# Research Papers — 2026-09 · bundle page 77 of 266 > Full-text markdown of papers #3801–3850 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/77 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/76.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/78.md) ### DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education Authors: Quang Nguyen, Hieu Nguyen, Hien Hoang, Toan Pham, Cong Tran, Nam Vu Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31568v1 AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to foreign servers---violating data-sovereignty laws such as Vietnam's Decree 53---and, pre-trained on Western-centric corpora, are not organized around the national textbook curriculum, so their knowledge of local content is unsystematic and frequently hallucinated. Self-hosting an open model keeps data on-premise but hits a two-fold wall: post-training quantization (AWQ, GPTQ) tames the static weight footprint, yet the dynamic KV cache and prefill latency of long tutoring contexts still cause out-of-memory failures and slow responses on consumer GPUs, while the model keeps hallucinating on region-specific material. We present DeepEdu-v1, an AI-tutoring system for Vietnamese education built on SCALE (Self-improving Context-Aware Learning Engine), a framework with two innovations. First, a long-context inference engine amortizes token selection from per-sub-chunk to per-cluster granularity; on long-context retrieval it issues x7.7 fewer retrieval calls than a state-of-the-art selective-attention baseline, cutting prefill latency (TTFT) by roughly 35% while matching or improving task accuracy. Second, a self-improving agentic layer continuously curates a verified playbook from past interactions instead of fine-tuning, a design intended to progressively reduce reliance on dominant-language priors as trustworthy local knowledge accumulates. In its deployed configuration, DeepEdu achieves a nearly x2 TTFT speedup over standard vLLM serving and lifts agentic accuracy from 70.0% to 79.5% on complex tasks, with the strongest per-track gains across financial-reasoning and interactive-agent benchmarks. --- ### Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights Authors: Irene Tallini, Daniele Solombrino, Alberto Cazzaniga, Emanuele Rodolà Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31564v1 We show that neural network weights can be explicilty fintuned to admit a smaller grammar. Weight Pair Encoding (WeightPE) does so by placing a lossy Re-Pair compressor inside a straight-through estimator. The int8 weights of the network are flattened into one string, and near-matching Re-Pair patterns are made exactly equal within a global L2 budget. The network computes with the rewritten weights and trains through them with a straight-through estimator. Unlike a flat codebook of fixed-size entries, a grammar offers variable-length patterns and reuses them hierarchically inside larger ones. On the MLP weights of ViT-B/16 and ViT-L/16 finetuned on CIFAR-10, WeightPE produces a Re-Pair grammar 0.43x and 0.38x the size of the one produced by an equivalent int8 QAT run, at a cost of 1.9 and 1.1 accuracy points. The trend extends to different grammar compressors (LZ78, SEQUITUR), over which the networks has not be finetuned against. To our knowledge, this is the first time grammar size has been used as an explicit training objective for network weights. --- ### Multi-agent Scaling Across Disjunctive and Compensatory Tasks Authors: Carolina Fortuna, Blaz Bertalanic Published: 2026-09-25 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.31563v1 Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of group tasks as a framework for analyzing multi-agent LLM scaling and focusing the analysis on disjunctive and compensatory tasks. We model independently sampled agents as conditionally independent given the item, which yields their large-team limits: plurality voting converges to the model's modal answer, and averaging converges to the model's item-level bias. Across selected representative benchmarks, 13 open-weight models, and teams of up to 30 agents, we find qualitatively different scaling behavior. On disjunctive tasks, the probability that at least one agent is correct grows by 5-20 points with team size, but plurality voting over agents that answer directly realises almost none of this potential, as the model predicts to within 0.5 points on average. Multi-round revision raises accuracy considerably, yet the gain is nearly the same with one peer as with 29. In contrast, scaling provides little benefit on Fermi estimation, despite its natural suitability for aggregation: item-level biases shared across the samples of a model account for about 87% of the squared error, so averaging reduces error by only about 6%. Combining model families helps on Fermi estimation but does not surpass the strongest member on disjunctive tasks. These results show that task structure, together with the mechanism combining member outputs, is a fundamental determinant of team scaling. --- ### Generalization behavior of OPTQ and the role of regularization Authors: Erin George, Rayan Saab Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31560v1 Large neural networks can be compressed by rounding or "quantizing" their weights to numbers that admit representations with fewer bits. One algorithm for quantization, OPTQ, progressively quantizes the weights of a neural network so that the squared quantization error on a specified calibration dataset is as small as possible. We study the performance of OPTQ and a variant algorithm, stochastic OPTQ, in a generalization setting and derive bounds for the expected squared error accrued by the algorithm when a test point is drawn from a fixed distribution. We prove two results. One result relates the generalization error to the error on a calibration dataset comprising independent samples from the same distribution as the test distribution. The other result bounds the generalization error of stochastic OPTQ for all sufficiently nice distributions, regardless of the calibration dataset. In both of these results, the regularization term $λ$ plays an important role. We use insights from these results to make a new recommendation for the choice of $λ$ and see that this choice of $λ$ preforms favorably in experiments when compared to prior recommendations in the literature. --- ### Online Learning via Learned Latent Bayesian Tracking Authors: Guy Gerson, Tomer Raviv, Nir Shlezinger, Tirza Routtenberg, Osvaldo Simeone Published: 2026-09-25 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.31559v2 Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled approach casts online learning as Bayesian state tracking, where model parameters are updated sequentially via Bayesian filtering. However, applying Bayesian filters directly to modern deep models is computationally prohibitive due to the high dimensionality of parameter space, forcing existing methods to rely on restrictive approximations or manually designed low-dimensional subspaces. In this work, we identify the absence of a suitable low-dimensional dynamical representation as the core bottleneck in Bayesian filtering-based online learning. Accordingly, we propose Adaptive Update through Representation Adaptation (AURA), a meta-learning framework that learns offline a low-dimensional latent state-space model governing the evolution of optimal model parameters under distribution shift. Online adaptation is then performed via extended Kalman filtering in this learned latent space followed by reconstruction of the full model parameters through a learned lifting map, enabling efficient single-step online adaptation while preserving model expressiveness. Evaluated on online adaptation of neural wireless receivers under time-varying channels and on non-stationary image classification, AURA shows substantial improvements in adaptation speed, accuracy, and computational efficiency over existing online learning and Bayesian filtering baselines, demonstrating that an adaptation-aware latent geometry is beneficial for effective Bayesian online learning in high-dimensional models. --- ### Online Learning via Learned Latent Bayesian Tracking Authors: Guy Gerson, Tomer Raviv, Nir Shlezinger, Tirza Routtenberg, Osvaldo Simeone Published: 2026-09-25 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.31559v1 Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled approach casts online learning as Bayesian state tracking, where model parameters are updated sequentially via Bayesian filtering. However, applying Bayesian filters directly to modern deep models is computationally prohibitive due to the high dimensionality of parameter space, forcing existing methods to rely on restrictive approximations or manually designed low-dimensional subspaces. In this work, we identify the absence of a suitable low-dimensional dynamical representation as the core bottleneck in Bayesian filtering-based online learning. Accordingly, we propose Adaptive Update through Representation Adaptation (AURA), a meta-learning framework that learns offline a low-dimensional latent state-space model governing the evolution of optimal model parameters under distribution shift. Online adaptation is then performed via extended Kalman filtering in this learned latent space followed by reconstruction of the full model parameters through a learned lifting map, enabling efficient single-step online adaptation while preserving model expressiveness. Evaluated on online adaptation of neural wireless receivers under time-varying channels and on non-stationary image classification, AURA shows substantial improvements in adaptation speed, accuracy, and computational efficiency over existing online learning and Bayesian filtering baselines, demonstrating that an adaptation-aware latent geometry is beneficial for effective Bayesian online learning in high-dimensional models. --- ### Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIP Authors: Ahmed Abdelnaby, Mohamed Elmahallawy Published: 2026-09-25 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2609.31558v1 Contrastive Language--Image Pretraining (CLIP) has emerged as a dominant vision backbone due to its strong transferability and zero-shot capabilities. However, recent studies reveal a critical vulnerability: embedding-space backdoor attacks. By poisoning only a tiny fraction of image--text pairs, adversaries can implant stealthy triggers that induce targeted shifts in CLIP's joint embedding space. Unlike conventional backdoors that manipulate classifier logits, these attacks corrupt representations directly, making them highly effective under extremely low poisoning ratios and difficult to detect. Existing defenses require access to model parameters, gradients, logits, or clean validation data---assumptions that rarely hold in realistic black-box deployments. Moreover, current black-box methods struggle to accurately localize small or out-of-distribution triggers. We propose CLIPGuard, a lightweight and fully black-box defense specifically designed to mitigate embedding-space backdoors in CLIP encoders. CLIPGuard identifies malicious regions by measuring segment-wise embedding perturbations and selectively purifies only suspicious segments via semantic inpainting, preserving benign visual content and alignment quality. Extensive experiments on STL-10, ImageNet, and diverse trigger families---including BadCLIP, BadNets, blended, patch-based, and typographic attacks---demonstrate that CLIPGuard reduces attack success rates to as low as 1.05% while maintaining clean accuracy up to 86.34%, consistently outperforming existing black-box defenses, including CleanCLIP and CleanerCLIP. Our code is available https://github.com/wsu-cyber-security-lab-ai/CLIPGuard.git --- ### MexHat: A Dataset for Hate Speech Detection in Mexican Spanish Videos Authors: Itzel Tlelo-Coyotecatl, Hugo Jair Escalante Published: 2026-09-25 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.31553v1 Ensuring online safety through content monitoring had raised Hate Speech Detection as a crucial task to be addressed. By essence the task demands the capture of contextual cues, which are essential for a precise understanding of the content's intent. Although automated detection approaches for the task have advanced significantly, the scarcity of non-English resources persists, limiting the ability of models to adapt to the subtle, context-dependent, and culturally related nature of multimodal content. In this paper, we introduce MexHat, a video dataset designed to capture the linguistic and cultural cues for the hate-speech detection task in a Mexican Spanish context. Our dataset comprises around 1k video clips annotated across two tasks: a three-way class evaluation (no negative content, offensive content and hate-speech content), and a fine-grained class evaluation including three hate-speech sub-categories. The dataset statistics and the baseline results highlight the inherent challenges associated with the task. Disclaimer: This paper contains sensitive content that may be disturbing to some readers. --- ### EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language Models Authors: Kunxiong Zhu, Zhihao Shu, Hangyu Zheng, Minghai Qin, Miao Yin, Gagan Agrawal, Wei Niu Published: 2026-09-25 Categories: cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2609.31551v1 Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multimodal LLMs (MLLMs), which add a third phase, Encode, pose new challenges for resource allocation. Encode turns images, video, or audio into embeddings that the language model can consume, yielding a three-stage Encode-Prefill-Decode (EPD) pipeline. Existing frameworks offer only partial answers: text-only PD systems lack Encode, while EPD frameworks expose it as a separate service without regulating downstream request flow. The pipeline also carries a structural resource imbalance: every request enters through Encode before downstream work can begin, yet per-request execution leaves the encode GPU severely underutilized even at high loads, starving the downstream Prefill and Decode workers. Addressing this, we reposition Encode as the control point of the EPD pipeline, exposing three tightly coupled dimensions: when work enters downstream, where prefill executes, and how the GPU is shared. We instantiate this in EAServe across two co-designed layers. Its runtime manages load-adaptive micro-batching, rate-controlled partial offload to a co-resident prefill worker, and dynamic SM partitioning for predictable co-location. The configuration layer, Hybrid Auto Selection (HAS), navigates the joint space of GPU allocation, encode batch size, and offload ratio by pruning unbalanced allocations with per-stage capacity profiling and refining the remainder through TPE-based Bayesian optimization. Evaluated on three MLLM architectures spanning image, video, and audio, EAServe delivers up to 4.3x and 1.7x higher goodput than NVIDIA Dynamo and vLLM, respectively, under identical SLO constraints, sustains more balanced and higher GPU utilization across the EPD pipeline, and reaches near-optimal configurations faster than baseline search methods. --- ### Two Conformal Constructions for Adaptive Within-Document AI-Text Screening Authors: Marco Mandap, Jerahmeel Hipolito, Arcel Galvez, Charlie Margaret Balagtas, Michael Joshua Buluran, Jeff Roel Durmiendo, Rizzette E. Lopez Published: 2026-09-25 Categories: stat.ME, cs.CL arXiv: https://arxiv.org/abs/2609.31547v1 We study false-alert control when screening for text generated by artificial intelligence (AI). The screening procedure selects document prefixes and detectors from observed evidence and may stop before exhausting its inspection budget. We give two finite-sample constructions under document-level exchangeability between human calibration documents and a new null document, with no restriction on dependence among tokens within a document. Construction A registers a finite family of prefix-detector scores and allocates a false-alert budget across their conformal ranks. A union bound protects any executed subset of that family. Construction B calibrates the complete-path maximum of a development-fixed adaptive policy. Each partial-path maximum is bounded by the complete maximum, so a terminal conformal rank protects early stopping without splitting the error budget. We prove marginal control of any false alert across the permitted inspection path and derive necessary calibration counts for rejection. We also state oracle testing, distribution-shift, and independent-audit bounds with their additional assumptions. Both constructions protect stopping within their specified scope; neither proof constructs an e-process or justifies multiplying conformal ranks. Detection power and computational savings remain questions for empirical evaluation. --- ### BeatGraph: Self-Supervised Heartbeat Graphs for Infant ECG Representations from the Home Environment Authors: Mohammad Nur Hossain Khan, M. S. Krafczyk, Beverly G. Bolster, Nancy McElwain, Mark A. Hasegawa-Johnson, Bashima Islam Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31546v1 Electrocardiogram (ECG) foundation models typically tokenize the signal into fixed-length patches that ignore cardiac structure, so a patch may split a heartbeat and the number of beats in each patch shifts with heart rate. This matters most for infants, whose heart rates are higher and whose ECG differs from the adult, clinic-recorded 12-lead data these models are built on. A model for infant ECG should therefore reason about heartbeats directly rather than recover them from arbitrary patches. We propose BeatGraph, which makes the heartbeat its unit of representation, modeling each 30-second window as a graph of beats. A shared beat encoder embeds each heartbeat from its waveform and inter-beat intervals, a Transformer with positional encoding orders the beats in time, and residual graph attention layers relate every beat to every other before attention pooling yields a window embedding. We pretrain BeatGraph on our new corpus of unlabeled infant recordings by predicting masked-beat embeddings, then fine-tune it for each task. One backbone supports sleep-wake detection, infant-state classification, activity-source identification (infant- or caregiver-initiated movement), and affect recognition, improving macro-F1 over the strongest baseline on each task by 0.076 to 0.158. It also transfers across age groups, reaching 0.892 AUROC on the ZZU-pECG pediatric benchmark (ages 0 to 14), within 0.001 of the best published self-supervised ECG model, and matching that model under linear evaluation on the adult PTB-XL benchmark despite infant-only pretraining. Finally, to our knowledge, we release the first public infant ECG corpus collected in homes, classrooms, and laboratory settings with state and affect labels. It contains 3,408 hours of single-channel ECG from 143 infants aged 3 to 11 months, with unlabeled pretraining data, benchmark tasks, and subject-level splits. --- ### A Flow Matching Framework for Neural Representational Dissimilarity Authors: Zeyuan Ye, Xue-Xin Wei Published: 2026-09-25 Categories: cs.AI, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2609.31544v1 Neural representational dissimilarity quantifies differences between neural response distributions, and is essential for comparing neural codes across stimuli, brain areas, tasks, and models. Commonly used distance metrics involve different assumptions and are estimated with separate methods. Here, we show that a variety of distance metrics can be unified under a flow matching framework developed in deep generative models. That is, these distances arise as Jeffreys divergences under different velocity constraints. We find that flow matching has advantages for estimating distances involving complicated distributions and continuous variables. Furthermore, this framework enables the design of new distance metrics in a principled way. Together, flow matching provides a unified approach for understanding, estimating, and designing neural representational dissimilarity metrics. --- ### Can You Check That? The Checkability Boundary for Local LLM Network Automation Authors: Maleeha Masood, Momina Nofal Published: 2026-09-25 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2609.31540v1 Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and logs. Querying small language models (SLMs) locally avoids this egress, but SLM outputs can be error-prone for direct use. This work introduces checkability as a criterion for determining which tasks are suitable for local inference. A task is checkable when it exposes a cheap, deterministic test - an intrinsic check - that rejects outputs violating a necessary correctness condition. We instantiate this idea in Touchstone, a local-first pipeline that uses seven off-the-shelf SLMs (1-8B parameters) to generate candidates, uses task-specific intrinsic checks to reject responses, and escalates unresolved inputs to a frontier LLM. On conflict detection and intent translation tasks, Touchstone reaches 98.6% and 93.8% end-to-end accuracy while escalating only 16% and 17% of inputs, respectively. On TeleQnA, a knowledge-only control that has no task-specific intrinsic checks, Touchstone is unable to match the accuracy of the frontier baseline. Our results support a simple deployment rule: keep inference local when task semantics support precise, low-cost checks; escalate the rest. --- ### NEXT: Physics-Informed Neuro-Spectral Exponential Time Differencing Architectures Authors: Márcio Marques, Leonardo Mendonça, Leonardo M. Moreira, Christian Júnior de Oliveira, Vitor Balestro, Tiago Novello, Daniel Yukimura, Pavel Petrov, Lucas Nissenbaum Published: 2026-09-25 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2609.31539v1 Physics-Informed Neural Networks (PINNs) build neural representations of time-dependent PDE solutions, naturally incorporating physics knowledge and observational data, which makes them well suited to both forward and inverse PDE problems. PINNs, however, are known to suffer from spectral bias and lack of causality. Neuro-Spectral Architectures (NeuSA), a recently proposed alternative to PINNs, mitigate both issues, but their numerical integration becomes unstable for stiff differential equations arising in many relevant physical problems. This study proposes Neuro-Spectral Exponential Time Differencing Architectures (NEXT), which combines the spectral representation of the PDE solution in NeuSA with high-order exponential integrators. Within this approach, the linear stiff part of the vector field induced by the PDE is integrated exactly through matrix exponentials, while the possibly nonlinear remainder is modeled by a neural network. The effectiveness of NEXT is verified through benchmark experiments on a set of stiff PDEs, in which NEXT is stable and accurate while NeuSA diverges numerically. It is also shown that NEXT can be applied to inverse problems, where the model has to learn unknown parameters or boundary conditions from sparse data. All code used in this work is publicly available at: https://github.com/marcioh2m/next.git . --- ### HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning Authors: Xinglong Luo, Yuding Zhang, Yuheng Kuang, Shuxuan Yuan, Zhenni Zeng, Weiqiang Zhu, Zhenhai Ji, Zhengning Wang Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31531v1 Cooperative multi-agent reinforcement learning under partial observability and shared rewards requires assigning team outcomes to individual agents and high-order coalitions. A MAPPO-style critic compresses joint behavior into one global value, while critics that dynamically reconstruct the grouping topology change the mapping from agents and coalitions to value components as interactions or active agents evolve. We refer to this inconsistency as structural target drift. We introduce HySTAR, a MAPPO-based framework that separates adaptive representation learning from a temporally consistent high-order value-decomposition basis. HySTAR anchors an overlapping sparse hypergraph as a uniformly covered decomposition scaffold, uses a spatiotemporal encoder to represent physical and task-dependent interactions, and combines temporal and structural relevance to construct agent-specific advantages. Experiments on SMAC, GRF, Traffic Junction, and MPE demonstrate consistent improvements over MAPPO-style, value-factorization, and dynamic-grouping baselines. On the hardest SMAC settings, HySTAR achieves relative gains of 16.7\% over MAPPO and 15.6\% over HYGMA, ranks first on all six GRF scenarios, reduces Traffic Junction convergence epochs by up to 40.2\% relative to MAGIC, and obtains the highest MPE episode rewards. Controlled topology, agent-death, neighborhood, and parameter analyses support the benefit of anchoring the decomposition scaffold while adapting the propagated representations. --- ### Structured Reasoning Agentic Framework for Interpretable Critical View of Safety Assessment Authors: Qing Xu, Yuxiang Luo, Zhen Chen Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31524v1 Surgical scene understanding is critical for computer-assisted intervention, yet laparoscopic cholecystectomy remains challenged by the complex anatomy of the hepatocystic triangle and the risk of bile duct injury. Existing methods for Critical View of Safety (CVS) assessment typically treat it as a holistic prediction task, mapping visual features directly to criterion-level labels. This black-box paradigm lacks explicit reasoning about anatomical relationships, limiting both interpretability and compositional generalization. To address this, we propose ReasonCVS, a structured reasoning agentic framework empowered by Vision-Language Models (VLMs) that decomposes CVS assessment into explicit, fine-grained anatomical verification. Specifically, we devise an Anatomical Scene Graph Abstraction (ASGA) that organizes anatomical entities and their spatial relationships into a structured representation. To operationalize this, we introduce a Rationale-Aware Reasoning Agent, powered by a Large Language Model (LLM) fine-tuned via rationale distillation. Functioning as a strict central decision-maker, it invokes VLM-driven Sub-criterion Verifier as a specialized perceptual tool to parse the graph and independently evaluate individual sub-criteria. Through calibrated soft reasoning, this agent synthesizes the tool-gathered distributed observations, yielding a final verdict alongside a traceable clinical rationale. Extensive experiments on the Endoscapes-CVS201 benchmark demonstrate that ReasonCVS achieves superior performance (68.1\% mAP) over state-of-the-art while providing interpretable, criterion-level explanations for reliable surgical assessment. --- ### Retrainable physics-integrated neural differentiable modeling of sintering across material systems Authors: Zeping Chen, Ani Aprahamian, Khachatur V. Manukyan, Tengfei Luo Published: 2026-09-25 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2609.31518v1 Sintering is widely used to manufacture ceramics, but coupled densification and grain growth, material-dependent kinetics, and sparse measurements complicate predictive modeling and process design. We present Sinter-PiNDiff, a retrainable physics-integrated neural differentiable framework for predicting density and grain-size evolution. Two neural networks learn densification and grain-growth coefficients within coupled rate equations, while a smooth saturation factor attenuates densification near theoretical density. The same governing structure, network architecture, and training procedure were fitted independently to published data for MgO, Al-doped ZnO, and CaO-doped ThO2. Tests at held-out temperatures and compositions yielded the lowest mean error in all twelve material-metric comparisons against multilayer perceptron and residual network baselines. For MgO, Al-doped ZnO, and CaO-doped ThO2, respectively, density normalized root-mean-square errors were 14.6%, 10.8%, and 14.4%, and grain-size errors using the same metric were 8.6%, 12.1%, and 19.3%. Removing evolving density from both neural-network inputs increased density and grain-size trajectory errors in all three systems and ten of twelve aggregate errors, supporting density-dependent kinetic feedback. Deep ensembles estimated model disagreement, but empirical coverage showed that the uncertainty bands were not calibrated and did not capture all model-data discrepancies. These results establish Sinter-PiNDiff as a retrainable framework for sparse-data prediction and uncertainty-informed selection of sintering conditions. --- ### Forensic Twins: Self-Supervised Residual Learning for AI-Generated Image Forensics Authors: Javier Muñoz-Haro, Ruben Tolosana, Ruben Vera-Rodriguez, Aythami Morales, Julian Fierrez Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31514v1 Detectors of AI-generated images are typically trained using samples from all Generative AI architectures they must catch, and struggle as soon as a new architecture emerges. Recent approaches have explored self-supervised pre-training as an alternative solution, yet standard frameworks work against the forensic task, e.g., their augmentations overwrite the micro-statistics of image formation. This paper introduces Forensic Twins, a Self-Supervised Residual Learning (SSRL) framework whose pretext task suppresses macroscopic content availability. Each image is mapped through a frozen, off-the-shelf forensic residual extractor, from which two spatially disjoint crops are drawn. Sharing no pixel, the two views retain minimal semantic structure to align, leaving a redundancy-reduction objective with a predominant common signal: the stationary fingerprint of the image acquisition pipeline. Additionally, Forensic Twins is trained exclusively on real images; no AI-generated image is observed at any stage. Experiments show that Forensic Twins attributes AI generator sources with 56.61% accuracy, i.e., 6.13% above the previous state-of-the-art zero-shot method at 375x lower latency. We also demonstrate that fitting a Gaussian Mixture Model (GMM) offline using only the real image embeddings extracted from Forensic Twins turns it into a state-of-the-art zero-shot detector, reaching 97.99% AUC across 27 unseen AI generators, including GANs, diffusion models and commercial systems. Code, weights and exact splits will be made publicly available --- ### Statistical Foundations for a Google Play User-Review Sentiment Index: Signal Fusion, Shrinkage, Distributional Validation, and Dynamic Smoothing Authors: Marco Mandap Published: 2026-09-25 Categories: stat.ME, cs.CL, stat.AP arXiv: https://arxiv.org/abs/2609.31513v1 We develop a statistically explicit sentiment index for Google Play user reviews and establish the mathematical results supporting its construction. Normalized star ratings and text-sentiment scores are treated as noisy measures of latent review valence and fused by covariance-aware inverse-variance weighting. Review-level estimates are aggregated with bounded helpfulness and recency weights, then shrunk toward a population mean using estimated precision rather than an arbitrary review-count threshold. App-level rating histograms provide a distributional diagnostic for samples returned under different API sort orders; because star ratings are discrete, classical continuous Kolmogorov-Smirnov critical values are not used. A local-level state-space model and the Kalman filter provide a denoised temporal trend. Full proofs cover the BLUE and Gaussian maximum-likelihood result, Gaussian-conjugate shrinkage, the Glivenko-Cantelli and Donsker theorems, count transformations via the delta method, and exact Gaussian Kalman filtering. A worked three-review example shows how textual complaints can materially reduce an apparently perfect star-only score. --- ### Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge Authors: Yahya Mohamed Elnawasany Published: 2026-09-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31511v1 We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (NeMo Arabic ASR, an OpenAI-compatible LLM endpoint, self-hosted TTS) and a deterministic multi-source retrieval layer routed across six Model Context Protocol servers, we report three things a research prototype typically lacks. First, a released family of fine-tuned Arabic Islamic model artifacts: an efficient tool-routing LLM (Muslim-6B-PRO, 5.94B parameters) and a Modern Standard Arabic TTS model (Fasih-TTS-V1) that ranks 5th of 17 overall and 2nd of 11 open-weight systems on the community-voted Arabic TTS Arena for MSA. Second, an account and metering layer - a free per-account turn allowance, capacity-aware refusal, and email verification deferred to the point it actually matters - that turns an open demo into an operable, abuse-resistant product. Third, a three-layer observability stack (liveness, error reporting, product analytics) built specifically around the system's characteristic failure mode: a GPU-bound agent host going silent while the web tier keeps serving normally. We report real, measured latency and accuracy figures (98.4% recitation-validation accuracy on 124 cases; end-to-end voice latency of 0.9-1.7s) and discuss the concrete engineering trade-offs and limitations of running an Islamic-knowledge voice product in production. --- ### ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos Authors: Xuanzhi Liu, Xinyi Wu, Hang Pan, Wensi Huang, Zhenyao Wu, Ruize Han, Song Wang Published: 2026-09-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31509v1 We present ClearGS for 3D Gaussian Splatting (3DGS) from handheld videos with uneven viewpoint coverage and mixed frame quality. Rather than selecting frames with binary decisions, ClearGS uses Reliability-aware View Allocation (RVA) to assign graded raw-supervision weights based on appearance reliability, degradation risk, and geometric utility, while weakly reactivating useful suppressed frames to maintain trajectory coverage. Since weighting cannot restore details lost to blur or distortion, ClearGS further introduces Render-Guided In-Video Restoration (RIVR). The current 3DGS render provides a pose-aligned structural candidate, a frozen no-reference restoration expert restores the corresponding raw video observation without any clean reference image, and no-reference perceptual scores select among the render, restored observation, and high-frequency fused candidate. ClearGS then applies Full-Trajectory Repair Consolidation to revisit accepted repairs and preserve details introduced early. On GS2E and GSOTM, ClearGS achieves state-of-the-art overall performance, with consistent CLIP-IQA and MUSIQ gains and LPIPS reductions in most degradation settings, without paired sharp supervision or matched clean references. --- ### SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery Authors: Jiajun Jiang, Chunliang Hua, Zichun Chen, Yanxing Wu, Zeyuan Yang, Jie Song, Xiao Hu Published: 2026-09-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.31507v1 Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across extended urban spaces, inherently demanding long-term memory and geospatial grounding. However, scaling existing benchmarks remains difficult because of their reliance on costly reconstructed 3D assets, limiting geographic diversity and episode scale. To address this, we introduce SatNav, a scalable, long-horizon UAV VLN benchmark built from high-resolution satellite imagery. SatNav targets city-level navigation missions and uses satellite crops as approximations of UAV nadir views for visual observations. Through an automated cue-to-episode pipeline, SatNav constructs 118K episodes from 59 scenes across 18 cities, with an average trajectory length of 379 m. To stress-test long-horizon memory and geospatial reasoning, SatNav defines three task families: Boundary, Landmark, and Route, targeting loop progress tracking, landmark-based spatial grounding, and route following with counting cues. Benchmarking classical VLN agents and recent agents based on large vision-language models (LVLMs) on SatNav shows that city-scale navigation remains challenging. We further introduce SwiftVLN, a modular framework with switchable memory components, and conduct systematic memory-design ablations. Finally, satellite-to-UAV transfer experiments show that satellite-trained navigation models can operate on real-flight UAV observations, showing the practical relevance of SatNav. Our project page: https://eku127.github.io/SatNav/ --- ### Evaluating Cultural Awareness of LLMs for Haitian Creole Authors: Christelle Clervilsson, Yanzhu Guo Published: 2026-09-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.31506v1 Large language models (LLMs) exhibit substantial performance disparities between high- and low-resource languages. Beyond lower task performance, they often fail to capture the cultural norms and values of underrepresented communities. In this work, we present the first systematic evaluation of cultural awareness in LLMs for Haitian Creole, a language spoken by millions but severely underrepresented in digital resources. We assess cultural awareness along four complementary dimensions---specificity, bias, diversity, and variation---using a benchmark of culturally salient prompts curated by native speakers in a text infilling setting. Our results reveal a clear gap between cultural awareness in Haitian Creole and higher-resource French, with Haitian performance being more uneven across domains and more affected by French linguistic interference. Story generation further reveals recurring portrayals of Haitian characters through hardship and resilience, showing that even positive characterizations can encode stereotypical narratives. Our code, benchmark, and evaluation framework are publicly available. --- ### Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity Authors: Marius F. R. Juston, Kevin A. Karim, Jonathan Gao, Kevin C. Li, Rudhi Bashambu Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31505v1 Despite the growing capabilities of large language models (LLMs), prompt design remains largely heuristic and ad hoc. This project will explore $\textit{prompt minimization}$, the process of reducing prompts to their smallest, most information-dense form while preserving output fidelity. Practically, shorter prompts reduce computational overhead and inference latency, especially when large contexts, such as entire documents or codebases, are included unnecessarily. Further, longer prompts can damage LLM reasoning and accuracy. Theoretically, the existence of multiple prompts yielding equivalent outputs suggests a high degree of redundancy in the input space, raising fundamental questions about what information is essential to elicit specific model behaviors. We propose three variant frameworks to identify and evaluate minimal prompts and demonstrate that minimal prompts often produce outputs comparable to those of their longer counterparts. These findings suggest new directions for efficient prompt engineering and deepen our understanding of input compression in LLMs. --- ### Retail Product Search: A Practical Approach at Target Authors: Darshan Sonagara, Qujiaheng Zhang, Ankit Singh, Alex Li Published: 2026-09-25 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.31498v1 Search is one of the most important features in e-commerce, directly driving customer engagement and business growth. A good product search system must show both relevant and desirable results. However, retail search presents unique challenges. User intent can range from exact matches to open-ended discovery. Search systems must also balance multiple goals, such as relevance, revenue, and profit, while keeping response times low. Traditional keyword-based methods often fall short in handling natural language or semantic queries. Vector search helps alleviate these issues, but it can miss key intent signals or return low-precision results. In this paper, we present the design of a hybrid search system at Target that combines lexical and vector search. We describe our approach to data processing, embedding training, precision control for the final result set, multi-channel result fusion (where we compared fusion strategies and adopted weighted interleaving), and the performance optimizations used to maintain low latency for production deployment. Our method improves offline evaluation metrics, and in online A/B testing it raised click-through rate by 0.97%, order conversion by 0.98%, and demand per visitor by 1.10% over lexical-only search, while roughly halving zero-result searches. The resulting system is deployed at scale and serves millions of guests daily. --- ### UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting Authors: Derrick Gilchrist Edward Manoharan, Eljas Linna, Kestutis Baltakys, Hao Dong, Juho Kanniainen Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31491v2 Forecasting short-horizon mid-price movements from limit order book (LOB) data is central to algorithmic trading, yet most deep LOB forecasters are point predictors: they output a direction or a displacement, but never indicate which of their forecasts can be trusted. We introduce UQ-LOB, a lightweight, encoder-agnostic uncertainty quantification module that attaches to any pretrained LOB encoder and, in the spirit of attentive neural processes, conditions each forecast on a context set of recently completed windows whose outcomes are already realised. The UQ-regression variant outputs a calibrated Gaussian over the future tick displacement, while the UQ-classification variant outputs a categorical distribution over down/up/stationary. Both expose a scalar confidence (predicted signal-to-noise ratio or class probability) that supports selective prediction. On 5.2 billion LOB events across seven cryptocurrency assets and horizons of 5, 10 and 15 seconds, UQ-regression attains near-nominal 68% interval coverage, and restricting to the most confident 10% of predictions raises directional macro F1 by 0.11-0.15 for UQ-regression and 0.05-0.11 for UQ-classification, at every horizon. On large, economically meaningful moves, the tightest confidence tier reaches a directional F1 of 0.88 (down) and 0.83 (up) at the 5-second horizon. --- ### UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting Authors: Derrick Gilchrist Edward Manoharan, Eljas Linna, Kestutis Baltakys, Hao Dong, Juho Kanniainen Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31491v1 Forecasting short-horizon mid-price movements from limit order book (LOB) data is central to algorithmic trading, yet most deep LOB forecasters are point predictors: they output a direction or a displacement, but never indicate which of their forecasts can be trusted. We introduce UQ-LOB, a lightweight, encoder-agnostic uncertainty quantification module that attaches to any pretrained LOB encoder and, in the spirit of attentive neural processes, conditions each forecast on a context set of recently completed windows whose outcomes are already realised. The UQ-regression variant outputs a calibrated Gaussian over the future tick displacement, while the UQ-classification variant outputs a categorical distribution over down/up/stationary. Both expose a scalar confidence (predicted signal-to-noise ratio or class probability) that supports selective prediction. On 5.2 billion LOB events across seven cryptocurrency assets and horizons of 5, 10 and 15 seconds, UQ-regression attains near-nominal 68% interval coverage, and restricting to the most confident 10% of predictions raises directional macro F1 by 0.11-0.15 for UQ-regression and 0.05-0.11 for UQ-classification, at every horizon. On large, economically meaningful moves, the tightest confidence tier reaches a directional F1 of 0.88 (down) and 0.83 (up) at the 5-second horizon. --- ### Scaling Density Functional Theory with Gaussian Splatting Authors: Andrés Guzmán-Cordero, Cindy Zhang, Majdi Hassan, Marta Skreta, Kirill Neklyudov, Matija Medvidović Published: 2026-09-25 Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2609.31483v1 Density functional theory (DFT) strikes a practical balance between accuracy and computational cost in many problems of computational chemistry and materials science. However, many DFT calculations are limited by fixed atom-centered basis sets, which dictate how accuracy and cost scale with system size. We propose Gaussian Splatting for Density Functional Theory (GS-DFT), which represents molecular orbitals as a cloud of Gaussians whose positions, shapes, and mixing coefficients are optimized jointly by gradient descent to minimize the energy without training data. Conceptually, GS-DFT is 3D Gaussian splatting with the renderer replaced by quantum mechanics. We introduce two key solver components: adaptive density fitting with screening for efficient evaluation of two-electron integrals, and a regularized differentiable orthogonalization of the molecular orbitals. Empirically, the optimized basis reaches the accuracy of the largest conventional basis sets with a fraction of the parameters, converging systematically in energy, density, and nuclear forces. At equal parameter count, it captures the stretched-bond and anion physics that fixed bases only recover with specialized basis augmentation. The resulting solver exhibits quadratic peak memory scaling in the cloud size, allowing us to simulate systems of up to 2,742 atoms (10,406 electrons) without any modifications at triple-zeta scale using a single four-GPU node. --- ### "AI is (not) the new...": A Diagnostic Analogy Framework for Generative AI's Cultural Impacts Authors: Rida Qadri, Vinodkumar Prabhakaran, Remi Denton Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31482v1 Generative AI is reshaping the cultural infrastructures through which knowledge is found, synthesized, and held accountable. To make sense of this shift, scholars and policymakers reach for historical analogies of technologies such as the printing press, steam power or electricity. But these comparisons are typically imprecise about which property of the technology carries the comparison, and imprecise analogies produce imprecise governance by designing interventions against the wrong property of the system. This paper offers a diagnostic framework for analyzing how generative AI can transform epistemic and cultural practice. This paper offers a diagnostic framework for analyzing how generative AI can transform epistemic and cultural practice. We decompose each intervention into three coordinates: the epistemic site at which a technology acts, the governing logic by which it organizes its object, and the technical mechanism through which the logic is instantiated. This framework allows us to distinguish between structural cultural consequences, which follow from the mechanism itself, from contingent ones, which remain open to design and institutional choice. Applying the framework to information discovery and knowledge synthesis, we show how the shift from indexicality to inference and from editorial authority to statistical consensus produces specific, traceable cultural effects and reveals governance levers that gestalt analogy obscures. --- ### Game Arena: Strategic LLM Evaluation in Competitive Environments Authors: Bovard Doerschuk-Tiberi, Yao Yan, Justin Chiu, Hann Wang, Timothy Chung, Martyna Plomecka, John Schultz, Jon Lipovetz, Clayton Drazner, Yuchen Zhuang, Jaimie Hwang, Nate Keating et al. Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31473v1 We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games. Different from static benchmarks, game arena enables models to play head-to-head matchups in structured environments where the gameplay strength naturally increases as models evolve, preventing performance saturation. This technical report details the infrastructure behind Game Arena and describes the three pilot game environments: Chess, Poker, and Werewolf. These environments span perfect information, imperfect information, and multiplayer game settings, enabling a systematic study of models' strategic planning, adaptation, and robustness under uncertainty. For each game, we provide a detailed description of the environment, evaluation metrics, and results from running full competitions across models. Through robust infrastructure and large-scale ground-truth based evaluation, Game Arena ensures reproducibility, transparency and generalizability to new games and variants over time. --- ### Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport Authors: Haixiang Sun, Andrew L. Liu Published: 2026-09-25 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.31470v1 Outliers are essential for evaluating and improving the robustness of machine learning systems, especially when future distributions may differ significantly from historical training data. In high-stakes applications, robustness often depends on rare cases that finite datasets fail to capture, making simple resampling or perturbation insufficient for stress scenario generation. Existing outlier synthesis methods typically rely on sparse neighborhoods, low support latent regions, or classifier boundary crossings, which can be heuristic, unstable, and tied to specific modalities or architectures. We therefore propose Sinkhorn Boundary Outlier Generation (SBOG), a structured framework for latent-space outlier generation that couples Sinkhorn optimal transport geometry with distributionally robust boundary modeling. The resulting Sinkhorn-induced support cost guides the sampler toward weakly supported boundary regions, while semantic constraints prevent uncontrolled drift from the intended context, yielding controlled deviations from the in-distribution reference measure rather than arbitrary sparse-region samples. Experiments on time series anomaly generation and image outlier synthesis show that our framework produces informative, semantically controlled outliers and improves downstream robustness evaluation across modalities, providing a foundation for stress scenario generation beyond empirical support. --- ### LandscapeSHAP: Which Persistent Homology Class Gets the Credit? Authors: Nikola Milićević Published: 2026-09-25 Categories: math.AT, cs.LG arXiv: https://arxiv.org/abs/2609.31469v1 Shapley values, a solution concept from cooperative game theory, have recently become a standard tool for feature credit allocation in machine learning. They provide an axiomatically justified method to fairly distribute a model's prediction among the data features. Shapley values have not yet been applied to explain machine learning models trained on features from topological data analysis. We develop what we believe is the first such approach, focusing on the persistence landscape featurization of persistence diagrams. Because each landscape coordinate is a rank statistic, crediting a model's prediction back to individual persistent homology classes (persistence diagram points) is nontrivial. We introduce LandscapeSHAP, a method for fair credit allocation to persistence diagram points based on a model's prediction. For linear models on persistence landscapes, LandscapeSHAP has a closed form expression that gives the exact Shapley value of every persistence diagram point. In particular, there is no coalition sampling required. We further prove that the four Shapley "fairness" axioms uniquely characterize this credit allocation for any model, not only linear ones. For a general nonlinear model, this unique value can only be calculated exactly from its defining coalition averaging formula, which requires considering all $2^N$ many coalitions, where $N$ is the number of points in the persistence diagram. This is computationally intractable for persistence diagrams of realistic size. We complement the exact linear model result with an efficient Monte Carlo sampling of persistence diagram coalitions. We give convergence rates in terms of number of samples needed to approximate to a desired degree of accuracy. We also prove stability results for the LandscapeSHAP credit allocation, for any model. --- ### PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents Authors: Pavel Kireyev Published: 2026-09-25 Categories: econ.GN, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.31468v1 LLMs increasingly act as purchasing agents, which makes the LLM, not the user, the one choosing among the options that satisfy a request; its preferences quietly fix what gets bought and what it costs. Hotel booking is a clean instance: a high-volume choice settled on a few comparable attributes, where the pick reveals those preferences. We introduce PriceBench, a diagnostic benchmark that recovers an LLM's price, quality, and brand preferences from its booking choices with a logit choice model, applied to 28 LLMs from 8 providers on 3,600 hotel tasks from 179 real New York City properties. We find that capability is associated with how consistently an LLM chooses, not with what it chooses: more capable LLMs hold stronger, more consistent preferences, while weaker ones either lock onto one position, exploitable by whoever controls listing order, or choose almost indifferently. What those preferences favor varies sharply across providers and even within one family: price sensitivity spans more than an order of magnitude, and the price/quality trade-off moves mean booked nightly price from \$247 to \$393 on identical tasks. What an agent buys must therefore be measured per LLM, not inferred, and we release the tasks, code, and all 28 response sets. --- ### Scaffold: Support Graph Theory Based Sparsification for Graph Neural Networks Authors: Siddhartha Shankar Das, Sai Karthik Navuluru, S M Ferdous, Ryan A. Rossi, Baris Coskunuzer, Lakshman Tamil, Edoardo Serra, Alex Pothen, Robert Rallo, Mahantesh M Halappanavar Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31466v1 Graph neural networks (GNNs) rely on message passing over graph edges, making their computational and memory costs strongly dependent on graph density. Graph sparsification offers a natural way to reduce these costs, but removing edges indiscriminately can distort important communication structure and degrade predictive performance. We introduce Scaffold, a topology-based, unsupervised graph sparsification framework derived from support graph theory preconditioners. Scaffold explicitly controls two complementary structural quantities: dilation, which measures the length of rerouting paths induced by removed edges, and congestion, which measures how strongly these rerouted paths concentrate on the retained support. By jointly controlling dilation and congestion, Scaffold preserves short communication paths while avoiding structural bottlenecks. To our knowledge, Scaffold is the first scalable GNN sparsification framework to use a joint supporting-path dilation-congestion criterion. Across 19 homophilic and heterophilic benchmarks spanning small to large graphs, Scaffold achieves the best aggregate rank among the evaluated sparsification and related methods. Using only 10%-50% of the original edges per sparse support, Scaffold recovers or closely approaches full-graph GNN performance while using less than half the memory of full-graph training and reducing end-to-end training time, including sparsification overhead. We provide an open-source software package at https://github.com/siddhartha047/Scaffold. --- ### Uncertainty-Aware Federated Learning for Infant Movement Analysis Authors: Edmond S. L. Ho Published: 2026-09-25 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.31463v1 Infant movement analysis provides valuable biomarkers for the early identification of neurodevelopmental disorders. Recent advances in deep learning have enabled automated analysis of infant movements from video-derived skeletal representations, achieving performance comparable to expert assessment for tasks such as General Movement Assessment (GMA). However, most existing approaches rely on centralized training, requiring data from multiple institutions to be collected and stored at a single site. Such assumptions are often impractical in clinical settings due to privacy, governance, and data-sharing constraints. To address these challenges, we present, to the best of our knowledge, the first federated learning framework for automated infant movement analysis and General Movement Assessment using skeletal motion data. As a clinically relevant use case, the proposed framework is evaluated on fidgety movement classification. To quantify model confidence, Monte Carlo (MC) Dropout is employed to estimate predictive uncertainty during inference. Building upon this, we propose an Uncertainty-Aware Federated Averaging (UA-FedAvg) strategy that incorporates predictive entropy derived from MC-Dropout into the federated aggregation process, enabling client contributions to be adjusted according to their predictive uncertainty. Experiments were conducted using a cross-subject evaluation protocol under a three-client federated learning setting. Results demonstrate that federated learning substantially improves classification performance compared with independently trained local models while achieving performance approaching that of centralized training. Furthermore, UA-FedAvg and its variant incorporating validation loss generally outperform conventional FedAvg across the evaluated data-split configurations. --- ### KneePreM: Towards 3D Knee MRI Foundation Models via Large-Scale Unlabeled Pretraining and Label-Efficient Fine-Tuning Authors: Xinxin Wang, Liam Hazan, Jing Li, Simona Rabinovici-Cohen, Xiaojuan Li, Mingrui Yang Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31461v1 Background: Large volumes of unlabeled knee MRI scans are available across repositories but remain insufficiently leveraged. We developed KneePreM, a knee-specific 3D self-supervised model, and evaluated transfer and label efficiency for classification and segmentation. Methods: A 3D U-Net masked autoencoder was pretrained on 19,011 unlabeled Osteoarthritis Initiative (OAI) MRI series from 4,791 participants. Downstream fine-tuning used full and reduced training sets for fastMRI+ two-label classification (1,172 examinations), Arthroscopic Partial Meniscectomy (APM) eight-target classification (1,716 examinations), SKM-TEA segmentation (155 examinations), and APM segmentation (25 examinations). Baselines were random initialization and SuPreM. Deployment workflow was implemented with a Model Context Protocol interface. Evaluation metrics included balanced accuracy, F1 score, ROC AUC, PR AUC, and Dice score. Statistical analysis used bootstrap confidence intervals and paired bootstrap tests for classification and Wilcoxon signed-rank tests for segmentation. Results: KneePreM achieved higher full-data macro ROC AUC than both baselines for fastMRI+ and APM (all p < .001). For fastMRI+ classification, KneePreM achieved a ROC AUC of 0.722 using 50% of the training data, exceeding both full-data baselines. In APM classification, KneePreM reached a ROC AUC of 0.740 with 70% of the data, matching the full-data random baseline and outperforming SuPreM. For SKM-TEA segmentation, its 70%-data Dice of 0.838 exceeded the full-data random baseline (0.835) and both same-budget comparators. In APM segmentation, its 75%-data Dice of 0.746 exceeded the full-data random baseline (0.731) and both same-budget comparators. Conclusion: KneePreM improves transfer performance and label efficiency across knee MRI classification and segmentation tasks, particularly when labeled training data are limited. --- ### Segment-Level Agentic Topic Modeling for Improved Data Exploration and Resource Efficiency Authors: Myeongjun Erik Jang, Antonios Georgiadis, Sae Young Moon, Fran Silavong Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31460v1 Topic modeling is an effective technique for discovering hidden themes within documents and is widely used in text mining and data analysis across a variety of industry sectors. Recently, large language model (LLM)-based topic models have been emerged that prompt LLMs to generate topics then assign the topics to documents, producing more natural and human-readable topics than conventional topic modeling algorithms. However, the nature of topic assignment process causes certain drawbacks, such as the incapability to produce topic distributions over a document, too broad or narrow topics, and high resource consumption, which increases with the number and length of of documents being assigned topics. These issues are particularly critical for industrial applications, which require high-quality, in-depth analysis and the processing of large volumes of documents. In this context, this paper introduces a framework called SeLATM, which addresses these concerns by employing segment-level topic generation and topic refinement through agentic feedback loops. Experimental results on various datasets demonstrate that SeLATM significantly reduces the LLM resources compared to methods based on topic assignment process, while maintaining superior performance. --- ### Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers Authors: Jaehee Seo, Jisu Kim Published: 2026-09-25 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2609.31458v1 Transformers have become a central architecture for in-context learning (ICL), particularly through their state-of-the-art performance in large language models. This success motivates understanding how transformers exploit task-relevant structure in geometrically heterogeneous data. However, existing nonparametric ICL theory has largely focused on Euclidean domains or single-manifold models. To address this gap, we study the prediction problem under unknown local geometry, modeled by sample size-dependent mixtures of manifolds with heterogeneous dimensions, smoothness, and sampling masses. Under local separation and small-perturbation conditions, we establish a minimax lower bound capturing the aggregate difficulty of the components and construct an oracle tangent local-polynomial estimator with a matching upper bound. This estimator is connected to a structure-informed, two-stage softmax transformer with a geometric preconditioner and chartwise reduced local-polynomial solvers. The transformer achieves negligible approximation error relative to the minimax rate with logarithmic depth and polynomial size. Finally, we derive an in-context generalization bound for near empirical risk minimizers over this class. Together, these results identify conditions under which the resulting predictor exploits local geometry and attains the aggregate minimax rate. --- ### Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis Authors: Mona Gandhi, Cenk Merih Olcay, Kuan-Chieh Lo, Santiago Castro, Christopher W. Myers, Srinivasan Parthasarathy Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31456v1 Vision-language models (VLMs) often struggle with compositional reasoning tasks, but the reasons for this underperformance remain unclear. A common hypothesis is that models struggle to integrate multiple components, leading to training interventions to improve compositional binding. However, this assumption has never been directly quantified. Existing benchmarks evaluate captions only in their composed form, making it impossible to separate the cost of joint reasoning from the cost of recognizing individual components under increasing load. We introduce COMPASS (COMPositional Analysis of SkillS), a controlled evaluation framework designed to isolate and measure the distinct factors underlying compositional failure. By comparing performance on composed captions with their decomposed counterparts , we directly quantify the cost of compositional integration across 87K image-caption pairs. Across multiple VLMs, this gap is real but partial, accounting for only part of the observed degradation. This motivates a finer-grained investigation into what additional factors govern model behavior. We analyze performance at the level of individual skills: object detection, attribute binding, and relation reasoning, using skill-targeted perturbations across 274K image-caption pairs. We find a consistent skill-specific pattern: each skill degrades primarily with the count of its own primitive type (self-load), while cross-load effects are predominantly positive, suggesting that primitives of different types provide useful grounding context. This pattern holds across standard contrastive encoders, explicitly trained compositional reasoning models, and non-contrastive architectures. These findings show that compositional degradation reflects multiple separable factors that cannot be reduced to joint reasoning alone. --- ### Different Corruptions, Different Signals: Uncertainty and Loss in Federated Data Quality Authors: Bradley Scott, Zeqi Luo, Edmond S. L. Ho Published: 2026-09-25 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.31454v1 Federated learning (FL) data corruption can affect either inputs or labels, but it remains unclear whether input-conditional uncertainty and prediction-label loss expose these corruption modes equally. This paper compares two corruption-detection signals in FL: input-conditional uncertainty and prediction-label loss. The uncertainty signal is characterised using a learned aleatoric variance estimate together with Monte Carlo (MC) dropout variance and entropy measures, while the loss is computed against the supplied label. We test these signals against additive image noise and persistent random label flips. On ResNet-20 with CIFAR-10 and SVHN under Dirichlet partitions with data that are not independent and identically distributed (non-IID), the two corruption types behave differently. For persistent random label flips, the within-client per-sample area under the receiver operating characteristic curve (AUC) is 0.85 on CIFAR-10 and 0.95 on SVHN for prediction-label loss, while every uncertainty estimator stays at chance (0.49--0.50). This pattern is consistent with the model remaining confident in the underlying image despite the supplied label being wrong. For image noise, expected-entropy uncertainty rises above chance (0.67 on CIFAR-10 and 0.66 on SVHN), while loss responds comparably (0.64 on both). Each signal is therefore the stronger detector for a different corruption: the prediction-label loss for persistent label flips, and expected-entropy uncertainty for image noise, with its advantage becoming apparent as federation-wide corruption prevalence increases. Robust FL data-quality assessment should match the signal to the corruption rather than rely on uncertainty alone across corruption types. --- ### Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfolding Authors: Domen Tabernik, Peter Nimac, Jan Jerićević, Danijel Skočaj, Andrej Gams Published: 2026-09-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.31452v1 Cloth manipulation is a challenging task due to the deformable and high-dimensional nature of cloth, which leads to complex interaction dynamics and perceptual ambiguity arising from frequent occlusions of critical visual cues such as folds, edges, and grasp points. In this work, we tackle cloth unfolding using a regrasping-in-the-air strategy, where one manipulator holds the cloth while the other grasps it at an optimally selected point to unfold it. To this end, we propose CeDiRNet-6DoF, a deep learning framework that jointly predicts effective grasp points and the complete 6-DoF grasp pose from the observed cloth configuration. By integrating dense 3D grasp regression with segmentation and sine-cosine-encoded Euler angles, the proposed method reliably estimates the grasp configuration that maximizes the unfolded cloth area. We extensively evaluated CeDiRNet-6DoF on a bimanual robotic setup within the ICRA 2024 Cloth Competition framework, achieving state-of-the-art performance. An ablation study further validates the benefits of key design components, including joint segmentation, background randomization, and image cropping. These results establish CeDiRNet-6DoF as a robust and versatile foundation for reliable robotic cloth manipulation in unstructured environments. --- ### TemplateCraft: Agentic Visual Template Generation Authors: Hongjie Yu, Zhiyuan Fan, Yuzhe Zhang, Jiangcun Du, Zhicheng Gao, Yuhong Zhang, Xiaokai Zhan, Zongshi Xie Published: 2026-09-25 Categories: cs.MM, cs.CV arXiv: https://arxiv.org/abs/2609.31451v1 The growing popularity of short videos has driven demand for one-click content creation. Visual templates turn uploaded images into personalized content with preset effects, but reusable template generation still requires substantial manual effort in asset preparation and tool orchestration. We propose TemplateCraft, a multi-agent system that converts natural-language instructions into client-executable templates through planning, material generation, effect-workflow generation, and protocol compilation. Its Planner-Evaluator loop uses execution feedback for targeted rollback, while stage-level and long-term memory support revision without parameter updates. We evaluate TemplateCraft on TemplateBench, derived from 60 real-world templates. With the same Qwen3-VL backbone, TemplateCraft raises image/video generation success rates from 56.7%/30.0% to 66.7%/50.0% over Planner-only (best-of-three) and improves template adherence and style consistency. With additional evaluation and revision, it matches or exceeds a GPT-4o Planner-only baseline on selected metrics. Persistent assets further improve cross-input style consistency. --- ### From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training Authors: Wang Jingxin Published: 2026-09-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31450v1 Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy. We examine how changes in accuracy and training objectives relate to image-conditioned decisions in a controlled Qwen2.5-VL-3B study on PMC-VQA. We compare supervised fine-tuning (SFT) with low-rank adaptation (LoRA) restricted to the language model, expanded multimodal adaptation scopes, standard answer-only Group Relative Policy Optimization (GRPO), and a counterfactual evidence objective. On 2,000 clean-test questions, language model LoRA SFT changes correct-image accuracy by +1.10 percentage points (95% paired bootstrap CI:-0.85 to +3.05), while visual-benefit events decrease by 2.40 points and image sensitivity decreases by 5.60 points. Paired records reveal 155 acquired and 203 lost visual-benefit events. Broader adaptation yields lower correct-image accuracy than language-model LoRA SFT. Standard GRPO produces mixed-reward groups and parameter updates, with an uncertain clean test accuracy change. A generation audit reveals that canonical option scores can follow a different token path from generated answers. With scores taken along the greedy generation path, the evidence target improves on the training set; its gains over standard GRPO remain inconsistent on validation data at matched training doses. Sample-level analyses trace how evidence scores, decision margins, and generated answers change during post-training. This empirical and measurement audit identifies gaps between optimization activity, target acquisition, and useful held-out visual behavior. --- ### ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs Authors: Junyi Gao, Yu Shi, Pingzhao Hu, Ewen M Harrison Published: 2026-09-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.31448v1 Clinical prediction models estimate risk from patient measurements, while large language models support medical text understanding and question answering. Yet their language capabilities do not ensure accurate prediction from structured, high-dimensional clinical time series. Improving this ability would connect risk estimation with flexible questions about a patient's evolving condition. We introduce ViSTA, a compact adapter that incorporates irregular numerical measurements into a pretrained vision-language model's chart representations. It learns corrections to visual tokens while leaving all pretrained parameters unchanged. On MIMIC-IV, ViSTA has the highest mean scores among the compared adaptations on all four metrics for acute kidney injury and mortality prediction across models with 2-9 billion parameters. With 0.516 million trainable parameters, the 2-billion-parameter model reaches an area under the ROC curve of 0.7376 for acute kidney injury, compared with GPT-5.6 Sol's 0.7380 with text input and high reasoning effort. Training for temporal question answering yields 69.27% accuracy at 4 billion parameters with over 90% fewer trainable parameters than low-rank adaptation using charts or numerical text, at a 2.82-4.88 percentage-point accuracy gap. ViSTA extends pretrained language models to numerical prediction and temporal questions. --- ### Implicit Neural Representation for Hyperspectral Video Compression Authors: Alfredo Scalera, Paul Murray, Jaime Zabalza Published: 2026-09-25 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31435v1 With the advent of snapshot cameras, hyperspectral video is becoming more readily available. In recent years, new applications have emerged which have led to increasingly larger datasets. However, hyperspectral video compression remains in the early stages. In this study, we explore the use of implicit neural representation as a candidate solution. We propose a novel extension of an existing RGB video compression model, achieving Bjøntegaard Delta PSNR gains of +4.99 dB and Bjøntegaard Delta rate of -88.88% compared to traditional hyperspectral image compression methods applied frame-by-frame. In addition to reconstruction quality, the effects on downstream task performance are measured in the form of object tracking success. Compared to video compressed with methods based on principal component analysis and JPEG2000 in low data regimes, our proposed method improves tracking area under the curve by up to 23.42% and distance precision by up to 35.56% on examples from the HOT2026 dataset. --- ### AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet Microscopy Authors: Edward Gaibor, Kyriaki-Margarita Bintsi, Carmen Luz Leiva Ureta, Zayneb Bellatif, Chiara Maffei, Wenze Li, Elizabeth Hillman, Yaël Balbastre, Anastasia Yendiki Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31431v1 Accurate segmentation of axons in 3D microscopy data is important for analyzing white-matter organization, but dense ground truth labels are expensive to obtain. Existing supervised axon segmentation methods rely on target-domain annotations and can be brittle when tissue type, species, modality, or acquisition conditions change. We present AxonSynth, a domain-randomized synthetic-data framework for training 3D axon segmentation models without manually annotated real training volumes. AxonSynth generates dense synthetic axon labels with orientation priors that reflect realistic fiber configurations and renders them with randomized density, contrast, bias fields, blur, and noise. A three-class 3D U-Net is trained to predict background, axon sheath and intra-axonal space. We evaluate zero-shot transfer on 10 held-out light-sheet microscopy (LSM) patches from macaque and human brain samples labeled with one of three axonal markers, comparing against calibrated thresholding and Frangi filtering using overlap, corrected detection, false-positive, and topology metrics. On macaque samples, AxonSynth achieved the best corrected Dice and corrected precision (0.826 and 0.851), compared with 0.765 and 0.754 for thresholding and 0.685 and 0.762 for Frangi. On human samples, corrected Dice was comparable to thresholding (0.857 vs. 0.868), while component-count error decreased from 22,504 to 3,377. Across all held-out patches, AxonSynth reduced component-count error in 10/10 patches and Euler-characteristic error in 8/10. These results show that synthetic-label domain randomization can reduce dependence on manual axon annotation while supporting synthetic-to-real 3D segmentation. --- ### Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents Authors: Zhensheng Zou, Guoqing Wang, Dan Hao Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31430v1 Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compression methods can discard information needed by later actions, while adapting agents to soft-token representations can compromise their original behavior. To reduce context while preserving action-critical information and agent behavior, we combine Latent Observations, Hard Actions (LOHA), a context layout that separates compressed history from text needed for exact reference, with Anchored Context Distillation (ACD), a training method that enables latent reading while constraining behavioral drift. LOHA compresses older tool observations into soft tokens while retaining the agent's own turns and the last K observations in text, providing compact access to historical information and exact access to recent content. To enable the agent to use this representation, ACD distills the base model's full-text predictions into the latent view while anchoring its behavior on plain-text inputs to the same base model. On SWE-bench Verified, K=3 reduces context per call by 43% for Qwen3-4B and 57% for SWE-Master-4B-RL, with resolve rates of 12.1% and 21.8% versus 14.5% and 27.5% for their uncompressed bases. A single-run recency sweep reaches 14.4% and 23.0% at K=8, with larger windows generally favoring task performance over compression. Under a 32K-token limit, Qwen3 with K=3 resolves 21.1% of a 199-instance subset versus 11.1% for the same adapted agent using full text. In concurrent single-GPU serving, it achieves 1.9 times that full-text agent's instance throughput. --- ### Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis Authors: Jakub Masłowski, Jarosław A. Chudziak Published: 2026-09-25 Categories: cs.MA, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.31422v1 Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. However, their final synthesis phase still remains inadequately controlled. Even with detailed debate logs, summarizing models are prone to fabricating smoothly written debate consensus that is not grounded in the debate's history. To address this safety gap, this paper presents empirical research and studies if the introduction of active post-debate verification can mitigate the production of such factually unsupported summaries, while still providing valuable information. Furthermore, it is examined whether explicitly signalling divergence is preferable in the absence of a reliable compromise. The Active Provenance Gate (APG) is introduced as a post-debate verification layer that treats the source as a hard constraint, analysing the debate logs, auditing each claim, and applying self-correction. In crisis simulations, the self-healing mechanism more than doubles the average data Provenance Fidelity in difficult condition scenarios, before the strict gate blocks unsupported claims and generates divergence reports. In the human study, a vast majority of the users (over 75%) preferred a report explicitly stating failure in critical scenarios, despite most of them perceiving fabricated consensus from the baseline system as more fluent. Our main contribution is the transition of data origin tracing from passive logging to active conditional blocking before publication. --- ### Evaluating the accuracy of KV cache reuse techniques Authors: Samuel Cestola, Tianxiang Xia, Pengfei Zheng, Weiyan Zheng, Bo Wang, Yi Zhao, Diego Didona Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31415v1 Position-independent KV cache reuse aims to reduce latency in retrieval-augmented generation by reusing chunk-level KV caches across prompts. We show that current evaluations of KV cache reuse techniques rely on measurements that fail to faithfully capture the loss of accuracy attributable to reuse, often artificially inflating the reported effectiveness. We also show that existing datasets do not exhibit the reuse dynamics needed to thoroughly evaluate such techniques. To address these issues, we propose an evaluation methodology that measures this accuracy loss without ambiguity and we introduce Boxoffice, a tool that programmatically generates evaluation datasets that exercise challenging KV cache reuse patterns. --- ### Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers Authors: Mert İncidelen, Yamen Kashkash, Asya Berker, Murat Aydoğan Published: 2026-09-25 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.31403v1 Vision-language models (VLMs), despite their success in optical character recognition (OCR) tasks, are vulnerable to typographic attacks and have a fragile structure for images with multiple text layers. In this study, the DecoyBench dataset was created using the Decoy Font method. The dataset consists of 300 images, each containing text with sharp contour lines superimposed on another text with soft shading. Six recent closed-source models from three different model families were evaluated using this dataset under two different prompting conditions (naive and guided) and at two different resolutions ($512\times512$ and $64\times64$). A validation study showed that human participants could read both text layers with high accuracy. In contrast, the models, with most variants and both prompting methods, read the contour text with near-human accuracy at high resolution, but almost never fully extracted the shading text. At low resolution, the contour text could not be read by either the models or humans, while the shading text could be extracted with high accuracy. The findings indicate that the evaluated VLMs exhibit a consistent behavioral limitation when processing typographic structures containing multiple spatial frequency layers. ---