# Research Papers — 2026-09 · bundle page 79 of 266 > Full-text markdown of papers #3901–3950 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/79 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/78.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/80.md) ### Gauss What You Need: Compact Gaussian Splatting Across Scene Scales Authors: Afif Boudaoud, Jiayi Liu, Alexandru Calotoiu, Torsten Hoefler Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31248v1 3D Gaussian Splatting reconstructs a scene as a collection of Gaussian primitives from a set of posed photographs called the capture. The number of primitives used to represent the scene affects reconstruction quality, storage, and rendering cost. How to select this number automatically across capture scales remains unresolved: configurations effective on standard benchmarks can leave larger captures with too few Gaussians to reconstruct fine details. We observe that the surface to represent, given by the capture's extent and resolution, is known before training, whereas its content complexity becomes apparent during training, through the reconstruction quality on the training views. We introduce TangoGS, which combines capture-derived model sizing with training-based adaptation: the capture determines the scale of the model, and training feedback determines its final size within that scale. Before training, TangoGS derives a learning allowance for model growth from the capture's total pixels after discounting views that re-observe the same scene points. During training, reconstruction quality guides how many Gaussians to add and remove. On 13 standard benchmark scenes, TangoGS matches the mean PSNR of the best-performing evaluated baseline, LeGS, with $48\%$ fewer Gaussians. On eight large captures, the same configuration automatically scales to larger models when necessary, achieving the highest mean PSNR among evaluated methods: $0.54$ dB above the runner-up with $2.3\times$ as many Gaussians. Together, capture-derived learning allowances and training-quality guided density control enable a state-of-the-art quality--size compromise across scene scales without retuning. --- ### Geometric Inconsistency Localization in Multi-View Image Sets Authors: Xander Staelens, Albéric Loos, Bert Ramlot, Hannes Mareen, Peter Lambert, Glenn Van Wallendael Published: 2026-09-25 Categories: cs.CV, cs.AI, cs.CR, cs.MM arXiv: https://arxiv.org/abs/2609.31247v1 Novel view synthesis (NVS) models can produce realistic new views of the same scene from different viewpoints. However, these generated views are not always geometrically consistent with one another. Multi-view (MV) consistency has shown promise as a tool for evaluating these NVS models. Its potential for multimedia forensics, however, remains largely unexplored, particularly for localizing geometric inconsistencies across wide-baseline image pairs. To enable research in this direction, we introduce DeformView, a wide-baseline MV dataset with pixel-level annotations of geometric inconsistencies. Using DeformView, we evaluate state-of-the-art MV consistency-scoring methods and show that approaches developed for NVS evaluation transfer poorly to the forensic task of geometric inconsistency localization. To address this limitation, we propose DEFECt3R, a lightweight learning-based classifier that uses cross-view feature relationships to localize geometric inconsistencies at the pixel level. By learning from explicit supervision, including hard negatives from geometrically consistent yet deformed views, DEFECt3R improves localization performance and substantially reduces false positives compared to existing consistency-scoring methods. Ablation experiments further show that both feature representations and correspondence quality contribute to localization performance. Overall, our findings demonstrate that MV geometric consistency is a promising yet underexplored signal for multimedia forensics and establish a benchmark and baseline for geometric inconsistency localization in wide-baseline MV image pairs. Code and dataset are available at https://github.com/IDLabMedia/DeformView-DEFECt3R --- ### RupeeBias: Auditing Demographic Bias in Indian Economic Guidance from Large Language Models Authors: Pavithra P M Nair, Bhavik Talaviya, Shourya Bhushan, Rahul Pankajakshan, Seema Guruvadoo, Avinash Agarwal, Gilad Gressel, Krishnashree Achuthan Published: 2026-09-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31245v2 Individuals turn to large language models (LLMs) for guidance across a wide range of economic tasks, from comparing loan options and planning savings to deciding what raise to ask for or how much to charge for their services. LLMs are known to reproduce social biases, and biased economic guidance may influence what users believe they are worth, what they ask for, and what they ultimately accept. This risk is especially salient in India, where economic outcomes are shaped by demographic categories such as caste and urban-rural location. Existing LLM bias benchmarks, however, are largely designed around Western demographic categories and therefore miss key axes of economic disparity in the Indian context. We introduce RupeeBias, a benchmark for auditing demographic bias in LLM-generated economic guidance across Indian economic settings. RupeeBias consists of 39,150 prompts spanning four use cases: salary estimation, salary increment estimation, counter-offer recommendation, and service pricing recommendation. The benchmark follows a single-attribute counterfactual design, holding the description of the user's qualifications, experience, or service offering fixed while varying one demographic identifier at a time. RupeeBias covers 87 India-specific demographic identifiers across six axes: caste, religion, regional identity, gender, disability, and urban-rural location, with all prompts constructed in both English and Hinglish. We evaluate nine LLMs on RupeeBias and find systematic demographic disparities across all six axes. For otherwise identical prompts that differ only in demographic identifier, LLM-generated economic outputs differ by 20.2% on average. We publicly release RupeeBias to support future research on demographic bias in LLM-generated economic guidance across India-specific demographic and economic contexts. --- ### Purin: A Biology-inspired Mechanism for Artificial Neural Networks Authors: Zishu Liu, Chunbo Luo, Christos Grecos Published: 2026-09-25 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2609.31235v1 Artificial neural networks (ANNs) usually represent neural transmission with fixed trainable weights during a training batch, which omits short-term changes in synaptic efficacy. In addition, the discrete time-step simulation requires additional temporal processing that many conventional ANN architectures do not use. To overcome these challenges, we propose Purin, a biology-inspired and ANN-compatible mechanism, that introduces synaptic efficacy modulation into conventional convolutional neural networks. Purin uses a time-interval-based abstraction for neural activities, which allows Purin to introduce short- and long-term synaptic efficacy changes without using discrete time-steps. Purin introduces a bounded factor to represent temporary synaptic efficacy changes, together with two weight matrices that represent input-side and output-side efficacy. The weight matrices are updated by backpropagation and interpreted as the long-term synaptic efficacy changes. Experimental results show that after removing the confounding factors in the AlexNet, VGG11, and GoogLeNet architectures, Purin improves the classification accuracies in all three models across the evaluated datasets. --- ### WeaveAgent: A Two-Stage Tool-Routing Agent for Ultra-High-Resolution Remote Sensing Imagery Authors: Zhongyu Pang Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31234v1 Problem. Ultra-high-resolution (UHR) remote sensing with vague user intents has two bottlenecks: visual tokens are expensive, and tool calling must be format-reliable (pretrained models emit zero tool calls zero-shot). Method. WeaveAgent, a two-stage tool-routing agent, decouples routing from visual perception. Stage A is routing-first: emission is trained, not elicited. Stage B executes conditionally: intrinsic queries enter visual answering (full-scene thumbnail; a WeaveEarth-style evidence board as an optional fixed-budget, approx. 5k-token compression interface); extrinsic queries execute tool call on original full-resolution imagery, answering from tool observations in a second, observation-masked round. Training: alignment SFT, then GRPO under reward R_WA2. Results. Alignment SFT lifts extrinsic routing from 0% to 80.75% (323/400); GRPO suppresses 9 intrinsic mis-emissions while tool selection is unchanged. The trained 2B system does not beat the zero-shot 8B baseline overall (0.263 vs. 0.250), a diagnostic contribution. Oracle attribution separates two repair ingredients: loading the observation into context lifts extrinsic answer accuracy from 0.025 to 0.425 under marker-free cross-mode returns, and the two-turn SFT stage adds a further +9.3 points to 0.518 at a small routing cost. A +/- image ablation shows emission suppression is visually grounded, and a query-register matrix shows LLM-rewritten queries cost trained checkpoints 2-11 points. Scope. All training and evaluation use the 5,000 / 3,273 / 1,000-record VagueUHR corpus (600 intrinsic + 400 tool-requiring; the base seeds synthesis and is not used for optimization). Single-pass evidence construction runs at 7.31 s per image on an RTX 4090. Code, data, and evaluation protocols will be released. --- ### Acoustic-to-Text KV Compression for Full-Duplex Speech Models Authors: Yejin Lee, Seungbeom Kim, Yongha Lee, Kyuhong Shim Published: 2026-09-25 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2609.31224v1 Full-duplex speech language models continuously accumulate acoustic key-value (KV) states, making long-running interactions memory-intensive. During listening, the model can finish processing an audio unit before the next arrives; we term the remaining interval listening-time slack. We propose acoustic-to-text KV compression, which introduces a transcription side channel to convert incoming speech into compact textual memory within this interval. When the cache exceeds a target budget during inference, older acoustic states are evicted while transcripts and recent acoustic context remain. We train the side channel with LoRA using cross-entropy on transcription segments. To preserve listening and speaking behavior, we apply knowledge distillation to the original model's token-level output distributions at native prediction positions. On ten-minute LongSpeech sessions, our MiniCPM-o 4.5 implementation reduces peak streaming KV-cache size by 64.6% compared with the same model without eviction. The proposed method also improves transcription, temporal question answering, and summarization over the baseline. Full-Duplex-Bench evaluations further show comparable pause-handling, turn-taking, and interruption performance. --- ### Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion Authors: Xinyu Wang, Jinbo Bi, Minghu Song Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31222v1 Pocket-conditioned molecular diffusion updates ambient atom coordinates, but many lead-optimization objectives are expressed on quotient features such as distances, contacts, and anchored substructures. We introduce budgeted quotient-residual guidance (QRG), an inference-time correction that makes these quotient objectives active without retraining the molecular generator. QRG lifts quotient covectors to metric-horizontal ambient directions and delivers them through a trust budget set by the frozen sampler's own step norm: quotient geometry chooses the direction, while sampler motion bounds the scale. We derive the horizontal lift, closed-form sampler-budget update, KL/kinetic interpretation around a frozen reverse step, equivariance conditions, and a product-budget split for budget-capped section and residual controls. Controlled quotient tasks confirm that sampler-relative delivery activates signals that raw local quotient gradients leave dormant. On frozen TargetDiff backbones, official seed-0 CBGBench ligand-generation/editing sweeps show practical quality-runtime gains: Local-QRG improves validity from 0.815 to 0.864 on fragment growing, 0.664 to 0.707 on scaffold hopping, and 0.681 to 0.712 on linker design, while PredNext-QRG improves fragment/scaffold and remains near-neutral on linker. Novelty remains 1.000 and diversity is preserved in the matched multi-seed molecular slice, giving task-dependent improvements without sampler retraining or backbone modification. Overall, QRG provides a lightweight route to quotient-aware inference for frozen molecular samplers with explicit runtime accounting. --- ### DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration Authors: Zesheng Cai, Yingqi Fan, Sichang Chen, Jin-Hong Du Published: 2026-09-25 Categories: cs.AI, stat.AP, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.31215v1 Large language models (LLMs) as a judge enable scalable evaluation, but their judgments can be sensitive to response order and, even after removing such position effects, can still diverge systematically from human preferences.We introduce DIAL, a unified framework that combines abundant LLM comparisons with limited human comparisons to separate judge-specific position effects, learn shared structure in position-debiased LLM preferences, and adaptively calibrate that structure toward the human preference target. Theoretically, we study three aspects of DIAL: (i) identification of latent LLM preferences, position effects, and human calibration; (ii) adaptive estimation that balances LLM anchoring against limited human evidence; and (iii) fixed-weight uncertainty quantification for the calibrated human preference. Empirically, we evaluate position debiasing and human alignment separately in controlled simulations and on three human-preference benchmarks, showing that DIAL remains robust to unbalanced response order, achieves strong human-aligned rankings with limited labels, and adapts toward human evidence when LLM information is imperfect. Our real-data study collects over 410K judgments from 21 LLM judges in both display orders, providing a resource for future studies of LLM-judge bias, heterogeneity, and human alignment. --- ### Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution Authors: Zhe Li, Wei Zhao, Peixin Zhang, Jun Sun Published: 2026-09-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31214v1 Estimating the influence of training examples on model behavior is essential for data debugging, valuation, and attribution. Existing influence estimators often produce incompatible rankings, which are commonly ascribed to approximation error. We argue that a more fundamental source of disagreement is specification mismatch: influence depends on the behavior being attributed, the intervention applied to each training example, and the counterfactual training process that maps the intervention to a model response. These choices are especially important when the target behavior requires a tractable surrogate, such as query loss, a logit, or a margin. We formalize influence as a counterfactual estimand, distinguish specification mismatch across estimands from approximation error in estimating a fixed estimand, and organize representative estimators by their implied specifications. We further derive a local decomposition that exposes how behavior signals, training signals, and counterfactual parameter responses interact. Controlled experiments show that exact estimands under different specifications can induce different rankings, whereas approximation error grows as perturbations move farther from their linearization points. Experiments on noisy label detection and LLM attribution show that specification choices significantly affect attribution quality, especially for the choice of behavior surrogate. Behavior-aligned specifications can identify target-specific training examples obscured by default loss-based or similarity-based specifications. These results establish specification analysis as a necessary first step for interpreting and comparing data influence estimators. --- ### Enabling a Unified Cross-Domain Representation for Two-Finger Gripper Manipulation via Interaction-Centric Modeling Authors: Guanlin Li, Shifeng Bao, Yihan Zhao, Haitao Shen, Haoyang Li, Chen Zhao, Tong Yang, Jie Tang, Jing Zhang Published: 2026-09-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.31207v1 Achieving robust cross-embodiment generalization in imitation learning demands overcoming a critical representation flaw that inextricably entangles task semantics with hardware-specific visual geometry. We propose an interaction-centric framework that leverages the shared structure of two-finger grippers via a parameterized universal gripper abstraction, yielding a canonical gripper-frame representation. Given language and RGB-D observations, a VLM infers the subtask and grounds an interaction triplet (gripper, held, target), while SAM~2.1 tracks masks to reduce VLM queries. We design concise hybrid features that combine target/collision artificial potential fields for global guidance with segmented gripper-frame point clouds for local geometry, and use a Flow-Matching Transformer to predict smooth 7-DoF action chunks. Experiments in simulation and real-world tasks demonstrate that ours is the first imitation learning approach to simultaneously achieve competitive benchmark scores and extreme cross-embodiment/cross-viewpoint zero-shot sim-to-real transfer to completely distinct, heterogeneous robot platforms. --- ### Self-Supervised Representation Learning: From Spectral Foundation Models to Auroral Emission Spectra Authors: Matthieu Le Lain, Gaël Cessateur, Sébastien Lefèvre Published: 2026-09-25 Categories: cs.LG, physics.space-ph arXiv: https://arxiv.org/abs/2609.31206v1 Auroral spectrographs such as the Auroral Spectrograph In Skibotn (ASIS) record hundreds of thousands of emission spectra, but only a few hundred can be labelled by an expert. To exploit the rest, we pretrain a 1D Vision Transformer with a masked autoencoder on 223,000 unlabelled spectra. Without labels, its representation recovers the emission-line intensity ratios that physicists use to diagnose the precipitating particles (R^2 0.91 vs. 0.77 for an untrained control) and, under one linear probe, classifies as well as 13 features designed by experts. Fine-tuned, the model outperforms the previous supervised auroral classifier on its own benchmark (macro-AP 88.5 vs. 77.8), reaches 0.870 mAP, and exceeds the same architecture trained from scratch by +0.159 with 10% of the labels; attribution shows that it uses both N2+ bands. Could an existing pretrained model replace it? Two astronomical spectral foundation models and a time-series model transfer according to their spectral window: SpectraFM, trained in the infrared, falls below the untrained control, whereas SpecFormer, trained in the optical, approaches in-domain pretraining without reaching it. --- ### FlatClip: A Geometry-Aware Surface-Level Baseline for fMRI Representation Learning Authors: Mo Wang, Wenhao Ye, Zihan Ning, Jiayu Zuo, Junfeng Xia, Hongkai Wen, Quanying Liu Published: 2026-09-25 Categories: cs.CE, cs.CV, q-bio.NC arXiv: https://arxiv.org/abs/2609.31204v1 Recent fMRI foundation models differ substantially in the spatial scale at which they represent brain activity. ROI- and connectivity-based models are efficient but coarse, whereas voxel-level models preserve fine-grained spatial structure but require specialized 3D/4D architectures and costly fMRI-specific pretraining. We ask how effectively an image-pretrained encoder can reuse the spatial organization of cortical activity. Motivated by evidence that macroscale brain activity is strongly constrained by brain geometry, we introduce FlatClip, a frozen-encoder surface-level baseline that renders cortical activity as geometry-aware flatmap sequences and reuses a frozen SigLIP2 image encoder with only a lightweight downstream probe. Across resting-state benchmarks, FlatClip serves as a competitive middle-ground representation, outperforming ROI-level baselines on HCP and ADNI tasks while remaining weaker on PPMI and below the strongest voxel-level models overall. On visual-fMRI decoding, restricting the input to visual or NSD-provided task-active cortex improves performance, highlighting the value of task-relevant cortical coverage. Spatial perturbation controls reduce the predictive performance of flatmap features under both retrained and fixed readouts, and anatomy-linked arrangements consistently outperform vertex permutations across three colormaps. Together, these results position surface-level flatmap sequences as a practical middle-ground baseline between ROI and voxel models, and support the utility of anatomy-linked spatial organization for reusing image-pretrained features. Code is available at https://github.com/OneMore1/FlatClip. --- ### Preserve-and-Compose Training for Composed Image Retrieval Authors: Sehyun Kwon Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31202v1 Composed image retrieval (CIR) aims to retrieve images that satisfy a user-specified modification while preserving relevant visual content from a reference image. Collecting target images for this purpose is costly, motivating zero-shot CIR methods that instead use target captions as supervision. However, target captions may omit source details that should be preserved. We therefore propose, Preserve-and-Compose Training, which complements target-caption supervision with visual evidence from the source image. PACT learns from image--text--text (ITT) triplets without target images or gallery updates, aligning composed queries with target captions while preserving source evidence through visual supervision. We further introduce Chord scoring, which combines target similarity with source-relative directional agreement in the frozen image space. Results across four ZS-CIR benchmarks show that combining target-caption supervision with source-image evidence leads to strong retrieval performance across datasets, backbone scales, and external galleries. The code is available on https://github.com/sehyunkwon/PACT. --- ### Samples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture Authors: Christian Schiffer, Mathis Bode, Thomas Lippert, Katrin Amunts, Timo Dickscheid Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31201v1 Scaling studies typically represent training data by a single count of samples. For hierarchically and spatially structured data, however, the same number of samples can be drawn from few or many sources and distributed differently across the underlying domain. We therefore study data scaling as an allocation problem, separating unique sample count, source diversity, and spatial coverage. We study this decomposition in microscopic whole-brain histology, where a source is an individual brain, and a sample is an image patch at a specific spatial location. Across 93 controlled pretraining runs of a contrastive model that uses spatial proximity for supervision, we vary data allocation, compute, and model capacity over 11.6 million spatially anchored image patches from 21 human brains. Performance improves with more unique samples, broader spatial coverage, additional compute, and larger model capacity. At fixed sample count, distributing samples across one to 18 subjects produces no detectable improvement, even though representations generalize substantially better to subjects encountered during pretraining. Inter-subject variation therefore strongly affects generalization, but additional subjects provide no benefit when a fixed sample budget is distributed across more sources. These results establish sample count, source diversity, and spatial coverage as distinct axes of data scaling in spatially structured representation learning. --- ### Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning Authors: Antoine Lorentz, Stéphane May, Valentine Bellet, Dawa Derksen, Bastien Nespoulous Published: 2026-09-25 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.31199v1 Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D maps are often contaminated by noise, outliers, and voids. On the other hand, aerial LiDAR provides high-accuracy elevation measurements at a substantially higher cost. In this work, we study diffusion models conditioned both on photogrammetric DSMs and Pléiades imagery to refine vertically co-registered DSMs. We introduce a modified Stable Diffusion 3 architecture with a pruned text stream and a patch-wise normalization strategy, enabling stable training on LiDAR data and transfer from natural images to elevation maps. Experiments in French cities demonstrate that multimodal conditioning improves elevation accuracy, reducing Dense Urban RMSE from 6.00 to 3.45 m in the in-context cities and from 4.16 to 2.77 m in the held-out city of Bordeaux. --- ### Light Field Primitive for Novel View Synthesis Authors: Liang Chen, Jiahui Ning, Xun Jiang, Xing Xu, Jimmy Ren, Fenglei Fan, Heng Tao Shen Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31198v1 We present Light Field Primitives (LFP), a formulation for novel view synthesis that replaces the dense ray database with a compact set of differentiable primitives in the classical two-plane parameterization. Each primitive condenses a group of rays into one learned record, and its response to a query is governed by how closely that query belongs to the group. Rendering a camera ray then reduces to compositing all responses it elicits, and a scene can be optimized directly from posed images and rendered in real time with rays. Beyond its competitive performance on standard benchmarks, the main advantage of LFP is structural: its primitives reside directly in the 4D ray space, so optical and appearance effects that are already operations on the light field become behaviors of a single shared renderer. With minimal changes to that renderer, LFP supports multi-scale anti-aliasing, defocus deblurring with refocusing, rendering for fisheye cameras, and even transparent object reconstruction with ray refraction, matching specialized frameworks that devote substantial machinery to these effects. --- ### ALF: An Active Learning Framework for Scientific Discovery Authors: Shikha Surana, Alex Hawkins-Hooker, Olivia Gallup, Christoph Brunken, Jules Tilly, Paul Duckworth Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31197v1 Machine learning for scientific discovery is almost systematically data bound. Producing relevant high quality data, under budget constraints, is amongst the most promising ways to advance the field. Active learning (AL) offers promise wherever labelling requires expensive experiment, measurement, or simulation. Most existing tools cover only part of the data acquisition loop, and typically focus on either offline benchmarking or online deployment, but not both. We present ALF, a modular AL Framework that runs the full data acquisition loop via five modular components. One clear API for both settings: offline, against an existing dataset for controlled and reproducible experimentation; and online, against an oracle for acquiring new candidates in real-world deployments. ALF is open-source and available at https://github.com/instadeepai/alf. --- ### Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs Authors: Jihoo Jung, Youngjoon Jang, Joon Son Chung Published: 2026-09-25 Categories: cs.CV, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2609.31193v1 Current Audio-Visual LLMs (AVLLMs) struggle with reasoning over videos featuring multi-speaker dialogues. In such videos, resolving "who says what" is crucial, which necessitates trimodal (text-audio-visual) binding. Motivated by these challenges, we systematically investigate how this trimodal binding is achieved in AVLLMs. Specifically, we identify emergent symbolic trimodal binding mechanisms in AVLLMs that utilize modality-specific symbolic variables. By encoding auditory and visual components into symbolic variables-capturing temporal utterance sequences and spatial entity coordinates, respectively-the model establishes cross-modal linking within this abstract space. Crucially, we reveal that when trimodal binding fails, the breakdown predominantly stems from misaligned audio-visual connections. To overcome this bottleneck, we introduce an audio-visual prompting method utilizing an off-the-shelf Active Speaker Detection (ASD) model. By simply overlaying visual bounding boxes on active speakers, this training-free approach yields immediate performance gains across four conversation-centric benchmarks. Moreover, lightweight fine-tuning of fewer than 300 steps on these ASD-prompted-videos extends these gains to three general AV benchmarks, suggesting the generalizability of our method. --- ### Rethinking Data Quality for AI-Driven Systems: Evidence from Practitioner Interviews Authors: Hariharan Gopinath, Jan Bosch, Helena Holmström Olsson Published: 2026-09-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.31191v1 Data quality research has usually treated data as an input that is stored, processed, and validated. In AI-driven software-intensive systems, data also shapes model behavior, evaluation, and lawful use. Empirical evidence remains limited on how practitioners define, assess, and manage quality under these conditions. We interviewed 16 practitioners from nine organizations and analyzed the transcripts using reflexive thematic analysis and developed six themes from participants' accounts. In AI systems, traceability shifted from modular debugging to attributing model behavior, while using models as quality assessors introduced circularity. Agent context and memory became data objects, and synthetic and pseudo-labeled data made authenticity a quality concern. In foundation-model development, lawfulness became a gate for training data, while representativeness was judged through coverage of situations in which the system must behave safely. Prior ML research examines many of these problems separately. Our study provides a practitioner-grounded account of how they are encountered together as an engineering and organizational concern. We also interpret five recurring conditions as helping explain how the themes relate to reduced trust in data and AI outcomes. We synthesize these findings through lifecycle assurance: a conceptual framing focused on producing evidence that data can support a specific AI claim when its influence may be embedded in model behavior, model-based judgments, or agent actions. --- ### Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation Authors: Chang Gong, Jingping Bi, Di Yao, Xinjian Liang, Chao Xiang, Ruijie Guo Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31186v1 Artificial intelligence is advancing rapidly, with increasingly capable systems taking larger roles in reasoning, decision-making, scientific discovery, and autonomous development. As AI begins to participate in its own improvement, from model training and experience accumulation to agent evolution and automated AI development, the prospect of recursive self-improvement (RSI) is becoming increasingly relevant. This transition raises a fundamental safety question: how can safety be maintained when the system, its accumulated experience, and even the process producing its successors continue to change? We introduce Evolutionary Safety as a perspective for studying safety under persistent and recursive self-improvement. It concerns not only whether an AI system is safe at a particular moment, but how safety properties change, persist, accumulate, and propagate throughout evolution. We characterize recurring manifestations, including intent drift, error accumulation, experience contamination, safety-property erosion, evaluator drift, and risk propagation. We then develop a taxonomy spanning persistent agent state, model state, evaluation and environmental feedback, computational substrate, and meta-level update mechanisms. Building on this taxonomy, we examine how evolutionary risks can be discovered and evaluated across states, updates, trajectories, and lineages, and derive governance principles for modification, selection, authorization, provenance, and recovery. Finally, we outline open problems toward maintaining safety guarantees as AI systems become increasingly persistent, adaptive, and recursively self-improving. Project resources and proposed evaluation systems are available at https://chaunceykung.github.io/evolutionary-safety-rsi. --- ### Accounting for Bias Enables Sustainable LLM Evaluation Authors: Harshita Katoch, David Antony Selby, Gerrit Großmann, Sebastian Vollmer Published: 2026-09-25 Categories: cs.AI, cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2609.31184v1 LLM-as-a-judge has become the de facto standard for scalable, subjective evaluation, yet current leaderboards compensate for systematic measurement bias by running ever more comparisons, an approach that is both statistically unsound and computationally wasteful. The root cause is an incomplete measurement model, treating LLM judges as neutral, interchangeable instruments ignores documented biases like position bias, verbosity bias, judge severity, and self-enhancement, that no volume of additional data can eliminate. We propose a unified latent variable framework that jointly models pairwise and ordinal data while explicitly correcting for these confounders, recovering reliable rankings from substantially fewer comparisons. Because fitting this model costs negligible compute relative to a single round of LLM inference, bias correction is not only more statistically rigorous but also a more sustainable approach to trustworthy evaluation. --- ### Where a Model Sends Its Own Repeated Token Authors: Nicolás Vera Zúñiga Published: 2026-09-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31181v1 Black-box model identification works by scoring a model's response to natural-language prompts. One line of work feeds models a degenerate input -- their own token, repeated -- to find a failure mode rather than an identity. We take that input and ask where the model goes when it does not. For each token t, read argmax p(. | t, t) in one forward pass; the result is a map on the whole vocabulary, with two halves. The first -- which tokens are fixed points -- is partially anticipated, and we report it as a failed estimand: the natural distance on it is 83% cardinality, separates a corpus manipulation by two bits in 3471 against a precision floor of zero, and attributes families at 0.5833. The second half, where the map sends tokens that are not fixed points, is unrecorded; the one paper holding those tokens logged them as a zero. Pairing on the source token removes the cardinality confound by construction (r from 0.9128 to -0.0932) and attributes families at 0.8333 -- twelve models scored against a pool of nineteen -- with chance 0.1389, across seven tokenizer groups and several corpora. Two nulls clear it: frequency-matched destinations agree at 0.1429, independent marginals at 0.0798. Family predicts agreement better than tokenizer (0.2031 against 0.1205), and recurrent architectures cluster at balanced accuracy 1.0 against a 0.7895 majority rate, or 0.90 once each model's dominant destination is excluded -- the figure we stand behind. We measure the robustness envelope: 8-bit weight rounding moves the map less than deduplicating the training corpus does (0.9004 against 0.6353, on one support), 4-bit destroys it (0.0098; 0.1812 at deployment granularity, so not a coarseness artefact), and the precision floor varies by model from 0.201 to 0.9778. All estimands and kill conditions were registered before the data, and the failed one is reported as fully as the surviving one. --- ### BAT-CLIP: Trimodal Alignment of Brain, Audio and Text Authors: Suhyun Kim, Jinmo Han, Danny Dongyeop Han, Ahhyun Lucy Lee, Jewoon Lee, Yonghyeon Gwon, Zach Paris, Chun Kee Chung, Saewoong Bahk, Nam Soo Kim, Seong Jae Hwang, Jiook Cha Published: 2026-09-25 Categories: cs.SD, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2609.31180v1 Decoding and interpreting naturalistic speech from the brain increasingly relies on alignment to pretrained speech and language representation spaces. However, current CLIP-style brain-speech alignment ground neural activity to a single anchor modality-audio or text-despite the brain's inherently multimodal speech processing. This induces a trade-off: audio anchoring preserves temporal structure but weakens linguistic separability, while text anchoring captures semantics yet discards acoustic detail. We propose BAT-CLIP, the first CLIP-style trimodal alignment framework for iEEG that jointly aligns neural embeddings to both pretrained audio and text anchors in a shared, frozen audio-text manifold. On the naturalistic Podcast benchmark, BAT-CLIP yields more robust representations than bimodal CLIP baselines. We also highlight the importance of using self-supervised foundation models for CLIP training. --- ### SPO: Discovering Adaptive Large Neighborhood Search Operators via Stackelberg Program Optimization Authors: Xinyi Ke, Kai Li, Junliang Xing, Yifan Zhang, Jian Cheng Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31179v1 Large neighborhood search (LNS) relies critically on destroy and repair operators, whose effectiveness depends on both adaptation to the evolving LNS state and interaction between the two roles. We introduce Stackelberg Program Optimization (SPO), an LLM-based framework for discovering adaptive executable destroy-repair programs. SPO conditions operator decisions on a compact LNS state, allowing state-dependent behavior to emerge through program discovery, and organizes destroy-repair discovery as a Stackelberg interaction over program space that reflects their asymmetric dependency. Role-specific credits evaluate destroy programs as leaders and repair programs as conditional follower responses, guiding a coupled optimization process that combines LLM generator learning with population-based evolutionary search over programs. Experiments on the traveling salesperson problem and capacitated vehicle routing problem show that SPO outperforms strong baselines across a broad range of settings and generalizes beyond the discovery scale to larger instances and benchmark sets. Behavioral analyses further demonstrate state-dependent operator behavior and coupled destroy-repair improvement during discovery. --- ### Semantic Navigation for Issue Localization in Code Repository Authors: Yunxiang Wei, Zhenyu Lei, Jundong Li Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31176v1 Repository-level issue localization aims to identify and rank the files and functions relevant to resolving a reported issue. LLM agents approach this task iteratively: they identify a set of potentially relevant locations, inspect the corresponding code, and revise their judgments about these candidates as new evidence is acquired. Existing environments, however, provide limited support for this loop: agents must search for unresolved relation targets, reconstruct entity semantics from raw source code, and revise candidates without evidential basis. To address these limitations, we present SemNav, a framework that leverages deterministic retrieval to seed a broad candidate set and an LLM agent to continually refine that set, thereby combining initial coverage with evidence-guided revision. SemNav supports this process through three key components. A Semantic Navigation Graph resolves program relations on demand through a language server, enabling direct navigation to related entities across files. Issue-conditioned Semantic Cards provide compact, source-grounded interpretations of each entity's role and relevance to the issue. A persistent Candidate Workspace records each candidate together with its evidential basis, enabling grounded verification, revision, and ranking. Across SWE-bench Lite and PLocBench, SemNav outperforms existing baselines, improving File Hit@10 from 68.33\% to 82.67\% with Gemma 4B. Component ablations and trajectory analysis support the complementary roles of all three components, while Semantic Cards reduce working-context load by 48.2\% relative to full-source reading. SemNav further ranks first on all seven evidence-quality metrics on SWE-Explore and improves downstream issue resolution from 44.00\% to 52.33\%. --- ### TaskIR: Task-Driven Image Restoration via Degradation Adaptation and Task Feedback Authors: Yanjie Tu, Qingsen Yan, Axi Niu, Wenxuan Cai, Tao Hu, Wei Dong, Haokui Zhang Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31170v2 Task-driven image restoration aims to improve both image quality and downstream task performance. However, existing methods predominantly focus on single degradation type and struggle to handle the diverse degradations encountered in real-world scenarios. Different degradations impose distinct restoration demands, and insufficient restoration may leave residual degradations and artifacts that impair object boundaries and semantic cues, thereby compromising downstream task performance. To address these challenges, we propose TaskIR, a two-stage task-driven unified image restoration framework that integrates degradation-adaptive restoration with task feedback refinement. In Stage I, a Degradation Representation Module (DRM) extracts degradation representations, enabling a Degradation-Guided Transformer Block (DGTB) to dynamically modulate feature transformations for adaptive restoration. In Stage II, a Task-to-Restoration Feedback Generation module (TRFG) transforms heterogeneous task features into restoration feedback by modeling task-representation discrepancies associated with the current restoration. Subsequently, a Selective Task Feedback Refinement module (STFR) assesses feedback relevance and selectively refines intermediate restoration features to mitigate interference with well-restored content. Extensive experiments demonstrate that TaskIR achieves competitive restoration quality and downstream task performance across diverse degradations and tasks. --- ### Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting Authors: Paweł Mąka, Piotr Andruszkiewicz, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis Published: 2026-09-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.31169v1 Multimodal Machine Translation aims to incorporate additional signal from non-textual modalities to improve translations by resolving ambiguities. While models, through multimodal fusion, are able to accept images related to the source text, they can ignore this information. Therefore, increasing their visual sensitivity remains an active research area. In this work, we introduce a training method, Metric-based Loss Weighting, that improves visual grounding of translations by increasing the loss function for tokens that benefit from the accompanying image. We identify these tokens using the Point-wise Cross-mutual Information (PCXMI) metric, which compares the model's output probabilities with and without visual context. We introduce a Congruency-based PCXMI metric and experimentally show that both metrics working in combination yield the best results. We evaluate our method by fine-tuning three pretrained Multimodal Large Language Models on the task of Image-guided Machine Translation for three language directions. Metric-based Loss Weighting outperforms other tested methods on the CoMMuTE contrastive dataset, improving accuracy by up to more than 7 percentage points compared to standard fine-tuning, while maintaining strong general translation performance. --- ### Audio emotion recognition for atypical hearing Authors: Ulysse Roussel Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31168v1 My doctoral work aims to explore Audio Emotion Recognition (AER) in the context of atypical listening. This research focuses on auditory hypersensitivity in people with autism, a phenomenon that is often difficult to evaluate and unique to each individual. Our core idea is to leverage our understanding of affect from acoustic traits, relying on the possibility of generalizing affective responses from a small amount of annotated data. As a first step, we fine-tune a large foundation model, Contrastive Language-Audio Pretraining (CLAP) using low-rank adaptation (LoRA), trained on a valence and arousal dataset of neurotypical listeners. --- ### Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models Authors: Kieren Yu, Ziyang Liu, Chang Huang, Jintai Chen, Kaishun Wu Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31167v1 EEG foundation models increasingly use masked prediction to learn from unlabeled recordings, but optimizing this objective does not ensure transferable neural representations. A central challenge is that stable positional cues and local correlations can make masked regions predictable without integrating distributed neural context. To reduce this reliance on low-information prediction paths, we introduce Neural State Prediction (NSP), a latent-predictive framework that constrains both the prediction target and the available context. NSP uses a Target Encoder updated by an exponential moving average (EMA) to define latent supervision. Identity residualization removes additive effects associated with channel identity and relative time from the targets, while topology-separated context excludes their immediate spatial and temporal neighborhood from the visible input. We pretrain NSP on 2.2 million EEG segments from TUEG and evaluate it across 30 downstream datasets spanning clinical diagnosis, sleep staging, emotion recognition, motor imagery, event-related potentials, cognitive-state decoding, and language retrieval. Under full-parameter multi-task fine-tuning on EEG-FM-Bench, NSP achieves 63.94 macro balanced accuracy across 14 datasets, exceeding the strongest evaluated baseline by 2.35 percentage points. Controlled component ablations assess the contribution of each mechanism, while matched context controls and held-out interventions characterize the role of context geometry, signal content, and positional information. Jointly designing latent targets and their context offers a promising direction for EEG foundation models that learn from distributed signal structure. --- ### AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side Authors: Ryoma Sato Published: 2026-09-25 Categories: cs.IR, cs.AI, cs.DB, cs.DL arXiv: https://arxiv.org/abs/2609.31166v1 Recommender systems have traditionally been developed for platforms. However, this has given rise to many phenomena that may be advantageous for platform lock-in but are a nuisance to users, such as clickbait, filter bubbles, and the spread of fake news. Recently, user-side recommender systems have been proposed as a new paradigm for solving this problem. If users deploy their own recommender systems, they are no longer at the mercy of the platform's interests. However, building a user-side recommender system is not trivial; in particular, customizing one for oneself requires additional data. We propose AgentRecommender, a method that leverages the investigation capability and internal knowledge of LLM agents to flexibly build user-side recommender systems without additional data. AgentRecommender allows users to easily create recommender systems tailored to their own preferences. --- ### BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio Authors: Sania Fatima Sayed, John W. Holloway, Reyer Zwiggelaar, Faisal I. Rezwan Published: 2026-09-25 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2609.31165v1 Speech-breath segmentation is a fundamental preprocessing step in respiratory audio analysis, enabling applications such as respiratory acoustic biomarker extraction, lung function prediction and disease monitoring. Existing approaches, including threshold methods, Fourier Transform-based techniques, and unsupervised and pretrained voice activity detection (VAD) models, primarily focus on speech detection and often classify breathing events as non-speech or silence, limiting their applicability for precise breath detection. To address this limitation, we propose BreathGRU, a semi-supervised Bidirectional Gated Recurrent Unit (BiGRU) framework specifically designed for speech-breath segmentation. The proposed framework combines frame-level acoustic feature extraction with bidirectional recurrent modelling, pseudo-label refinement and duration-constrained Segmental Viterbi decoding to produce speech and breath segmentation. BreathGRU was evaluated against the existing approaches, using manually annotated recordings. Performance was assessed using event-based, time-based, overlap-based, duration-based and boundary-based segmentation metrics. Experiment results demonstrated that BreathGRU achieved the highest breath event recall (0.83), the lowest onset-localisation error (0.14s) and the highest Mean Match Intersection over Union (0.81), with competitive overall segmentation performance compared to large pretrained VAD models like Silero. Qualitative evaluation on manually annotated recordings further showed close agreement between BreathGRU and manual annotation, with better breath detection compared to Silero. These findings demonstrate that explicit breath event modelling provides advantages over general-purpose VAD models and establish BreathGRU as an effective speech-breath segmentation framework which can be applied for respiratory audio analysis and pulmonary healthcare applications. --- ### SPADE: Escaping the Popularity-Similarity Frontier to Measure Serendipitous Recommendations Authors: Tobias Vente, Maarten Peirsman, Noah Daniëls, Hannu Toivonen, Bart Goethals Published: 2026-09-25 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31164v1 Recommender systems engineer serendipity to foster active exploration and break predictable consumption cycles. The problem with existing offline beyond-accuracy metrics is that they often either isolate historical similarity or global popularity. We aim to design an evaluation metric that examines similarity, popularity, and actual user relevance. To achieve this, we introduce SPADE (Serendipitous Pareto Distance Evaluation). SPADE maps all items into a two-dimensional space to directly calculate a user-specific Pareto frontier of maximally popular and historically similar items. The final serendipity score is then computed by averaging the minimum Euclidean distance from this boundary strictly for the correctly recommended test-set items. Evaluating SPADE across five datasets and five baseline algorithms confirms its effectiveness; our results show that the metric successfully prevents algorithms from exploiting beyond-accuracy measures with irrelevant or non-personalized recommendations, reliably isolating serendipitous discoveries. --- ### WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting Authors: Yuhan Zhu, Xiangfei Qiu, Hanyin Cheng, Wangmeng Shen, Chenjuan Guo, Bin Yang, Jilin Hu, Christian S. Jensen Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31162v1 Time series forecasting is typically framed as learning a direct mapping from historical to future observations in the observation space. However, sequences of observations generally provide only a partial view of the dynamics of the underlying system, with future observations being shaped by latent dynamics. Recent latent-space forecasting methods thus achieve improved performance by predicting future observations from latent-space representations of historical observations rather than directly forecasting future observations in the observation space. Next, while future observations are also shaped by external factors, how to incorporate external, often multimodal, information into forecasting, so that it can shape latent-state formation and evolution directly, remains underexplored. We propose WorldTS, a world-modeling based forecasting framework that integrates multimodal covariates directly into the forecasting to further improve forecasting performance. Specifically, WorldTS employs a two-stage training strategy. First, it learns forecasting-relevant latent state dynamics conditioned on multimodal covariates, yielding encoded future states. Next, the learned state dynamics are frozen, and an observation decoder is trained to map the predicted future states back to future observations. Extensive experiments on 21 real-world datasets offer insight into WorldTS and its effectiveness. --- ### I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms? Authors: Yuhang Liu, Zhuo Huang, Javen Qinfeng Shi Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31161v1 Recent empirical and theoretical advances suggest that joint-embedding predictive architectures (JEPAs) may learn meaningful representations for action-conditioned prediction of future outcomes, thus becoming one of the foundational structures for world models. However, accurate prediction does not, in general, necessarily imply recovery of underlying causal states that give rise to the observed dynamics. This work investigates when and how JEPAs can recover the underlying causal states from observations. We first introduce a latent variable model, in which high-dimensional observations are generated from latent causal states whose dynamics are governed by action-conditioned transition mechanisms. Based on this formulation, we develop a general information-theoretic objective that combines conditional likelihood maximization for learning transition dynamics with entropy maximization for preserving latent state information. We then establish identifiability conditions under which representations learned by this general objective recover the underlying latent causal states up to component-wise invertible transformations and permutation. One key condition for such identifiability is sufficient action-induced variation in the transition mechanisms. Guided by this finding, we instantiate the general objective with an action-modulated Gaussian additive-noise model, yielding action-modulated JEPA (A-JEPA). Experiments on synthetic environments verify the theoretical findings under the identifiability conditions and robustness to moderate violations, while visual benchmarks demonstrate improved state recovery and transfer to unseen transition mechanisms. --- ### ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation Authors: Donghang Lyu, Zichen Zhang, Oleh Dzyubachyk, Marius Staring Published: 2026-09-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31160v1 Vessel segmentation in medical images is essential for many clinical tasks, ranging from diagnosis to treatment planning. However, it remains challenging due to complex vascular morphology and diverse imaging conditions. Existing deep learning methods rarely aim at building a generalizable vessel segmentor across anatomies and modalities. While the Seg- ment Anything Model (SAM) has shown promise for med- ical image segmentation, its original design does not fully exploit vascular morphology and struggles with fine-grained vascular structures, leading to suboptimal performance. In this paper, we propose ReG-SAM, a SAM-based framework tailored to 2D vessel segmentation that leverages reference graph set for enhancing vascular representations. Specifically, we introduce two modality-aware representations derived from the reference masks: graph prompt embeddings (GPEs) that encode global spatial features from graphs, and vascu- lar prototype embeddings (VPEs) that capture fine-grained modality-specific vessel characteristics from multi-scale fea- ture maps and vascular masks. Since both require vascular masks that are unavailable during inference and require robust modality-aware vascular feature representations, we construct a modality-wise vascular database and develop two reference graph-guided representation learning schemes for estimating GPEs and VPEs using samples from the database rather than ground-truth masks. Extensive experiments across 19 datasets demonstrate that ReG-SAM consistently outperforms existing baselines, even those using manual prompts, particularly on challenging thin vessels. --- ### Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence Authors: Ahmed-Rafik Baahmed, Jean-François Dollinger, Amine Brahmia, Mourad Zghal Published: 2026-09-25 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2609.31159v1 We propose a momentum-guided federated split distillation framework for personalized, efficient, and autonomous temporal edge intelligence. We introduce TeRR-SAtt, our novel temporal reservoir student attention design that combines fixed reservoir representations, a lightweight temporal student, and personalized output modules. We also present AMGF, our anticipatory momentum-guided fusion mechanism that clusters clients through learning momentum and derives specialized teacher updates. On real-world smart-building data, TeRR-SAtt reduces edge training latency by 65.50%, inference latency by 44.70%, training memory usage by 18.40%, and inference CPU usage by 33.10% over the considered baselines. At the same time, AMGF improves local learning by up to 35.31% in RMSE compared to global updates. --- ### Bayesian Tensor Autoencoder with Physics-informed Predictive Prior for Multi-dimensional Time Series Anomaly Detection Authors: Jianan Liu, Chunguang Li Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31157v1 Multi-dimensional time series, inherently tensorial, are common in practice. Despite great progress in time series anomaly detection, most existing methods are confined to uni-/multi-variate time series. When handling multi-dimensional time series using these methods, reshaping operations are required, which inevitably break the intrinsic correlations and thus lead to performance degradation. In uni-/multi-variate time series anomaly detection, AutoEncoders (AEs) are widely adopted and generally categorized into reconstruction-based and prediction-based AEs. The reconstruction-based AE utilizes the current observation for reconstruction, while the prediction-based AE utilizes the historical information to predict the current observation. Thus, the two AEs utilize different information. To bridge the gap between reconstruction-based and prediction-based AEs, so as to fully leverage the available information and thus further enhance performance, we propose a predictive prior and incorporate it into the reconstruction-based AE. It may not be very difficult to conceive this idea, but designing the predictive prior so that it can work for tensor anomaly detection is non-trivial. Specifically, to avoid breaking the intrinsic correlations within the multi-dimensional time series, we use the tensor AE as the backbone. To incorporate the predictive prior into the reconstruction-based AE, we propose a Bayesian fusion approach and our analysis reveals that this approach can enhance the modeling capability of the model for normal data. To mitigate the over-generalization problem of AE, we incorporate physical laws, i.e. tensor low-rank decomposition rules, into the neural networks in the predictive prior, leading to the Physics-informed Predictive Prior Tensor AE (PPPTAE) framework. Experimental results on real-world datasets demonstrate the effectiveness of the proposed method. --- ### Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift Authors: Alejandro Rodriguez Dominguez, Muhammad Shahzad, Xia Hong Published: 2026-09-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.31155v1 Compressing a trained model yields a family of deployment candidates, and under domain shift the most compressed one need not be the one to deploy. We study selection over such a family, with candidates and teacher fixed and target labels absent or scarce. Two findings organize the label-free case. Minimum teacher distortion behaves almost as a constant rule, selecting the same eight-bit, per-channel, unclipped configuration in every run, which does not minimize empirical target cross-entropy. Established estimators divide sharply: in the overconfident-collapse regime of the CNN families, confidence-based estimators order the family close to backwards, and the diagnostics that identify it need the labels the setting denies, while output-distribution estimators match the teacher-relative anchor and on one architecture beat it. Distortion is nonetheless stable, so a supervised term can move selection away from it. Combining the two, we give exact quadratic identities for a canonical quadratic analogue of the family. We also show that under symmetric corruption the label-dependent part of a criterion linear in the label indicator is multiplied by one common factor whenever its coefficient sums are candidate-invariant, a class holding teacher contrasts and accuracy but not cross-entropy. These characterize the score's components without bounding selection regret. Across one hundred and thirty-four candidate families, one per independently trained convolutional or Vision Transformer teacher, anchoring reduces mean regret at the smallest label budget in every setting, an advantage that fades beyond twenty-five labels. --- ### HyperErase: Scale-Calibrated Hypernetwork for Multi-Concept Erasure in Text-to-Image Models Authors: Yi Sun, Xinhao Zhong, Zhiqi Zhang, Yimin Zhou, Junhao Li, Yuxia Qiao Published: 2026-09-25 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2609.31154v1 Recent advances in text-to-image (T2I) generation have substantially improved visual synthesis, but have also raised increasing safety concerns due to their potential to generate harmful or undesirable content. Existing concept erasure methods predominantly follow a static weight paradigm, producing a single frozen adapter that struggles to adapt to diverse prompt variations and suffers from parameter interference when scaling to multiple concepts. We propose \textbf{HyperErase}, a framework for concept erasure based on hypernetwork-driven prompt-conditioned parameter synthesis. Our approach first reframes concept erasure as prompt-conditioned parameter amortization and trains a hypernetwork to map textual descriptions to prompt-specific LoRA updates, eliminating the need for per-prompt gradient optimization or manual LoRA merging. To further improve the stability and precision of synthesized adapters, we develop a decoupled rectification strategy, which disentangles LoRA tokens into pattern and scale subspaces, applies a square-root transform to curb multiplicative over-scaling, and leverages teacher-derived canonical priors for inference-time correction. Extensive experiments across major concept categories demonstrate that HyperErase consistently improves the trade-off between erasure effectiveness, image quality, and semantic alignment, achieving performance comparable to gold-standard single-concept baselines. Furthermore, the resulting models can provide specialized LoRAs for each input prompt variation in a single forward pass without requiring gradient updates during inference. These principled and flexible framework offers a new paradigm for concept erasure in T2I models. --- ### FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification Authors: Muhammad Muhtasim Shahriar, M. M. Golam Hafiz, Saad Aloteibi, Mohammad Ali Moni Published: 2026-09-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31150v1 Cross-site lung histopathology classification must account for stain variation, non-IID client data, missing classes, and the cost of adapting large pathology encoders. This study evaluates FedHisto-PAST v2 for three-way classification of adenocarcinoma (ACA), Normal, and squamous cell carcinoma (SCC). FedHisto-PAST v2 combines a frozen HIBOU-B foundation model with parameter-efficient adaptation, stain-conditioned paired-view prediction and feature consistency, reliability-aware prototype learning, and adaptive federated aggregation. Experiments used a five-client, non-IID, raw-data-local simulation with fixed internal evaluation, client-level analysis, component ablations, communication accounting, and a development-influenced exploratory LungHist700 cohort. All principal methods achieved near- ceiling internal performance, which limited discrimination on the fixed split. On LungHist700, FedHisto- PAST v2 achieved a Macro-F1 of 0.728560 and a balanced accuracy of 0.730454. Higher recognition of Normal and SCC was accompanied by lower ACA recall, and calibration remained imperfect. Prediction-level consistency was the only component with a clearly supported independent contribution in the external ablation analysis. Feature consistency and prototype regularization showed no conclusive independent overall gains in Macro-F1. The framework updated 1.253841% of the model parameters. The results provide exploratory cross-dataset evidence for stain-aware, parameter-efficient federation; they do not establish formal privacy, patient-level independence, prospective deployment, or clinical validation. --- ### CRNDiff: Count-Native Diffusion Framework via Chemical Reaction Networks Authors: Yuxuan Qiu, Praful Gagrani, Tetsuya J Kobayashi Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31149v1 Scientific measurements such as single-cell RNA (scRNA) sequencing often take the form of nonnegative integer counts, whereas continuous-state diffusion models approximate this discrete structure using continuous coordinates. Building on stochastic chemical reaction networks (CRNs), a class of count-native Markov jump processes, we introduce CRNDiff, a structured framework that combines count-space diffusion with inference-time conditioning on rare subpopulations. An independent birth--death instantiation yields a closed-form transition kernel for forward noising. This kernel enables reverse sampling via forward-filtering backward-sampling (FFBS) and supports data-driven selection of the terminal noising time, eliminating the need for a validation sweep. This tractability also lets us introduce tilted Feynman--Kac (FK) steering, a method for sampling target subpopulations from a frozen generator without retraining. By tilting posterior marginals before FK particle correction, steering mitigates importance-weight concentration when the target population is rare. Using scRNA-seq data from the human heart cell atlas, we test the ability of CRNDiff to generate cell-type-specific distributions. Across the three evaluated target populations, CRNDiff achieves the highest conditional fidelity among the evaluated generative models, with larger mean purity margins for rarer target populations. Generated cells preserve marker-level differential-expression structure. Replacing real training cells for the target classes with generated cells yields downstream classification performance approaching that of the real-data reference. --- ### Seeing Semantic Shift: Difference-Aware Sentence-Level Temporal Segmentation of Sign Language Videos Authors: Bowen Guo, Shiwei Gan, Yafeng Yin, Xiao Liu, Kuizhuang Liu, Zhiwei Jiang, Lei Xie Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31148v1 Recent advances in sign language understanding have achieved impressive success on short, single-sentence videos, yet their performance drops sharply when applied to long, continuous sign language videos. To bridge this gap, we focus on a challenging and realistic setting: Visual-only Sentence-level Sign Language Segmentation (Vis-SSLS), which aims to partition continuous sign language videos into non-overlapping sentence-level segments without any caption assistance, serving as a crucial prerequisite for downstream recognition and translation tasks. However, sentence transitions in sign language are often smooth and visually ambiguous, lacking explicit pauses or posture resets. As a result, static frame representations may fail to capture the subtle temporal changes that indicate sentence boundaries. To address this challenge, we propose \textbf{SignShift}, a difference-aware segmentation framework that explicitly models frame-to-frame feature variation as semantic cues for sentence boundary detection. First, to model the feature variation, we design a Temporal Difference Module, which incorporates full-frame, facial, and hand cues, and employs inter-frame differencing to learn multi-scale temporal variations that capture both fine-grained local kinematics and global semantic transitions. Second, to mitigate over- and under-segmentation issues, we design a Segment Count Prediction module, which predicts the number of sentences to guide boundary selection. Extensive experiments on benchmark datasets demonstrate that SignShift substantially outperforms existing methods, validating its effectiveness. --- ### JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models Authors: Jianyi Hu, Hangtao Zhang, Yi Liu, Yeqi Zeng, Li Zeng, Xianlong Wang, Rui Wang, Leo Yu Zhang Published: 2026-09-25 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.31142v1 Models trained with reinforcement learning for calibrated decisions (RLCD), such as Jev, answer a typed question about an input, the state, with a probability, a choice, or a score, and software acts on the answer without a person reading it. Their robustness has not been measured: adversarial benchmarks score what a model generates or executes, whereas a typed model generates nothing and returns a well-formed answer even when manipulated. Measurement is also hard, because identical requests can return different answers, most available labels come from the model itself, and the API preprocesses each request out of view. Our key idea is to score each attacked decision against the model's own clean decision rather than against labels, and to read it against the change caused by an identical re-run. Building on this, we introduce JevAdvBench, to our knowledge the first adversarial benchmark for RLCD models, with 812 typed questions over 66 scenarios, and a black-box attack suite of 9,744 single-edit variants that each edit one part of a request, with billed input tokens confirming that the edit reached the model. On jev-1.13.0, rewording stays within 1.2 percentage points of the re-run baseline, and fields outside the schema never reach the model. In contrast, one unverified opinion appended to the state flips 12.1% of decisions, statistically tied with the strongest injected command (10.1%), and pushes 38% of confident answers below the 0.8 confidence threshold that routes them to human review. Applications built on RLCD models should therefore treat the state as untrusted, argued input. Project website: https://JevAdvBench.github.io/JevAdvBench/ --- ### Unknown-Traffic Detection, Calibration and Shortcut Reliance in Distilled Encrypted-Traffic Classifiers over One Year Authors: Mahmoud Abbasi Published: 2026-09-25 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2609.31141v1 Knowledge distillation is the standard way to compress encrypted-traffic classifiers for the edge, and almost all such work judges students by accuracy alone. We ask what else a student inherits: unknown-traffic detection, calibration, shortcut reliance, and whether any survives a year of drift. Resemblance proves little on its own, since soft targets also regularise. We therefore distil one 101k-parameter student from two teachers of equal accuracy but different construction, a five-member ensemble and a single wider model, so that following one rather than the other is attributable to it. The design was pre-registered before any test result was seen. We tested ten hypotheses on CESNET-TLS-Year22, a year of real TLS traffic, across 18 test windows over 35 weeks. Two are supported: a student's per-flow unknown-scores shift toward its own teacher, but only at a conventional temperature, not the accuracy-optimal one; and a shortcut-reliant teacher passes its over-confidence to a student that never sees the feature. The drift prediction is reversed under both scores, the gap narrowing rather than widening and the student overtaking under the energy score in two of three replicates, as is the prediction that such a teacher harms its student's detection, which improves slightly. Shortcut reliance is set by model size, not distillation. Under the logit-based scores nothing else transfers: distillation beats neither a temperature-scaled direct student nor label smoothing. Exploratory analysis shows this turns on the scoring rule: with a feature-space detector the teacher detects unknown traffic 0.073 AUROC better than the direct student, where the energy score sees 0.000, and the conventional-temperature student inherits most of it. Label smoothing, with no teacher, recovers more. Distillation transfers the teacher's habits; what looks like an inherited ability is available without one. --- ### Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability? Authors: Ziyi Wang, Li Li, Aolin Zhou, Yankun Shen, Chonghan Liu, Shuxia Lin, Xu Yang Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31140v1 Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However, this multimodal scaling often degrades the language-side reasoning ability originally encoded in the base LLM. While the base LLM retains usable reasoning after scaling, the aligned VLM itself cannot reliably access this ability. Therefore, recovering the degraded reasoning capability in VLMs would benefit more from seeking help from the base LLM than from the VLM alone. Motivated by this, we propose LIFT (Language-side reasonIng Facilitation and Transfer), a lightweight vector-intervention method that transfers reasoning capability from the base LLM to the VLM without retraining the backbone. LIFT defines Reasoning Vectors as answer-token hidden-state differences between a Reasoner path with an explicit reasoning trace and a Solver path without it, and injects these vectors into language-side activations of the target VLM. LIFT further supports learnable vector adaptation while keeping the VLM backbone frozen. We evaluate LIFT on two VLMs across six reasoning benchmarks, comparing Reasoning Vectors extracted from the base LLM and from the aligned VLM under matched protocols. Results show that LLM-derived vectors consistently outperform VLM-derived vectors, confirming that the base LLM is a more effective source for recovering reasoning. LIFT partially recovers degraded reasoning through lightweight language-side interventions. Further analyses show that Reasoning Vectors influence intermediate reasoning behavior rather than merely altering final answers. The source code will be released soon. --- ### Toward AI-Augmented Cooperative Engineering Workflows: Requirements and Architecture the European Rover Challenge Authors: Ahmed R. Sadik, Frank Joublin, Mariusz Bujny, Antonello Ceravola, Joan Smith Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31136v1 The growing availability of Artificial Intelligence (AI) tools creates new opportunities to support engineering design processes, yet their current use often remains limited to isolated tasks such as coding, documentation, or information retrieval. Less attention has been given to how AI can support cooperative engineering workflows at the process level, where teams must coordinate requirements, tasks, communication, knowledge transfer, and subsystem integration. This paper investigates this challenge in the context of the European Rover Challenge (ERC), where student teams design and integrate complex rover systems within a single academic cycle under strict time constraints and high subsystem interdependence. We conducted a role adaptive 40 question survey with ERC 2025 teams, yielding 104 responses from 14 teams. The survey examined team structure, knowledge transfer, task management, integration practices, communication patterns, and current AI usage. The results reveal recurring workflow bottlenecks, including limited documentation, unclear requirements, fragmented communication, informal task monitoring, and substantial integration rework. Based on these findings, we derive requirements for AI augmented cooperative engineering work-flows and propose an initial assistant system architecture that connects user facing interfaces, credential management, service selection, specialized AI services, and external engineering tools. The proposed architecture aims to support task clarification, requirement and compliance management, communication summarization, integration risk detection, and continuous knowledge capture. In doing so, the paper contributes empirical requirements and an architectural direction for AI augmented cooperative engineering workflows in hybrid human AI team settings. --- ### Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding Authors: Alberto Presta, Michal Byra, Grzegorz Stefański, Karol Szurkowski, Eryk Kołodziejczyk, Krzysztof Arendt Published: 2026-09-25 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2609.31135v1 Spatio-Temporal Video Grounding (STVG) aims to localize the spatio-temporal tube in a video corresponding to a natural language query. While recent methods achieve strong performance in fully supervised, weakly supervised, and zero-shot settings, they typically rely on computationally expensive architectures, complex training pipelines, or multimodal large language models. We present Pocket-STVG (P-STVG), a lightweight cascade architecture that addresses STVG by combining efficient pre-trained components instead of large end-to-end models. P-STVG integrates a temporal-aware video encoder based on MobileViCLIP, a spatial encoder-decoder derived from MDETR, and a shared aligned text encoder. Temporal localization is performed through either a lightweight 1D U-Net or a simple thresholding strategy, enabling the same framework to operate in both weakly supervised and zero-shot settings. Furthermore, video representations are precomputed independently of the query, yielding an indexing-friendly pipeline for efficient inference and large-scale video collections. Despite requiring fewer than 90M parameters, P-STVG performs on par with weakly supervised methods and improves on earlier zero-shot approaches at a fraction of their memory and computational cost, establishing a favorable performance-efficiency trade-off for STVG. --- ### AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution Authors: Tian Luo, Ruge Zhang, Haozhi Han, Yifrng Chen, Yunquan Zhang, Yunxin Liu, Ting Cao, Kun Li Published: 2026-09-25 Categories: cs.AI, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2609.31133v1 High-fidelity atomistic evolution over long timescales requires more than observing the current crystal configuration. Instantaneous atomistic snapshots are often incomplete: locally similar configurations can correspond to different hidden dynamical contexts, future event preferences, and waiting-time scales. We argue that this snapshot ambiguity makes long-horizon atomistic evolution fundamentally a memory-based world-state restoration problem. To address this, we introduce AtomWorld-Mem, a memory-restored atomistic world model that recovers the latent world state missing from instantaneous crystal snapshots. AtomWorld-Mem treats the evolving alloy as an AtomWorld: spatial encoders write multi-scale atomistic keyframes from dense local topology and sparse long-range defect context, while short-term event memory and long-term structural memory integrate these keyframes across time to restore a future-predictive evolutionary state. The restored state is used to prioritize legal vacancy-mediated events under single-event Kinetic Monte Carlo (KMC) constraints, while event legality, physical execution, and residence-time updates remain governed by the underlying simulator. Empirically, AtomWorld-Mem improves long-horizon atomistic progress under fixed microscopic event budgets while maintaining high-fidelity evolution across energetic, structural, and vacancy-transport observables. It further transfers zero-shot across diverse unseen alloy-temperature AtomWorlds, suggesting that the learned memory-restoration mechanism captures reusable principles of hidden-state inference rather than a system-specific local energy heuristic. These results position memory-restored world-state modeling as a promising route toward efficient, physically grounded, and transferable atomistic evolution. --- ### Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue Authors: Amandine Decker, Maxime Amblard, Ellen Breitholtz Published: 2026-09-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31130v1 We empirically investigate Question Under Discussion based modelling in naturalistic dialogue by studying whether the salience of generated potential questions predicts their subsequent resolution. Building on Wu et al. (2024), we construct a dataset of 7,124 questions automatically generated from utterances and preceding context from the British National Corpus, and annotated for salience and answerability. We find a robust but low positive correlation between salience and answerability in dialogue, indicating that more salient questions are more likely to be addressed. However, this effect is markedly weaker than in monologic text, suggesting that conversational structure is less predictable. We further observe that structured interactions exhibit stronger alignment between annotators than less organised dialogues. --- ### Frame the adversary: a structure-aware attack methodology Authors: Vicky Kouni, Stelios Perrakis, Francis Bach, Pascal Frossard, Yann Chevaleyre Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31128v1 Frequency-based adversarial attacks have recently grown popular by exploiting spectral sensitivities shared across neural architectures. Unlike spatial perturbations, frequency-based attacks expose deeper vulnerabilities, making them especially valuable for robust evaluation of safety-critical and security-sensitive applications. Yet, existing approaches are typically not derived as solutions to an optimization problem that explicitly captures transform-domain structure. In this paper, we propose a methodology for crafting principled frequency-based adversarial attacks, via a dedicated optimization framework. A cornerstone of our method hinges on the introduction of a perturbation constraint set, tied to highly structured non-orthogonal transforms, well-known for their flexible, non-predefined frequency handling. We prove that the attacks emerge as weighted $\ell_2$-projections onto this set, yielding a general and controlled attack generation mechanism. By this, we provide a clear geometric attack characterization, ensuring alignment between the optimization objective and the perturbation constraint. We assess our framework on standardized datasets, for pretrained and adversarially robust models. Results highlight that our attacks, being solutions to an optimization problem, over a structured perturbation set, are highly effective, even across different, unseen architectures. Our methodology could serve as a theoretical baseline for designing and analyzing transformed-based attacks, targeting fundamental model vulnerabilities, instead of mere architecture-specific artifacts typically studied in the robustness literature. ---