses, while federal policy directs expanded AI vulnerability-detection tooling to critical infrastructure operators such as rural hospitals. Spectral signature analysis and activation clustering are two established backdoor detection methods routinely evaluated as independent baselines, but their outputs are not ordinarily combined, and reported detection performance on medical imaging benchmarks remains sparse relative to the natural-image setting. This paper contributes three things: a score-level fusion rule combining per-class spectral ranking with activation-clustering flags into a single per-sample poisoning score and a model-level agreement statistic; an open-source implementation of the resulting eight-stage pipeline; and an evaluation of that pipeline against synthetically poisoned variants of a public medical imaging benchmark and CIFAR-10 at four poisoning rates (0%, 1%, 5%, 10%) over five seeds each, measuring each detector alone against the fusion. On the medical benchmark, the fused detector reaches AUROC >= 0.99 at every nonzero poisoning rate tested. On CIFAR-10, fusion does not uniformly help: at 10% poisoning, activation clustering's true-positive rate collapses to 0.000 and spectral AUROC independently degrades to near-chance (0.545), despite a 97.2% attack success rate confirming the backdoor was fully installed. The fused score, a weighted combination of both signals, inherits this joint failure. Detection output is expressed in NIST AI RMF Measure-function and MITRE ATLAS terms, so findings are reported in the vocabulary security and compliance teams already use. --- ### Editorial routing shapes how computational results are qualified in AI-assisted scientific writing Authors: Jihan Kim Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14288v1 Large language models increasingly analyze computational results and draft manuscripts, making reliable communication as important as correct analysis. Using fixed computational evidence, we tested whether assigning comparisons across modeling choices elsewhere in a research workflow changes manuscript reporting. In constrained sentence-writing tasks, Anthropic's Claude Sonnet 5 often omitted numerical qualifications when detailed comparisons were assigned to a group repository, but retained them more often when the same comparison was assigned to Supporting Information or its own working notes; Claude Opus 5 was less sensitive. These effects did not follow a simple accessibility ordering. A targeted placement rule largely restored sentence-level qualification, whereas a generic accuracy reminder did not. Longer contributions retained numerical qualifications, although some summaries across computational settings were still redirected to the repository. Thus, documenting context within an AI workflow does not ensure its communication where readers encounter the result. --- ### Vision-Language Models for Criterion-Level Grading of Handwritten Examinations in Outcome-Based Education Authors: Asif Hasan Tonmoy, Saad Ahmed, Md Khalid Syfullah, S. M. Jahangir Alam Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14284v2 Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. This study evaluates vision-language models (VLMs) for handwritten outcome-based assessment across five dimensions: accuracy, human agreement, repeated-run reliability, error concentration, and explanation quality. Using 1,982 criterion-level records from 485 undergraduate examination answers, we compare 20 configurations spanning Qwen2.5-VL, InternVL3, Pixtral, a Donut baseline, and a cascade ensemble. Evaluation setups include zero-shot prompting, few-shot prompting, partial fine-tuning, and Low-Rank Adaptation (LoRA). Two independent faculty markers regraded all 291 test criteria, providing a human agreement baseline on the same assessment materials. Qwen2.5-VL with LoRA achieved Quadratic Weighted Kappa (QWK) of 0.727 and mean absolute error of 0.435 marks against the examiner, compared with mean human-pair QWK of 0.551. This comparison reflects calibration to the examiner's training marks. LoRA outperformed partial fine-tuning for all three instruction-tuned VLMs, while few-shot prompting reduced QWK in every configuration with valid prompted scores. Aggregate reliability and exact repeatability diverged: intraclass correlations ranged from 0.790 to 0.874, yet 50.2-63.6% of criteria changed marks across five sampled runs. Attention-guided deletion showed no statistically significant advantage over random masking, and four faculty reviewers reached no consensus on explanation usefulness. These findings highlight the need for rubric-specific calibration, repeatable scoring, review of consequential errors, and separate validation of explanations. The released evaluation protocol supports criterion-level assessment research and grading tools with teacher oversight. --- ### Biquaternionic Space with Complex-valued Attention for Temporal Knowledge Graph Completion Authors: Rushan Geng, Cuicui Luo Published: 2026-09-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.14279v1 Temporal knowledge graph embedding (TKGE) models infer missing facts in knowledge graphs that evolve over time. Many existing models use a single geometric space, which can limit their ability to represent diverse relational patterns, or treat entity representations as static. We propose Biquaternionic Space with Complex-valued Attention (BSCA), a TKGE model that combines circular and hyperbolic rotations within a unified biquaternionic framework. A complex-valued attention mechanism adaptively fuses time-conditioned and relation-conditioned entity representations, allowing them to vary with temporal and relational context. Experiments on five benchmark datasets show competitive performance across datasets, with the largest improvement on GDELT: BSCA achieves an MRR of 52.1\%, compared with 38.1\% for the strongest baseline in our comparison. --- ### SpermYOLO: A Coordinated YOLO-Based Detector for Accurate and Efficient Sperm and Impurity Detection in Microscopic Images Authors: Shengqi Chen, Zilin Wang, Xingyu Pan, Wenting Yu, Pengchao Deng, Guohua Wu Published: 2026-09-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.14278v1 Accurate sperm detection is essential for computer-assisted semen analysis, yet it remains challenging in microscopic images due to dense distributions, visually similar artifacts, and sperm-like impurities. In this paper, we propose SpermYOLO, a coordinated and compact YOLOv11-derived framework for joint sperm and impurity detection in microscopic images. SpermYOLO introduces four architectural improvements: C3k2-IDB for channel-wise discriminative feature extraction, D2SEM for spatial--spectral semantic enhancement, MFM for adaptive multi-scale feature fusion, and the DESD Head for detail-enhanced shared prediction. Experiments on the SVIA semen microscopic imaging benchmark show that SpermYOLO achieves 97.2\% sperm AP and 75.4\% impurity AP, outperforming generic detectors, dedicated sperm detection models, and improved YOLO variants. Compared with the baseline model, SpermYOLO improves sperm AP, impurity AP, $\mathrm{mAP}_{50}$, and $\mathrm{mAP}_{50:95}$ by 1.6, 10.0, 5.8, and 2.7 percentage points, respectively, while preserving a lightweight model scale. Cross-scene evaluation on the SDTB testicular-biopsy microscopy benchmark shows that SpermYOLO remains effective with extremely small sperm targets and complex tissue backgrounds, achieving the highest $\mathrm{mAP}_{50}$ and $\mathrm{mAP}_{50:95}$ of 74.8\% and 31.2\%, respectively. Ablation studies and qualitative analyses further support these improvements by demonstrating the contributions of the proposed modules and showing more focused feature response patterns than the baseline model. These findings suggest that SpermYOLO is an effective and efficient approach for sperm detection in challenging microscopic imaging scenarios. --- ### Parameter Estimation of Ringdown Quasinormal Modes with Autoencoder Authors: Momoka Iida, Hayato Motohashi, Hirotaka Takahashi Published: 2026-09-13 Categories: gr-qc, astro-ph.HE, astro-ph.IM, cs.LG, hep-th arXiv: https://arxiv.org/abs/2609.14277v1 Ringdown gravitational waves from binary black hole mergers can be modeled as superpositions of quasinormal modes (QNMs), whose frequencies and excitation factors encode properties of the remnant Kerr black hole. Reliable extraction of multiple QNM components is challenging because of mode overlap and noise. We develop an autoencoder-based framework for multi-component QNM analysis, in which the latent space is trained to represent the physical parameters of individual modes, enabling waveform denoising and parameter estimation within a common framework. Using controlled model waveforms constructed as finite sums of Kerr QNMs with recently established high-precision frequencies and excitation factors, including their nontrivial spin dependence near resonant excitation, we assess the method across partitioned spin intervals. The model achieves good in-domain waveform reconstruction and parameter recovery for the two longest-lived components of eight-component input waveforms, while its performance degrades when the validation spins lie far outside the training range. In a selected spin interval, the framework also recovers the 32 parameters of an eight-component waveform with good overall agreement. These results demonstrate the feasibility of physics-informed autoencoder-based inference for a prescribed multi-component ringdown waveform family and motivate further tests with progressively more realistic signals. --- ### Sparsity-Adaptive Sharpness-Aware Minimization Authors: Shiryu Ueno, Yoshikazu Hayashi, Kunihito Kato Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14274v1 Deploying deep neural networks in real-world settings requires models that are both compact and robust to common corruptions. However, at deployment-relevant high sparsity, standard pruning pipelines often degrade corruption robustness, and existing sharpness-aware training/pruning approaches provide limited robustness gains. We address this issue by introducing Sparsity-Adaptive Sharpness-Aware Minimization (SA-SAM), which derives a sparsity-dependent SAM/ASAM perturbation radius by keeping the mean absolute perturbation (an $\ell_1$-based proxy) approximately invariant as sparsity increases. As a simple complementary option, we evaluate Magnitude-Weighted Hessian (MWH), derived from a second-order removal-path analysis, yielding an importance proportional to $\mathrm{Diag}(F)_i\,|w_i|$, where $\mathrm{Diag}(F)$ is the diagonal empirical Fisher used as a curvature proxy in our implementation. Across CIFAR-10-C, CIFAR-100-C, and ImageNet-100-C, our approach achieved stronger corruption robustness than the considered pruning baselines at 80--90\% sparsity, while preserving clean accuracy. We additionally quantify the robustness--throughput trade-off by reporting measured inference throughput under sparse execution at deployment-relevant sparsity levels. --- ### Bayesian optimization with kernel ensembles and disagreement-based acquisition for source localization and acoustic inversion Authors: Heng Zhang, Haotian Xiang, Florian Meyer, Qin Lu Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14262v1 Joint source localization and geoacoustic inversion requires optimizing an objective built from an expensive normal mode propagation model. Bayesian optimization (BO) with a Gaussian process (GP) surrogate can obtain accurate parameter estimates within a limited number of forward model evaluations, but its performance depends on the choice of kernel family. With few observations in a seven-dimensional search space, no single kernel can be expected to perform consistently well across individual inversions. To reduce this dependence, we use a weighted ensemble of GPs with different kernel families, allowing the surrogate to adapt to the observed objective without committing to one kernel in advance. The ensemble is combined with an optimum-conditioned acquisition function that determines where the expensive objective should be evaluated next. Experiments on simulated and measured SWellEx-96 data show that the resulting method achieves the lowest mean final objective among the considered BO strategies and reduces parameter estimation error on most coordinates. Ablation results further show that the ensemble provides robustness to kernel choice, while the acquisition function accounts for most of the optimization gain. --- ### VGFM: Expressive Robot Policies via Dense Value Guidance in Flow Matching Authors: Prajwal Koirala, Mark Campbell Published: 2026-09-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.14261v1 Recent robot learning paradigms increasingly rely on large offline datasets of robotic interactions to train control policies. Expressive generative models enable rich and multimodal action representations, expanding the capability of this paradigm for complex robotic control. However, policy improvement with multi-step generative actors remains challenging. In offline reinforcement learning (RL), incorporating value-based objectives along generative trajectories often introduces substantial training complexity, including backpropagation through time (BPTT), auxiliary architectures, or distillation losses. We propose Value-Guided Flow Matching (VGFM), a scalable offline RL framework that enables dense value-guided shaping within a flow-based policy while avoiding BPTT and additional algorithmic overhead. VGFM parameterizes the policy as a conditional flow-matching model in action (x-prediction) space, ensuring that each intermediate flow step produces a valid robot action that can be directly evaluated by a standard offline RL critic. This design allows value guidance to be applied at randomly sampled flow times without differentiating through the entire generative trajectory, while preserving inference-time flexibility by varying the discretization of the underlying flow ODE without retraining. Evaluated on robotic locomotion and manipulation tasks in OGBench, VGFM achieves strong performance across a wide range of tasks under rigorous evaluation protocols. With minimal hyperparameter tuning, these results demonstrate that VGFM provides a simple, scalable, and effective approach for expressive policy learning in long-horizon, goal-oriented robotic control. --- ### SPARK: Representation-Level KV Memory Alignment for Safer Vision-Language Models Authors: Mohd Azfar, Izhar Dad Khan Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14258v1 Vision-language models (VLMs) remain vulnerable to jailbreaks that distribute harmful intent across text and images, making unimodal safety mechanisms insufficient. We investigate whether this vulnerability can be mitigated directly in the multimodal key-value (KV) memory formed during prefill, without modifying model parameters at inference time. We introduce SPARK, a two-stage framework for targeted KV-memory repair. Stage 1 uses a disposable diagnostic adapter to identify harm-associated directions in multimodal key and value representations. Stage 2 projects out these directions, learns a lightweight residual repair, and anchors repaired keys with an image-structural prior to preserve visual grounding. Rather than applying the intervention uniformly, SPARK mixes repaired and original memory using a head-wise coefficient g_h* determined by intervention-relevant subspace energy E_h, requiring no explicit harm classifier at inference. Across LLaVA-OneVision-7B, Chameleon-7B, Qwen2-VL-7B, and InternVL2-4B, SPARK reduces multimodal attack success while preserving general capability. On LLaVA-OneVision-7B, image-only jailbreak attack success falls to 4.7%, while MMMU remains within 0.6 points of the undefended model (47.8 vs. 48.4) with near-baseline language quality. On MM-SafetyBench, attack success decreases from 39.2% to 12.4%. Even under white-box adaptive joint prompt-image attacks, attack success is limited to 20.3%, compared with 54.6% for the undefended model. These results suggest that multimodal jailbreak behavior can be substantially mitigated by selectively repairing intervention-relevant KV subspaces at prefill, particularly when harmful evidence is carried by the visual modality. --- ### DenMark: Robust Semantic Watermarking for Diffusion Language Models Authors: Tianhao Ma, Weihao Xuan, Dong-Dong Wu, Farshid Nooshi, Takashi Ishida, Gang Niu, Naoto Yokoya, Masashi Sugiyama Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14257v1 Semantic text watermarks encode signals in meaning rather than surface token choices, offering robustness to paraphrasing and other semantic-preserving edits. Existing semantic watermarking methods are primarily designed for autoregressive language models (ARLMs), where completed candidate units can be generated and scored before generation proceeds. This paradigm does not naturally extend to diffusion language models (DLMs), where semantic units remain incomplete during intermediate denoising steps and tokens may be updated in flexible orders. We propose DenMark, a semantic watermarking framework that injects key-dependent signals directly into the DLM denoising process. DenMark partitions the output into fixed token regions and uses temporary rollouts as semantic lookahead: conditional completions estimate the eventual semantics of an incomplete region, enabling DenMark to select local updates with higher estimated semantic watermark scores. Repeating this procedure across denoising steps progressively accumulates watermark evidence in the final output. For detection, DenMark uses calibrated scanning over candidate unit sizes to remain robust to boundary shifts introduced by semantic attacks. Across four DLMs, three datasets, and four semantic attacks, DenMark achieves the best results across all reported detection metrics in all 48 backbone-dataset-attack combinations. These results demonstrate that DenMark provides an effective mechanism for robust semantic watermarking in DLMs. --- ### Document Topic Alignment Metrics for Evaluating Topic Models of Short-Text Public Health Communications on Social Media Authors: Wangjiaxuan Xin, Shuhua Yin, Yaorong Ge, Shi Chen Published: 2026-09-13 Categories: cs.CL, cs.SI arXiv: https://arxiv.org/abs/2609.14256v1 Topic models are widely used to analyze public health-related social media short texts, yet their evaluation remains dominated by metrics that focus entirely on generated topics alone. There is a lack of metrics that quantitatively assess whether assigned topics meaningfully represent the corresponding short-text posts. We propose Document-Topic Alignment metrics (DoTA), an assignment-aware evaluation framework comprising metrics that measure semantic alignment between documents (posts) and their assigned topics. We also introduce margin-based and discriminative variants that capture topic assignment confidence and distinguishability. We evaluate DoTA across five topic models on three public health-related social media datasets from X and compare DoTA metrics with conventional topic-based metrics. Results show that DoTA provides complementary evaluation cues and aligns meaningfully with human evaluations. These findings establish the need for assignment-aware evaluation and demonstrate that the addition of DoTA enables a more comprehensive and practically meaningful evaluation for assessing short-text topic modeling performance. --- ### Towards Anticipatory Databases Through Shared Data and Workload Semantics Authors: Farzaneh Zirak, Kasper Overgaard Mortensen, Farhana Choudhury, Renata Borovica-Gajic Published: 2026-09-13 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2609.14255v1 Database management systems increasingly serve dynamic and exploratory workloads, yet many of their decisions still rely on low-level signals such as recency, frequency, and address locality. These signals capture how data was accessed, but not what is being examined or how an analytical focus evolves. We argue for treating workload semantics as a first-class control signal for anticipatory decision making. Central to this view, we introduce semantic locality and semantic trajectories, which capture relationships among nearby queries and how those relationships evolve across a session. We propose a framework that represents semantic context at the data, query, and session levels, models its evolution over time, and translates it into task-specific utility estimates. We instantiate this framework in semantic prefetching and semantic cache eviction, which share a semantic layer to make two separate decisions. Prefetching uses semantic trajectories to anticipate future accesses beyond what address-based locality can capture, while eviction uses semantic relevance to inform block replacement. These systems provide initial evidence that shared semantic context can support multiple DBMS components. We further outline how this principle can extend to other decisions and data systems, and discuss key challenges in representation, cost, adaptation, and evaluation. --- ### ATTRICITE: Training an Open 4B Model for Citation Recovery toward Faithful Attribution Authors: Yee Man Choi, Xuehang Guo, Songcheng Cai, Yimu Wang, Yi R. Fung, Qingyun Wang Published: 2026-09-13 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2609.14248v1 Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability through citation recovery: recovering the paper cited by the original author from a citation-bearing passage. Our evaluation adopts the published author's citation as an observable human attribution signal and uses target recovery as a proxy for progress toward faithful attribution. We introduce ATTRICITE, an open 4B-parameter model trained for tool-using citation recovery within the CiteGuard retrieval environment, together with CITEALIGN, a 7,607-instance computer-science dataset drawn from recent scientific literature. For controlled evaluation, we construct a 709-instance benchmark subset of CITEALIGN, comprising 410 development instances from 2024 publications and 299 temporally held-out test instances from 2025 publications. Across three runs at an inference temperature of 0.7, GRPO fine-tuning improves Qwen3-4B from 49.4%$\pm$1.5% to 59.8%$\pm$0.2% target-match accuracy, a gain of 10.4 percentage points. Despite using only 4B parameters, ATTRICITE outperforms gpt-oss-20b and comes within 3.9 points of GPT-5.4-mini, while Gemma 4 31B IT achieves the strongest overall performance at 72.0%$\pm$1.0%. We release the model and collection pipeline https://github.com/KathCYM/AttriCite to support reproducible research on citation recovery toward faithful attribution in a continually evolving scientific literature. --- ### What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures with On-Device Measurements Authors: Takeshi Nishikawa Published: 2026-09-13 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2609.14247v1 Bird-strike mitigation at wind farms requires identifying distant birds that span only tens of pixels, so the classifier's input resolution N is a design variable, not a fixed specification. We study it with a factorial design over 14 side lengths N (16 to 224), six architectures, two training and evaluation regimes and 30 random seeds -- 2,520 checkpoints and 5,040 evaluations -- plus latency measured on an NVIDIA Jetson Orin Nano. Four results. (1) The selected N depends on the target: 0.90 is met on validation by ResNet50 at N=112 in an estimated 1.85 ms (0.8980 on test) and 0.95 by DINOv2-L at N=144 in 12.70 ms; changing the model buys more accuracy than raising N (+5.93 versus +2.33 points at N=112). (2) The benefit of lowering N depends on the assumed preprocessing path: N=224 -> 80 saves 13.5% when each individual is decoded from its own file but 46.2% when the detector decodes the 4K frame once; the Pareto set grows from 20 to 23 configurations. (3) Accuracy must be measured on the deployed engine: half precision costs ViT-S/16 alone 4 to 7 points at N>=96 while the CNNs stay within 0.1 points, and with selection held at validation the choice differs at 26 of 176 targets. A broken FP16 engine can run faster than a correct one, undetectable from latency; admitting 14 ViT-S/16 FP32 configurations moves the recommendation over the 0.931-0.938 band and under the 10 ms budget. (4) ViT-L-scale models fit this device, but activations exceed the FP16 range; splitting the graph at transformer-block boundaries confines FP32 to the affected segments, making the deployed DINOv2-L chain 1.85x faster than the single-engine build. We also quantify how the regime-difference sign stabilises with seed count; a sensitivity split removing some forms of group sharing preserves all 14 non-trivial signs at the selection boundary. --- ### Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data Authors: Changheng Wang, Xianchao Zhang, Zhiqing Wei, Lingzhu Zhao, Zhongming Yang, Zhiyong Feng Published: 2026-09-13 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.14246v1 In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further affected by unreliable wireless links, as transmission errors may invalidate model updates. To address these challenges, we propose a federated random walk averaging (FedRW) framework, which is a variant of federated averaging (FedAvg) that mitigates data heterogeneity by updating models along random walk (RW) paths and aggregating them at the server. Model parameters are transmitted in packets with retransmission support to improve training quality by mitigating wireless errors along RW paths. Meanwhile, wireless transmission delays hinder the exploration of FedRW. To this end, we formulate a joint optimization problem that integrates learning, RW path selection, and transmission parameter tuning, aiming to minimize the training loss under delay constraints. By deriving an upper bound on the expected convergence of FedRW over unreliable wireless networks, we reduce the problem to a general form agnostic to task type and model architecture. A distributed solution is then proposed, in which the server or clients optimize packet size and maximum number of retransmissions locally, and efficiently select reliable and expandable next-hop nodes via a resilience-aware beam search with dynamic pruning. Simulation results show that FedRW achieves 2.26%-9% higher accuracy than state-of-the-art baselines under high data heterogeneity. Furthermore, the jointly optimized FedRW yields at least 2.78% higher accuracy and faster convergence compared to baselines. --- ### The Attribution-Compression Frontier in Retrieval-Augmented Generation Authors: Deepanshu Mody Published: 2026-09-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.14245v1 Context compression reduces generator input in retrieval-augmented generation, but answer quality alone does not characterize citation attribution. We measure citation attribution across compression methods and budgets, comparing reranking, extractive selection, abstractive summarization, token pruning, and an extract-cluster-rewrite construction on ASQA and QASPER under a fixed generator and primary entailment evaluator. On ASQA at a nominal 0.25 budget (achieved compression 0.08), a RECOMP-style compressor's citations score 0.86 precision against its summaries but 0.12 against source spans under our re-attributability protocol. These estimates depend on a shared NLI model for span recovery and citation scoring and lack independent human calibration. Extractive selection's observed grounded precision ranges from 0.43 to 0.49 across nominal budgets from one-half to one-tenth of the ASQA context, while answer quality declines. For the same RECOMP setting, claim verification after source recovery yields an unsupported rate of 0.88 versus 0.17 when checking summaries. This gap persists beyond structural rejection of missing provenance, but remains evaluator-dependent. A 200-question TRUE T5-XXL audit also finds emitted--grounded gaps under both fixed and recomputed source mappings, without establishing human-calibrated support rates. --- ### CoArena: Evaluating Computer-Use and Multi-Agent Systems in Real Time Authors: Nitish Kovuru, Prateek Jannu Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14239v1 Static benchmarks for computer-use agents fix a task set at release and score every system against it once. That makes them reproducible, and it lets them drift from what they should measure: a fixed task set ages, leaks into training corpora, and cannot follow how people actually use agents from week to week. CoArena measures use directly. Real users submit tasks; two systems, each a single model or a multi-agent pipeline behind the same tool interface, execute the same task concurrently in identical sandboxed desktops; users judge the two outcomes without knowing which system produced them; and a public leaderboard is refit from those judgments. The central contribution is a formal account of what makes such an evaluation real-time. We define real-time as five measurable properties, each with an equation and a worked example: continuous task arrival, live concurrent execution, online rating updates, freshness with contamination resistance, and bounded feedback latency from a failed run to a reusable training environment. The rating methodology follows in full: the Bradley-Terry pairwise model, its likelihood with weighted observations and ties, the penalized maximum-likelihood estimator, and the streaming update applied when a single vote arrives (a stochastic-gradient step on the same likelihood, recovering Elo). It gives confidence intervals from the observed information and a cluster-robust sandwich, rank bands from a parametric bootstrap, the rule by which a new system enters the board, and the convergence rate of the estimate. Vote quality is treated with inter-judge agreement statistics, redundant judging, and explicit handling of ties and abstentions. A five-system example with 211 votes is carried from the vote matrix to ratings, intervals, and rank bands. Every number is derived from stated inputs or labeled illustrative; none is a measurement of a deployed system. --- ### OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving Authors: Zikun Li, Yixuan Mei, Shiqi Pan, Zixuan Chen, Xiaowen Zhang, Mengdi Wu, Shuhuai Lin, Yutong Yang, Zhihao Zhang, Xupeng Miao, Rashmi Vinayak, Zhihao Jia Published: 2026-09-13 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2609.14237v1 LLM serving systems increasingly disaggregate inference into finer-grained stages, with recent approaches separating attention from FFN or MoE execution during decode. This operator-level disaggregated serving (ODS) can improve hardware matching and enable independent scaling, particularly across heterogeneous devices. However, existing systems fix operator boundaries and lack a unified characterization of when disaggregation reduces serving cost. We present OpWeave, an end-to-end framework for heterogeneous ODS. OpWeave provides an analytical cost model that bounds the gains of homogeneous and heterogeneous ODS over colocated serving. It jointly optimizes operator partitioning and deployment configuration through a regularity-aware planner that keeps the search tractable even for hybrid-attention models. A vLLM-based runtime executes the synthesized plans with flexible operator stages across heterogeneous device groups. In our evaluation, OpWeave reduces serving cost by up to $1.78\times$ on homogeneous and $1.89\times$ on heterogeneous GPU clusters relative to the best feasible baseline, while meeting latency SLOs. --- ### Assessing the Applicability of Existing Design Recommendations to AI Companion Design: A Multi-Method Study Authors: Soobin Cho, Deveshi Modi, Divya Mavinkurve, Jieqiong Ding, Mark Zachry Published: 2026-09-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.14236v1 With the rapid proliferation of large language model (LLM)-based systems, AI companions have emerged as conversational agents designed to cultivate emotional connection rather than primarily to support humans in instrumental tasks. Because engagement with AI companions involves relational, emotional, and potentially long-term interactions, their design is consequential. Prior work has offered guidance for designing trustworthy and relational AI systems and has begun to examine design for AI companionship. However, while such work provides insights into possible design solutions, less is known about what makes AI companion design difficult as a design problem. To examine this challenge, we assessed the applicability of existing design recommendations from adjacent domains in the context of AI companion design. Our multi-method investigation unfolded across four phases: literature review, practitioner co-analysis, internal heuristic evaluation, and external expert assessment. Throughout this process, we synthesized nine design principle areas that surfaced tensions in the applicability of existing recommendations to AI companion design. Our findings show that ethical and UX-oriented considerations are deeply intertwined and often require context-sensitive application. We document a systematic, multi-method problem analysis that uses these principle areas as an analytic artifact to examine why existing recommendations cannot be directly transferred to AI companion contexts. --- ### Graph-Transformer Fraud Detection with Self-Supervised Pretraining and Conformal Risk Control Authors: Sergei, Komarov Published: 2026-09-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.14234v1 Financial fraud in corporate transaction networks has grown more coordinated and harder to detect with rule-based engines and with classical learning models that treat each transaction in isolation. This paper presents GTFD, a graph-transformer fraud detector that fuses structural and temporal evidence from a corporation's payment graph. GTFD encodes the graph with a multi-head graph attention network, encodes ordered transaction sequences with a gated transformer, and combines both views through a cross-modal gating layer. A conformal risk-control head converts the fused representation into threshold-free anomaly scores with finite-sample coverage guarantees, and the network is trained with self-supervised link-mask pretraining plus adversarial augmentation so it remains stable under scarce labels and under adversarial perturbation. On a corporate transaction benchmark enriched with coordinated fraud rings, GTFD reaches an AUROC of 0.990, an F1-score of 96.1% (precision 96.3%, recall 95.9%), and an accuracy of 98.4%. It reduces the false-positive rate by about 29% relative to the strongest baseline while raising coordinated fraud-ring recall from 85.1% to 96.5%. Ablations attribute roughly 2.0 AUROC points to self-supervised pretraining and 1.9 AUROC points to the conformal head, and adversarial stress tests show GTFD retains 89.2% accuracy at perturbation magnitude 0.20 where the next-best model falls to 76.4%. --- ### Modeling, Scaling, and Decoding: Optimizing Controllable Speech Generation with Nonverbal Vocalizations Authors: Ziyu Zhang, Yun Chen, Taihui Wang, Hanzhao Li, Qicong Xie, Rilin Chen, Zhixian Zhao, Lei Xie Published: 2026-09-13 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2609.14231v1 Controllable synthesis of nonverbal vocalizations (NVVs) is es- sential for natural and expressive speech, but remains challeng- ing due to their acoustic diversity and imbalanced distribution in existing corpora. To address these challenges, we develop an NVV-aware DiTAR system that models continuous speech latents, encodes the 16 target NVV categories as dedicated to- kens, and adapts stop prediction to distinguish mid-utterance vocalizations from utterance boundaries. Training begins with large-scale bilingual pre-training on diverse NVV speech, fol- lowed by continued supervised fine-tuning on a corpus en- hanced through targeted synthetic augmentation and frequency- aware rebalancing. At inference time, we select the acoustic prompt, tune the LM-guidance and noise-injection scales, and apply Best-of-N sampling with multi-metric selection to re- duce generation failures. The final system achieves an official weighted bilingual score of 62.786, ranking first in Mandarin, second in English, and first overall among participating systems in Track 2 of the ISCSLP 2026 NVVSpeech Challenge. Ab- lation studies show that targeted augmentation benefits under- represented NVV categories the most, while robust candidate selection requires balancing NVV correctness, lexical fidelity, and perceptual quality. --- ### Corpus Characterization and Inverse Constitutional Fine-Tuning for Style-Aware Radiology Reports Authors: Sarah Y. Li, Elijah Renner, Rayan Ansari, Alaa Youssef Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14226v1 Automated radiology report generation has advanced rapidly in diagnostic accuracy, yet generated reports frequently diverge from the stylistic conventions of authentic radiologist writing in structure, diction, and uncertainty language, a gap which has direct implications for clinician trust and user experience. To address this, we characterize stylistic variation across 2,000 reports from the CheXpert Plus dataset using Bio-ClinicalBERT embeddings, UMAP dimensionality reduction, and HDBSCAN clustering, identifying five distinct reporting patterns differing in pathology focus, narrative structure, and lexical preference. Drawing on these findings, we adapt the inverse constitutional AI framework to derive a style-focused constitution from radiologist-written report pairs without requiring a formal preference dataset. This constitution, encoding conventions of tone, diction, uncertainty calibration, and report structure, is incorporated into the supervised fine-tuning of a MedGemma-4B base model on 25,245 CheXpert Plus training pairs. Constitutional fine-tuning produces a substantial increases in text alignment (BLEU-4: 0.006 to 0.308; ROUGE-L: 0.171 to 0.484) relative to the untuned baseline. These gains show a qualitative shift in structural and lexical alignment rather than marginal improvement, as the baseline model produces near-zero scores due to format mismatch. Overall, we establish corpus-level style characterization and constitutional modeling as an effective and data-efficient strategy for producing radiology reports that conform to authentic radiologist writing conventions. --- ### Task-Specified Active Metrological Inspection with Measurement-Steered VLA Manipulation and Deterministic Evidence Gating Authors: Zhiling Chen, Jingzhan Ge, Ruimin Chen, Matthew P. Castanier, David Gorsich, Farhad Imani Published: 2026-09-13 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.14219v1 High-mix low-volume (HMLV) manufacturing requires inspection systems to adapt to changing parts, specifications, and work orders without repeated task-specific programming. Existing inspection automation typically assumes predefined sensing sequences, while general purpose robot agents optimize task completion rather than the completeness and validity of metrological evidence. We formulate task-specified active metrological inspection and propose From Requirements to Admissible Metrological Evidence (FRAME), a hierarchical dual-arm framework that converts an inspection instruction and structured specification into traceable conformance evidence. FRAME coordinates learned manipulation with calibrated laser profilometry: a task manager grounds and schedules requirements, active surface correspondence verifies physical-to-specification localization, and evidence memory tracks measurement provenance, admissibility, and coverage. Learned components may propose inspection targets and physical access actions, but deterministic datum-grounded measurement, admissibility checks, coverage auditing, and conformance evaluation prevent incomplete or unverified evidence from authorizing PASS. A series of physical experiments shows that FRAME achieves higher end-to-end inspection reliability, fewer false accepts, and shorter task completion time. ---