# Research Papers — 2026-08 · bundle page 177 of 240 > Full-text markdown of papers #8801–8850 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/177 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/176.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/178.md) ### Adaptive KappaSharp: Condition-Number Shaping for Preferential Bayesian Optimization Authors: Ketong Shao, Jialu Wang, Xuekai Pei, Ali Mesbah Published: 2026-08-08 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.07859v1 Preferential Bayesian optimization (PBO) optimizes objectives accessible only through pairwise user comparisons. The standard approach fits a Gaussian process surrogate for observed pairwise comparisons (PairwiseGP) using the Laplace approximation and selects queries with the Expected Utility of Best Option (EUBO) acquisition function. EUBO queries new candidates at each step, producing pairs that share no candidates with previous queries. Each such pair forms an isolated component in the comparison graph, removing one degree of freedom from the likelihood Hessian and making it rank-deficient. This deficiency is structural and cannot be resolved by changing the surrogate modeling approach. Existing approaches to remedy this issue either waste query budget by forcing comparisons to stay connected, or apply uniform regularization that also perturbs directions already well-constrained by the observed comparisons. We propose KappaSharp that enables a diagonal correction to the Hessian to reduce its condition number, with larger corrections where the prior uncertainty is higher. The correction is only applied in the model fitting step, not query selection. An adaptive variant of KappaSharp is also presented that activates the correction only when the surrogate is confident about recent comparisons, avoiding unnecessary corrections when the problem is well-conditioned. On 11 benchmarks (5--20 dimensions), including a 16-dimensional controller tuning problem in plasma medicine, Adaptive KappaSharp outperforms the standard PBO baseline, with up to +10.9% ($p{=}0.003$). --- ### Distilling CT Foundation Models into Editable Concept Bottlenecks for Lung Nodule Malignancy Prediction Authors: Fakrul Islam Tushar, Stephen Adamo, Geoffrey D. Rubin Published: 2026-08-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.07857v1 Foundation models provide transferable CT representations, but predictions based directly on these embeddings are difficult to interpret. We developed concept bottleneck models that map two frozen CT foundation-model representations to eight radiologist-defined pulmonary-nodule attributes and predict malignancy from the estimated concepts and nodule size. The models included CT-FM, a whole-CT self-supervised encoder using a 96^3-voxel nodule-centered patch, and FMCIB, a nodule-focused contrastive encoder using a 50-mm crop. Eight ridge-regression concept heads were trained on 2,610 LIDC-IDRI nodules. Malignancy models were trained on LUNA25 and evaluated on a held-out internal test set and the external DLCS cohort. Concept fidelity was assessed using five-fold cross-validated R^2, and malignancy discrimination was assessed using AUROC with 95% confidence intervals estimated by patient-grouped bootstrap resampling. Concept fidelity was modest but higher for FMCIB than CT-FM for subtlety (R2, 0.24 vs. 0.11), spiculation (0.17 vs. 0.08), texture (0.17 vs. 0.07), and lobulation (0.15 vs. 0.05). Internally, the CT-FM and FMCIB concept+size models achieved AUROCs of 0.86 (95% CI, 0.80-0.92) and 0.86 (0.79-0.92), respectively. Externally, AUROCs were 0.72 (0.68-0.75) and 0.73 (0.70-0.76), compared with 0.73 for nodule size alone and 0.60 and 0.67 for the corresponding embedding only probes. Additive predictions could be decomposed into feature-level contributions and modified through controlled concept interventions. Concept bottlenecks provided transparent malignancy predictions with discrimination similar to nodule size alone, while differences in concept fidelity suggest that concept recovery depends on the underlying foundation-model representation. --- ### CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents Authors: Weizhong Huang, Jinchao Zhang, Xiawu Zheng Published: 2026-08-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.07855v1 Multi-turn Reasoning-and-Acting (ReAct) agents accumulate growing trajectories of reasoning, tool calls, and observations. Their key-value (KV) caches grow accordingly, increasing memory use and attention cost during model inference. Existing KV cache compression methods reduce these costs by evicting states with low attention scores. However, low attention in the current turn does not imply future irrelevance, as temporarily inactive information may become important later. Snapshot-based eviction methods therefore do not explicitly distinguish temporarily dormant information from information that appears to have completed its role. In this paper, we present CommitKV, which identifies KV lifecycles through commit transitions. Specifically, CommitKV first divides completed agent events into token pages and compares each eligible page's deletion effect before a tool-call commit and after the commit's returned observation has been incorporated. Based on these paired measurements, CommitKV distinguishes dormant pages from high-to-low completion candidates. It then applies a greedy joint test, accepting candidates for retirement only when their combined post-commit effect remains bounded. Finally, at a later compression checkpoint, accepted pages are excluded, a bounded set of pages awaiting post-commit measurement is protected, and the remaining KV states are retained within the cache budget using the same token indices for keys, values, and absolute positions. These mechanisms ensure that CommitKV can distinguish dormant information from information that has completed its observed role and can be safely removed. Experiments on various benchmarks show that CommitKV reduces agent memory use, accelerates end-to-end inference, and achieves higher accuracy than existing KV cache compression methods. --- ### "Many Are My Names": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders Authors: Adelaide Danilov, Aria Nourbakhsh, Oleksandr Marchenko Breneur, Salima Lamsiyah Published: 2026-08-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.07852v2 How a language model internally represents who is speaking, the Assistant, an assigned roleplay persona, or a narrated story character, remains underexplored. We study speaker representations using a dataset of user-expressed emotional text and corresponding model responses. We decompose three generation settings (Assistant, Roleplay, and Story) into sparse autoencoder features extracted at turn-boundary and pronoun-token positions and selected through a filtering pipeline for different depths. We characterize each surviving feature through its steering effects and activation distribution. Our main finding is that the Assistant and roleplay personas are not independent alternatives: personas retain the Assistant-associated feature core while progressively differentiating from it across layers, starting from operational machinery towards behavioral and stylistic features. Meanwhile, generated story characters lack the Assistant-associated core. Both Story and Roleplay can be distinguished from the Assistant with Immersive Simulation Mode. However, the Assistant can sometimes enter or slowly drift into it even in the default setting. --- ### TEMPER: Tensorized Efficient Manifold-constrained Parameterization for Expressive Residual Routing Authors: Yuxuan Gu, Wuyang Zhou, Huijun Xing, Danilo Mandic Published: 2026-08-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.07851v1 Residual connections rely on a static residual pathway, and are essential for training deep neural networks. Hyper-connections (HC) increase the expressivity of residual routing by incorporating multiple residual streams and learning dynamic information flow, while manifold-constrained (mHC) variants stabilize training through doubly stochastic residual mixing. However, a generator-level bottleneck remains in existing methods: they use dense, unstructured generators for pre-branch aggregation, residual mixing, and post-branch redistribution, which results in parameter count growing rapidly with the number of streams. To address this issue, we propose \underline{\textbf{T}}ensorized \underline{\textbf{E}}fficient \underline{\textbf{M}}anifold-constrained \underline{\textbf{P}}arameterization for \underline{\textbf{E}}xpressive Residual \underline{\textbf{R}}outing (\textbf{TEMPER}), which represents these generators as multi-way tensors over the input-stream, feature, and output-stream modes, and parameterizes them using tensor networks. Such a structured low-rank formulation is shown to preserve token-dependent manifold-constrained routing interface while substantially reducing parameter growth. It also promotes interpretability and intuition, as: i) tensor ranks control the dimensionality of the learned routing subspace, with full ranks recovering dense routing; while ii) the generator approximation errors bound differences in routing logits and, consequently, in the routed-block outputs. Comprehensive experiments show that TEMPER matches or outperforms existing methods across language modeling and commonsense reasoning tasks, while requiring substantially fewer additional parameters. At eight residual streams, TEMPER achieves the best CORE score while using about $84\%$ fewer additional parameters than mHC, thus showing a stronger performance-parameter efficiency trade-off. --- ### IRPol-Fuse: Energy-structure coordination for infrared polarization fusion under low visibility Authors: Zhuangfan Huang, Chusheng Fang, Xiaosong Li, Yang Liua, Xiaoqi Cheng, Haishu Tan Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07848v1 Robust perception under low-visibility conditions requires fused imagery that jointly preserves infrared thermal saliency and polarization-derived structural details. However, existing infrared-polarization image fusion (IPIF) methods often overemphasize dominant infrared responses, causing weak yet informative polarization textures in dark regions to be suppressed. To address this issue, we propose IRPol-Fuse, an energy-structure coordinated IPIF framework for challenging low-visibility scenarios. The proposed framework contains three key modules: Polarization Attention Fusion for adaptive infrared-polarization allocation, Infrared Highlight Injector for highlight-guided infrared preservation, and Polarization Texture Injector for polarization texture restoration and fine-detail recovery. We further construct LI-PI, a dedicated infrared-polarization evaluation dataset for low-visibility and visually concealed scenes. Experiments on LI-PI and the public LDDRS dataset demonstrate that IRPol-Fuse achieves favorable performance in thermal target preservation, structural detail recovery, and visual naturalness. Region-aware evaluation and downstream object detection further verify that the proposed energy-structure coordination strategy effectively preserves both infrared target saliency and polarization-derived structural information. Code is available at https://github.com/1hzf/IRPolar-Fuse . --- ### Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge Authors: Shibo Chu, Yuze Liu, Tiehua Zhang, Zhishu Shen, Lianghua He, Haofen Wang, Zhijun Ding Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07838v1 Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge spanning heterogeneous structures. However, existing benchmarks provide limited assessment of whether LLMs can faithfully perform multi-hop reasoning chains across such knowledge contexts while remaining robust to variations in their input order. We introduce TKFQA, a factuality consistency benchmark comprising 10,130 question-answering (QA) pairs grounded in tables, texts, and knowledge graphs (KGs). Each example is constructed from an explicit counterfactual reasoning chain, enabling the joint evaluation of answer correctness, reasoning-chain accuracy, and robustness to different input-order. An extensive evaluation of 14 open- and closed-source LLMs reveals that state-of-the-art models exhibit limited reasoning-chain accuracy and remain sensitive to variations in the input order of heterogeneous knowledge contexts. To address these limitations, we propose ORLF, an LLM-agnostic training framework that models cross-context topological relations through knowledge-specific latent vectors. ORLF integrates context-wise position encoding, a latent-bridge attention mask, and topological knowledge bias to preserve knowledge-specific bias and encode topological semantics. Experiments across four LLM backbones show that ORLF outperforms competitive training-free and LoRA-based baselines, improving average Exact Match and Reasoning-Chain Accuracy by 2.15% and 4.29%, respectively, while reducing order-induced performance standard deviation by 0.04% to 3.01%. --- ### SeqLoc: Beyond the Single Frame for Cross-View Geo-Localization in Feature-Sparse Scenes Authors: Junwei Zheng, Yun Huang, Ruize Dai, Ruiping Liu, Yufan Chen, Kunyu Peng, Kailun Yang, Jiaming Zhang, Guangming Wang, Olaf Wysocki, Rainer Stiefelhagen Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07835v2 Cross-View Geo-Localization (CVGL) with OpenStreetMap (OSM) performs well in structure-rich urban environments but collapses in feature-sparse scenes such as rural roads. To study this failure mode, in this work, we introduce CV-FSS, a benchmark that pairs sequential panoramas from five rural regions with aligned OSM maps, on which single-frame methods degrade drastically. We then propose SeqLoc, an online test-time sequence aggregation mechanism that recursively maintains a log-belief volume with three key components: (1) Entropy-Tempered Uncertainty (ETU) tempers each incoming pose likelihood volume by its normalized entropy; (2) Map-Guided Relocalization (MGR) mixes a map-shaped recovery distribution into the belief so that a suppressed true pose can recover; (3) Peak-Anchored Smoothing (PAS) derives the final pose at sub-grid precision. Extensive experiments on CV-FSS and CV-RHO demonstrate that SeqLoc outperforms single-frame localization by a large margin, improving both position and orientation recall by over 50%. The benchmark and source code are publicly available at https://zhengjunwei.com/publications/SeqLoc/SeqLoc.html. --- ### From token probabilities to calibrated confidence: An empirical study of mathematical question answering Authors: Avery Ma, Lorne Schell, Vin Bhaskara, Leila Pishdad Published: 2026-08-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.07827v1 Confidence estimation for large language models (LLMs) aims to estimate the probability that a generated answer is correct, while calibration aligns these estimates with empirical accuracy. Prior work has shown that token probabilities are often overconfident, we investigate whether these readily available signals can nevertheless provide well-calibrated confidence estimation for mathematical question answering. We compare single-pass estimators, which reuse token probabilities from the original generation, with multi-pass estimators, which obtain additional confidence signals through verification or stochastic forward passes. While individual token probabilities can be highly saturated, we find that aggregating token probabilities over the full sequence captures small but consistent differences between correct and incorrect generations, yielding more informative confidence estimates. Multi-pass methods can yield calibrated confidence estimates. We study two such approaches: self-verification through re-prompting, including a lower-cost in-situ variant, and Monte Carlo Dropout, which derives confidence from variation across stochastic forward passes. We further evaluate two post-hoc calibration methods, Platt scaling and isotonic regression, both of which substantially reduce in-domain calibration error. However, their data efficiency varies with dataset difficulty, and the calibration mappings often transfer asymmetrically across datasets and models. --- ### VACS: Value-Aligned Compositional Shielding for Multi-Agent Reasoning Authors: Yiyao Zhang, Diksha Goel, Hussain Ahmad, Shixun Huang, Jun Shen Published: 2026-08-07 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.26135v1 Multi-agent reasoning systems in high-stakes domains must be both accurate and safe, yet agents often follow heterogeneous value priorities (e.g., rigor, conciseness, safety), causing conflicting recommendations. Existing methods do not jointly provide: (i) principled inference of each agent's implicit values from behavior, (ii) compositional formal safety guarantees without full online communication, and (iii) value-aware conflict resolution with faithful explanations. We present VACS (Value-Aligned Compositional Shielding), a four-layer framework addressing all three. Layer 1 learns value-dimension rewards from pairwise preferences using Bradley-Terry modeling and infers per-agent value weights via deep MaxEnt IRL. Layer 2 encodes value constraints in a Lean-inspired DSL and synthesizes compositional assume-guarantee shields for runtime safety. Layer 3 resolves disagreement through nucleolus-based credit allocation and Hamiltonian consensus optimization under long-term value constraints. Layer 4 extracts a critical reasoning path from co-state sensitivities and generates formally grounded natural-language explanations. Our contribution is primarily a unified systems design with formalized interfaces and operational guarantees at the verifier-constrained decision level, rather than a complete end-to-end formal proof of all language-model internals. In controlled proof-of-concept evaluations with role-conditioned agent panels on NEJM-AI QA, MathInstruct-Subset, and a cybersecurity incident-response benchmark (CyberSec-Eval), VACS outperforms strong baselines in accuracy (85.4%, 95.0%, and 90.0%) while reducing logical inconsistency rates to near zero. --- ### StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots Authors: Jiageng Zhang, Doniyorkhon Obidov, Kaichen Yang Published: 2026-08-07 Categories: cs.RO, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.26131v1 Large language models and vision-language models are increasingly used as high-level planners in robotic systems, using task goals and sensor summaries to select navigation or manipulation actions. This creates a new backdoor surface: a compromised planner can behave normally in most runs, yet change its target selection when a hidden trigger is present. Prior attacks on LLM-powered or embodied agents mainly rely on triggers that appear in language, camera-visible objects, scene semantics, or specific sequences of past actions. This paper presents StepTrigger, a contact-state-triggered backdoor attack for VLM-powered legged robots. The trigger is not a prompt token or a visible marker. It is produced by pressure and foot-ground contact patterns that arise when a Unitree Go1 quadruped walks across a dense terrain patch. Unlike conventional visual or textual triggers, contact signals are inherently noisy and may also arise during benign locomotion. To avoid treating every pressure anomaly as a trigger, StepTrigger learns a selective backdoor policy from multimodal robot state, using incidental pressure events as benign examples and dense-patch contacts as poisoned examples. In a stratified offline evaluation, the trained planner achieved 98.75% clean behavior preservation, 92.50% false-trigger rejection, 76.25% true-trigger activation, and 89.17% overall parsed behavior accuracy. These results reveal a backdoor surface in proprioceptive and contact channels that is not captured by defenses focused only on language, vision, or action history. --- ### FairMon: A Tool for Monitoring and Visualizing Algorithmic Fairness Authors: Jan Baumeister, Bernd Finkbeiner, Vladimir Krsmanovic, Frederik Scheerer, Julian Siber, Tobias Wagenpfeil Published: 2026-08-07 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2609.26123v1 Runtime monitoring has recently been proposed as a rigorous method for analyzing algorithmic fairness of autonomous decision systems used in critical scenarios such as credit lending, job application, and the criminal justice system. Prior work has shown that runtime monitoring, in principle, can be an effective technique for establishing the kind of human oversight required by legislation such as the EU Artificial Intelligence Act. In practice, the available monitoring tools have not been developed with this application in mind and display several critical shortcomings in these scenarios. In this paper, we present FairMon, a runtime monitoring tool tailored to fairness analysis of high-stakes decision systems. FairMon uses RTLola as a flexible specification language for monitors, which we have extended with conditional probability operators that allow for concise descriptions of algorithmic fairness properties. The tool also features a real-time visualization of intermediary values, enabling human insight into the dynamics of the monitored system. --- ### Deepfakes and Synthetic Media: Generation, Detection, and Governance Authors: Alexandros Gazis, Efstathios Karypidis, Kleanthi Santamouri, Theodoros Vavouras, Nikos E. Mastorakis, Stylianos Pappas Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25017v1 Deepfakes, synthetic audiovisual content produced by deep generative models, have escalated into a critical threat across civilian and military domains, enabling identity fraud, disinformation campaigns, and evidence fabrication. In high-stakes environments, ranging from journalism and finance to healthcare and legal contexts, the consequences extend to severe misinformation, market manipulation, identity fraud, and the erosion of institutional trust. This entry explores how modern visual intelligence and computer vision techniques are used to detect deepfakes. It outlines key deepfake generation models, such as GANs, autoencoders, neural rendering, and diffusion systems, while also explaining how adversarial methods enhance realism and challenge existing detectors. The overview highlights visual artifacts, digital patterns, and physiological cues commonly leveraged in detection and reviews major CNN, transformer, and frequency-based approaches. It also summarizes evaluation practices and the difficulty of achieving strong generalization. Finally, it identifies emerging directions, including modern intelligence techniques for civilian and military content verification. This survey covers generation architectures (GANs, latent diffusion, neural rendering, video synthesis), the spatial, temporal, frequency-domain, and physiological artifacts they produce, and the detector families that exploit them. We examine evaluation benchmarks and protocols, highlighting cross-generator generalization as the field's central open challenge. Beyond detection, we discuss cryptographic provenance standards, watermarking, and regulatory frameworks (EU AI Act, DSA, GDPR). We conclude that effective deepfake governance requires defense-in-depth integrating forensic detection, verifiable provenance, and institutional accountability. --- ### Enhancing Audio Reasoning via Semantic Summary Prediction Authors: Francesco Bonzi, Pooneh Mousavi, Cem Subakan, Mirco Ravanelli Published: 2026-08-07 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2609.20849v1 Large Audio Language Models (LALMs) perform well on complex question answering but often show a reasoning gap, where explicit Chain-of-Thought (CoT) reduces accuracy compared to direct answers. We hypothesize that long reasoning sequences shift attention away from the audio input. To address this, we propose SPARE (Semantic Prediction for Audio REasoning), which introduces a register token aligned with the final conclusion using a cosine similarity loss with a Sentence-BERT embedding. This conditions the model's latent space with the target semantic goal before reasoning begins. Experiments on MMAU and MMAR with SALMONN show improved zero-shot reasoning and stronger early attention to audio without additional inference cost. --- ### VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots Authors: Marco S. Tayar, Felipe Tommaselli, Gianluca Capezutto, Pedro Antonio Rabelo Saraiva, Pedro H. V. de Freitas, Lucas Kido, Guilherme Sonego, Ricardo V. Godoy, Marcelo Becker Published: 2026-08-07 Categories: cs.RO, cs.AI, cs.CV, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.20191v1 Running vision-language navigation fully onboard an aerial robot is hard, since grounding, planning, and control must share limited compute and a single-stage error is difficult to isolate in flight. End-to-end aerial policies fuse these stages into one network, giving up the observability and safety checks a modular stack keeps available. We propose VLN on the Fly, an onboard stack that keeps grounding, planning, and control as separate, inspectable stages. A quantized VLM grounds an instruction to a coarse image cell, depth lifts it to a 3D goal, a fast B-spline planner returns a feasible trajectory, and a pretrained reinforcement learning policy tracks it to motor commands across quadrotors. Across 15 onboard flights over three everyday referents in a controlled indoor volume, the stack reaches the target in 13 of 15 trials with 5.72 cm mean goal error and 39.3% average GPU utilization. In 6 additional cluttered-environment trials, the stack tracks collision-free trajectories under onboard perception gating. --- ### StableEval Arena: A Cost-Aware Agentic Benchmark for Stablecoin Price Stability Prediction Authors: Sean Wan, Dongping Liu, Luyao Zhang Published: 2026-08-07 Categories: cs.LG, cs.AI, cs.CE, econ.GN, q-fin.CP arXiv: https://arxiv.org/abs/2609.18949v1 We introduce StableEval Arena, a cost-aware benchmark framework for evaluating agentic AI systems on stablecoin peg-risk prediction. StableEval Arena evaluates LLM-backed agentic systems on diagnosing peg stress and forecasting deviations from the one-dollar peg over a hidden seven-day horizon, using leakage-safe historical replay with exchange price-volume data and market-context features. We report two complementary experiment blocks: a 120-case stress-enriched validation block and a 507-case natural-distribution full-arena evaluation block. Across six LLM-backed agent configurations and baselines, StableEval Arena measures prediction quality, calibrated-label behavior, structured-output reliability, latency, token consumption, and estimated inference cost. Rather than ranking agents by accuracy alone, the framework treats trustworthiness as a joint property of forecast quality, operational reliability, and computational cost. The results show a gap between protocol-following reliability and financial-risk reliability: agents reliably produce valid structured outputs at modest measured cost, but still miss most rare severe-stress and sustained-depeg cases. To support auditing and replication, we release the benchmark dataset on Hugging Face and the source code on GitHub. --- ### Training-Free Speech-Centric Omni Understanding with Frozen VLMs Authors: Ankan Deria, Hanoona Rasheed, Xilin He, Fahad Shahbaz Khan, Salman Khan Published: 2026-08-07 Categories: eess.AS, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2609.04242v1 Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships. Existing omni models typically introduce dedicated audio encoders and rely on expensive audio-video-text training, tightly coupling omni capability to specific VLM backbones and potentially weakening their existing visual and reasoning abilities. This raises three questions: whether native omni training is necessary for every new VLM, whether speech-centric omni capability can be added while preserving the original backbone, and where richer acoustic representations remain essential. We introduce Training-Free Omni (TFO), a plug-and-play framework that converts a frozen VLM into a speech-centric omni model without architectural modification, or multimodal re-alignment. TFO uses Whisper to extract confidence-filtered, timestamped transcripts and routes them through the VLM's existing language interface, while leaving its visual pathway unchanged. Across matched comparisons with native omni models on 56 benchmarks and 21 languages, TFO is competitive on audio-visual understanding, improves average audio-only performance across all five model settings, and achieves substantial multilingual speech gains. Freezing the VLM also generally preserves stronger image/video understanding, visual grounding, coding, mathematical reasoning, and medical question answering than the corresponding native omni checkpoints. These results show that strong speech-centric omni understanding can often be obtained through modular audio-to-language routing rather than costly backbone-specific training. --- ### The Utility of LLMs in Recommender Systems Explanation Evaluation Authors: Kathrin Wardatzky, Oana Inel, Luca Rossetto, Abraham Bernstein Published: 2026-08-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2609.01627v1 Explanations play a crucial role in creating trustworthy recommender systems (RS), yet choosing a good explanation method presents challenges. Many explanation methods exist, but little guidance exists on which is best for which setting. Existing explanation generation methods often produce abstract outputs that require further formatting to become user-friendly, with a seemingly endless pool of options. Running user-based evaluations of all possible options is usually unfeasible, while automated evaluation metrics often either assess only the explainer's abstract output or require comparison with a ground truth, which is generally unavailable. Recent studies have shown that large language models (LLMs) can serve as ``judges'' for explanation evaluation, but their reliability has not yet been thoroughly explored. This paper studies the utility of LLMs in selecting an effective explanation method for a given application. We first explore their ability to generate explanation prototypes given varying information about the RS and the user. Specifically, we generate 18 distinct explanation prototypes, which are subsequently evaluated by 14 LLMs of varying sizes across two temperature settings. We compare these against human ratings derived from a user study. Our results show that while LLMs exhibit human-like rating patterns and achieve moderate rank correlation with human raters, their absolute rating agreement is low and varies substantially by model size and evaluation construct. We derive four practical recommendations: keep explanation-generation prompts concise, prefer larger models for evaluation, pre-test evaluation constructs, and audit explanations for factual accuracy, as neither humans nor LLMs reliably detect non-factual content. --- ### PAUSE: Editable Strategy Artifacts for Long-Form Cultural Story Adaptation Authors: Taaha Kazi, Vasu Sharma, Mohammad Saifullah, Abdur Rahman Published: 2026-08-07 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.28633v1 Generative AI systems increasingly mediate cultural adaptation, but their cultural decisions are often hidden inside prompts, transient model plans, or final prose. We study PAUSE (Pause-And-Update Strategy Editing), an intervention that exposes an editable adaptation strategy as a human control surface for cultural decisions in long-form story adaptation. The strategy is a structured artifact that can be inspected, edited, and then projected through downstream character, entity, and chapter-localization stages. In two Chinese-source serialized novels, we test whether human edits to this strategy propagate into chapter-level prose. Across 9 edited-vs-control chapter comparisons, judges select the edited-strategy output in all 9; a marker audit shows target markers in 8/9 edited outputs and 0/9 controls, with forbidden markers absent from edited outputs and present in all controls. We frame these results as a smoke-scale edit-adherence study, not a claim that the outputs are culturally authoritative or literary-quality improvements. PAUSE offers one practical way to make AI-mediated cultural adaptation more inspectable and contestable before decisions propagate through long-form generation. --- ### Selective Cross-View Consistency for World Action Models: Held-Out Viewpoint Robustness Without Test-Time Camera Information Authors: Bingqi Huang, Bingchuan Wei, Yingkai Cai, Zhaokui Wang Published: 2026-08-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.21402v1 World action models (WAMs) jointly denoise future video frames and robot actions, and the video prior is expected to generalize their control. Camera viewpoint change remains one of their hardest perturbation axes. We study a question specific to this model class: when training with same-state cross-view image pairs, on which output coordinates should a consistency loss be imposed? The WAM denoising target mixes view-covariant coordinates, namely the predicted future scene, with view-invariant coordinates, namely the action chunk, future proprioception, and value. We show that consistency applied to the covariant block is provably harmful, shrinking legitimate view-specific content to a fraction $1/(1+4λ)$ of its true value, and we verify this shrinkage law in controlled experiments. Selective cross-view consistency (SCVC) therefore constrains only the invariant block, requires no camera labels, extrinsics, depth, or view synthesis at training or test time, and leaves the deployment interface unchanged. We introduce a carve-and-hold-out evaluation protocol on the LIBERO-Plus camera track that separates a distribution-matched ceiling from genuine interpolation and extrapolation to held-out viewpoints, with a matched pair-trained control isolating the effect of the consistency term from pair exposure. On held-out orbital viewpoints beyond the training envelope, SCVC improves closed-loop success over the matched control by 12.2 points (95% CI (7.4, 17.0); +15.5, CI (11.7, 19.4), under an independent second seed) -- an effect two further camera axes replicate -- while interpolation within the envelope shows no gain in either seed (-1.2 and -4.3 points) and in-distribution competence is preserved (-0.6, -0.2). We also report a cross-backbone audit showing that published camera-robustness numbers are confounded by wrist-camera pose stability. --- ### Generative Gap Filling Authors: Yonathan A. Arbel, David A. Hoffman Published: 2026-08-07 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2608.21401v1 Most contract litigation turns on contracts that imperfectly record parties' bargains. When the parties' dispute can't be solved by interpreting the text, courts fill the gap. Scholars have long assumed that the remaining text runs out quickly, and provides thin evidence of the actual deal on the disputed point. On that view, a judge who supplies the missing term must be drawing on something else, from commercial defaults to her own policy preferences. Despite generations of work, courts have no real alternative to such unruly methods. We tested that assumption. Taking real contracts, we masked a term the parties had negotiated and asked readers to predict what we removed. Lay respondents recovered the hidden term about half the time, twice what chance predicts. Law students and lawyers did marginally better. But large language models, given nothing but the rest of the contract, recovered it nearly nine times in ten. The deal, in short, testifies to far more of the agreement than the literature assumes, including terms the parties never wrote. A contract, we argue, is like a radio signal from far away. Even when incomplete, enough of the message is carried elsewhere that the missing part can be reconstructed with the right receiver. True gaps are rarer than supposed. Courts can weigh model predictions as ordinary, contestable evidence, and parties can discipline the practice with "Choice of Model" clauses. --- ### Machine Learning and ARIMA Model Averaging for Adaptive Public Health Forecasting: Comparative Evaluation and an Ontario COVID-19 Case Study Authors: Yushu Zou, Ye Li, Johra Moosa, Martin Grunnill, Samir N. Patel, Venkata R. Duvvuri Published: 2026-08-07 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2608.20406v2 Public health forecasts must respond to abrupt changes in surveillance data without over-extrapolating noise, reporting artifacts, or temporary trends. We evaluated autoregressive integrated moving average (ARIMA), random forest, and extreme gradient boosting (XGBoost) models using 190 weekly observations of publicly available Ontario COVID-19 case counts from January 2020 to October 2023. Rolling-origin time-series cross-validation preserved temporal order during model tuning and evaluation. Performance was assessed across three operating dimensions: responsiveness following selected turning points, forecast horizons of one to six weeks, and the amount of historical training data. We also developed Machine Learning and ARIMA Model Averaging (MLAMA), a non-negative performance-weighted ensemble with weights that vary by forecast horizon and responsiveness setting. Retrospective comparisons showed that ARIMA adapted rapidly after turning points but its normalized error increased at longer horizons. Random forest and XGBoost were less responsive initially but maintained more stable normalized error over longer horizons. For two-week forecasts at the end of the study period, training on the most recent data outperformed using longer historical periods, particularly for XGBoost. MLAMA achieved the lowest normalized mean absolute percentage error across most forecast horizons and ranked among the best-performing methods across responsiveness settings. These findings support selecting forecasting models according to operating conditions rather than relying on a single universally preferred approach. MLAMA provides a practical framework for combining complementary statistical and machine-learning forecasts. The accompanying Python package is currently maintained in a private repository while software validation and reproducibility testing are completed. --- ### Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level Authors: Hannah Cha Published: 2026-08-07 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.14692v1 Personalized, generative AI systems increasingly adapt their behavior to individual users over time, fundamentally changing model behavior. While existing auditing approaches have been effective at surfacing harms in non-personalized contexts, they often rely on static, simulated evaluations and definitions of harm that aggregate across broad, group categories. In this position paper, we argue that such approaches can fail to capture emergent harms in personalized generative AI systems, where harms surface through interpretations of ongoing interaction and evolve with user history. We identify three presuppositions underlying many harm auditing paradigms: that harms can be (1) specified outside real-world interaction, (2) defined non-pluralistically within groups, and (3) treated as static. One might argue that personalized systems could simply learn definitions of what constitutes harm to individual users through repeated interactions. However, we argue that attempts to surface user harms through deeper personalization risk imposing asymmetric burdens of labor and privacy on marginalized users. Consequently, we propose reframing understandings of harm as adaptive, user- and community-centered processes, and outline design directions that shift auditing from retrospective evaluation toward infrastructures that support ongoing articulation of harm in interaction. Our work highlights the need for auditing and design practices that better reflect the pluralistic and evolving nature of harm understanding in personalized generative AI systems. --- ### The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models Authors: Ahmed Nebli, Hadi Saadatdoorabi, Christopher Keibel, Kevin Yam Published: 2026-08-07 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2608.14691v1 Sequence models are conventionally distinguished by their backbone, the mechanism that routes information across positions, such as attention or recurrence. This paper varies a choice that is prior to the backbone and shared by nearly all current models: the \emph{substrate}, the number system in which the hidden state is represented together with the form of the map from state to prediction. The prevailing substrate is a real-valued state with an affine--softmax readout; we study a complex-valued alternative drawn from the mathematics of quantum theory, in which information is carried by the phases of the state and scores are quadratic Born forms. Prior work proved an idealized version of this substrate representationally stronger than any real model with a linear readout; we ask whether it also trains faster. Relaxing the two properties that block deployment, exact unitarity and the Born vocabulary readout, we instantiate it in the Mamba state-space model and an attention-based Transformer. At 253M parameters, matched to within $0.02\%$ and trained under one fixed protocol on three byte-level corpora, the complex models reach every measured validation loss in approximately one third (state-space) and one half (attention) of the optimization steps of their real counterparts. The two backbones then diverge. Once the learning-rate warmup ends, the state-space advantage continues to widen, from $0.321$ to $0.354$ bits per character on OpenWebText and from $0.368$ to $0.396$ on FineWeb, which an artifact of the warmup ramp would not do; the attention advantage instead decays toward zero on every corpus, and is therefore an effect of early training. --- ### Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation Authors: Lunjie Zhu, Xingtong Ge, Fangyu Lin, Yi Zhang, Zhening Liu, Mengfei Li, Yumeng Zhang, Guanglu Song, Yu Liu, Jun Zhang Published: 2026-08-07 Categories: cs.MM, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2608.13602v2 Joint audio-video generative models serve as foundation for immersive and interactive digital-human generation. Nevertheless, most existing models rely on bidirectional attention and multi-step denoising and can generate only short clips, making them unsuitable for real-time interaction over extended durations. We present Omni-LiveAvatar, the first framework for minute-level, real-time streaming joint audio-video avatar generation. Specifically, we propose (1) a progressive autoregressive distillation pipeline that transfers a large bidirectional joint audio-video diffusion model into a few-step autoregressive generator without auxiliary stabilization mechanisms; (2) a synchronized audio-video long-short-term memory that preserves global consistency under a bounded memory budget; and (3) a hierarchical rolling prompt planning strategy that enables coherent semantic evolution and seamless prompt transitions. Extensive experiments show that Omni-LiveAvatar generates high-quality, synchronized minute-level avatars in real time. In terms of speed, it achieves a 33$\times$ generation speedup over its teacher, LTX-2, on a single NVIDIA H200 GPU; in terms of generation quality, it outperforms accelerated baselines across visual quality, audio quality, cross-modal synchronization, and human fidelity. Our code is available at https://github.com/Aoko955/Omni-LiveAvatar. --- ### Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning Authors: Shibo Gao, Peipei Yang, Xu-Yao Zhang, Linlin Huang Published: 2026-08-07 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.11260v1 Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals. Existing approaches exhibit a "when-what" dissociation: traditional DNN-based methods localize when anomalies occur but lack semantic understanding, whereas LLM-based methods explain what happens but neglect precise temporal grounding. We attribute this to the absence of a unified reasoning paradigm. Inspired by how humans inspect surveillance videos - glancing globally to form temporal hypotheses, scrutinizing suspicious segments, and thinking iteratively to correct errors - we study this global-to-local paradigm from two perspectives. We first propose Glance then Scrutinize (GtS), a training-free framework using static and dynamic textual guidance for coarse-to-fine anomaly grounding and understanding, balancing accuracy and speed. To break the ceiling imposed by frozen external modules, we further propose a tool-augmented agentic VAD method, where a multimodal large language model learns to invoke a video cropping tool, inspect densely resampled frames, and self-correct mislocalized hypotheses, via cold-start supervised fine-tuning followed by reinforcement learning with a joint answer-grounding reward. For training and evaluation, we extend our prior VAGU benchmark into VAGU-T (Video Anomaly Grounding, Understanding, and Thinking), comprising 7,567 real-world videos over 21 anomaly categories with human-validated grounding, explanations, QA pairs, and chain-of-thought tool-calling traces. We further introduce JeAUG, a metric jointly evaluating semantic interpretability and temporal precision. Experiments show that GtS substantially surpasses training-free baselines, while the agentic model delivers both higher accuracy and faster inference. --- ### Methodologies for Improving the Quality of AI Tutoring in K-12 Education Authors: Tushar Udeshi, Anna Khazenzon, Kabir Khan, Nick Breen, RJ Corwin, Chris DiGiano, Kodi Weatherholtz, Marek Zaluski Published: 2026-08-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.11259v1 Many AI tutors leverage large language models (LLMs) today. Given that LLMs are opaque black boxes, robust evaluation and live experimentation to measure the impact of every change are essential. We pioneered AI-powered tutoring for K-12 with the launch of Khanmigo (Khan Academy, 2023). We describe the metrics we use to measure AI tutoring quality and student engagement as well as various experiments we have run. We highlight the changes that have moved our metrics, including models, prompting, personalization and agents. --- ### Adaptive Hybrid Particle Swarm Optimization with Gradient Descent Authors: Aryan Gurudeo Published: 2026-08-07 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2608.11258v1 Gradient injection helps Particle Swarm Optimization (PSO) only when the swarm has identified a basin with smooth local structure, not universally. We propose Adaptive Hybrid PSO (AHPSO), which uses a sigmoid function on swarm diversity to automatically modulate gradient influence: near-zero during exploration, near-maximum during exploitation, with no manual phase-switching. Under budget-normalized comparison (PSO given equivalent total function evaluations), PSO wins 52.5% of 40 configurations versus AHPSO's 20% (p = 7.0e-5, Friedman). AHPSO retains advantage specifically on problems with smooth local basins (F8, F24-F27) where directed descent outperforms undirected sampling even at equal cost. Under iteration-matched comparison across 29 functions (42 configurations, 14,700 runs), AHPSO-Adadelta ranks first of 9 methods including CMA-ES (p = 9.75e-4). The contribution is a principled characterization of when gradient injection provides value in swarm-based search, not a claim of universal superiority. --- ### Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness Authors: Srijith Ravikumar Published: 2026-08-07 Categories: cs.IR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.10008v3 LLM recommenders for top-K item suggestion regularly emit titles outside the target catalog. Prior audits report a binary out-of-domain rate; none ask whether the model knew. We jointly audit hallucination rate (OOD@10) and verbalized-confidence calibration (ECE, Brier, reliability) for four zero-shot LLM recommenders from four independent vendors (Mistral Large, Llama-3.3-70B, GPT-OSS-120B, Claude Sonnet 4.6), not grounded or fine-tuned systems, across three catalogs (MovieLens-25M, Amazon Reviews 2023 Toys, Yelp Open Dataset), stratified by item popularity. Measuring catalog membership is itself the hard part: on identical outputs the reported rate moves by an order of magnitude with the string matcher used, and F1 cannot separate the candidates. We validate the instrument against 201 human judgments and select on net bias, where the adopted one is off by -0.040 against +0.144 for the common fuzzy rule. Hallucination is then strongly catalog-dependent (0.6-2.7% on MovieLens, 11.6-38.7% on Yelp, 49.3-61.0% on Amazon Toys). Each model holds a near-constant confidence level barely responsive to the catalog, while the catalog-hit rate swings 60 points, so the sign of the error is set by where a model's constant lands against a catalog's accuracy: 7 of the twelve cells are under-confident and 5 over-confident, all four under-confident on MovieLens, all four over-confident on Amazon Toys. We read this as an elicitation mismatch: "Just Ask" elicits a generic quality rating, not a catalog-membership probability. A conformal abstention threshold over verbalized confidence changes hallucination by at most 1.65 pp across four alpha levels, because the channel cannot separate correct items from hallucinations. We recommend that audits report calibration alongside OOD, validate the matcher producing the OOD number, and use catalog-anchored elicitation. --- ### Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification Authors: M. Sajid, A. Quadir, A. Rahaman, P. N. Suganthan, M. Tanveer Published: 2026-08-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.10007v1 The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL), treat all training samples uniformly, which limits their robustness and effectiveness when applied to real-world datasets containing noise and outliers. Furthermore, the propagation of contaminated features across hidden layers negatively influences the decision-making capability of these models. To overcome these limitations, we propose intuitionistic fuzzy dRVFL (IF-dRVFL) and intuitionistic fuzzy edRVFL (IF-edRVFL) frameworks that enhance model robustness. The proposed models unify intuitionistic fuzzy theory to exploit sample neighborhood information in the kernel space by jointly considering membership and non-membership degrees for each sample. Membership degrees are computed based on the distance of samples from their respective class centroids, while non-membership degrees quantify sample heterogeneity within local neighborhoods. These measures are employed to assign adaptive weights to training samples, enabling effective discrimination among clean, noisy, and outlier data points. Extensive experiments conducted on UCI and KEEL benchmark datasets, with and without the presence of Gaussian noise, demonstrate the superiority of the proposed IF-dRVFL and IF-edRVFL models over existing SOTA fuzzy and non-fuzzy approaches. The source code is available at https://github.com/mtanveer1/IF-edRVFL. --- ### ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models Authors: An Sui, Yuzhu Li, Fuping Wu, Xiahai Zhuang Published: 2026-08-07 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.10004v1 Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time intervention. Recent variants have improved CBMs through richer concept representations, uncertainty estimation, and dependency modeling. However, robust reasoning under unreliable concept states remains underexplored. Without such reasoning, misleading semantic evidence can propagate through the bottleneck, compromising both explanations and downstream predictions. To address this issue, we propose ReCBM, an uncertainty-gated relational reasoning framework for CBMs. ReCBM introduces semantically defined concept relations into the bottleneck and uses uncertainty to guide their refinement. By modeling co-occurrence, implication, and exclusion, ReCBM specifies how evidence is exchanged across concepts, while uncertainty modulates the contribution of each concept during this process. Experiments across diverse datasets showed that ReCBM improved concept and task recovery under missing and flipped concepts, supported uncertainty-aware intervention, and extracted compact task-relevant concept subsets without degrading downstream performance. --- ### LoRCA: LoRA Cycle Adaptation for Histology to HiP-CT Translation with DINOv3 Authors: Yang Zhou, Edoardo Occhipinti, Banboye Kidzeru Elvis, Jishizhan Chen, Stathis Megas, Joseph Brunet, Joanna Purzycka, Theresa Urban, Hector Dejea, Sarah Amalia Teichmann, Menna R Clatworthy, Paul Tafforeau et al. Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.10002v1 Hierarchical Phase-Contrast Tomography (HiP-CT) is a synchrotron based X-ray imaging technique that enables non-destructive, volumetric imaging of intact organs with multi-resolutions bridging 20 $μm$/voxel for whole organs to near-cellular resolution ($\sim$0.8 $μm$/voxel) in local regions. This offers the opportunity to bring volumetric whole-organ context to histology. However, nonlinear registration between H\&E histology and HiP-CT volumes is challenging due to the differences in feature representations of different colour spaces. Synthesis-before-registration methods have shown strong results in histology-to-MRI and histology-to-CT alignment. However, existing approaches either rely on manual anatomical contours or are trained from scratch without semantic constraints, limiting their generalisability to soft tissue organs and novel modalities. We propose LoRCA (LoRA Cycle Adaptation), a cycle consistent style translation framework built on a shared frozen DINOv3 with modality-specific LoRA adapters, learning modality-specific representations that are decoded and adversarially trained. LoRCA enables structure-preserving translation without requiring paired training data. The frozen backbone is intended to be a structural anchor that prevents content drift by preserving pretrained semantic-extraction capability. We evaluate translation quality using Fréchet Inception Distance (FID) and structural fidelity via mutual information and Canny edge preservation. LoRCA outperforms CycleGAN in both translation quality and structural consistency. As a preliminary indicator of downstream registration utility, we find that style-translated images yield increased feature correspondences under MatchAnything on manually aligned HiP-CT and histology test pairs, suggesting that LoRCA-style translation is a promising step towards 2D histological sections to 3D HiP-CT volumes registration. --- ### Implicit representations are dead. Long live explicit primitives! Authors: Nil Stolt-Ansó, Maik Dannecker, Wenqi Huang, Andras Jakab, Daniel Rueckert Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.10001v1 Continuous parameterization of medical data has emerged as a powerful paradigm for resolution-independent image representation. While Implicit Neural Representations offer high fidelity and compact storage, their reliance on global Multi-Layer Perceptrons incurs sizeable computational costs, large memory requirements, and extensive optimization times. As medical imaging trends towards ever-more detailed, high-resolution volumes, these costs impose significant bottlenecks in the applicability of implicit approaches. Recently, explicit Gaussian-based primitives have revolutionized the representation learning paradigm by trading deep network evaluations for localized, rasterization-friendly primitives. In this paper, we present a comprehensive, cross-dimensional evaluation of Gaussian representations against implicit approaches for medical imaging applications. First, we outline a theoretical overview on the mathematical properties offered by explicit primitives beyond what is capable under the implicit neural paradigm. Subsequently, we benchmark the computational performance on two demanding image datasets: 2D microscopy histology and 3D lung Computed Tomography (CT). Our experiments demonstrate that Gaussian representations consistently match or surpass reconstruction metrics compared to implicit methods across all compression factors, while displaying significantly lower optimization times, and memory requirements. Together with the compelling mathematical properties offered by explicit primitives, these findings motivate the wider adoption of Gaussian representations and position them as an attractive direction for future research in medical imaging. --- ### Pre- to Post-Contrast Synthesis of Breast DCE-MRI using Latent Bridge Matching Authors: Sina Amirrajab, Zohaib Salahuddin, Henry C Woodruff, Philippe Lambin Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.10000v1 Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is central to breast cancer imaging, but gadolinium administration increases scan burden and motivates contrast-reduced alternatives, including synthetic contrast generation. We propose a latent bridge matching (LBM) framework for synthesizing peak-enhanced breast DCE-MRI from pre-contrast images in the MAMA-SYNTH challenge setting. Instead of starting from Gaussian noise as in conventional latent diffusion models (LDMs), the proposed model learns a conditional bridge between paired pre-contrast and peak-enhanced VAE latents. A latent UNet predicts the remaining correction from intermediate bridge states to the peak-enhanced latent, enabling iterative refinement while keeping the trajectory anchored to patient-specific anatomy. We evaluated two LBM conditioning variants on 91 DUKE validation cases. For the tumor-conditioned variant, tumor masks were used as conditioning inputs. Tumor-conditioning improved performance compared with pre-contrast conditioning, reducing MSE from 1.023 to 0.940 and FRD from 7.523 to 4.716, while increasing tumor SSIM from 0.355 to 0.429. The tumor-conditioned LBM also outperformed the evaluated LDM baseline on this validation cohort. These results suggest that latent bridge matching is a promising pre-contrast-anchored formulation for virtual contrast enhancement, while further work is needed to validate generalization and remove dependence on ground-truth tumor masks at inference. --- ### Robustness of transferability estimation metrics for medical imaging Authors: Niclas Claßen, Théo Sourget, Dovile Juodelyte, Rob van der Goot, Veronika Cheplygina Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.09999v1 In transfer learning, the choice of source model largely influences the performance on a target dataset. Still, selecting a fitting source remains a challenging task, especially in medical imaging where one has to decide between models pre-trained on off-the-shelf options, such as ImageNet, and domain specific datasets. Transferability estimation (TE) metrics address this problem by aiming to predict the best performing source model in a computationally cost effective way. However, previous work has reported conflicting TE metric performances due to differences in experimental setups. Moreover, most TE metrics are designed for and evaluated on natural images, while being optimized for accuracy, whereas in medical imaging metrics that are more robust to class imbalance are typically used. We study the impact of varying the target dataset as an isolated factor, by constructing miniature populations of different sample sizes and random seeds. In addition, we investigate the influence of the evaluation metric used to obtain the reference ranking. We find that small modifications to the target dataset change the rankings. Furthermore, we show that the choice of evaluation metric affects the reference rankings and therefore the evaluation of TE metrics. Overall, we observe a low agreement between rankings from TE metrics and reference. The code, model checkpoints and data splits used in this work are available through https://github.com/niclasclassen/robustness-of-transferability-estimation-metrics-for-medical-imaging. --- ### Towards Sustainable Artificial Intelligence: A Comprehensive Review and Comparative Analysis of Deep Learning Models' Carbon Footprint Authors: Samar Garrab, Sarra Boughriou, Manel BenSassi Published: 2026-08-07 Categories: cs.AI, cs.CY, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2608.09998v1 Artificial Intelligence (AI) and Machine Learning (ML) have become powerful tools for supporting and automating complex human tasks. Despite their benefits, growing attention has been directed toward their environmental implications, primarily due to their high energy demands and associated carbon emissions. This concern is particularly relevant in light of the increasing deployment of large-scale models, especially Deep Learning (DL) architectures, which provide advanced predictive capabilities but require substantial computational resources. This paper presents a systematic review of research on Green AI, Green DL, and optimization techniques aimed at reducing the environmental impact of AI models. In addition, we examine and compare several carbon measurement tools for estimating emissions generated by AI algorithms. To complement the review, we conducted an empirical evaluation using a CPU-based experimental setup, in which six DL models were implemented for a multi-label classification task. The objective was to quantify and compare their overall carbon emissions and to determine which stages of the DL lifecycle contribute most significantly to the total footprint. The results show that the training phase is the primary source of emissions. Moreover, the findings reveal that increased architectural complexity does not systematically translate into proportional accuracy gains, highlighting the importance of carefully balancing predictive performance and environmental cost. These results reinforce the need to integrate sustainability considerations into model selection and AI system design. --- ### Transformer Geometry Observatory TGO-IV: Developmental Topology Observatory Authors: Kaustubh Kapil, Kishor P. Upla Published: 2026-08-07 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.09997v1 Transformers have had a profound impact on the world of language processing and computer vision. As efforts to answer the million-dollar question of ``How does a Transformer learn?" have been increasing, existing interpretability studies primarily analyze representations at isolated layers or the network as a whole, while the developmental evolution of individual representations and its manifolds across transformer layers remains underexplored. With this work, we aim at providing a comprehensive analysis of the evolution of representations as the representation point cloud transforms across the layers; thereby attempting to isolate layers or establish a trend which comes closer to justifying how and when raw input representations evolve into task-relevant feature representations. Thus, Transformer Geometry Observatory-TGO-IV introduces a topological framework for analysing the evolution of Transformer representations through the lens of Persistent Homology. Rather than studying local geometric properties alone, TGO-IV constructs Vietoris--Rips simplicial complexes from token-level representation point clouds and investigates the evolution of their persistent topological signatures across Transformer layers. The proposed framework comprises complementary topological observatories including Persistence Diagrams, Barcode Diagrams, Betti Curves, Persistence Landscapes, Bottleneck Distance, and Wasserstein Distance, enabling a comprehensive analysis of how the global topology of representation point clouds develops throughout the forward pass. --- ### Energy and Performance Benchmarking of Deep Learning Models for Breast Cancer Detection Authors: Samar Garrab, Ghada Achour Published: 2026-08-07 Categories: eess.IV, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.09996v1 Recent advances in machine learning have greatly improved breast cancer detection, enabling more accurate and timely diagnosis. Deep learning (DL) models show strong potential for medical image analysis; however, as their architectural complexity increases, their environmental impacts are becoming a growing concern. In this paper, we present a comparative analysis of seven DL models for breast cancer detection on two medical datasets: Breast Ultrasound and BreakHis 400X. The evaluated architectures range from Convolutional Neural Networks (CNNs) and transformers to hybrid models. In addition to performance metrics, we assess CO2 emissions during both training and inference. Our results show that EfficientNet and ResNet consistently deliver strong performance, although with higher CO2 emissions. The selected transformers, such as DeiT-Tiny, perform competitively on both datasets, whereas DenseNet121 achieves lower accuracy. On the Breast Ultrasound Dataset, DeiT provides the most favourable balance between accuracy and energy consumption, whereas on the BreakHis dataset, the ViT and Swin models achieve the best results. Overall, our findings indicate that no single architecture category from the evaluated ones consistently dominates across the two selected datasets. Our results highlight the importance of jointly considering performance, emissions, and dataset characteristics when selecting models for medical applications. --- ### Structural Guidance for Unified Joint Demosaicing and Denoising Authors: Qixin Zheng, Ping Chen, Qiangqiang Shen, Haijin Zeng Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.09995v1 Joint demosaicing and denoising is a fundamental step in camera image signal processing, yet remains challenging because different Bayer-like color filter arrays (CFAs) and sensor noise jointly corrupt both color sampling and image content. Existing unified restoration networks explicitly model CFA geometry but are still driven primarily by pixel-level supervision, making them prone to structural degradation around edges, repetitive textures, and moiré patterns where local evidence is unreliable. We attribute this limitation partly to the absence of explicit structural guidance beyond pixel-level reconstruction supervision. Motivated by this observation, we propose a structural-guided unified restoration framework that injects pretrained structural knowledge into CFA-aware image restoration. Our model receives a unified five-channel observation consisting of the raw mosaic, CFA masks, and a noise-level map. A SwinIR restoration branch reconstructs pixel details under CFA-conditioned modulation, while a parallel structural reasoning branch extracts complementary structural cues from a sparse pseudo-RGB observation. To bridge the substantial domain gap between sparse noisy sensor data and the natural-image pretraining domain of the structural encoder, we introduce a lightweight trainable adapter before residually fusing structural and restoration features. A shared decoder jointly predicts the restored RGB image and an auxiliary clean mosaic, providing supervision in both image and sensor domains. Extensive experiments across multiple CFA patterns and noise levels demonstrate consistent improvements over state-of-the-art unified and CFA-specific methods, indicating that adapted structural priors can enhance robust camera image restoration. The source codes and dataset are provided in the supplementary material. --- ### SpecF2M: A Spectral-Aware Multi-task Network Estimating Axial Length and Refractive Error from Pediatric Fundus Photographs Authors: Mengxian He, Xinyue Liu, Yunyun Sun, Wei Hao, Minqing Zhang, Lichun Wang, Shunyi Zhang, Wu Yuan Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.09994v1 Spherical Equivalent Refraction (SER) and Axial Length (AL) are core indicators for pediatric myopia screening, yet their measurements require dedicated biometry and cycloplegic refraction. Fundus photography offers an accessible imaging modality, as myopia-related posterior-pole changes are visible in 45$^\circ$ fundus images. However, these cues are often low-contrast, spatially diffuse, and multi-scale. Moreover, AL, Sphere (SPH), and Cylinder (CYL) share partially overlapping but non-identical anatomical correlates. We propose SpecF2M, a spectral-aware multi-task network for estimating AL and SER components from pediatric fundus photographs. SpecF2M integrates a deterministic anatomy-guided enhancement module, a hybrid spatial--spectral backbone combining MixCNN and Hybrid Spectral Learning (HSL) blocks, and an expert-routing head for component-level estimation of AL, SPH, and CYL. On a pediatric cohort of 4,359 eligible child visits and 6,966 fundus images, SpecF2M outperforms controlled CNN/ViT baselines for AL and SPH estimation, achieving MAEs of 0.5347 mm and 0.7062 D, respectively. Component-level analysis further reveals asymmetric task coupling, where CYL exhibits weaker association with fundus-derived myopic patterns than AL/SPH. These results support fundus-based, screening-oriented estimation of pediatric myopia indicators, while external validation remains necessary before deployment. --- ### APCReg: Anatomical-Prior-Guided Coarse-to-Fine CBCT--IOS Registration via Multi-View Projection and Reliability-Controlled Residual Correction Authors: Xincan Zheng, Yaqi Wang, Zhi Li, Jiahao Bao, Lan Feng, Yiru Xia, Shuai Wang Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.09993v1 Registration between cone-beam computed tomography (CBCT) and intraoral scans (IOS) is essential for patient-specific surgical planning. However, disparate imaging modalities, limited overlap, and large pose offsets make automated registration unreliable. Consequently, clinical registration remains dependent on conventional geometry pipelines and manual clinician adjustment. To address these challenges, we propose APCReg, an anatomical-prior-guided coarse-to-fine framework for global registration and reliability-controlled residual correction. Specifically, multi-view anatomical coarse registration (MACR) performs ordered orthogonal projection alignment (buccal, proximal, and occlusal) to decompose the six-degree-of-freedom search before three-dimensional refinement. Overlap-aware residual registration (OARR) combines shared KPConv features, a folded arch-length cue, overlap-gated cross-attention, and Sinkhorn matching. Finally, dental-arch-structured hypothesis selection evaluates diverse poses on held-out reliable correspondences, while a ground-truth-free coarse-retention guard conditionally retains a geometrically reliable coarse pose. On 60 held-out jaw pairs, APCReg achieves a submillimeter mean Chamfer distance of 0.87 mm and a Hausdorff distance of 2.92 mm under this evaluation protocol, and ranks first across the six reported metrics among the evaluated open-source baselines. --- ### Knowledge-Guided 3D CT Generation: A Conditioning-Centric Taxonomy Authors: Francesca Pia Panaccione, Eugenio Lomurno, Matteo Matteucci Published: 2026-08-07 Categories: eess.IV, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.09992v1 Controllable generation guided by external knowledge is a key requirement in modern generative deep learning applications, enabling the synthesis of samples with explicit constraints on semantic content, structural properties, and variability. In 3D Computed Tomography (CT), such control is essential for clinical applications, including data augmentation, privacy-preserving data sharing, and the simulation of specific anatomical or pathological scenarios. While research on conditional 3D CT generation has expanded rapidly, the diversity of existing approaches makes systematic comparison difficult and obscures fundamental design choices. In this survey, we propose a conditioning-centric taxonomy that organizes the literature along three orthogonal dimensions: the type of external knowledge (K), the knowledge integration paradigm (I), and the generative architecture (A). This factorization defines an explicit design space (K x I x A) that provides a unified perspective on prior work. Using this framework, we systematize existing methods, identify dominant trends and recurring design patterns, and highlight underexplored regions of the design space that point toward promising directions for future research. --- ### Longitudinal 3D Foundation Modeling for Neoadjuvant Breast Cancer Response Prediction from Serial DCE-MRI Authors: Fidel Omar Tito Cruz, Neda Ghafouri, Zengyan Wang, Pegah Khosravi, Yu Tian, Chen Chen Published: 2026-08-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.09991v1 Pathologic complete response (pCR) is an important endpoint in neoadjuvant chemotherapy (NAC) for breast cancer, and predicting pCR from imaging during treatment could support treatment response assessment. Many existing imaging-based approaches rely on a single static timepoint, which fails to capture changes that occur during treatment. In this work, we present a longitudinal framework that combines a frozen 3D foundation encoder (Pillar-0) with our Temporal Dynamics Network (TDN) to predict treatment response from serial Dynamic Contrast-Enhanced (DCE) MRI acquired across four clinical timepoints from pre-treatment to pre-surgery. The TDN combines time-aware volumetric embeddings with clinical and treatment data to predict pCR. Evaluated on 982 patients from the combined I-SPY2 and ACRIN-6698 cohort, the proposed model achieves strong performance across all reported metrics when longitudinal 3D imaging is fused with clinical data (test AUROC: 73.6%, balanced accuracy: 69.1%). While clinical variables provide the strongest individual predictive signal, longitudinal 3D imaging contributes complementary information when fused with clinical data, improving pCR prediction. Our source code is available at: https://github.com/omarftt/longitudinal_temporal_pillar. --- ### Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks Authors: Christopher Fulton, Irene Tsapara, Lawrence Fulton Published: 2026-08-07 Categories: cs.PF, cs.LG arXiv: https://arxiv.org/abs/2608.07822v1 Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood. We compare real-valued, quaternion-valued, and quantum classification heads on identical frozen features across MNIST, FashionMNIST, and CIFAR-10. CIFAR-10 uses a learned 16-dimensional bottleneck and frozen ImageNet-pretrained ResNet18 features to separate architecture from representation quality. Quaternion classifiers match or approach real-valued baselines while outperforming shallow VQCs. On MNIST and FashionMNIST, quaternion networks nearly equal real-valued MLPs, whereas product-state VQCs show lower accuracy and higher cost. On CIFAR-10, quaternion networks retain 94--97% of real-valued performance and remain stable under a 32-fold increase in dimensionality. Product-state circuits underperform quaternion classifiers, while entanglement gives modest grayscale gains but reverses under pretrained CNN features (9.25 pp degradation vs.\ product-state). Fubini--Study/QFI natural gradients improve geometric alignment but not short-horizon loss reduction vs.\ Adam. A Friedman test on five-seed MNIST detects model differences ($χ^2=12.796$, $p=0.0051$, $n=5$), with Wilcoxon tests yielding large effect sizes ($d>5$) for QuatNet vs.\ quantum comparisons. For FashionMNIST and CIFAR-10, large effects ($d>2.0$) are the primary statistic given $n=3$. These results indicate that quaternion networks provide efficient, stable $\mathrm{SU}(2)$ alternatives to shallow VQCs on tasks lacking intrinsic quantum structure. Shared local $\mathrm{SU}(2)$ geometry and shallow entanglement are insufficient, within the regime studied, to confer practical quantum advantage. Conclusions are limited to shallow, measurement-limited circuits on such tasks. --- ### Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation Authors: Donald Loveland, Liam Collins, Bhuvesh Kumar, Danai Koutra, Neil Shah Published: 2026-08-07 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.07816v1 Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories. In these systems, items are often represented through semantic IDs (SIDs) added to the LLM vocabulary as special tokens. Ideally, SIDs imbue item token representations with semantic priors, thereby improving model generalization. However, standard vocabulary expansion typically initializes these tokens as random Gaussian vectors, discarding the SIDs' underlying continuous geometry and forcing the LLM to relearn token relationships from interaction data. To demonstrate the consequences of this design, we first show that training from this initialization tends to organize SID embeddings around item popularity rather than semantics. We further show that, despite partially reducing the reliance on popularity and improving cold item performance, the computationally expensive process of continual pretraining (CPT) fails to reliably recover the original semantic geometry. To address these findings, we propose a simple, parameter-free intervention that initializes SID token embeddings directly from their corresponding centroids in the semantic embedding space. Requiring only a few lines of code and no additional training or inference overhead, this drop-in approach improves pure-SFT Recall@5 by up to 16%, reaches peak performance with up to 40% fewer SFT steps, and improves cold-item Recall@5 by up to 60%. Moreover, on datasets that benefit from additional CPT, centroid initialization reaches comparable performance while requiring half as many CPT epochs. Together, our findings show that preserving SID geometry, beyond shared-prefix structure, provides a simple and effective semantic prior for LLM-based GR. --- ### Shape Mutating Expert Compression:LorExperts and BTExperts Authors: Inesh Chakrabarti, Sourjya Roy, Bowen Bao, Thiago Crepaldi, Spandan Tiwari, Ashish Sirasao Published: 2026-08-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.07814v1 Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many expert weight matrices. Expert pruning (e.g., REAP) and merging reduce cost but sacrifice accuracy and require retraining the router; low-rank delta decomposition of experts (e.g., D^2-MoE) preserves all experts and the router, but degrades sharply as the expert count grows because a single shared component cannot approximate many near-orthogonal experts. Because MoE expert weights are near-orthogonal, a single shared component (as in prior delta decomposition) scales poorly with the expert count; we show that experts nonetheless organize into functional co-activation communities that are decoupled from weight similarity. Building on this, we introduce LorExperts, a router-preserving compression method that clusters experts, keeps one full-precision dominant per cluster, and represents the remaining members as low-rank corrections to their local dominant. LorExperts retains all experts and the original router (no router retraining). At ~50% expert compression on Qwen3-30B-A3B and Gemma-4-26B-A4B, LorExperts preserves downstream accuracy and perplexity better than the baselines on most of the tasks; the margin over D^2-MoE grows with expert count E. We further give a reconstruction fine-tuning procedure for LorExperts, and BTExperts, a tree organization of dominants and corrections that enables inference-time amortization of shared computation. --- ### When the Judge Should Not Decide: Evidence-Locked, Non-Compensatory Selection Bounds LLM-Judge Failure in Reasoning Pipelines Authors: Yiyao Zhang, Diksha Goel, Hussain Ahmad, Shixun Huang, Jun Shen Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07813v1 An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships. We show that the cost of that decision depends less on judge accuracy than on the decision rule the judge is embedded in. On frozen candidate pools from four GRPO policies, an unconstrained scalar DeepSeek-R1-7B judge buys almost nothing over answer-level majority vote (+1.0 pp on 500 GSM8K questions, +0.34 EM on 300 HotpotQA questions), and on a frozen-rule 30-question confirmation split it is 10 points worse than majority, a judge that destroys accuracy while scoring candidates confidently. We then subordinate the same judge to Evidence-Locked Derive-Gate-Repair (EL-DGR), a task-adaptive non-compensatory rule under which a judge preference may override evidence-supported consensus only with an extractive evidence certificate, and a repair only when neither alternative is certified and the repair is. With no change to the judge, the candidates, or the budget, EL-DGR reaches 58.2% on GSM8K (vs. 56.8% judge, 55.8% majority, 55.4% first candidate) and 17.33 EM / 25.46 F1 on HotpotQA (vs. 15.67/23.49, 15.33/23.19, 15.33/22.97), improving on first-candidate GRPO by +2.8 pp (exact McNemar p=0.0026) and +2.00 EM (p=0.070, borderline). A decision audit shows why: EL-DGR overturns consensus on only 8 of 30 pilot questions and never converts a correct consensus into an incorrect answer. We also report what did not work: the same seven-channel decomposition used as a step-level gated training reward is null, and corrected channel-drop ablations show no channel is individually necessary (p=1.0 throughout). The practitioner-facing finding is negative about judges and positive about admissibility, bound the judge's blast radius rather than trying to make it accurate. --- ### On the use of foundation models in cognitive science Authors: Raj Sanjay Shah, Alex Warstadt, Michael Frank, Sashank Varma Published: 2026-08-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.07812v1 A host of recent studies have evaluated the cognitive and developmental alignment of Foundation Models (FMs). These investigations include evaluations of their correspondence to adult performance across a range of cognitive domains, as well as whether aspects of model training track children's cognitive development. However, using FMs as candidate cognitive models poses significant methodological and conceptual challenges. A key question underlies this effort: under what conditions does behavioral alignment justify treating FMs as explanatory models of cognition? In this paper, we articulate a four-stage inferential framework for evaluating FMs as cognitive and developmental models: adapting human experimental tasks to model-compatible formats, specifying linking hypotheses that map model outputs to human measures, evaluating behavioral correspondence, and comparing across candidate models or manipulations. We clarify the role of linking hypotheses in mapping model outputs to human behavioral measures, identify challenges that constrain alignment claims, and propose principles for theory-driven and comparative evaluation. Throughout, we argue that behavioral fit alone is insufficient. Alignment becomes scientifically meaningful only when embedded within explicit theoretical commitments, theory-diagnostic tasks, and systematic contrastive evaluation across candidate models. --- ### CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift Authors: Yiyao Zhang, Diksha Goel, Hussain Ahmad, Shixun Huang, Jun Shen Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07809v1 A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong. We study both halves of that requirement with CausalNav, a controller built around a signed, action-conditioned transition graph over identified state coordinates. At deployment CausalNav simulates a small library of intervention sequences, converts their objective error into policy-logit advice, and admits that advice only when a scale-free predictive-reliability certificate, a policy-margin gate, and an argmax-agreement gate all pass; otherwise it falls back exactly to its own model-based base controller. We evaluate against nine controlled baselines (transformer, recurrent, split-latent, graph, causal-induction, and three recent model-based reasoning modules) on CartPole-v1 and discretized Pendulum-v1 with physical-parameter shifts, under one shared PPO trainer, one interaction budget, and ten held-out seeds (200 runs). CausalNav attains the best average rank (1.25 of ten). The diagnostic result is more informative than the ranking: the learned graph recovers structure well above chance (CartPole F1 = 0.59 +/- 0.09), yet per-seed structural fidelity is uncorrelated with per-seed control benefit (r = -0.15, p = 0.67), and the certificate abstains on 10/10 Pendulum seeds, where forcing the planner on costs return. Model fidelity did not predict downstream control utility in our setting; certified abstention, not better prediction, is what made the world model safe to deploy. --- ### The Anatomy of a Prompt Injection: A Component Model for Structured Analysis Authors: Jeremy McHugh Published: 2026-08-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.07808v1 Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis. This paper formalizes the structure of prompt-injection artifacts, enabling defenders, red teamers, and cyber threat intelligence (CTI) teams to label, compare, and mutate attacks without relying on fragile string matching. Because large language models compile varied natural-language realizations into identical executable actions, labeling must track attacker intent (tool targets, sinks, and effects) rather than surface wording. We propose a seven-component model (carrier, delivery vector, concealment, context-break, privilege escalation, payload, and return channel) consisting of five artifact fields and two environment fields. This framework unifies roles partially addressed by HOUYI's payload decomposition, the Promptware Kill Chain, and campaign taxonomies, while framing minimal jailbreak frameworks like ReNeLLM as projections onto a restricted subspace. We provide clear labeling rules, a logical analysis record mapping directly to industry CTI schemas, worked examples including EchoLeak (CVE-2025-32711) and an in-the-wild malware AI-evasion sample, and an illustrative agentic flowchart. ---