# Research Papers — 2026-09 · bundle page 102 of 266 > Full-text markdown of papers #5051–5100 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/102 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/101.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/103.md) ### XLOG: A CUDA-Native Engine for Neurosymbolic Integration Authors: Levi Dubrovin, Nikita Pospelov, Kirill Sabitov Published: 2026-09-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.27203v1 xlog is a CUDA-native logic programming engine integrating neural perception with deterministic Datalog, probabilistic inference, and epistemic world views through a typed frontend and provider-owned CUDA runtime. Its reasoning modes share device data planes, but their execution boundaries differ: ordinary Datalog and exact inference are host-orchestrated, while certified resident recursive and Monte Carlo sampled cores record zero tracked host-device transfers before a bounded terminal receipt. The probabilistic path supports end-to-end gradients through GPU knowledge compilation from provenance to CNF to Decision-DNNF, exact weighted model counting, and backward gradients. A final smoothed circuit is certified against its source formula before caching or evaluation. Circuit caching yields a 2.74x MNIST-addition training speedup; a worst-case-optimal join subsystem yields a 27.96x geometric-mean gain over xlog's binary-join baseline. MNIST-addition accuracy matches Scallop's (0.9561 versus 0.9468), but no per-epoch speed claim is made because baseline epoch time varies with CPU quota. In five hub-skewed triangle-counting cases, the Souffle-to-fused-xlog execution-time ratio rises from 0.88x at 150k edges, where Souffle is faster, to 5.54x at 1.2M; fused peak device allocations are 85-1,033 MB versus 3,287-44,979 MB for the materializing arm. Exact inference is correctness-equivalent to but slower than ProbLog2. On a public video benchmark, a proximity predicate trained only through symbolic credit replaces hand-set geometry at unchanged held-out accuracy; within Event-Calculus rule search it fails ten-fold cross-validation and does not transfer on a leak-free split. On a maritime corpus, weighted clauses beat crisp selection by 0.065 F1, with the result reproduced by one chronological training pass. --- ### Reliable Federated TinyML Deployment for IoT Security Authors: Younsoo Park, Seokhyoen Bae, Shasi Kumar Ramachandran Prabhu, Suman Saha, Peilong Li Published: 2026-09-23 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.27202v1 The growing deployment of Internet of Things (IoT) devices has increased the need for privacy-preserving intrusion detection systems that operate directly on resource-constrained hardware. Federated Learning enables collaborative model training without sharing raw data, but conventional federated models are often too large and unstable for deployment on microcontroller-class devices. TinyML techniques enable compact neural networks but are typically designed for inference-only workloads. This work investigates combining Federated Learning with TinyML-based model compression for intrusion detection in IoT environments. We evaluate compression strategies including knowledge distillation, structured pruning, and quantization within a federated training pipeline. Preliminary results show that training stability plays a critical role in federated TinyML systems. In particular, server-coordinated cosine learning-rate scheduling improves Attack Recall from 46.7% to 93.85% while enabling substantial model compression and efficient edge deployment. These findings provide insights for designing lightweight and privacy preserving intrusion detection systems for IoT devices. --- ### A Systematic Benchmark of Explainable Methods for Temporal Attribution in Sequential Recommendation Systems Authors: Akash Pandey, Kanisha Shah, Addrish Roy, Dwipam Katariya, Hongyangyang Shi, Amanda Ding, Kalanand Mishra, Pranab Mohanty Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27201v1 Sequential RecSys are central to modern personalization, exploiting user's historical interaction sequences to drive next-step decisions. Deep learning models, particularly CNN and Transformer-based architectures, have proven highly effective at capturing temporal dependencies in these histories. For transparency and trust, understanding which past interactions drive a given recommendation is increasingly important --- both for developers auditing model behavior and for users seeking a rationale. However, the non-linearities that give these models their predictive power also render them black boxes, making it difficult to attribute decisions to specific interactions. While gradient-based, perturbation-based, and attention-based explainability methods exist, a systematic benchmark of their faithfulness for sequential recommendation is missing. We address this gap by introducing a dual-model masking metric in which one model supplies per-timestep attribution scores and a separately trained, masking-robust probe measures the resulting change in predicted probability. Using this metric, we benchmark ten XAI methods across CNN, Transformer, SASRec, and BERT4Rec backbones on KuaiRand and MovieLens, complemented by analyses of temporal attribution patterns, item popularity confounding, and robustness to input corruption. Our key findings are: (1) gradient-based methods, particularly GradientSHAP and Integrated Gradients, yield the most faithful and robust attributions; (2) raw attention weights are unreliable, but gradient-weighted attention restores faithfulness on shorter sequences, with degradation on longer horizons as softmax attention probabilities converge toward uniform importance scores, diminishing the method's ability to identify informative interactions; and (3) temporal attribution patterns in faithful methods reflect genuine task structure rather than recency or popularity bias. --- ### ZO-COSMO: Index-Free One-Hop Mixing for Decentralized Zeroth-Order Optimization Authors: Shengjun Zhang, Tingyi Liu, Heng Zhang, Dong Xie Published: 2026-09-23 Categories: cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2609.27199v1 Sparse communication in decentralized zeroth-order learning requires compatible peer-state coordinates. We characterize this one-hop condition and develop \textsf{ZO-COSMO}, coupling two-query estimation with average-preserving masked consensus using $q$ values per active link. Global supports serve all-neighbor mixing; matching updates require agreement only within each pair. We derive a sharp contraction-per-scalar bound within the matching class and convergence guarantees for the core and sparse-momentum updates. At fixed matching, exact moment identities characterize how shared directions preserve gradient-heterogeneity cancellation and redistribute estimation error and disagreement. Mechanism experiments cover unequal curvatures, noise, and sparse momentum. Further tests span $64$ synthetic agents and eight logical Qwen LoRA workers. At matched payload budgets, Qwen2-7B QNLI gains $3.65$ accuracy points over explicit-index Rand-$k$; edge-local updates gain $3.42$ and $2.53$ points over all-neighbor mixing on eight-worker complete and ring graphs. A matched-first-step ablation gives a $3.92$-point momentum benefit. Seed-aware and same-matching controls distinguish encoding, scheduling, and query correlation. --- ### Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training Authors: Hung Phan, Waqwoya Abebe, Youssef Hussein, Supriya Chinthavali, Dalton Lunga, Ali Jannesari Published: 2026-09-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.27197v1 Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on token- level maximum-likelihood objectives Shen et al. (2016). Although introduced a decade ago, recent work shows renewed potential for risk-based optimization in modern language models Yang et al. (2024), Jinnai et al. (2025). We apply MRT to power outage report generation for the Outage Data Initiative Nationwide (ODIN), transforming heterogeneous reports into standardized XML compliant with CIM IEC 61968-3. Our MRT approach improves Qwen2.5-7B-Instruct overall accuracy from 16.20% to 68.95%, demonstrating the effectiveness of sequence- level optimization for domain-specific structured generation --- ### Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders Authors: Vsevolod Kovalev, Pranay Manocha Published: 2026-09-23 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2609.27195v1 Non-speech interference can change a speech representation without causing comparable task loss. We test eight frozen encoders on four tasks, adding non-speech sounds throughout recordings, during speech, or in pauses. Under whole-recording interference, embedding drift tracks task loss across seven sounds, with mean Spearman correlations of 0.81-0.88. Moving the same sound between speech and pauses changes this pattern. At quiet to moderate levels, pause interference produces larger drift, while speech interference usually causes greater loss on intent recognition, speaker verification and speech recognition. Emotion recognition shows a weaker placement effect. Pause interference also changes speech-frame representations beyond the injected region. Even below the estimated recording background, interference can change embeddings as much as repeated speech takes do. Drift helps rank the effects of different sounds, but larger drift does not consistently indicate greater task loss. --- ### Diverse by Design: Architectural Constraints for Prototype-Based Interpretability Authors: Xinmiao Lin, Matthew Wright Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27194v1 Prototype-based neural networks provide inherent interpretability through case-based reasoning, yet suffer from critical limitations: prototypes converge to redundant features, fail to capture diverse semantic parts, and lack quantitative interpretability assessment. We propose Diversity-Aware Prototype Learning (DAPL), which enforces prototype diversity through architectural constraints rather than explicit regularization. Our approach leverages multi-head self-attention with strict one-to-one attention-to-prototype mapping, ensuring each prototype specializes in distinct visual features. We further introduce foreground-aware training to focus prototypes on semantically meaningful regions and develop comprehensive evaluation metrics (Coverage and Diversity) for quantitative interpretability assessment. Experiments on CUB-200-2011 demonstrate substantial improvements: DAPL with foreground-aware training achieves 81.69\% accuracy with 0.596 Coverage and 0.427 Diversity, providing the best overall balance across all evaluated prototype-based methods. Code is available at https://github.com/xinmiaolin/DAPL. --- ### Data-driven discrete-time deep recurrent neural network-based modeling for dissipative systems Authors: Tuan Luong, Hyungpil Moon Published: 2026-09-23 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.27186v1 Physical AI has gained increasing attention for its role in developing AI systems that better understand, predict, and control real-world dynamics. Achieving this requires AI models that not only achieve high prediction accuracy but also preserve fundamental physical properties of dynamical systems. In this paper, we propose a deep discrete-time dissipative recurrent neural network (DissipNet) that explicitly enforces dissipativity, a key property related to stability and energy dissipation, through structural weight constraints and a dedicated training algorithm. By construction, the proposed network is capable of learning dissipative dynamics while preserving their inherent stability, which is formally analyzed using Lyapunov theory. In contrast to Physics-Informed Neural Networks (PINNs), which incorporate governing equations into the training loss but do not guarantee preservation of internal analytical properties such as dissipativity or passivity, our approach provides explicit guarantees on stability at the model level. We demonstrate the effectiveness of the proposed method through several modeling applications, and compare its performance with a naive recurrent neural network (RNN) and a PINN-based model. --- ### Artificial intelligence surrogates for treatment effect estimation with before-and-after data Authors: Frances Dean, Anna Neufeld, Joshua Barrios, Geoffrey H Tison, Ahmed Alaa Published: 2026-09-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.27180v1 Estimating the causal effects of medical treatments is difficult when clinically important outcomes are costly to measure or require long follow-up. Short-term or inexpensive surrogate outcomes offer a potential alternative, but surrogate biomarkers may be unavailable or difficult to identify. Advances in artificial intelligence (AI) have enabled increasingly accurate prediction of clinical outcomes from inexpensive, high-dimensional measurements, which creates an opportunity to use AI predictions themselves as surrogates. To this end, we develop a framework for estimating treatment effects from paired measurements obtained before and after treatment for each treated individual. A pretrained AI model is applied to the before and after measurements, and our estimator compares the resulting outcome predictions. We characterize the technical assumptions under which this within-person contrast identifies the average treatment effect on the treated, even when clinical outcomes are never observed for treated individuals. When these assumptions cannot be justified, we use prediction-powered inference to correct bias using a small number of observed clinical outcomes and obtain valid inference. Synthetic and real-world cardio-oncology experiments demonstrate the validity and accuracy of the approach. --- ### Change detection with conformal martingales: new optimal constructions, and suboptimality of existing methods Authors: Swapnaneel Bhattacharyya, Aaditya Ramdas Published: 2026-09-23 Categories: math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.27179v1 We study distribution-free sequential changepoint detection for independent observations with unknown and unrestricted pre- and post-change laws. We build on the conformal test martingales and associated e-detectors of Vovk(2021), which control the probability of false alarm (PFA) and the average run length (ARL) respectively. The majority of these works focus on validity, with statistical efficiency usually left for simulations. We develop a comprehensive theory of how conformal p-values behave under non-exchangeable data with a changepoint at an unknown time $T$. We use this to analyze the post-change growth and resulting detection delay of conformal martingale methods, and prove that the standard existing methods are suboptimal for PFA and ARL control, and can lead to delays that are $Ω(T)$ and $Ω(\sqrt{\text{ARL}})$ respectively. We propose different conformal e-processes and e-detectors that are provably minimax optimal, with delays $Θ(\log T)$ and $Θ(\log \text{ARL})$ respectively, and have much shorter delays in simulations. --- ### LeakScale: Estimating the Causal Effect of Benchmark Exposure Authors: Divyansh Singh Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.27176v2 Evidence that evaluation material entered training does not reveal how much it affected evaluation. This distinction leaves a contaminated benchmark score difficult to interpret: provenance can establish contact, but only a counterfactual can quantify the performance attributable to that contact. We present LeakScale, an interventional framework for estimating this missing quantity. LeakScale creates fresh executable tasks that require private, family-specific information absent from and non-derivable from the public task, controls access to that information, and estimates the resulting control-adjusted change in executable accuracy. Across 2,048 unique families, two model families, two executable domains, and 262,144 generations, exposure improves accuracy in every model-by-domain combination, with gains ranging from +7.17 to +27.31 percentage points. These findings separate two empirical questions that are often conflated: whether benchmark contact occurred and how strongly a reported score depends on it. LeakScale makes the latter directly measurable. --- ### Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences Authors: Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Hoang-Loc Cao, Phuc Ho, Truong Thinh Nguyen, Van Pham, Hung Cao Published: 2026-09-23 Categories: cs.MM, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.27175v1 Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems often lack explicit mechanisms for revising intermediate reasoning or preventing harmful knowledge transfer. We present SEMV (Self-Evolving Multimedia Verification), a self-evolving multi-agent framework that treats provenance-bearing arguments as the interface between evidence, reasoning, human contestation, and memory. SEMV combines arena-based quantitative bipolar argumentation (A-QBAF), causal and scoped revision, and verification-gated memory consolidation with explicit conflict retention. On COSMOS benchmark, SEMV achieves 91.88% accuracy versus 89.10% for the strongest comparable baseline. Verified memory reduces negative transfer from 5.7% to 0.2%. On CTR benchmark, constructed from reviewer contestations, scoped causal revision corrects 96.7% of initial errors while saving 52.8% compute. MV2026 Grand Challenge dataset further supports evidence-grounded, temporally consistent reporting. These results show that SEMV can evolve through verified experience while keeping accumulated knowledge and subsequent decisions traceable, revisable, and contestable. --- ### Realize What Matters: Principled Context Representation for Large-Scale Reasoning Authors: Michael Theologitis, Dean Light, Shuyue Stella Li, Benjamin Newman, Yulia Tsvetkov, Dan Suciu Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.27173v1 Solving complex tasks in domains such as science, medicine, law, and finance often requires assembling interdependent information scattered across vast, heterogeneous sources far beyond model context limits. Existing approaches tackle this challenge by organizing information into more manageable representations over which models can reason, such as graphs, textual memories, and retrieval collections. These representations dictate what downstream reasoning is possible and, ultimately, whether it succeeds; yet their design and construction remain largely ad hoc. In this work, drawing on the cognitive theory of relevance realization, we propose concrete principles for designing AI systems that construct effective representations of very large contexts. We analyze existing approaches and show how their successes and failures map onto their alignment with these principles, and introduce R3Con, a harness designed to operationalize the principles more systematically. We evaluate R3Con against nine state-of-the-art baselines on two recent benchmarks of reasoning over large document corpora. On these benchmarks, R3Con substantially outperforms the strongest baseline, by $20$ and $8.4$ percentage points. It also enables smaller models to outperform much larger ones: R3Con with 4B and 9B models outperforms all evaluated 35B baselines, while R3Con with a 35B-A3B model outperforms Claude Code with Claude-Sonnet-5 at $3.7\times$ lower cost. Our results show that context representations following our principled approach can reduce reliance on model scale, pointing toward a future of AI systems with frontier-level performance powered by smaller models. Our code is available at https://github.com/michaeltheologitis/r3con --- ### Meta-learning accelerates detector design optimization Authors: Maxim Borisyak, Nikita Gladin, Andrey Ustyuzhanin Published: 2026-09-22 Categories: physics.ins-det, cs.LG arXiv: https://arxiv.org/abs/2609.35827v1 The quality of a detector design is ultimately determined by the quality of the inference it enables, that is, by the accuracy with which the quantities of interest are reconstructed from the raw detector response. For complex detectors, the inference is performed by machine learning models, and the relation between the design and the attainable inference performance is, in general, non-trivial. In this work, we consider the optimization of the inference performance with respect to the detector design. The conventional approach prescribes retraining the inference model at every candidate design, thus, treating the evaluations as independent tasks and discarding the shared structure of the optimal inference algorithms at different designs. We propose the meta-learned objective estimate (MLOE): instead of solving the inference problem anew at every candidate design, a single meta-inference model, conditioned on the design and trained continually along the optimization path, is shared across all of them. We test MLOE on three families of optimization problems, the last of which comprises two design spaces of the Spectrometer Straw Tracker of the Search for Hidden Particles (SHiP) experiment; under matched budgets of simulation calls, the meta-inference model evaluates a candidate design using fewer simulation calls than the baseline strategies and holds the better rank over the convergence curve in all examined cases. --- ### Reliable but Design-Sensitive: Instrument Uncertainty in LLM Annotation Authors: Thomas Reiter, Christoph Kern, Fedor Miasnikov, Sofiia Nikolenko, Rob Chew, Stephanie Eckman, Frauke Kreuter Published: 2026-09-22 Categories: cs.CL, stat.ME arXiv: https://arxiv.org/abs/2609.35824v1 Large language models (LLMs) can give reliable labels under one setup yet change those labels when researchers make other reasonable design choices. We tested seven LLMs, 12 task designs, three independent runs, and 3,000 tweets labeled for offensive language and hate speech. Repeating the same model and task design produced high agreement (median Fleiss' $κ= 0.91$). Agreement fell when we changed the task design for the same tweets (median Cohen's $κ= 0.76$). Task design and model choice increased the variance of estimated prevalence by factors of 76.7 for offensive language and 110.6 for hate speech compared with sampling variance alone. Variation across LLM task designs reached 560-572 basis points, compared with 270-331 basis points across five human instrument versions. Confidence scores did not solve this problem. They tracked repeated model outputs more closely than agreement with human labels, and grouping six tweets in one prompt lowered mean offensive-language confidence by 660 basis points. We call the variation caused by task design and model choice instrument uncertainty. Researchers can measure it only by comparing reasonable task designs. Repeating one setup or relying on confidence scores cannot replace that test. --- ### CoVLM-Bench: A Real-World Benchmark for Cooperative Driving Question Answering and Planning Authors: Kang Yang, Shuai Liu, Hang Li, Yance Fang, Deying Li, Yongcai Wang Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35823v1 Vision-language models (VLMs) have made substantial progress in autonomous driving, but their success has primarily been studied in ego-centric scenes. Infrastructure-side observations provide views beyond the ego vehicle's field of view, yet conventional cooperative-driving systems typically transform them into geometric representations for downstream perception and planning. Directly incorporating these views into VLMs offers an opportunity to improve cooperative scene understanding and trajectory planning. However, question answering and trajectory planning have not been jointly evaluated on the same real-world vehicle-infrastructure scenes. We present CoVLM-Bench, a benchmark for cooperative driving question answering (CDQA) and cooperative planning (CP) on vehicle-infrastructure paired scenes. CoVLM-Bench provides scene-grounded CDQA annotations, three-part rationales as auxiliary supervision, and future trajectory targets derived from recorded ego motion. It contains 2,196 paired frames with 35,136 CDQA annotations, while CP predicts six waypoints over a three-second horizon. The annotations combine model-assisted drafting, record-based computation, and human verification. Built upon CoVLM-Bench, we introduce CoVLM-Drive, a unified VLM baseline that directly uses paired views for both CDQA and CP. Experiments show that CDQA adaptation improves answer accuracy and that CoVLM-Drive reaches a lower FDE than the compared V2X planners; QA initialization and rationale supervision each reduce planning error. Together, CoVLM-Bench and CoVLM-Drive support the training and comparison of VLMs for cooperative scene understanding and planning. --- ### Beyond Volume Overlap: Surface Matching for Topology-Aware Coronary Artery Segmentation Authors: Rafael Velasquez, Esther Puyol-Antón, Pablo Arbeláez Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31740v1 Accurate coronary artery segmentation on coronary computed tomography angiography (CCTA) is essential for diagnosing coronary artery disease. Deep networks are conventionally trained and evaluated with the Dice coefficient, but volume-overlap metrics are poorly suited to thin, tubular anatomy: since most voxels belong to a few thickproximal segments, a missing distal branch barely affects Dice despite severely disrupting the connectivity required for clinical use. We introduce a surface metric that matches predicted and reference surface points via bipartite assignment under a localized, vessel-radius tolerance, reporting precision, recall, and F1 with decoupled false positives (spurious branches) and false negatives (missed branches) a distinction the symmetric Dice cannot make. With it we show that a strong Dice-trained baseline omits far more vessel surface than it hallucinates, an asymmetry its high Dice hides. Building on this, we propose a differentiable surface loss that simultaneously suppresses spurious mass and recovers absent structure, validated by fine-tuning three backbones (nnU-Net, SwinUNETR, NexToU) on two public benchmarks (Image-CAS, ASOCA). Against a matched-epoch control, it significantly improves surface F1 by recovering missed distal vessels at comparable Dice. Our findings argue for measuring and optimizing the vessel surface, not the volume it overlaps. Code --- ### Seeing the Heat: Synthesizing High-Resolution Wood Thermal Responses from Optical Imagery Authors: Jingren Xie Published: 2026-09-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.31737v1 The thermal behavior of wood is a critical factor in advanced material assembly. However, pixel-level thermal analysis remains fundamentally constrained by the low resolution and noise inherent to infrared thermography. To address this, we introduce an end-to-end computational framework that synthesizes high-resolution thermal responses directly from wood RGB images. We first establish a core physical linkage: because spatial color variation in natural wood is driven by cellular anatomy, optical intensity serves as a reliable geometric proxy for the localized solid volume fraction. By leveraging this theoretical insight, we develop an automated finite-element-method data engine that maps pixel-level optical intensity to a 3D thermodynamic voxel grid, generating high-fidelity synthetic thermal responses. We find that 1) when the thermal conductivity along the thickness direction is uniform or linear, wood RGB images and their corresponding thermal responses exhibit extreme morphological similarities, and the lateral thermal diffusion acts as a low-pass filter that smooths out high-frequency details; 2) when the thermal conductivity along the thickness direction is random, such morphological similarities are destroyed, and wood's 3D structure dominantly governs its thermal response. We further utilize these synthetic thermal responses to supervise a neural surrogate model built upon the DINOv3 foundation model. Our results demonstrate that the neural surrogate model successfully internalizes the governing thermodynamic laws, thereby bypassing computationally expensive simulations and enabling high-resolution thermal inference. This methodology effectively bridges the semantic and thermodynamic domains, unlocking systematic, pixel-level analysis of fine-grained wood thermal responses. Project: https://zekifayes.github.io/seeheat --- ### LukeNet: A lightweight CNN integrated with an XAI model for Smart acute lymphoblastic leukemia detection and management Authors: Md Taimur Ahad Published: 2026-09-22 Categories: cs.CV, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2609.31736v1 Acute Lymphoblastic Leukemia (ALL) patients require early, accurate detection to enable timely treatment and effective patient management. A Convolutional Neural Network (CNN) is well-suited for creating an end-to-end enabling environment for ALL detection and classification. However, most CNN-based ALL detection systems are theoretical and unsuitable for deployment on edge devices due to high computational demands. The Internet of Medical Things (IoMT)-enabled devices offer an opportunity to monitor ALL patients in real time. Wearables that track temperature, heart rate, oxygen saturation, and activity can deliver critical data to support timely clinical intervention and improve patient outcomes. In smart IoMT environments, a lightweight CNN is essential because connected devices often operate under limited computational power, memory, and latency constraints. To address this need, this study proposes LukeNet, a lightweight CNN integrated with explainable artificial intelligence (XAI) for an IoMT-based SMART Acute Lymphoblastic Leukemia Detection and Management System. Trained on three (3) ALL datasets and five-fold cross-validation, LukeNet achieved an impressive 99% model accuracy as well as 99% unseen test accuracy, which is higher than six state-of-the-art (SOTA) CNNs, such as DenseNet121, MobileNet, ResNet50, InceptionV3, Xception, and VGG16, as well as transfer learning models. Furthermore, LukeNet was compared with two ensemble models. In addition, explainable AI methods are integrated to highlight relevant regions in microscopic images. The novelty of this study lies in the architecture of LukeNet, which balances model depth and computational efficiency by using depthwise separable convolutions, mitigates the risk of gradient loss in deeper layers, and provides strong global and local feature extraction capabilities. --- ### Measuring the evolution of camera distance across a century of film Authors: David Bamman, Allison Cooper, Dan Hickey, Madison Mar Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31734v1 The rise of computer vision and artificial intelligence has made possible new forms of large-scale computational measurement. We apply these techniques to a deep collection of 5,205 digitized films viewed in theaters between 1922-2025 (covering popular, prestigious, and independent movies) to trace the development of one of the most fundamental ways through which film communicates: by manipulating the space between the camera and its subject. This work finds abrupt changes with the rise of new technologies in sound and television, and allows us to shed an empirical light on gender disparity (women, despite having substantially less screentime than men, are disproportionately the subject of closer shots), and illustrate how animated films both inherit and break free from the norms of live-action filmmaking. --- ### When Retrieval Hurts: Measuring and Explaining Retrieval-Induced Hallucination in Chest X-ray Report Generation Authors: Emmanuel Idoko, Abdusshakur Olabisi, Shiloh Oni, Adesola Josiah Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31733v1 Retrieval-augmented generation is an attractive way to improve chest X-ray reporting, because reports from similar prior studies supply clinical context a general vision-language model lacks. We show the same mechanism is a reliable source of clinical error. Over 100 MIMIC-CXR studies with a frozen LLaVA-1.5 generator and BioMedCLIP retrieval, CheXbert clinical F1 doubles under relevant retrieval (0.201 to 0.402) and collapses to 0.043 under clinically mismatched retrieval, a fifth of the image-only score; the retrieval-induced hallucination rate, counting only unsupported findings traceable to retrieved evidence, rises from 0.00 to 0.76 and 0.98. To show this is not an artefact of evidence-set coverage, we introduce a coincidental-overlap control that scores image-only generations against evidence they never saw, placing the chance base rate at 0.18, four to five times below the observed rates. The generator does not merely acquire findings, it transcribes text: 95% of reports produced under relevant retrieval contain an eight-word span occurring verbatim in the retrieved evidence but absent from the reference, against 0% without retrieval. We then explain the mechanism: a normal chest X-ray retrieves at least one abnormal precedent in 24 of 28 cases, because medical image-embedding similarity is dominated by anatomy and acquisition rather than by the presence of disease. This has a direct design consequence. Retrieval similarity does not predict harm (RIH rates 0.80/0.80/0.60/0.84 across similarity quartiles), so relevance gates conditioned on embedding similarity cannot work; gating on predicted pathology agreement removes 61% of unsupported evidence at no cost to useful coverage. We argue that retrieval-augmented clinical systems must be evaluated under retrieval failure, not only under retrieval success. --- ### GERIS: A Game-Theoretic Framework for Filtering Instance-Dependent Label Noise in License Plate Data Augmentation Authors: Seyedeh Sara Jalili Shani, Rouhollah Ahmadian, Amin Rahmani, Mahdi Bideh, Mehdi Ghatee Published: 2026-09-22 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31731v1 In this paper, we propose GERIS, a game-theoretic framework for instance selection in the data augmentation phase of license plate recognition systems. During augmentation, synthetic license plate images are generated and transformed using stochastic noise to simulate real-world conditions. However, certain noise configurations lead to highly distorted, unreadable images that degrade model performance by introducing instance-dependent label noise. GERIS formulates a non-cooperative game in which each noise vector competes for inclusion in the training set based on its similarity to labeled data and its contribution to model reliability. By identifying and pruning low-quality instances, GERIS improves the overall quality of the augmented dataset. Unlike traditional black-box learning methods, GERIS offers a transparent, theoretically grounded mechanism for data filtering. Experimental results demonstrate that GERIS outperforms existing instance selection methods in terms of classification accuracy and robustness. --- ### The Ongiini-Eval-OW Benchmark: A Concept Paper for the Planned Benchmarking of Machine Translation and Large Language Models on Oshindonga and Oshikwanyama Authors: Sebastian Küpers Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31727v1 Oshiwambo -- a cluster of mutually intelligible Bantu languages spoken by over a million people across northern Namibia and southern Angola, and the home language of roughly half of Namibian households -- has, to our knowledge, no published machine-translation evaluation benchmark. Major commercial services (Google Translate, DeepL, Microsoft Translator), open multilingual MT models (NLLB-200, MADLAD-400), and the open Masakhane checkpoint collection all lack coverage of either standardised dialect, Oshindonga or Oshikwanyama. We announce Ongiini-Eval-OW, a planned 600-item English-Oshindonga and English-Oshikwanyama benchmark with native-speaker references from two independent translators, a 30-item inter-translator agreement set, an 11-tag phenomenon-tagged stratification (at least 30 items per tag), a deterministic 30% blind split, and a reproducible scoring protocol over chrF++, BLEU, and COMET-22, supplemented by a 50-item human-evaluation round. We document the empirical coverage gap, the dataset composition, the launch-leaderboard model matrix across American, European, and Chinese frontier and open-weight systems, and the contribution pipeline. The dataset is targeted for first public release in Q4 2026; this v1.0 concept paper announces the design and the call for participation. Data and code will be released under CC-BY-4.0 and MIT respectively. --- ### High-Capacity Robust Medical Image Exfiltration via Neural Network Weight Replacement Authors: Elie Thellier, Huiyu Li, Nicholas Ayache, Hervé Delingette Published: 2026-09-22 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.31726v1 Collaborative medical AI platforms allow researchers to train models on sensitive imaging data while restricting data export. However, trained models can serve as covert carriers of patient information: medical images may be encoded within model parameters and reconstructed outside the secure environment. Existing defenses rely on lightweight sanitization (e.g., fine-tuning, pruning, quantization) and limited statistical auditing, creating a realistic insider exfiltration risk. We introduce a high-capacity neural steganography attack that encodes medical images as continuous latent representations embedded into model initialization. A StyleGAN2-based adversarial autoencoder learns compact latent codes regularized to match standard weight initialization statistics, keeping embedded parameters statistically consistent with clean models. Noise injection during training improves robustness to export-time mitigation. The carrier model remains functional on its intended task and hidden images can be reconstructed directly from its weights after export. This continuous encoding enables robust and scalable exfiltration, allowing up to 99 brain MRI volumes to be embedded within a 30MB model, and remains recoverable under mitigations that disrupt prior bit-level schemes. While reconstructions are approximate rather than pixel-exact, embedded content remains anatomically recognizable and recoverable at scale, exposing a privacy risk distinct from prior bit-level approaches. Experiments on MIMIC-CXR, BraTS, and LiTS demonstrate effectiveness across modalities, tasks, and architectures, highlighting the need for structural defenses beyond parameter-level sanitization. Code is available at https://github.com/ElieThellier/high-capacity-robust-medical-image-exfiltration. --- ### SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation Authors: Zhengtong Zhu, Jiaqing Fan, Hanwen Qian, Fanzhang Li Published: 2026-09-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31725v1 Video Object Segmentation (VOS) aims to accurately segment target objects from consecutive video frames and track the changes of the objects in each frame of the video. Conventional VOS methods typically demand substantial quantities of pixel-level labeled video sequences for fully supervised learning, which limits the performance of the model in sparse video scenes, while existing VOS methods have limited adaptability to global changes in objects. Based on this observation, in this paper, we propose self-supervised VOS with Sliding window, Wavelet transform and optimal Transport (SWT), a self-supervised VOS framework entirely trained on static dataset using contrastive learning. Firstly, a rolling sample buffer reuses overlapping groups of independently sampled images across successive updates. Secondly, to address the long-distance modeling difficulty caused by simple convolutional structures, we introduce wavelet transform to expand the receptive field of convolutional kernels, thus improving the model's representational capability. Finally, we incorporate optimal transport to assist the model in finding the globally optimal match between the target across two frames, improving the model's ability to handle nonrigid deformations of objects. SWT only requires training on the COCO dataset once and achieves excellent results on five VOS datasets as well as an additional body part propagation dataset. The code will be released soon at (https://github.com/machine928/SWT.git)(https://github.com/machine928/SWT.git). --- ### Frequency-Domain AI-Generated Image Detection: Exploring Decoder and Channel Attention for Feature Refinement Authors: Uday Shankar Roy, Mahbuba Jahan Minu Published: 2026-09-22 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31723v1 With the rapid progress of AI, the number of AI-generated images has increased significantly in recent years. However, the increasing variety of image generation models makes detection more difficult. In this work, we use Fast Fourier Transform (FFT) representation with EfficientNet-B0 for AI-generated image detection. EfficientNet-B0 provides a lightweight architecture that can be useful for resource-limited applications. Most frequency-domain detectors use a standard encoder to extract features from the FFT spectrum and directly pass them to a classifier. We explored a different approach by investigating ECA, U-Net, and Attention U-Net as alternatives to this direct encoder-to-classifier approach. ECA applies channel attention, while U-Net and Attention U-Net use decoder-based architectures to recover and refine spatial information in the extracted frequency features. We used a balanced subset of the MS COCOAI dataset that includes AI-generated images from five different models. Three runs were carried out for each experiment, and the average values were recorded. Experimental results indicate that EfficientNet-B0 obtained an accuracy of 84.64%, which is 4.50 percentage points higher than the ResNet-50 baseline reported in the dataset paper. EfficientNet-B0 with U-Net provided a small improvement, achieving an accuracy of 84.85%, while ECA did not increase the overall performance. EfficientNet-B0 with Attention U-Net achieved the best overall performance, with an accuracy of 85.51% and an ROC-AUC of 92.99%. This represents an improvement of 0.87 percentage points in accuracy compared to the EfficientNet-B0 baseline and 5.37 percentage points over the ResNet-50 baseline reported in the dataset paper. --- ### Where Does the Watermark Hide? Push-Pull Disentanglement for Invisible Watermark Removal Authors: Jidong Yang, Huaike Yu, Qi Li, Chunpeng Wang, Yuantian Miao, Suo Gao, Xiao Chen Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31722v1 Fixed image distortions do not cover an attacker that learns from paired clean and watermarked images. We study this paired-training threat with single-image inference: deployment uses neither the clean reference nor the watermark key, payload, or decoder. An encoder maps each image to a structural latent $g$ and an auxiliary residual latent $u$. Push supervision reconstructs the watermarked image from $D(g_w,u_w)$. Pull supervision trains the zero-auxiliary output $D(A_g(g_w;k),0)$ toward the paired clean image. At $k=1.10,u=0$, the four-method sweep gives an average BER of $0.3958$, PSNR of $31.07$ dB, and SSIM of $0.9554$. Restoring $u$ from $0$ to $0.15$ moves average BER from $0.3893$ to $0.3357$, while PSNR falls from $30.99$ to $28.23$ dB. The intervention supports decoder dependence on the auxiliary input in the evaluated setting. The accompanying theory is a conditional, post-hoc account of this behavior rather than an experimentally verified information-relocation result. --- ### Stochastic Inertial Krasnosel'skii-Mann Iteration Achieves Near-Optimal Sample Complexity Authors: Tong Yang, Tao Jiang, Yuejie Chi, Ashok Cutkosky, Lin Xiao Published: 2026-09-22 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.28543v1 We analyze a simple stochastic inertial Krasnosel'skii--Mann (iKM) method for finding a fixed point of a nonexpansive operator in a real Hilbert space. Our method is obtained simply by adding two inertial extrapolations to stochastic KM (Bravo and Cominetti, 2024), and it retains one call to a possibly biased stochastic oracle per update and achieves sharp rates in both the stochastic and deterministic regimes. Specifically, with our proposed parameter schedule, we prove the following last-iterate fixed-point residual bound: \( {O}\!\left(\frac{1}{K} +\frac{σ\log K}{\sqrt K} +\frac{B_K\log K}{K}\right), \) where $K$ is the horizon, $σ$ is the noise level and $B_K$ is the accumulated root-mean-square bias. When $B_K=O(\sqrt K)$, this yields $\widetilde O(ε^{-2})$ sample complexity that matches, up to a logarithmic factor, the stochastic-oracle lower bound given under the unbiased subclass of our model (Foster et al., 2019, Theorem 2). It also improves the best-known $O(ε^{-4})$ random-iterate guarantee for stochastic KM (Bravo and Cominetti, 2024, Corollary 5.4). To our knowledge, this is the first single-loop method for general nonexpansive fixed-point problems to attain this near-optimal sample complexity without variance reduction or batching. When the oracle is exact, the same method attains the worst-case-optimal $O(K^{-1})$ last-iterate residual rate (Park and Ryu, 2022, Theorem 4.6), improving the $O(K^{-1/2})$ rate of classical KM (Cominetti et al., 2014; Bravo and Cominetti, 2018). --- ### Adaptive Tiling for Least-Squares Phase Unwrapping: Runtime and Accuracy Authors: Antoine Moevus, Max Mignotte Published: 2026-09-22 Categories: eess.IV, cs.CV, cs.DC arXiv: https://arxiv.org/abs/2609.28541v2 Phase unwrapping estimates the missing multiples of $2π$ in measured phase images. For large images, tiling limits the size of local reconstruction problems and enables parallel processing. Adaptive tiling could further reduce the number of local problems and boundaries by retaining large tiles where little refinement is needed. We investigate whether this reduction makes reconstruction faster. We compare complete reconstruction time and accuracy for a regular grid, quadtree, and kd-tree partitions. We also evaluate nine criteria for deciding where quadtree tiles should be subdivided, including residue count, fringe density, and measures of phase variation, at different tile sizes and budgets. In single-threaded experiments on a heterogeneous image dataset, optimized adaptive partitions use fewer tiles but remain slower than the optimized grid, and some reconstructions lose substantial accuracy. Stage measurements explain why: constructing the partition and solving larger retained tiles outweigh the savings at tile boundaries. The criterion comparison also shows that more refinement does not consistently improve accuracy. These results motivate evaluating adaptive partitions by the complete time needed to reach a chosen reconstruction accuracy, including whether limited refinement can provide a faster approximate result. --- ### $\unicode{x1F493}$Heartian: Physiology-Aware Relightable Gaussian Head Avatar Authors: Xiaoyue Fan, Jose Echevarria, Akshay Paruchuri, Kaan Akşit Published: 2026-09-22 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.28539v1 Gaussian head avatars typically model intrinsic facial appearance as temporally static, omitting subtle cardiac-induced skin-color variation. We propose $\unicode{x1F493}$Heartian, a physiology-aware modulation framework that learns cardiac-cycle-dependent per-frame albedo modulation of facial skin-region Gaussians within a relightable head avatar to encode remote photoplethysmography (rPPG) signals. Using synchronized contact PPG supervision, $\unicode{x1F493}$Heartian models the prescribed cardiac waveform as the sum of two Gaussian functions and learns per-frame spatial residuals via a lightweight MLP. Across 152 stationary recordings from UBFC-rPPG, PURE, and MMPD, attribute-space recovery of the supplied signal achieves a pooled recording-level heart-rate MAE of 0.29 bpm and MAPE of 0.38%. The signals remain detectable after rendering by benchmark rPPG methods, with the best tested configuration - a motion-augmented TS-CAN decoder pretrained on UBFC-rPPG - recovering heart rate from the rendered MMPD avatars at 0.97 bpm MAE and 1.21% MAPE. Meanwhile, $\unicode{x1F493}$Heartian maintains reconstruction quality comparable to the baseline, with negligible average PSNR degradation of 0.005 dB. Overall, our work embeds recoverable rPPG signals as controllable material attributes to subject-specific Gaussian head avatars while retaining the reconstruction quality. --- ### An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting Authors: Jalaj Upadhyay Published: 2026-09-22 Categories: cs.CR, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2609.28528v1 The goal of this note is to give a detailed proof, to the best of our understanding, of the recent presentation by Harrison and Leeman (arXiv:2609.17650v01 and arXiv:2609.17650v02) of the proof by Astra on the lower bound for differentially private continual counting. We believe a more natural and easy proof is possible and hope that this note will help in that effort. Prior to the initial preprint by Harrison and Leeman (arXiv:2609.17650v01), Bairaktari and Larsen (arXiv:2607.00876) gave an elegant proof to show a lower bound of $Ω(\log^{3/2}(n))$ for both pure and approximate-DP continual counting, and in personal communication had informed us that they have a proof of optimal $Ω(\log^{2}(n))$ for pure-differential private continual counting as well. They have subsequently published their $Ω(\log^{2}(n))$ bound, which is now a joint work of Bairaktari, Dahl, and Larsen (arXiv:2607.00876v3). Their new result is an elegant extension of their technique for approximate-differential privacy. Although the two proofs are technically different, the Astra argument uses related tree geometry introduced in Bairaktari and Larsen. --- ### Sequential Confidence Sets for Coverage-Constrained Conformal Model Selection Authors: Jing Li, Haibin Zhu Published: 2026-09-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.28522v1 Modern conformal forecasting systems often maintain several adaptive pipelines that differ in base forecasters, conformity scores, calibration windows, and update rules. Comparing them is difficult because coverage is a hard constraint, whereas efficiency should be optimized only among feasible pipelines. We formulate this problem as sequential inference for a stochastic constrained argmin. At each time, the target is the set of minimum-cost pipelines satisfying multiple prefix-average conditional miscoverage constraints. We introduce Coverage-Constrained Sequential Model Confidence Sets (CC-SMCS), which separate certifiably feasible, possibly feasible, and possibly constrained-optimal pipelines. Using simultaneous martingale confidence sequences, CC-SMCS projects a rectangular confidence region onto the constrained argmin and admits an exact closed-form rule. With probability at least $1-δ$, it contains every constrained-optimal pipeline simultaneously over all times. This finite-sample guarantee requires no stationarity or mixing assumptions and remains valid under data-dependent stopping. We also establish an impossibility result for safe certification at the coverage boundary and extend the construction to delayed multi-horizon feedback and outcome-dependent efficiency objectives. --- ### Certified Task-Conditioned Active Observability Authors: Linzhe Zhang, Changming Xu Published: 2026-09-22 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.28520v1 Before acting upon an unobservable physical system, an autonomous agent must determine which latent distinctions govern downstream tasks, how many active interventions are necessary to certify them, and when to abstain to prevent catastrophic errors. Classical observability treats state reconstruction as an unconditioned binary predicate, failing when passive observations cannot break latent degeneracies without perturbation, full microscopic inversion is prohibitively costly, and distinguishing task-irrelevant degrees of freedom wastes interaction budgets. We formalize task-conditioned active observability complexity: the minimum worst-case expected interaction cost required to identify task-relevant states under certified error and safe abstention guarantees. We prove that task-predictive equivalence induces the unique minimal sufficient quotient $\mathcal{H}/\!\sim_τ$, leaving active observability complexity strictly invariant while eliminating superfluous distinctions. In deterministic regimes, this complexity is characterized by an optimal adaptive distinguishing tree and Bellman recursion; in noisy regimes, it obeys a stopped-transcript relative-entropy lower bound and adaptive martingale certificates that compose without independence assumptions. We instantiate a prospective certified observer with staged recovery: a nominal verifier defers candidate compilation, triggering active probing only upon evidence, while a history-measurable score shell prunes hypotheses without sacrificing risk bounds. Stress audits across high-dimensional physical systems and thousands of operational trials demonstrate certified state recovery with zero false acceptances and substantial reductions in sensor reads and model steps. --- ### Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies Authors: Yuhang Jiang Published: 2026-09-22 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.27167v1 Action-chunked visuomotor policies predict overlapping trajectories, so every executed action is covered by several predictions. Temporal ensembling smooths execution by combining these predictions with an exponentially weighted mean. One corrupted prediction can move the aggregate without bound: its breakdown point is 0. We use adversarial corruption to stress this deployed aggregator and to compare two kinds of guarantee. A metric guarantee bounds the response to a perturbation of a given size. A combinatorial guarantee instead bounds the damage when at most q of the M candidates covering a timestep are corrupted, whatever their size. Encoder adversarial fine-tuning recovers 44% of the loss under the published patch attack, but only 7.3% after the attacker's step size is increased. By contrast, the coordinate-wise median of the same candidate set keeps its recovered fraction flat as attack optimisation increases. Median temporal ensembling costs one line and requires no retraining. Across 25 (configuration, corruption-level) combinations it is never worse than the mean and is significantly better in 15. It also transfers to a second policy class, and it recovers performance under a failure with no attacker in the loop at all: camera frames that arrive blank. Its effect on clean data is configuration-dependent, from -0.04 to +0.07. We also give the boundary: corruption that shifts every covering prediction by the same amount is invisible to this whole family of statistics, and no equivariant aggregator can remove it. --- ### Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models Authors: Moritz Laber, Zohair Shafi, Germans Savcisens, Brennan Klein, Matteo Chinazzi, Samuel V. Scarpino, Albert-László Barabási, Alessandro Vespignani, Tina Eliassi-Rad Published: 2026-09-22 Categories: cs.LG, physics.soc-ph arXiv: https://arxiv.org/abs/2609.27166v2 Capability and efficiency are two key dimensions of reasoning in large language models (LLMs). Capability refers to the ability to solve a given problem correctly, whereas efficiency refers to the ability to do so with limited resources. When LLMs use Chain-of-Thought (CoT) reasoning to solve problems of controlled hardness, both the number of problems solved correctly and the number of tokens required to reach a correct answer depend on problem hardness and model size. However, how these factors jointly shape capability and efficiency remains poorly understood. Here, we use hierarchical Bayesian models to evaluate the capability and efficiency of LLMs from the DeepSeek-R1-Distill model family across four classes of arithmetic and algorithmic reasoning problems. At a fixed model size, the probability of correctly solving an instance decays approximately exponentially with instance size, our proxy for problem hardness. The decay scale grows sublinearly with model size, indicating that larger models are more capable, but that capability gains diminish with scale. Output length grows as a power law with instance size, which serves as a proxy for difficulty. However, the parameters of this power law do not vary systematically with model size, suggesting that larger models do not become more efficient. Together, these findings reveal potential limitations of naive scaling as a strategy for developing more capable AI systems: capability improves with diminishing returns, while efficiency shows little to no improvement. --- ### Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement Authors: Yuhe Wu, Rui Qian, Guangyu Wang, Yuran Chen, Yuanchao Zhu, Junjie Yang, Zhengheng Li, Jiulin Cai, Tianyi Zhang, Zihan Dong, Jiaxin Liu, Yujie Chen et al. Published: 2026-09-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.27165v1 Large language models (LLMs) are increasingly used to measure public value orientations from long social media posts, yet such posts often mix background, quotations, concessions, and only a few stance-bearing sentences. Existing approaches either ask the model to predict a document-level label directly, which can be overconfident, or aggregate sentence-level predictions by majority or soft voting, which treat uncertain and decisive sentences as equally informative. We formulate long-text value measurement as a decision-fusion problem and propose Tempered Evidence Fusion (TEF), a training-free rule that weights each sentence's log-odds by its normalized information gain, as derived from a generalized Bayesian posterior. This makes the fused score nearly vanish for uncertain sentences while preserving the Bayes-optimal weight of decisive evidence. We further introduce Multi-event Insight Network Dimensions (MIND), a benchmark of 8,358 Chinese and English posts spanning five years of public events and six value dimensions. On MIND, TEF outperforms the strongest baseline among Direct, Majority Vote, and Soft Vote by an average of 4.5 accuracy points and 4.6 macro-F1 points across five LLMs and two languages. MIND dataset and code are available at https://github.com/Kzczc/ICASSP2027-TEF. --- ### The Linear Representation Hypothesis Needs a Group Action Authors: Louie Hong Yao, Yuhao Li, Shengchao Liu Published: 2026-09-22 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.27158v1 To make claims about representations that generalize beyond a particular trained model, we need to specify when two representations should count as equivalent. The Linear Representation Hypothesis is often discussed without making this equivalence explicit. Different notions of equivalence preserve different structures, so metrics, probes, and interventions that appear to study the same representation may in fact correspond to different hypotheses. We therefore argue that the Linear Representation Hypothesis is not one hypothesis but a family of claims distinguished by representation equivalence. We formalize this idea using group actions, specifying the representation object, the procedure that produces it, and the property ultimately asserted, while accounting for equivalences imposed by the model architecture. This framework clarifies how assumptions can change across metrics, reading points, and analysis stages, and we use it to audit common representation quantities and recent interpretability analyses. --- ### Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning Authors: Yuqing Zhou, Hong Wang, Manqing Mao, Zhuoer Wang, Samson Koelle, Jie Yuan, Yanjun Lin, James Feng, Nikki Lijing Kuang, Ziwei Zhu, Wei Niu Published: 2026-09-22 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.27156v1 Large reasoning models can produce correct yet unnecessarily long reasoning traces. Existing methods improve reasoning efficiency with trajectory-level objectives or local token- and step-level signals, but rarely model inter-step semantic dependencies. This limits their ability to distinguish redundant steps from those that support later deductions, making it harder to shorten reasoning without sacrificing accuracy. We introduce RECAP (REdundancy-aware Credit Assignment via Propagation), which addresses this limitation by assigning credit where it is due based on both a step's downstream role in the reasoning structure and its contribution to solving the problem correctly. We define structural responsibility to capture the step's downstream role by measuring how strongly later reasoning depends on it, using credit propagated backward from the final-answer node through an outcome-independent, LLM-annotated semantic dependency graph. However, a step can have high structural responsibility yet steer the reasoning away from the correct solution. RECAP therefore introduces step efficacy to measure answer-directed progress through changes in gold-answer log-likelihood as each step is added. Together, these signals reshape rollout-level GRPO advantages into step-specific updates. RECAP requires neither a separately trained process reward model nor preconstructed concise trajectories. Across two 7B models and four mathematical reasoning benchmarks, RECAP improves the accuracy-efficiency trade-off. On Qwen2.5-Math-7B, it improves pass@1 by 2.0-3.7 percentage points while reducing reasoning tokens by 8%-31% relative to GRPO across all four benchmarks. Analysis suggests these savings reflect fewer reasoning operations and less dead-end reasoning, rather than more compact expression. --- ### The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems Authors: Yue Xing, Pengfei He, Zitao Li Published: 2026-09-22 Categories: cs.CR, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.27155v1 With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader access to act on users' behalf on the internet. However, the vulnerability of automated agents deployed on social media platforms (e.g., for managing a user's personal account) remains underexplored. Existing studies on agent poisoning typically assume that the adversary can expose poisoned content to the agent. Although such an attack is direct and effective, it is more easily detected and mitigated. In the context of social media platforms, this leaves open whether the recommendation system itself would surface such content to the agent in a more subtle manner. Through theoretical analysis, we show that the like-score mechanism used in OASIS can be exploited, and we characterize the conditions under which a multi-stage chain of poisoned posts can steer the agent's feed. Based on these insights, we further develop an algorithm that crafts realistic poisoned posts. Experiments support our theoretical findings and demonstrate the effectiveness of the proposed algorithm. Notably, by exploiting the like-score feedback loop, the attack causes the recommendation system to select poisoned posts even when their user-post similarity falls below the retrieval threshold. --- ### Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate Authors: Boxuan Wang, Zhuoyun Li, Xiaowei Huang, Yi Dong Published: 2026-09-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.27150v1 Multi-agent debate (MAD) has emerged as a promising paradigm for improving the reasoning accuracy of large language models (LLMs) through iterative peer interaction. Communication topology plays a central role in this process, motivating increasingly sophisticated mechanisms that learn, adapt, or dynamically reconfigure agent interactions to improve accuracy or reasoning reliability. Meanwhile, prior studies suggest that much simpler sparse communication can already achieve competitive performance at substantially lower cost. In this work, we take a closer look at sparse MAD and ask whether complex topology control is actually necessary to improve collective reasoning. We find that a simple random-without-replacement routing policy, which lets each agent debate with two distinct and newly sampled peers at every round, provides a surprisingly strong baseline and consistently improves the accuracy-cost trade-off of sparse MAD. Building on this observation, we further study deliberation stopping and show that lightweight stopping can substantially reduce inference cost while preserving competitive accuracy. Our results suggest that sophisticated topology control such as learned topology adaption should be evaluated against strong simple routing and stopping baselines before its additional complexity is justified. --- ### Temporally Ordered Region-Token Mamba with Logit-Space Diffusion for Remote Sensing Change Detection Authors: Anuvab Sen, Maneet Chatterjee, Aparup Ghosh, Udayon Sen, Arnav Aditya, Yixin Zhang Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27149v1 Remote sensing change detection requires both global reasoning across bitemporal images and precise localization of changed regions. However, dense attention is computationally expensive for high-resolution imagery, while conventional feature fusion and coarse decoding may inadequately separate genuine changes from appearance variations or preserve object boundaries. We present Bitemporal Mamba-Diffusion for Change Detection (BMD-CD), which combines temporally structured state-space modeling with logit-space diffusion refinement. BMD-CD converts deep bitemporal features into region tokens and arranges them in explicit temporal partitions before bidirectional state-space propagation. Its Bitemporal Ordered Mamba Operator enables long-range cross-temporal interaction with linear sequence complexity, while Orthogonal Feature Disentanglement forms a change-oriented output and a complementary rotated output using learned pairwise rotations and unchanged-region consistency. Multiscale decoding then produces coarse change logits, which are refined through a five-step Conditional Diffusion Decoder operating directly in logit space. Experiments on LEVIR-CD, WHU-CD, DSIFN-CD, CDD, and S2Looking demonstrate strong performance across diverse change-detection settings. BMD-CD achieves F1 scores of 93.7%, 96.0%, 97.8%, and 99.0% on the four standard benchmarks and improves 3-pixel Boundary-F1 to 87.7% and 91.4% on LEVIR-CD and WHU-CD, respectively. The full model requires 32.09 GFLOPs and 47 ms per 256 x 256 image pair, while also showing zero-shot transfer to ValaisCD and B-FLAIR-test. Our code is available at https://github.com/Aparup2139/Public_WACV/ --- ### Learning Risk Scores Robust to Unobserved Confounders Authors: Ryan Edmonds, Yingxiao Ye, Sina Aghaei, Andrés Gómez, Çağıl Koçyiğit, Phebe Vayanos Published: 2026-09-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27144v1 We consider the problem of learning risk scores to prioritize individuals for scarce resources or interventions, from historical observational data affected by unobserved confounding. Decisions about who receives scarce resources are often guided by risk scores based on recorded characteristics, such as responses to a survey. These risk scores are increasingly being learned directly from observational data: historical records of individuals' characteristics, allocation decisions, and outcomes. Standard methods such as inverse propensity weighting (IPW), which corrects for the bias introduced by the historical allocation policy, can be used to learn accurate risk scores if the historical decision process is fully explained by the recorded characteristics. In practice, however, historical decisions often depend on unrecorded information, causing learned risk scores to systematically under-prioritize exactly the individuals whose unrecorded circumstances drove past prioritization. We propose a method for learning risk scores that are robust to this kind of unobserved confounding, building on IPW. Since propensity weights cannot be reliably estimated under unobserved confounding, we instead treat them as belonging to an uncertainty set determined by the observable data and domain-informed estimates of the degree of confounding, combining sensitivity analysis from causal inference with Wasserstein distributionally robust optimization. The resulting robust risk score learning problem admits a sample-based approximation that we reformulate as an exponential cone program compatible with off-the-shelf solvers. We demonstrate the effectiveness of our approach on semi-synthetic data derived from datasets in the UCI Machine Learning Repository. Our method improves calibration by up to 29.2% over traditional benchmarks and up to 11.1% over the state of the art, without compromising other metrics. --- ### A Systematic Evaluation of Infrastructure-Based Radar System for Highway Traffic Monitoring Authors: Tianheng Zhu, Woei-chyi Chang, Alamss Riaz, Sogand Hasanzadeh, Yiheng Feng Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27143v1 Infrastructure-based radar systems offer robust and long-range solutions for traffic monitoring, yet their detection and tracking performance under real-world conditions remains insufficiently evaluated. This study introduces DRaT (Drone and Radar Trajectories), a dual-modality dataset of naturalistic vehicle trajectories collected at a highway merging segment in Fort Worth, Texas, to systematically assess radar sensing performance against drone-derived ground truth. The performance is evaluated at three levels: individual vehicle detection, trajectory tracking, and macroscopic traffic parameter estimation. For individual vehicle detection, the radar achieves an overall precision of 78% and a recall of 57%, with degraded performance under congested traffic conditions and at longer distances. At the trajectory level, the radar demonstrates reasonably strong tracking performance (IDF1 = 0.699), maintaining reliable vehicle identities when tracks are successfully established. For macroscopic traffic flow metrics, the radar accurately estimates space-mean speed (MAPE < 4%) but underestimates density and volume by approximately 23% due to missed detections. The paper also discusses practical deployment considerations and potential downstream applications of roadside radar sensing systems. To support reproducible research on infrastructure-based sensing systems, we have open-sourced the DRaT dataset on Zenodo: https://zenodo.org/records/20171110. --- ### MINER: Multi-crop INference-time Enhancement for Rare-Object Retrieval with Frozen Dual Encoders Authors: Abdulmalik Alquwayfili, Faisal AlMeshal, Jumanah Almajnouni, Huda Abdulhadi Alamri, Muhammad Kamran J Khan Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27142v1 Text-to-image retrieval with frozen dual encoders degrades when the query names a small, visually subordinate object in a cluttered scene: a single global image embedding underrepresents the localized visual evidence. We present MINER, a training-free inference framework that augments a frozen dual encoder's global image embedding with a small bank of region-level embeddings and a hubness-correcting similarity rescoring, recovering visual evidence that global pooling underweights. To evaluate this setting, we introduce ROCS, a benchmark built from high-clutter subsets of Flickr30K and MS COCO whose images are re-captioned to name a single low-salience object. Experiments on CLIP, SigLIP, and SigLIP 2 show that MINER improves retrieval on every backbone, on ROCS and on the standard splits. Analyses show that these gains come primarily from broader spatial coverage rather than precise crop placement, revealing a simple and general way to recover localized evidence from frozen representations. Code: https://github.com/aalquwayfili/MINER. Dataset: https://huggingface.co/datasets/aalquwayfili/ROCS. --- ### A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery Authors: Ana Manzano Rodríguez, Pascal Mettes, Marlies P. Schijven, Cees G. M. Snoek Published: 2026-09-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.27139v1 Surgical procedures follow a phase-to-step hierarchy, yet the video-language models used to recognize them are evaluated with flat per-level metrics that ignore cross-level coherence and error structure. In this paper we make two contributions to address this problem, (i) we introduce SurgHiBench, the first hierarchy-aware evaluation suite for surgical video understanding, with three tasks measuring recognition, consistency, and severity across granularity levels. We evaluate a general-purpose CLIP model, a Euclidean surgical model, and, as second contribution: (ii) HyperSurg, a new hyperbolic model that enforces phase-step containment via entailment cones, across four (existing) datasets spanning three procedure types. The suite reveals that two models with the same accuracy can produce predictions of very different error severity, ranging from sibling confusions within the correct phase to unrelated cross-phase predictions. Hyperbolic geometry shifts predictions toward the correct procedural neighborhood, and these gains scale with the tree-likeness of each dataset's annotation hierarchy, providing a principled indicator when hierarchy-aware geometry helps. --- ### Super-Resolution of Solar Magnetograms via Adaptive Stratified Ensemble Learning with Uncertainty Estimation Authors: Sina Norouzi Kandalan, Haodi Jiang, Jason T. L. Wang, Qin Li Published: 2026-09-22 Categories: cs.CV, astro-ph.SR arXiv: https://arxiv.org/abs/2609.27131v1 Single-image super-resolution of Sun's photospheric magnetograms enables consistent analysis across heterogeneous space-based instruments and supports long-term studies of solar magnetic field evolution. We address the super-resolution task from SOHO/MDI (low-resolution) to SDO/HMI (high-resolution) line-of-sight (LOS) magnetograms using a modified RRDBNet architecture initialized by ESRGAN pretrained weights. Through systematic per-image diagnostic analysis, we identify image complexity as the dominant predictor of reconstruction errors. To exploit this finding, we introduce an adaptive stratified specialist ensemble (SSE) of three specialist networks with uncertainty estimation, where each specialist network is trained by images from three different complexity strata using a weighted random sampling strategy. During inference, a lightweight router based on input image statistics assigns each test image to the appropriate specialist network. Our experimental results demonstrate the good performance of the proposed ensemble and its superiority over closely related methods. --- ### When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense Authors: Mohamed Shaaban, Ahmed Abdelnaby, Mohamed Elmahallawy Published: 2026-09-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.27124v1 Federated Learning enables decentralized model training by exchanging model updates--rather than raw data--with a central parameter server (PS). While most of the existing defenses primarily assume static or independently acting adversaries, we reveal a new class of dynamically adaptive attacks that systematically bypass such protections. We propose Fed-ADR, a holistic attack framework in which a malicious orchestrator server (OS) dynamically coordinates a heterogeneous set of adversarial clients, including both targeted and untargeted attackers. Through real-time coordination by the OS, malicious clients strategically adapt their gradient updates to evade defenses deployed by the PS, while either severely degrading global model performance or steering training toward adversarial objectives.To mitigate this threat, we offer a detection mechanism that estimates each client's true gradient from historical updates, enabling real-time detection of coordinated malicious behavior without additional overhead. We further introduce an in-situ recovery mechanism that restores global model performance without restarting training, preserving convergence and minimizing recovery time. Comprehensive experiments on MNIST, Fashion-MNIST, and CIFAR-10 benchmark datasets demonstrate that Fed-ADR's attack scheme can reduce global accuracy from over 90% to below 10%, bypassing several state-of-the-art defenses. When our detection and recovery modules are employed, they identify malicious clients and restore accuracy to over 90% within a few rounds, at a substantially lower cost than retraining from scratch--achieving a reduction of at least 20x in computational overhead. --- ### PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perception Authors: Armin Maleki, Hayder Radha Published: 2026-09-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.27123v1 Heterogeneity across Collaborative Perception (CP) agents is a major challenge for emerging CP frameworks due to domain gaps from differing sensors, architectures, and training data. Prior works mitigate this challenge by aligning features in a unified space via model retraining or per-agent-type interpreters. These strategies (a) require access to neighbor configurations, (b) do not fully address real-time CP deployment, and (c) generalize poorly to unseen agents joining at run time. To overcome these challenges, we present PEARL, a Prompt-Embedding framework for Anonymous and Real-time Lightweight heterogeneous CP. PEARL supports multiple CP interpreters and selects one for a new-joining agent in real time using two lightweight, multi-scale interpreters trained in parallel: a sparse-detection (LWSD) interpreter that aligns salient regions for cooperative detection, and a dense, domain-invariant (LWDDI) interpreter that produces agent-invariant features for fast interpreter selection. Both interpreters use low-rank visual prompts to reduce computation, storage, and model complexity. Extensive experiments on simulated (OPV2V, V2XSet) and real (DAIR-V2X) datasets show that PEARL generalizes across simulated and real-world cooperative driving scenarios. Its real-time model-selection strategy yields an 8.2% Average Precision (AP) gain over a random-selection baseline while running in 1.67 ms on average. Although primarily designed for real-time CP, PEARL also outperforms state-of-the-art heterogeneous CP frameworks under traditional offline training by 5.6% AP on average while reducing communication cost by up to 34.7 times. Equally important, PEARL does not require sharing agents' configurations or model settings, thereby protecting information that may be proprietary or private. These results establish PEARL as a scalable and practical framework for heterogeneous collaborative perception. --- ### From greenhouse climate to individual leaves: an organ-resolved model of lettuce growth Authors: Md Hasibur Rahman, Faraz Ahmed, Hafiz Muhammad Bilal, Daniel Wells, Dylan Tobin, Tanzeel U. Rehman Published: 2026-09-22 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.27118v1 Greenhouse climate management aims to improve crop production while limiting energy use. This requires knowing how a crop will respond before conditions are changed. A crop digital twin can support this decision only if it represents how plant physiology and structure develop together. A unified framework was developed to simulate lettuce growth from the physiology of individual leaves. Each leaf received the conditions at its position in the canopy and contributed carbon through photosynthesis. Part of this carbon was used for maintenance and the remainder supported growth, distributed among leaves by their age, size and local environment. The predicted leaf mass, area and age generated an evolving three-dimensional plant in NVIDIA Isaac Sim. Ray tracing calculated the radiation intercepted by each leaf and returned it to photosynthesis, so structure and growth influenced each other over time. Against greenhouse measurements, the relative root mean square error was 9.5% for total dry weight and 9.2%, 12.7% and 13.1% for leaf number, canopy diameter and largest-leaf area, respectively. A 30% decrease in incident radiation reduced final dry weight by 10.4%, while the same increase raised it by 6.9%, and adding 200 ppm carbon dioxide raised it by 46.1%. Within a simulated 40-plant block, interior plants accumulated 8.6% less dry weight than border plants with identical initial states, and the leaf-specific tipburn index rose in the enclosed leaves over the period in which tipburn appeared on the greenhouse plants. Resolving individual leaves therefore explains how local exposure changes plant growth within the greenhouse. The framework provides the forward plant model needed for a bidirectional digital twin, where observations of the physical plant can update predictions and support greenhouse climate decisions. --- ### Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models Authors: Ünsal Öztürk, Vedrana Krivokuća Hahn, Sushil Bhattacharjee, Sébastien Marcel Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27115v1 A face recognition model links two images of a person recorded on separate occasions when their embedding similarity exceeds an operating threshold. We consider making chosen identities unlinkable across separate occasions while the model remains in service for the rest of the population. Deleting their images and retraining does not achieve this, since the model recognises identities never observed in training. Therefore, the embedding space must be altered against these identities, the process of which we call open-set adversarial forgetting. We propose three loss functions, one that disperses an identity's embeddings from their centroid, and two that map each image onto its own near-orthogonal target, learnt with the classifier head or fixed in advance as an almost-orthonormal frame. Each is fine-tuned alongside the classification objective on a subset of each identity's images. We evaluate them against four methods from prior work in verification and identification, at two forget scales and three backbones. Every loss acting on the embedding geometry makes the forget identities nearly unidentifiable. The orthonormal frame alone achieves strong forgetting, which holds wherever an image of that subset enters the comparison and leaves distinct forget identities unlinkable. It also surpasses a concurrent unsupervised method at a higher retain rate. ---