# Research Papers — 2026-09 · bundle page 199 of 266 > Full-text markdown of papers #9901–9950 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/199 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/198.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/200.md) ### Artificial Intelligence Literacy and Sustainable Development: An Ethical Governance and Development Goals Framework Authors: Md. Masudul Islam, Mirza Niaz Morshed, Md. Shafiqul Islam Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10489v1 AI literacy provides foundational competencies that support ethical, transparent, and sustainable technological development, although higher-order capabilities such as governance, critical evaluation, and strategic decision-making extend beyond basic literacy into advanced levels of AI competency. This study positions AI literacy as a governance capacity that complements and strengthens all 17 SDGs. It introduces a six-level taxonomy of artificial intelligence reasoning and ethics that extends traditional learning models by incorporating ethical judgement and strategic foresight. This taxonomy forms the foundation of an integrated framework linking education, governance, and sustainable development. A survey of 300 participants from diverse professional backgrounds within a national context which reveals strong technical awareness but limited ethical and governance readiness, highlighting critical gaps in public capacity to manage artificial intelligence responsibly. Findings show that ethical reasoning and reflective thinking are the strongest predictors of sustainable and trustworthy artificial intelligence use. The study proposed to embed literacy-based competencies into curricula, institutional policies, and governance mechanisms to accelerate equitable and responsible progress toward sustainable development goals --- ### Nonmaximal sums of maximally monotone operators under Rockafellar's constraint qualification Authors: Weifeng Yang Published: 2026-09-09 Categories: cs.LG, math.FA arXiv: https://arxiv.org/abs/2609.10487v4 We construct counterexamples to Rockafellar's sum conjecture in which two maximally monotone operators satisfy the interior-domain condition but their sum is not maximally monotone, thereby providing the complete disproof of the conjecture. We establish a general construction theorem that computes the entire monotone polar of a class of graphs and characterizes their maximal monotonicity by the nonexistence of solutions to explicit equations in the continuous dual. We also prove a pullback theorem that transfers counterexamples through bounded linear surjections. These theorems provide a systematic mechanism for generating entire families of counterexamples and lead to further structural consequences for the resulting operators. Specifically, we obtain four classes of counterexample families: weighted constructions with different curves, first operators with prescribed affine value dimensions, second operators obtained by positive rescaling and norm-continuous monotone perturbation with full domain, and counterexamples on further Banach spaces. The last class yields counterexamples on every Banach space containing a closed subspace isomorphic to $c_0$ or $\ell^1$, or admitting such a quotient. We also give explicit constructions on $c_0$ and standard $\ell^1$ that realize the construction and pullback mechanisms, respectively. We further determine the domain geometry and exact radial bounds of the constructed operators, characterize reflexivity by a fixed rank-one test in two classical classes of Banach spaces, identify maximal monotone extensions under surjective pullback, and compute exact Fitzpatrick identities. The appendices further extend these constructions to additional parameter and product families, nonlinear scalar and strictly monotone second operators, normal-cone and subdifferential partners, and examples with prescribed radial bounds, and more counterexample families. --- ### Nonmaximal sums of maximally monotone operators under Rockafellar's constraint qualification Authors: Weifeng Yang Published: 2026-09-09 Categories: cs.LG, math.FA arXiv: https://arxiv.org/abs/2609.10487v1 We construct counterexamples to Rockafellar's sum conjecture in which two maximally monotone operators satisfy the interior-domain condition but their sum is not maximally monotone. We give one counterexample on $c_0$ and another on $\ell^1$ with its usual norm. We establish a general construction theorem that computes the entire monotone polar of a class of graphs, gives a necessary and sufficient condition for their maximal monotonicity, and shows how a positive rank-one perturbation yields a nonmaximal sum under this condition. We verify the theorem's hypotheses and its maximality criterion on $c_0$, thereby obtaining a counterexample to the conjecture. Furthermore, we construct a bounded linear surjection from $\ell^1$ onto $c_0$ and use it to obtain the counterexample on $\ell^1$. --- ### Deep Learning-Based Detection of Electrical Faults and Power Quality Disturbances in Aerospace Power Systems Authors: Ian C. Guzmán, Radu Babiceanu, Berker Peköz Published: 2026-09-09 Categories: eess.SP, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.10479v1 More Electric Aircraft require fast and reliable monitoring of high-frequency electrical networks, yet most power quality disturbance and fault diagnosis methods are developed for conventional 50 or 60 Hz grids. This work presents a hardware-aware deep learning framework for multiclass detection of electrical faults and power quality disturbances in a 400 Hz aerospace power system. A high-fidelity simulation model inspired by the Boeing 787 electrical architecture generates voltage and current waveforms for 21 normal, disturbance, switching, open-circuit, and short-circuit conditions. Two datasets, each containing 73,500 samples, are formed from one-dimensional time-series signals and short-time Fourier transform time-frequency representations. Signal-processing augmentation, domain randomization, and class-specific generative adversarial networks increase waveform diversity, and the time-series dataset is released through IEEE DataPort. We compare 1D and 2D convolutional neural networks, long short-term memory networks, CNN-LSTM hybrids, ResNet, MobileNet, and VGG models under common training conditions. A compact ResNet provides the best accuracy-complexity tradeoff, achieving 96.94 percent software test accuracy with 175,685 parameters. After 8-bit quantization and deployment on a Xilinx Zynq UltraScale Plus MPSoC ZCU102, the model achieves 95.87 percent accuracy and a measured mean neural-network accelerator latency of 6.90 ms per input record. The results establish simulation-based, accelerator-level feasibility for embedded edge AI in aircraft electrical health monitoring and motivate future end-to-end data acquisition and experimental validation. --- ### AgroVisNet: A lightweight Convolutional Network and the BD-PlantDX Expert-Validated Benchmark for Radish, Potato and Pointed Gourd Disease Classification Authors: Md. Abdullah Mandal, Saad Ahmed, Md. Khalid Syfullah Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10469v2 Automated plant disease diagnosis is increasingly deployed on farmer-held devices in regions where agronomic expertise is scarce and network connectivity is unreliable. Three obstacles limit its practical value: public benchmarks are dominated by a small set of non-native crops, region-specific datasets are rarely validated by domain experts, and the architectures that reach competitive accuracy carry parameter budgets that are unsuited to low-cost hardware. We propose AgroVisNet, a compact convolutional network trained from scratch, together with BD-PlantDX, an expert-validated benchmark of 12,432 field images spanning 12 classes of radish, potato and pointed gourd in healthy and diseased states, collected across the Bogura and Nilphamari districts of Bangladesh. AgroVisNet couples grouped bottleneck residual blocks carrying sequential channel and spatial attention with multi-scale depthwise blocks and a dual-pooling classification head, reaching 290,572 trainable parameters. On BD-PlantDX the model attains 99.52% test accuracy and 99.52% weighted F1, exceeding all six ImageNet-pretrained lightweight backbones evaluated under an identical protocol while using 8.7 to 16.8 times fewer parameters and 1.3 to 8.5 times fewer multiply-accumulate operations. Exported for deployment, the model quantises to a 0.46 MB full-integer network at a 0.22 percentage-point accuracy cost and classifies an image in 8.40 ms on a single CPU. Across five random seeds accuracy remains at 99.57 +- 0.10%, a ten-variant ablation isolates the contribution of each component, and the same architecture transfers without redesign to two independently collected datasets at 98.71% and 99.05% accuracy. Grad-CAM evidence indicates that predictions rest on lesion-bearing leaf regions rather than on background cues. --- ### AgroVisNet: A lightweight Convolutional Network and the BD-PlantDX Expert-Validated Benchmark for Radish, Potato and Pointed Gourd Disease Classification Authors: Md. Abdullah Mandal, Saad Ahmed, Md. Khalid Syfullah Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10469v1 Automated plant disease diagnosis is increasingly deployed on farmer-held devices in regions where agronomic expertise is scarce and network connectivity is unreliable. Three obstacles limit its practical value: public benchmarks are dominated by a small set of non-native crops, region-specific datasets are rarely validated by domain experts, and the architectures that reach competitive accuracy carry parameter budgets that are unsuited to low-cost hardware. We propose AgroVisNet, a compact convolutional network trained from scratch, together with BD-PlantDX, an expert-validated benchmark of 12,432 field images spanning 12 classes of radish, potato and pointed gourd in healthy and diseased states, collected across the Bogura and Nilphamari districts of Bangladesh. AgroVisNet couples grouped bottleneck residual blocks carrying sequential channel and spatial attention with multi-scale depthwise blocks and a dual-pooling classification head, reaching 290,572 trainable parameters. On BD-PlantDX the model attains 99.52% test accuracy and 99.52% weighted F1, exceeding all six ImageNet-pretrained lightweight backbones evaluated under an identical protocol while using 8.7 to 16.8 times fewer parameters and 1.3 to 8.5 times fewer multiply-accumulate operations. Exported for deployment, the model quantises to a 0.46 MB full-integer network at a 0.22 percentage-point accuracy cost and classifies an image in 8.40 ms on a single CPU. Across five random seeds accuracy remains at 99.57 +- 0.10%, a ten-variant ablation isolates the contribution of each component, and the same architecture transfers without redesign to two independently collected datasets at 98.71% and 99.05% accuracy. Grad-CAM evidence indicates that predictions rest on lesion-bearing leaf regions rather than on background cues. --- ### Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization Authors: Andy Zeyi Liu, Haoran Sun, Lucas Baker, Randall Balestriero, John Sous Published: 2026-09-09 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.10464v1 Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning, but their capability to learn physics and generate physically realistic dynamics remains hitherto untested. In this work, we introduce SemiGroup-JEPA (SG-JEPA), which extends the LeWorldModel framework by supplying the parameter governing the physics to the temporal model via action-conditioning and jointly training an encoder and predictor through an autoregressive latent rollout. To evaluate the model's ability to generalize out of distribution, we design dynamical tasks under different gravitational fields that, despite obeying the same physical law, exhibit qualitatively different dynamics, ranging from floating motion in weak gravitational fields to rapid bouncing in strong ones. In contrast to DINO-WM, SG-JEPA reduces open-loop prediction error by up to 2 times on two-dimensional datasets, and increases control success rate up to 2.5 times for three-dimensional robotic datasets, for which we train independent diffusion policies. To explain this advantage, we develop a linear feature model that separates local law-conditioned error from its recursive amplification under rollout. Guided by this model, we find that back-propagating the multi-step rollout loss into the representation trains the encoder to keep the features that the predictor can carry forward, and that those are the features the dynamics depend on, so most of the gain comes from the encoder learning better features rather than from the predictor learning better dynamics. See project page at https://sg-jepa.github.io. --- ### Advanced Brain Tissue Imaging with Data-Consistent Diffusion Priors in Laminographic X-Ray Nanoimaging Authors: Wenxuan Fang, Abraham L. Levitan, Ana Diaz, Carles Bosch, Adrian Wanner, Andreas T. Schaefer, Mirko Holler, Tomas Aidukas, Nicholas W. Phillips, Yuxin Zhang, Alexandra Pacureanu, Manuel Guizar-Sicairos et al. Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10456v1 Nanoscale imaging of mammalian brains is critical for connectomics. X-ray laminography enables high-throughput imaging of extended, plate-like biological specimens. However, the tilted acquisition geometry leads to incomplete Fourier-space coverage, giving rise to a missing-cone of information. Conventional reconstruction methods cannot recover unmeasured information within the cone, resulting in artifacts that distort fine brain structures. While resolving these requires modeling 3D structure, direct 3D deep learning approaches are limited by data scarcity and computational cost. Here we introduce LUCID (Laminography with Unified Consistent Diffusion), a framework that combines multi-view diffusion priors with projection-domain data consistency. LUCID integrates complementary 3D structural information while enforcing strict alignment with the laminography forward model. On simulated datasets, LUCID substantially improves spatial fidelity and restores missing Fourier components, outperforming baseline methods. Applied to experimental laminography data, LUCID generalizes robustly despite being trained exclusively on fully sampled tomographic volumes, and effectively recovers unmeasured Fourier information. --- ### JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition Authors: Zixiang Chen, Yuheng Lu, Zihao Cheng, Zeming Liu, Jizeng Bai, Ziye Huang, Zhiyin Lin, Zihan Li, Yuhang Guo, Yunhong Wang, Haifeng Wang Published: 2026-09-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.10451v1 Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, resulting in an overly optimistic assessment of agents' readiness for real-world usage. We introduce JarvisGUI, a dynamic benchmark that evaluates GUI agents on cross-device workflows requiring coordinated interaction across heterogeneous platforms, including Android, Windows, and Ubuntu. Specifically, JarvisGUI formulates GUI tasks as input-output transformations under a lightweight type system, which allows us to automatically compose multi-step, cross-device workflows and dynamically evaluate agent performance within a unified framework. By evaluating agents in virtual environments spanning multiple operating systems, JarvisGUI reveals that state-of-the-art open-source GUI agents struggle with the state-transfer awareness, cross-platform contextual reasoning, and long-horizon dependency management required for real-world workflows, exposing a critical capability gap invisible to existing benchmarks. --- ### Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning Authors: Mehrnaz Mofakhami, Ananya Sahu, Alejandro R. Salamanca, Daniel D'souza, Alexandre Berard, Thomas Euyang, Marzieh Fadaee, Julia Kreutzer Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10445v1 Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: models primarily reason in English regardless of the language they are prompted in. This is inaccessible for non-English-speaking users, risks losing the intent of the original question, and forgoes knowledge more readily expressed in the target language. In this work, we advance L2 reasoning, the ability of a model to reason consistently in the language of the user's prompt, thus building an in-language bridge between the prompt and the answer. We approach this problem from a data-centric angle, investigating how to optimize data composition and scheduling in SFT for reasoning generalization. Building Tiny Aya L2-Thinker at 3.35B scale, we achieve an L2 reasoning rate above 93% across 60 languages on 6 benchmarks spanning math, commonsense reasoning, instruction following, open-ended generation, and cultural reasoning while keeping performance strong. We show the path to generalizing L2 reasoning to held-out languages goes through broader language coverage, readily available multilingual non-reasoning data, and a sufficient English reasoning backbone. These findings indicate that reasoning is a language-agnostic behavior that can be transferred across typologically diverse languages through careful data mixing and without requiring reasoning supervision in every target language. We release our model weights and multilingual reasoning data to support further research on accessible, in-language reasoning. --- ### ConvMem: Convolutional Memory for Long-Context Reasoning Authors: Hongming Zhang, Zhaozhen Gu, Fengshuo Bai, Ming Hao, Qingyang Zhang, Yuanyuan Wang, Shiyang Tang, Yanna Wang, Bo Xu Published: 2026-09-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.10441v1 While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the effective context by reading text in segments and iteratively updating a fixed-size memory. However, this sequential paradigm suffers from high latency and requires costly reinforcement learning (RL) training, which can lead to overfitting on specific datasets. To overcome these limitations, we propose ConvMem, a training-free, highly parallelizable framework that reformulates long-context reasoning as a hierarchical convolution. Inspired by CNNs, ConvMem treats an LLM prompted with a specific query as a convolutional kernel. This kernel summarizes text segments hierarchically, shortening the reasoning path from a linear chain into a logarithmic tree. Specifically, ConvMem integrates \textit{Configurable Strides} and \textit{Skip Connections} to ensure robust evidence capture and propagation, while employing \textit{Multi-Kernel Convolution} to decompose complex queries into disentangled semantic channels. This design not only mitigates error accumulation but also enables massive parallelization across both text segments and reasoning threads. Experiments on RULER-HotpotQA and RULER-2WikiMultiHopQA demonstrate that ConvMem outperforms training-free baselines and avoids the risk of overfitting to parametric priors often observed in RL-trained models on out-of-distribution tasks. --- ### Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs Authors: Ravi Ranjan, Olivera Kotevska, Agoritsa Polyzou Published: 2026-09-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.10439v1 Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machine unlearning offers a practical alternative to full retraining, but many existing methods apply broad or fixed parameter updates that can degrade utility and remain brittle under deployment changes such as post-training quantization, where forgotten knowledge may partially re-emerge. We propose Forgetting Only What Matters via Unlearning Layers (FOM-UL), a layer-level unlearning framework that selects transformer layers using a forget-to-retain significance score. This score identifies layers with high influence on the forget set and low sensitivity to the retain set, allowing FOM-UL to concentrate updates where they are most effective while leaving most of the model unchanged. This targeted update strategy improves the forgetting-utility trade-off and provides an empirical path toward quantization-resilient unlearning by reducing the chance that small, diffuse updates are erased by low-bit rounding. Across TOFU, KnowUnDo, and MUSE-style evaluations, FOM-UL reduces residual memorization compared with strong GA, NPO, KLD, SURE, ReLearn, and LUNAR-based baselines while preserving retain-set utility close to the vanilla model. Under 8-bit and 4-bit post-training quantization, FOM-UL maintains stronger memorization suppression and utility preservation than competing methods, and adversarial prompt evaluations show lower recovery of forgotten content. Overall, FOM-UL provides an efficient unlearning strategy that improves targeted forgetting, utility preservation, and deployment robustness without claiming formal guarantees of erasure. --- ### Do speech foundation models really learn words? Authors: Robin Huo, Ewan Dunbar Published: 2026-09-09 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.10434v1 Self-supervised speech foundation models are now used in a wide array of downstream applications, including traditional speech recognition and as the basis for tokens in speech-aware language models. Attempts to understand their usefulness have largely focused on probing their representations' ability to discriminate phonemes and words. However, discriminative ability for words need not imply specialized representation of words per se. Good discrimination of words may be explained by good encoding of word form (phonemes) rather than form-independent word representations encoding identity or syntactic/semantic properties. By partialling out phoneme information using residualization, we show that, in later layers, HuBERT and wav2vec 2.0 do in general learn representations which encode words with reasonable fidelity independently of local phonetic content. We show that this simple approach to disentanglement can enhance higher-order linguistic information in word discovery tasks. --- ### Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in Wildfire Response Authors: Caden Chandra, Jerry Ng Published: 2026-09-09 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.10433v1 This study develops a deep reinforcement learning framework for training Unmanned Aerial Vehicle (UAV) agents to navigate and monitor simulated wildfire environments. Results show that agents learn increasingly stable and effective behaviors over time, as demonstrated by converging loss trends, improved reward signals, and more consistent navigation patterns such as fire-boundary tracking. Overall, these findings highlight the potential of deep reinforcement learning (DRL) based UAV systems for autonomous wildfire monitoring and suggest that environmental structure and reward design influence policy effectiveness. --- ### Algorithmic stability via ensembling Authors: Rina Foygel Barber, Richard J. Samworth Published: 2026-09-09 Categories: math.ST, cs.LG arXiv: https://arxiv.org/abs/2609.10428v1 Algorithmic stability refers to the property of an algorithm being insensitive to perturbations of the input data, where the type of perturbation may vary depending on the setting. In this work, we develop a general framework to quantify the extent to which any ensembling strategy defined via averaging can yield stability guarantees for any type of data perturbation. Our main theoretical result is a guarantee on the stability of this ensembled algorithm, given in terms of the norm of a certain covariance operator that describes the ensembling process. We show how our general framework yields interpretable and intuitive insights in several examples of perturbations of practical interest, and provides much sharper guarantees than those obtained from privacy considerations. --- ### Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence Support Authors: Jonathan A. Handler, Marlene I. Robles-Granda, Jacob E. Mefford, Jeremy S. McGarvey, Gregory S. Podolej, Colleen J. Klein, Matthew D. Dalstrom, William F. Bond Published: 2026-09-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.10421v1 Background: Emergency Department (ED) return visits are commonly reviewed for quality assurance, but are often limited (e.g., to revisits within 48-72 hours) to increase actionable finding yield while minimizing chart review burden. Those limitations may lead to missed quality improvement opportunities. Methods: We conducted an exploratory, retrospective study of randomly selected ED visits to a multihospital health system having an ED revisit within 1-14 days to the same health system. Given only each visit's primary diagnosis, raters (2-3 clinicians and GPT-4 large language model (LLM)) assessed characteristics of the diagnosis pairs, including the "target": whether a pair warranted further assessment. Informed by rater response analyses, an algorithm leveraging an LLM-populated knowledge graph ("KGA") was created to automatically screen for potentially concerning pairs, then preliminarily assessed. Results: 99 diagnosis pairs were included. GPT-4 responses poorly correlated to clinician raters, rating nearly all (94%) pairs as warranting follow-up (4.4-13.3 times more than clinicians). However, prompt engineering was minimal. Among clinician raters, revisit medical gravity was consistently significantly associated with the target, while a differential diagnosis/complication composite was significantly associated on unadjusted, but not adjusted (though less powered) analysis. The KGA achieved 83-100% positive predictive value for at least one clinician rater determining further assessment was warranted based on the diagnosis pair. Conclusion: These results can inform next steps for improving screening with LLMs like ChatGPT. Further research is warranted to validate this preliminary work's finding that the KGA may enable enhancing the scope and yield of screening without substantially increasing reviewer workload. --- ### Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs Authors: Ansuman Mullick, Eray Tüzün Published: 2026-09-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.10413v1 Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is lifecycle management: which memories should persist, which should be replaced, and at what rate, conditioned on the behavioral type of each fact. Fortunate Recall (FR) is a composable policy layer that classifies personal facts into a 10+1 behavioral ontology and applies category-specific lifecycle policies (differential temporal decay, slot-key supersession, event-time validity, and category-aware retrieval routing) as deterministic functions over LLM-extracted metadata. FR-Bank, our infrastructure-independent implementation, reaches a 76.9% pass rate on LifecycleBench, a new 516-question temporal-disambiguation benchmark, ahead of Mem0, A-MEM, Memory-R1, and MemoryOS (61% to 70.5%), and 75.2% on the full LongMemEval-S under the canonical Wu et al. judge protocol, so lifecycle policies impose no measurable cost on standard retrieval. A pre-registered ablation locates the gains: replacing the typed layer with three generic lifecycle primitives leaves correctness statistically unchanged (-1.7pp, 95% CI (-6.0, +2.7)), so the generic lifecycle metadata carries the correctness advantage, while the behavioral ontology carries calibration, halving downstream confabulation (12.0% vs 24.2%, p<0.001). End-to-end, FR-Bank cuts confabulation from Mem0's 45.1% to 22.4% over answered queries and from 32.2% to 13.0% over all queries while answering more of them correctly (31.2% vs 18.6%); the ranking replicates on the open-weight Kimi K2.5. The decomposition transfers to BEAM, an independently built benchmark: 46.8% correct vs Mem0's 32.9% over 280 questions, with the ontology's benefit concentrated in contradiction resolution and saturating near seven policy clusters. The ontology, benchmark, and code are released. --- ### Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization Authors: Ayan Majumdar, Shounak Paul, Pushpdeep Singh, Ines Abdelaziz, Sayeh Jarollahi, Seungeon Lee, Krishna P. Gummadi, Ingmar Weber, Abhisek Dash Published: 2026-09-09 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.10410v2 The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models possess the basic capabilities needed to confront this challenge, whether they can reliably moderate online content remains an unanswered question. In this paper, we systematically compare two competing paradigms for Vision-Language Model (VLM) guidance: an instruction-driven approach where models reason from policy precepts, and an example-driven approach where they generalize from prior precedents. We ground this investigation in ModerationBench, a new benchmark of 4,000 manually annotated, in-the-wild posts from the Bluesky platform. Our experiments reveal that foundation models can substantially outperform Bluesky's deployed moderation system, nearly tripling its $F_1$ score (0.60 vs. 0.22) on Random Posts in the benchmark, with both instruction- and example-driven paradigms achieving comparable peak effectiveness. Our findings thus chart a path toward reliable and adaptable policy operationalization at scale. --- ### Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization Authors: Ayan Majumdar, Shounak Paul, Pushpdeep Singh, Ines Abdelaziz, Sayeh Jarollahi, Seungeon Lee, Krishna P. Gummadi, Ingmar Weber, Abhisek Dash Published: 2026-09-09 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.10410v1 The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models possess the basic capabilities needed to confront this challenge, whether they can reliably moderate online content remains an unanswered question. In this paper, we systematically compare two competing paradigms for Vision-Language Model (VLM) guidance: an instruction-driven approach where models reason from policy precepts, and an example-driven approach where they generalize from prior precedents. We ground this investigation in ModerationBench, a new benchmark of 4,000 manually annotated, in-the-wild posts from the Bluesky platform. Our experiments reveal that foundation models can substantially outperform Bluesky's deployed moderation system, nearly tripling its $F_1$ score (0.60 vs. 0.22) on Random Posts in the benchmark, with both instruction- and example-driven paradigms achieving comparable peak effectiveness. Our findings thus chart a path toward reliable and adaptable policy operationalization at scale. --- ### HybridFLow: SDN-Orchestrated Client Partitioning for Hybrid Federated Learning Authors: Osama Abu Hamdan, Rabin Pandey, Hao Che, Engin Arslan, Md Arifuzzaman Published: 2026-09-09 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2609.10404v1 Cross-silo Federated Learning (FL) enables geographically distributed institutions to collaboratively train machine learning models without sharing raw data. In wide-area deployments, however, communication delays often dominate round completion time and exacerbate the straggler effect. Hybrid FL addresses this challenge by combining synchronous and asynchronous client participation, but effective partitioning requires visibility into network conditions such as shared bottlenecks, link utilization, and path contention that individual clients cannot observe. We present HybridFLow, a closed-loop SDN-driven orchestration framework that integrates network-layer intelligence directly into hybrid FL. Leveraging the SDN controller's global topology view, HybridFLow generates calibrated per-client communication-time estimates before each training round and uses them to partition clients into synchronous and asynchronous groups while balancing round latency and update staleness. After each round, measured communication times are fed back to the controller to continuously refine future predictions. Experimental results across multiple network topologies show that HybridFLow reaches 80% target accuracy 33-40% faster than SmartFLow and reduces average round duration by 30-40 seconds, while FedAsync fails to reach the target accuracy under non-IID data distributions. --- ### Retrofitting Code Using LLMs to Support Exceptional Behavior Authors: Linghan Zhong, Jiyang Zhang, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric Published: 2026-09-09 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2609.10397v1 Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is an essential component of software systems, allowing developers to detect and handle exceptional states that deviate from the expected program behavior. However, manually writing ERC across large codebases is tedious. We propose a novel task: retrofitting existing code with ERC. Namely, given code (without ERC) and Exceptional Behavior Tests (EBTs) (e.g., check if method throws InvalidArgumentException if null is given as the value to the argument) we aim to automatically generate missing ERC, such that the given tests pass. We design and implement Exception Coder (EXCODER) that performs context engineering to help Large Language Models (LLMs) tackle this task. EXCODER integrates static and dynamic program analysis with LLMs by providing the extracted contextual information to the LLMs. To evaluate EXCODER, we build a benchmark constructed from GitHub Java repositories, where we systematically remove ERC in 304 methods from 75 projects. Our results demonstrate that EXCODER provides an effective, though imperfect, solution to this problem in automated code generation, offering developers the first way to implement ERC following test-driven development. When combined with Qwen 2.5 Coder 32b, EXCODER achieves pass@1, 5, and 10 rates of 85.92% (12.56 percentage points over baseline), 86.18% (12.82 p.p. over baseline), and 86.51% (13.15 p.p. over baseline), respectively, on developer-written test suites. Our manual inspection of the generated code further reveals limitations of EXCODER, pointing to directions for future work. --- ### Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation Authors: Nada Esmaeil, Fathima Rena, Sibi Subhash, Osama Elgendy, Mina Naguib, Salma Omar, Muhammad Arif Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10395v1 This paper describes the Rosetta system for Subtask 1 (Context-Aware English-to-Dialectal Arabic Dialogue Translation) of the AlexandriaX shared task, participating in both constrained and unconstrained tracks. The approach fine-tunes a LoRA adapter on NileChat-3B using structured system/user prompts that condition generation on dialect and dialogue context. For the unconstrained track, the adapter is additionally pretrained on MADAR and PADIC. Rosetta ranked 4th in the constrained track (spBLEU 26.10) and 5th in the unconstrained track (spBLEU 25.09). The experimental results demonstrate that external pretraining helps only two of thirteen dialects while slightly hurting overall performance, suggesting negative transfer. --- ### Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition Authors: Rishabh Jain, Aristeidis Papadopoulos, Zhaofeng Lin, Naomi Harte Published: 2026-09-09 Categories: eess.AS, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2609.10394v1 Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the complexity of natural conversation, which involves overlapping speech, spontaneous turn-taking, unscripted vocabulary and variable acoustic conditions. To shift the field toward realistic dialogue, we introduce Candor-LR, a conversational benchmark derived from the CANDOR corpus of 1,656 natural dyadic videoconferences. Our custom data preparation pipeline yields 713.5, 10.1, and 60.1 hours of training, validation, and test data, respectively. Evaluating pretrained AVSR models on Candor-LR reveals that audio-only accuracy drops sharply compared to LRS3, but visual cues compensate effectively, driving much larger performance gains on Candor-LR than on LRS3. Furthermore, training on this corpus significantly improves cross-domain robustness under both clean and noisy conditions, as its realistic conversational data captures broader audio-video features. We open-source our pipeline to ensure reproducibility, establishing Candor-LR as a challenging benchmark for conversational AVSR. --- ### Enhanced Deformable Convolution with Center-invariant Offset and Edge-aware Mask Authors: Yixiao Li, Xiaoyuan Yang, Jin Jiang, Minghao Zou, Guanghui Yue, Baoquan Zhao, Jun Liu, Wei Zhou Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10387v2 Deformable convolution networks have recently become popular for many computer vision tasks, especially for semantic segmentation, because of their exceptional capabilities in dynamic spatial modeling. However, due to the dense deformable offsets and the lack of longer-range dependencies, they can not fully adopt proper and precise deformations for feature representations. To tackle the issues, in this paper, we propose Enhanced Deformable ConvNets (EDCN) for semantic segmentation. Specifically, a novel Enhanced Deformable Convolution (EDC) is exploited in the decoder, which integrates the Center-invariant Offset Module (COM) and Edge-aware Mask Module (EMM). The COM employs larger kernels and eliminates deformations at the kernel center, obtaining offsets that are more in line with the target from richer spatial information. Concurrently, the EMM obtains the significance of image content via Sobel edge detection, then selectively applies deformations based on the content significance, minimizing unnecessary deformations associated with relatively less important information, thereby avoiding impact from less informative regions. Experiments show that EDC outperforms state-of-the-art deformable convolution variants, including Deformable ConvNets V1-V4 and Entire Deformable ConvNets, across mainstream segmentation datasets with various decoder settings. Moreover, ablation studies confirm the effectiveness of each component. In addition, visualizations illustrate that EDC enhances spatial adaptation and target focus. We further analyze the extendibility of EDC to larger kernels on the image classification benchmark. Code will be publicly released. --- ### Enhanced Deformable Convolution with Center-invariant Offset and Edge-aware Mask Authors: Yixiao Li, Xiaoyuan Yang, Jin Jiang, Minghao Zou, Guanghui Yue, Baoquan Zhao, Jun Liu, Wei Zhou Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10387v1 Deformable convolution networks have recently become popular for many computer vision tasks, especially for semantic segmentation, because of their exceptional capabilities in dynamic spatial modeling. However, due to the dense deformable offsets and the lack of longer-range dependencies, they can not fully adopt proper and precise deformations for feature representations. To tackle the issues, in this paper, we propose Enhanced Deformable ConvNets (EDCN) for semantic segmentation. Specifically, a novel Enhanced Deformable Convolution (EDC) is exploited in the decoder, which integrates the Center-invariant Offset Module (COM) and Edge-aware Mask Module (EMM). The COM employs larger kernels and eliminates deformations at the kernel center, obtaining offsets that are more in line with the target from richer spatial information. Concurrently, the EMM obtains the significance of image content via Sobel edge detection, then selectively applies deformations based on the content significance, minimizing unnecessary deformations associated with relatively less important information, thereby avoiding impact from less informative regions. Experiments show that EDC outperforms state-of-the-art deformable convolution variants, including Deformable ConvNets V1-V4 and Entire Deformable ConvNets, across mainstream segmentation datasets with various decoder settings. Moreover, ablation studies confirm the effectiveness of each component. In addition, visualizations illustrate that EDC enhances spatial adaptation and target focus. We further analyze the extendibility of EDC to larger kernels on the image classification benchmark. Code will be publicly released. --- ### MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Production Authors: Shih-Yu Lai, Wen-Fan Wang, Sai Ling, Shaune Jan, Bing-Yu Chen, Xiang Anthony Chen Published: 2026-09-09 Categories: cs.HC, cs.AI, cs.GR, cs.MA arXiv: https://arxiv.org/abs/2609.10385v1 Animation and VFX pre-production review requires teams to translate loosely specified creative intent--briefs, evolving specifications, heterogeneous references, and verbal decisions--into revisions that junior artists can execute without repeated clarification. In practice, criteria drift across iterations, review judgments lose their evidential basis, and the reasoning behind a request rarely survives the senior-junior handoff. We contribute a design framework for intent-evidence-action alignment: intent is articulated into a shared project record, judgments are anchored to grounded evidence, and authorized decisions are converted into clear revision tasks tied directly to reference notes. We instantiate this framework in MOONWALK, a professional pre-production review system comprising a shared intent record, reference/specification anchoring, structured work-in-progress comparison, and supervisor-authorized action planning. In this workflow, AI handles administrative coordination--flagging missing context and organizing notes--while artists retain full creative direction. An in-studio study with professional practitioners compares MOONWALK with a chat-only (chatbot) interface using matched production materials, while participants' existing workflows provide a retrospective ecological baseline. Results indicate stronger intent alignment, decision traceability, and checklist executability, while also showing that aesthetic authority and final prioritization must remain with practitioners. The evaluation establishes the value of the integrated structured workflow over unstructured conversational AI chatbot. Code: https://github.com/Akinesia112/Moonwalk/tree/english-version --- ### Searching for New Physics with Reinforcement Learning Authors: Jacky Kumar, Marianne Bouchard, David London Published: 2026-09-09 Categories: hep-ph, cs.LG arXiv: https://arxiv.org/abs/2609.10382v1 Finding new physics (NP) is the most important problem in particle physics today. Studying ``anomalies'', i.e., measurements of low-energy observables whose values disagree with the predictions of the Standard Model (SM), is a powerful search strategy. The SM Effective Field Theory (SMEFT) provides a general model-independent framework for parameterizing NP; it is natural to try to find the SMEFT operator(s) that can explain such anomalies. This is a challenging task because (i) the number of SMEFT operators is enormous, and (ii) at loop level there are very complicated correlations among the operators. Analyses by humans typically rely on phenomenological intuition to decide which operators are relevant. This is often biased and does not explore the complete SMEFT operator space. Interestingly, reinforcement learning (RL) techniques excel at tasks that require decision making to achieve their goals. In this paper, we introduce an RL method that can be used to find the SMEFT operators that explain any anomalies. We test it on the CDF $W$-mass anomaly, and show that it reproduces (and improves upon) known results. We then consider a far more complicated situation with multiple anomalies and show that, even here, this method is able to find the SMEFT operators that explain the data. Our RL method can therefore be used to efficiently search for NP at the level of SMEFT. --- ### Data-Driven Risk Fields for Safer End-to-End Autonomous Driving Authors: Yuanxin Tian, Zhiyuan Liu, Jinhao Li, Liangfan Zhu, Shuai Wang, Heye Huang, Qingwen Meng, Fang Zhang, Liuzhu Tong, Zhenhua Xu, Wenhao Yu, Jianqiang Wang Published: 2026-09-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.10377v2 Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities. Existing rule-based risk models provide interpretable safety priors, yet their absolute risk scores depend on handcrafted functions, coefficients, and thresholds. Learning-based risk representations reduce part of this manual design, but their supervision often relies on occupancy-derived labels or heuristic cost values, which may not capture ego-conditioned planning risk. In this paper, we propose DRiF, a data-driven risk-field framework for safer end-to-end autonomous driving. DRiF learns a shared BEV feature with static map segmentation, dynamic risk prediction, and vehicle planning. For dynamic risk learning, DRiF converts rule-based safety priors into pairwise risk labels, and trains the risk field to preserve relative risk ordering instead of regressing handcrafted absolute scores. Experiments on Bench2Drive show that DRiF achieves competitive overall performance, with consistent improvements in driving score, success rate, and collision-related metrics. These results establish relative risk supervision as an effective way to connect explicit safety structure with end-to-end planning. The data and code will be publicly available. --- ### Data-Driven Risk Fields for Safer End-to-End Autonomous Driving Authors: Yuanxin Tian, Zhiyuan Liu, Jinhao Li, Zhenhua Xu, Wenhao Yu, Jianqiang Wang Published: 2026-09-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.10377v1 Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities. Existing rule-based risk models provide interpretable safety priors, yet their absolute risk scores depend on handcrafted functions, coefficients, and thresholds. Learning-based risk representations reduce part of this manual design, but their supervision often relies on occupancy-derived labels or heuristic cost values, which may not capture ego-conditioned planning risk. In this paper, we propose DRiF, a data-driven risk-field framework for safer end-to-end autonomous driving. DRiF learns a shared BEV feature with static map segmentation, dynamic risk prediction, and vehicle planning. For dynamic risk learning, DRiF converts rule-based safety priors into pairwise risk labels, and trains the risk field to preserve relative risk ordering instead of regressing handcrafted absolute scores. Experiments on Bench2Drive show that DRiF achieves competitive overall performance, with consistent improvements in driving score, success rate, and collision-related metrics. These results establish relative risk supervision as an effective way to connect explicit safety structure with end-to-end planning. The data and code will be publicly available. --- ### Shape-guided Gaussian Splatting for Sparse-View X-ray 3D Reconstruction Authors: Pranav Poudel, Florence Dell'Aniello Picard, Nairouz Shehata, Frédéric Lavoie, Herve Lombaert Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10376v1 Sparse-view X-ray 3D reconstruction is essential for reducing radiation exposure, but recovering a density field from a handful of X-ray projections is severely ill-posed. Recently, 3D Gaussian Splatting has achieved state-of-the-art performance in sparse-view reconstruction by representing the volume using explicit, optimized primitives, but it requires dozens of projected views. With fewer views, reconstruction quality degrades severely since the explicit primitives are optimized freely without any anatomical information. Anatomical structures, in contrast, share similar geometry and density across a population. Their variations are bounded within a limited range that statistical shape models can capture. This paper proposes a shape-guided Gaussian splatting framework for sparse-view X-ray 3D reconstructions. Our contribution lies in driving Gaussian positions toward anatomically valid configurations, alongside atlas-based density regularization. Our method ensures anatomically consistent reconstruction and improves PSNR by 2.83 dB over a state-of-the-art Gaussian splatting baseline with as few as 5 views. Code Available: https://github.com/polyshape-lab/ShapeGuidedGaussian --- ### PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving Authors: Lin Huang, Yujuan Tan, Weisheng Li, Lixiang Zeng, Kun Yang, Yongzong Wang, Suihan Xiao Published: 2026-09-09 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.10372v2 We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Response (PTFR) as a QoE objective and minimizes it under quality/cost constraints. Unlike prior work on cascaded routing, semantic caching, or adaptive retrieval, PACE jointly controls which answer source composes the response and what fills the waiting window. Deployed on a humanoid-robot sales service, it combines three mechanisms: a load-adaptive cascading router, a joint path-filler controller, and volatility-aware cache admission. On 75k CarQA requests, the cascade halves pure-LLM PTFR at P95 (0.29 vs 0.53s at c16). The adaptive controller reaches 0.41s P95, outperforming RAG by 2.4 times at high load with equal quality. The filler controller cuts calls by 94% with zero conflict. Volatility-aware admission reduces stale answers from 86% to 0%. A gating rule ensures the controller never worse than the baseline, with exposure bounded by one hold period. This is the first quantification of filler-answer conflict risk in deployed services. --- ### PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving Authors: Lin Huang, Yujuan Tan, Weisheng Li, Lixiang Zeng, Kun Yang, Suihan Xiao Published: 2026-09-09 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.10372v1 We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Response (PTFR) as a QoE objective and minimizes it under quality/cost constraints. Unlike prior work on cascaded routing, semantic caching, or adaptive retrieval, PACE jointly controls which answer source composes the response and what fills the waiting window. Deployed on a humanoid-robot sales service, it combines three mechanisms: a load-adaptive cascading router, a joint path-filler controller, and volatility-aware cache admission. On 75k CarQA requests, the cascade halves pure-LLM PTFR at P95 (0.29 vs 0.53s at c16). The adaptive controller reaches 0.41s P95, outperforming RAG by 2.4 times at high load with equal quality. The filler controller cuts calls by 94% with zero conflict. Volatility-aware admission reduces stale answers from 86% to 0%. A gating rule ensures the controller never worse than the baseline, with exposure bounded by one hold period. This is the first quantification of filler-answer conflict risk in deployed services. --- ### Beyond Weak Labels: Prompt-Guided Local Refinement for Weakly Supervised Water Segmentation in High-Resolution Multispectral Imagery Authors: Muhammad Farhan Humayun, Mohammad Imangholiloo, Afifah Shah, Tomi Westerlund, Jukka Heikkonen Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10371v1 High-resolution water mapping supports environmental monitoring and related applications, but accurate pixel-level labels are difficult and costly to produce. Official hydrographic vectors provide scalable weak supervision, but they contain artifacts like boundary noise, temporal mismatch, and omissions of small water structures. We propose a two-stage framework for weakly supervised water segmentation in high resolution multispectral imagery. Stage 1 learns initial masks from rasterized vector pseudo-labels, and Stage 2 converts these masks into structured component-wise prompts for localized refinement. On a manually corrected validation set, refinement improves SegFormer-B0 from 0.9509 to 0.9535 IoU and U-Net from 0.9408 to 0.9486 IoU, with corresponding F1 gains from 0.9749 to 0.9762 and 0.9695 to 0.9736. It leads to sharper shorelines, reduced boundary spillover, and better thin-structure delineation. The results indicate that prompt-guided refinement can improve pseudo-label-based water segmentation by targeting local errors that are poorly captured by global training supervision. --- ### AVSRBench: A Multi-Condition AVSR Benchmark Authors: Rishabh Jain, Naomi Harte Published: 2026-09-09 Categories: eess.AS, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2609.10366v1 While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true generalization or just domain adaptation. To investigate this gap, we evaluate three AVSR architectures across six conditions: controlled broadcast speech, fixed-grammar utterances, hyper-articulated Lombard speech, read speech from professional lipspeakers and non-professional speakers, and spontaneous multi-party video conversations. We find that visual-only performance deteriorates rapidly beyond broadcast domains, and audio-video fusion mainly benefits Lombard speech environments. Visual understanding degrades sharply at 90° profile views, with multimodal systems relying largely on acoustic fallback. Additionally, speaker articulation proves more critical than minor camera shifts, and LLM-based architectures suffer from poor out-of-domain generalization. Our work highlights a significant generalization gap in current AVSR research. To address this, we also introduce RoomReader-AV as a new benchmark for AVSR and release a unified data preprocessing pipeline to make comprehensive multi-condition evaluation accessible. --- ### OmniMed-FL: A Robust Multimodal Federated Learning Framework for Clinical Diagnosis Authors: Ayush Debnath, Ruelia Saha, Sudip Misra Published: 2026-09-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.10364v1 Simultaneous assessment of medical imaging and patient records is often required in clinical diagnosis. However, standard machine learning algorithms cannot analyze these data types together. Meanwhile, compliance with HIPAA and GDPR can constrain centralized aggregation of sensitive patient data. This leaves a crucial void of secure fusion of visual and textual context across distant networks. Thus, we present OmniMed-FL, a controlled systems study of multimodal federated learning for five-class clinical condition classification (Normal, Pneumonia, COVID-19, Pleural Effusion, Cardiomegaly). Our proxy corpus pairs 3,000 public chest radiographs with 3,000 class-conditioned synthetic notes, matched by class, not by patient. The framework benchmarks eight fusion strategies, three initializations, four missing-text imputation rules, and matched federated baselines under non-IID Dirichlet partitioning across 3 to 20 hospital clients. As all notes are synthetic and pairing is not patient-level, these are descriptive proxy comparisons, not estimates of diagnostic performance or deployment readiness. Within those limits with clients ($K=5$) and severe skew ($α=0.1$), local-only training achieves a macro-F1 score of 0.297, FedAvg achieves $0.662\pm0.074$, FedProx $0.737\pm0.085$, a matched FedMME-style one-shot ensemble $0.647\pm0.080$, and our SCAFFOLD-AdamW adaptation $0.070\pm0.015$, the 0.075 FedProx-FedAvg gap falling inside the wider of the two two-seed standard deviations. Over a $4\times3$ grid, label skew costs up to 0.27 F1 whereas a near-sevenfold client increase costs at most 0.10, while bidirectional volume grows linearly to 183.5 GiB at $K=20$. Multimodal fusion leads on both corpora, scoring 0.956 against 0.934 for text and 0.664 for images on the synthetic corpus and 0.906 against 0.880 and 0.737 on the radiograph corpus, for $2.3\times$ the model state of text alone. --- ### SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination Authors: Athanasios Tragakis, Marco Aversa, Daniela Ivanova, Chaitanya Kaul, Roderick Murray-Smith, Daniele Faccio, Paul Henderson Published: 2026-09-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.10363v1 SceneHI is a framework that lifts high-resolution, illumination-aware priors from 2D diffusion models to perform 3D texture synthesis. It is the first to demonstrate that high-resolution textures, previously limited to 2D synthesis, can be generated directly on 3D objects without model fine-tuning or optimization. Designed for complex, multi-object environments, SceneHI uniquely combines 3D-consistency, high-resolution fidelity, and physically plausible baked shadows within a single generative pipeline. To enforce strict geometric coherence, we introduce an exact analytical pixel-to-texel mapping that aligns diffusion trajectories across multiple viewpoints. We utilize High-Resolution Latent Textures (HRLTs) as a persistent canvas for gradually denoised textures, while camera views perform the denoising steps in latent pixel space. This ensures a shared base texture that can be subsequently refined to high resolution without compromising multi-view consistency. Finally, a light-aware generative pass embeds realistic geometry-consistent shadows directly into the atlases, bridging the gap to production workflows. SceneHI achieves high visual fidelity while reducing generation time by 80% compared to existing scene-level methods. --- ### A Later Test Set Is Not a New Domain: Pretraining Familiarity Survives a Contamination-Free Hold-Out Authors: Mahdi Naser Moghadasi, Faezeh Ghaderi Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10357v1 Time-series foundation models are evaluated almost exclusively on public archives that predate them, so a strong score cannot be separated from having seen the test set during pretraining. The obvious remedy is a hold-out that postdates the models. We build one: thirteen forecasters -- four classical, three trained per dataset, six pretrained -- on seven groups drawn from five domains, every observation published after the last model was released, and every dataset rebuildable without an API key. Under this protocol pretrained models win 5 of 7 groups, lose one to a Theta baseline, and on daily exchange rates are indistinguishable from a seasonal naive forecast, along with every other method tested. We then ask what separates the wins from the losses, and report a negative result: the two intrinsic properties one would reach for -- seasonal strength and spectral entropy, measured on the input window -- do not account for the pattern, and seasonal strength is if anything negatively associated with the advantage. What does track it is corpus familiarity. Our largest gain (28% lower MASE than the best classical method, on weekly Wikipedia pageviews) falls on Wikipedia pageviews, the domain TimesFM's authors describe as the bulk of its pretraining corpus, at the same granularities and differing only in time window. Within the pretrained family, where every model forecasts identical series so that series difficulty cancels, the TimesFM family outranks the Chronos family by -0.53 ranks on Wikipedia against -0.09 everywhere else (1,500 vs. 754 series, Mann-Whitney p < 1e-5). We conclude that a temporal hold-out removes memorisation of a window but not familiarity with a domain, that benchmarks therefore need domain hold-outs stated relative to disclosed corpora, and that the practitioner's question is less which model is better than whether their domain is one the model was raised on. --- ### Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changes Authors: Benedetta Liberatori, Nermin Samet, Paolo Rota, Matthieu Cord, Elisa Ricci, Andrei Bursuc, Monika Wysoczańska Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10356v1 Long-term change understanding from images of the same place revisited over time is a challenging task with applications in map maintenance and urban infrastructure monitoring. Prior work addresses it either through pixel-level prediction or difference captioning, neither of which is sufficient to reliably measure how well models detect and describe such changes. We introduce SPOT-THE-SHIFT, a human-verified benchmark for grounded image difference captioning of long-term changes in real-world driving scenes. Our benchmark provides natural language captions and spatial masks for structural changes across each image pair. We further propose an evaluation protocol that reliably assesses models' captioning ability, validated through human studies. Benchmarking state-of-the-art MLLMs, we find that models struggle with the fine-grained multi-image spatial capability required for this task. Finally, we develop a synthetic data generation pipeline that improves an off-the-shelf MLLM without sacrificing general capabilities. --- ### Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs Authors: Killian Steunou, Yannis Tevissen, Mounîm A. El Yacoubi Published: 2026-09-09 Categories: cs.CV, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2609.10355v1 Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained large language models and condition generation on a textual prompt. Their strong performance on captioning, question answering, retrieval and temporal grounding comes at a computation and memory cost that grows with frame count and context length, limiting deployment in real-time, mobile and resource-constrained settings. This survey covers inference-efficiency mechanisms for visual and audiovisual VideoLLMs that report concrete reductions in parameter count, FLOPs per input, latency, memory, or visual and audio token count. We analyze bottlenecks across frame sampling, modality encoding, connector-level token reduction, and LLM prefilling and decoding. We organize methods by the pipeline stage at which they act, covering VideoLLMs developed since late 2022 together with earlier frame-sampling and vision-encoder mechanisms that remain components of current pipelines. We assemble literature-reported accuracy--cost comparisons under shared host models and input protocols wherever available, distinguish them from heterogeneous cross-paper evidence, and identify gaps in audiovisual efficiency and standardized evaluation. We maintain a repository at https://github.com/momentslab/awesome-efficient-videollm. --- ### Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking System Authors: Alex Leytes Published: 2026-09-09 Categories: cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2609.10350v1 The banking system now depends on a small set of shared artificial intelligence vendors for fraud screening, credit decisioning, anti-money-laundering triage, customer analytics, and internal decision support. This paper studies how a compromise inside one of those vendors can propagate along a chain of operational, informational, and financial linkages until it triggers losses that look, from the outside, like a classical banking crisis. We build a four-layer heterogeneous network that couples AI vendors, financial institutions, interbank exposures, and customer accounts, and we propose CFC-Prop, a stochastic epidemic-and-clearing model that runs on that network. On a synthetic dataset with 60 vendors, 220 banks, roughly 2,500 vendor-bank service edges, and 1,400 interbank exposures, CFC-Prop reproduces the heavy-tailed loss distributions and the sharp dependence on patch latency that are consistent with prior cyber-financial evidence. We also train an early-warning model, CFC-GNN, that uses vendor-side incident telemetry and graph structure to flag high-cascade-risk vendors before impact. Across four baselines the proposed model reaches AUROC 0.82 and AUPRC 0.60 while keeping calibration errors bounded. We release the full code, synthetic data, and reproducible scripts. The results argue that cyber concentration among AI vendors is a first-order financial-stability problem and give supervisors a concrete quantitative tool for reasoning about it. --- ### Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs Authors: Haiji Liang, Pengfei Zhou, Zhenglin Wan, Wei Wang, Yang You, Wangbo Zhao Published: 2026-09-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.10346v1 Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existing vision token pruning methods mitigate this overhead, they implicitly assume that a single fixed pruning strategy can be applied uniformly across all inputs. Our analysis further reveals that ranking pruning methods by average benchmark accuracy conceals substantial sample-wise complementarity: although the average-best strategy excels overall, alternative strategies prove superior on a significant fraction of individual samples. To harness this diversity, we propose VIP-Router, a lightweight VIsion Pruning Router that adaptively selects the pruning strategy predicted to be best suited to each input at a specified pruning level. Conditioned on low-cost visual and textual features, VIP-Router identifies the most suitable candidate strategy while retaining full-token inference as an option when pruning is predicted to be unfavorable. Evaluated on a curated suite of pruning-sensitive visual perception benchmarks, VTC-Bench Group A, VIP-Router consistently outperforms the best fixed strategy baseline across all reduction ratios, achieving a 26.9% relative improvement in average accuracy, and a 22.0% relative increase in average utility after accounting for realized token cost. Crucially, VIP-Router operates in a plug-and-play manner without modifying underlying pruning algorithms or model weights, introducing trainable parameters equivalent to merely 0.017\% of the backbone. Furthermore, VIP-Router proves effective across various MLLM backbones and yields consistent gains on unseen benchmarks, highlighting the potential of sample adaptive routing for visual token pruning. --- ### TimeCues Studio: A Workspace for Music Annotation and Algorithm Prototyping Authors: Sapir Caduri, Yoav Goldberg Published: 2026-09-09 Categories: cs.SD, cs.HC, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2609.10338v1 Multimedia applications require precise music annotation-labeled positions, segments, or loops-placed by hand or algorithmically. Machine-learning algorithms are scalable and effective but need annotated training data, scarce for many tasks. TimeCues Studio is an open-source workspace where algorithm-development teams annotate a music corpus, compare detection algorithms against those annotations, and prototype new ones. Unlike existing tools built for a single track at a time, TimeCues targets teams annotating whole collections, tightly integrated with algorithm development. Annotators place several marker types-each supporting ambiguity-aware labeling-on a grid-locked timeline that visualizes many music features, including separated audio stems. The same timeline drives an algorithm-comparison engine with bundled baselines, a Python sandbox for prototyping new models, and an ambiguity-aware evaluator that honors the structured fields. The same visualization suits solo annotators on music-sync projects. TimeCues is MIT-licensed and deploys via one Docker Compose command. --- ### From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning Authors: Weichen Dai, Rafael Medeiros Cabral, Ziyi Shou, Yan Cao, Xin Shen, Dongcai Lu, Yi Zhou Published: 2026-09-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.10335v1 Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are often computationally intensive and opaque. We demonstrate that a pure Large Language Model (LLM), when equipped with specialized modules, can rival state-of-the-art LMMs on complex geometry problems. Our framework integrates a Geometric Vision Parser, which translates diagrams into symbolic form, with a Symbolic Solver that performs formal deductions, thereby mitigating hallucinations and promoting interpretable reasoning. To enable rigorous evaluation, we curate a benchmark of challenging problems from the 2025 Chinese Zhongkao examinations, ensuring data novelty and testing deeper deductive skills. Experiments demonstrate that our approach achieves performance comparable to Gemini 2.5 Pro while delivering clearer, human-like solutions. --- ### Dimensionality Reduction for Hyperspectral Image Classification Authors: Mohamed Cherifi, Ammar Mesloub, Mohammed Nabil El Korso, Tayeb Touhami, Abdennour Hacine Gharbi Published: 2026-09-09 Categories: cs.CV, eess.SP arXiv: https://arxiv.org/abs/2609.10334v1 This paper addresses the issue of supervised classification in the context of hyperspectral satellite images. It deals with two fundamental aspects: dimensionality reduction of data and the selection of appropriate supervised classification techniques. Firstly, we delve into dimensionality reduction, a critical step in simplifying the management of hyperspectral data. The reduction aims to decrease complexity in terms of memory and computing time. We examine two commonly used methods: Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). Subsequently, we explore the selection of the most suitable supervised classification algorithms for hyperspectral images. We compare the performance of three methods: K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Random Forest (RF) using real hyperspectral data. The results highlight that the combination of PCA and RF yields the highest overall accuracy and Kappa coefficient. --- ### Learning to Adapt and Calibrate: Score Distribution Alignment for Few-Shot Uncertainty Prediction in Medical VLMs Authors: Xuan Cuong Ngo, Ngan Le Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10333v1 Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-free coverage guarantees. However, standard conformal prediction relies on exchangeability between calibration and test data and typically requires a sufficiently large calibration set to obtain reliable coverage. These assumptions are difficult to satisfy in few-shot transfer settings, where only a small labeled support set is available to adapt a pretrained VLM to a new medical task, while an unlabeled query set is used for evaluation. Supervised fine-tuning on the support set changes the model parameters and consequently shifts the nonconformity score distribution, breaking exchangeability between calibration and query samples and leading to unreliable coverage under distribution shift. Existing transductive conformal adaptation methods often preserve validity by avoiding supervised updates. While this helps maintain conformal assumptions, it underutilizes the scarce labeled support data and limits task adaptation, which is the primary objective in few-shot learning. In this setting, conformal prediction should serve as an uncertainty estimation layer that supports the adapted model, rather than preventing adaptation itself. To this end, we propose AlignCP, a framework that reconciles supervised few-shot adaptation with conformal uncertainty estimation under non-exchangeability. AlignCP learns a reweighted calibration distribution that reduces the score-level discrepancy between the labeled support set and the unlabeled query set. By aligning the one-dimensional nonconformity score distributions, AlignCP aims to close the coverage gap induced by adaptation without requiring query labels. --- ### Geometry Without Coordinates: LiDAR Diffusion as a 3D Feature Bridge Authors: Samed Doğan, Nico Leuze, Alfred Schöttl Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10322v1 Transferring the rich priors of large 2D foundation models to sparse 3D LiDAR remains challenging, as training native 3D foundation models at comparable scale is limited by data and annotation scarcity. We introduce a LiDAR-conditioned diffusion model trained on pseudo-labels from off-the-shelf 2D foundation models. The model supports multiple output modalities, including depth, semantic segmentation and instance prediction, selectable via a textual task prompt. Because the model is conditioned on LiDAR, both its outputs and its intermediate UNet features can be projected back onto the input point cloud, enabling analysis of a 3D representation learned entirely under 2D supervision. We study this representation directly in point-cloud space, explicitly excluding raw spatial coordinates to isolate feature content from projection geometry. Linear probes recover up to ~23% Mean Intersection over Union (MIoU) on 3D semantic classes, compared to ~3.5% for a matched Gaussian-noise control, indicating substantial non-trivial structure. Pairwise cosine similarity across modality-specific feature streams reveals a layered organization. Early encoder layers remain weakly aligned across modalities while individually decodable, intermediate layers converge toward a shared representation, and decoder layers re-specialize toward task-specific outputs. These findings indicate that LiDAR-conditioned diffusion models can induce structured 3D representations from 2D supervision alone, with a modality-dependent manifold that locally unifies near a shared bottleneck. This positions diffusion as a viable mechanism for transferring large-scale 2D priors into sparse 3D domains. --- ### On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data Authors: Hongyuan Zhang, Xianda Guo, Yanlun Peng, Qianlong Yang, Yubin Guo, Pinhan Fu, Mulin Chen, Xiaozhen Qiao, Ping Luo Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10321v1 Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in current vision-language distillation methods is typically constructed from the teacher prediction and applied uniformly to all training samples, making it unreliable under class and domain shifts. In this paper, we argue that distillation target construction should be treated as a dynamic training decision rather than a fixed recipe. To this end, we propose OnPoKD, an on-policy distillation framework for vision-language model adaptation. To the best of our knowledge, OnPoKD is the first framework that applies on-policy distillation to vision-language model adaptation by learning target construction as a policy decision. OnPoKD learns a lightweight controller that constructs sample-wise adaptive targets using reliability and disagreement cues from the teacher model, student model, and zero-shot prior. Instead of relying on a fixed teacher prediction, the controller dynamically balances teacher supervision, zero-shot prior guidance, and hard-label anchoring through bounded policy actions, allowing the distillation target to adapt to varying sample reliability and training stages. The policy controller is updated with validation feedback, encouraging target construction to optimize transferability rather than merely fitting the training distribution. Since the controller is only used during training, OnPoKD can be seamlessly integrated into existing vision-language distillation pipelines while preserving the original inference architecture and test-time cost. Extensive experiments on Base-to-novel generalization and Cross-dataset transfer benchmarks show that OnPoKD consistently improves over strong vision-language distillation baselines. --- ### Decoupled Self-Forcing Distillation for Streaming Talking Head Generation Authors: Yanru An, Ruiyan Wang, Wenwu Wei, Rui Bu, Qi Wang, Hongwei Hu, Zhengxue Cheng, Rong Xie, Li Song, Wenjun Zhang Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10317v1 Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite directions: end-to-end methods condition a video diffusion model on audio directly and achieve high quality but only at large scale, while cheaper two-stage methods generate an intermediate motion representation and trail in fidelity. We argue the cost of the former lies in the target of fusion: the video latent is dominated by identity, appearance and background, none of which audio bears on, so coupling audio to every pixel blurs detail and wastes capacity. We instead fuse conditions in a low-dimensional identity-disentangled motion space, routing audio and motion captions by their temporal granularity, and generate motion latents with a small causal autoregressive transformer that a pretrained diffusion renderer turns into video. Conditions thus control video transitively, and high fidelity no longer requires a large backbone. Streaming this decomposition needs both models to be causal, and the exposure-bias problem could be solved by self-forcing given a bidirectional teacher. But there is no such teacher in motion space. Our decoupled self-forcing distillation resolves both models under one frozen teacher: conditioned on motion, it distills the renderer into a block-causal student; unconditionally, it scores rendered rollouts against real videos, supervising motion by the video it produces. This lifts the fidelity ceiling from the motion generator onto the stronger renderer. The two models run as parallel causal streams, reaching 15.4 FPS at 1.3 s latency with no quality degradation. --- ### TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards Authors: Rui Sun, Zhan Shi, Bing He Published: 2026-09-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.10315v1 Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective answers are inexpensive to check. Diagnostic reasoning over complex data lacks this advantage: establishing the true cause of an anomaly often requires costly expert investigation and may remain ambiguous after the fact. We ask whether this asymmetry of verification can instead be engineered. We sample an intervention, inject it into a controlled simulator, and generate the observations it would produce. The hidden intervention provides an oracle label and objective reward, while the agent must still investigate noisy, confounded, and distributed evidence. We instantiate this approach in TRACE, a digital-advertising diagnostic environment with 12 root causes and fine-grained segment attribution. Agents investigate each episode using Python and SQL and must identify both the root cause and, when applicable, the affected segment assignment. On a held-out 235-episode test set, the strongest prompted baseline, Claude Opus 5, reaches 0.686 FullAttr@1. Supervised fine-tuning raises Qwen3.5-35B-A3B from 0.159 to 0.637, and subsequent RL with synthesized rewards reaches 0.757, outperforming all evaluated prompted baselines, including frontier closed-source models and a prompted Qwen3.5-122B-A10B model. The resulting policy also uses substantially fewer tool calls than the prompted 35B base. These results provide evidence that access to a scalable, objective training signal can be a more important constraint than model scale alone. More broadly, simulation-based verification can make otherwise ambiguous diagnostic reasoning tasks amenable to scalable reinforcement learning. --- ### Semiparametric Inference for Conditional Shapley Feature Importance Authors: Agostino Gnasso Published: 2026-09-09 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.10313v3 Shapley values are widely used for post-hoc feature attribution, but most estimators return point quantities and do not quantify uncertainty, and popular implementations sample out-of-coalition features from their marginal distribution, which misattributes importance when features are dependent. This paper studies the conditional formulation, in which out-of-coalition features are integrated out under their true conditional distribution. The target is a global, loss-based importance that pairs a conditional value function with a SAGE-style loss aggregation. We propose a one-step estimator with K-fold cross-fitting and a U-statistic correction of the squared loss that removes the Monte Carlo bias of the naive plug-in; it is $\sqrt{n}$-consistent and asymptotically normal under double-robust rate conditions, and the resulting Wald interval attains nominal coverage. A Pinsker-type bound quantifies the bias from misspecifying the working copula class, while vine copulas keep conditional sampling tractable. In a Gaussian design study with n= 500, the empirical coverage of the 95% interval lies between 0.91 and 0.96 across all features, the test holds its Type-I rate at 0.05, and it reaches power one for moderate signals. Applied to the UCI Concrete and California Housing data, the method identifies the conditionally informative features with Bonferroni-controlled significance. ---