# Research Papers — 2026-10 · bundle page 130 of 156

> Full-text markdown of papers #6451–6500 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-10/page/130
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/129.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/131.md)

### When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models

Authors: Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu, Morris Yu-Chao Huang, Yicheng Lin, Wei Han, Tianlong Chen, Mingyuan Wu, Hanchao Yu, Gaojie Jin, Lu Liu, Bo Sun et al.
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07018v1

Vision-language models (VLMs) have achieved strong performance in multimodal reasoning, yet they remain prone to generating plausible but incorrect answers. Self-verification offers a practical way to improve answer reliability without relying on external judges, but existing methods typically depend on a single verification criterion or fixed prompt, resulting in incomplete and unstable reliability estimates. We first systematically analyze how verifier capability and prompt design affect verification performance. Our findings show that stronger verifiers provide more reliable judgments, while verification performance is highly sensitive to prompt choice, with no single prompt consistently dominating across tasks. Guided by these findings, we propose \texttt{MOTIVE}, a \textbf{M}ulti-View Self-Verificati\textbf{O}n wi\textbf{T}h Rel\textbf{I}ability-Guided Selecti\textbf{VE} Rethinking framework for reliable multimodal reasoning. \texttt{MOTIVE} evaluates each candidate answer from complementary verification perspectives and learns a correctness-aligned reliability score through correctness-grounded multi-view verification learning. During inference, this score governs an accept-or-rethink decision, allowing reliable answers to be returned directly while uncertain ones trigger history-guided rethinking. Extensive experiments across diverse multimodal benchmarks and VLM backbones demonstrate that \texttt{MOTIVE} consistently outperforms strong self-verification and self-correction baselines. Further results show that reliable verification improves accept-or-rethink decisions and reduces unnecessary reasoning turns, enabling more reliable and efficient self-verification without an external judge.

---

### Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection

Authors: Mengyang Zhao, Teng Fu, Haiyang Yu, Ke Niu, Bin Li, Xiangyang Xue
Published: 2026-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.07016v1

In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn from these samples alone. Some vision-language methods therefore use manually specified descriptions to supply explicit anomaly semantics. However, constructing these descriptions requires product-specific effort, and their effectiveness depends on prompt selection. We propose Anchor and Adapt, a two-stage prompt learning framework that separates the acquisition of anomaly semantics from adaptation to target normal appearance. Stage I learns transferable normal and abnormal anchors from annotated auxiliary data. Stage II keeps these anchors fixed and adapts an additional normal branch using the few target normal samples. The inherited and adapted normal branches jointly characterize target normality, with text-anchor regularization encouraging consistency with the generic normal prior and separation from the abnormal anchors. This design retains learned anomaly knowledge while reducing dependence on category-specific anomaly templates, without requiring synthetic anomaly generation. Cross-dataset experiments between MVTec-AD and VisA under 1-, 2-, and 4-shot settings demonstrate competitive detection and localization performance. Controlled ablations assess the roles of transferred anchors, asymmetric adaptation, dual-normal representations, and anchor regularization.

---

### DTFormer: Text-Guided Semantic Alignment for RGB-D Segmentation

Authors: Ziang Wei, Yinlong Liu, Yan Xia, Alois Knoll, Hu Cao
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07014v1

RGB-D semantic segmentation has made notable progress by fusing RGB and Depth, yet mainstream models still learn features almost exclusively from pixel-level supervision, lacking direct high-level semantic constraints. This raises a central question-can external knowledge such as language priors inject stronger semantic discriminability into mainstream RGB-D segmentation models. We present DTFormer, a novel tri-modal (RGB-D-Text) semantic segmentation framework. At its core is Text-guided Semantic Alignment Module (TSAM) that first encodes textual cues into a set of semantic prototypes and then explicitly aligns multi-modal RGB-D features with these prototypes at multiple encoder and decoder layers. This design imposes strong semantic regularization on representation learning, guiding the network toward more discriminative features. Extensive experiments on multiple benchmarks show that DTFormer delivers consistent gains while remaining simple and efficient. Our results demonstrate that explicit semantic alignment offers an effective and practical route to improving RGB-D semantic segmentation. The code will be released upon acceptance.

---

### Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks

Authors: Boyuan Chen, Yehia Dawoud, Hailemariam Mersha, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad Shafique
Published: 2026-10-04
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.07009v1

Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313-prompt StrongREJECT slice, using five multimodal models and an additional appendix evaluation of InternVL3.5-8B. The harmful instruction is held constant across conditions; the baseline matrix uses one draw per prompt, and paired ablations use three draws with an automated rubric judge. A bare harmful query, with or without a benign unrelated image, produces little attack success on most victims, while attack images substantially increase it. First, per-tile entropy and JPEG size do not reliably distinguish attack tiles from size-matched benign distractors, limiting density-only screening. Second, earlier tile-count ladders were confounded by payload visibility. A corrected region-count test found no detectable effect, so the role of tile-count structure remains unresolved. Third, on Qwen3-VL-8B, the E4 manipulation that removes query-specific relatedness lowers ASR by about 0.12. This supports a bounded attribution to the relatedness manipulation, although image-text congruence remains unmeasured. A within-category control reproduces the direction on overlapping stimuli. Five tests survive the global statistical correction, but only E4 supports attribution to one measured descriptor; the within-category result is a robustness check, not a separate attribution. These conclusions remain conditional on the rubric judge.

---

### Learning to Curate What You Generate for Generalizable Few-Shot Class-Incremental Learning

Authors: Junhui Yin, Yuchen Yang, Yilin Yin, Shuai Na, Haoran Xi, Jianhua Yang, Muyi Sun, Man Zhang, Shengfeng He
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07008v1

Few-shot class-incremental learning (FSCIL) aims to learn novel classes from limited annotations while preserving prior knowledge. Existing methods typically assume a sufficiently large base session, but this assumption fails when both base and incremental data are scarce, leading to weak initial representations, semantic drift, and unstable boundaries. We study this underexplored yet realistic setting, termed Generalizable FSCIL (G-FSCIL), where the base session itself contains only a few classes. Although synthetic data can alleviate supervision scarcity, naively mixing generated samples often introduces semantic noise and exacerbates old-new boundary conflicts. To address this, we propose a framework that curates trustworthy synthetic knowledge for stable G-FSCIL. Specifically, we first construct class-specific synthetic candidate pools using a frozen latent diffusion model, where class inversion is performed at the first observation and the resulting condition embeddings are reused for on-demand generation. Building on these candidates, we learn a knowledge curation strategy that selects samples with both semantic consistency and visual diversity, and distill this process into a transferable selection policy during the base session, which is then reused without further optimization. Leveraging the curated synthetic data, we further design a boundary-stable incremental adaptation scheme, including synthetic-informed prototype initialization and bidirectional boundary calibration to mitigate old-new conflicts. Extensive experiments demonstrate that our method consistently outperforms existing FSCIL baselines, with reduced forgetting and improved balance between old and new classes. Code is available at https://github.com/NiHaoWoJiaoYYC/G-FSCIL.

---

### STOCK-JEPA: Prior-Anchored Latent Revision Representation Learning in Equity Markets

Authors: Yizhi Luo, Jiahe Yi, Jianhui Zhang, Shuo Sun
Published: 2026-10-04
Categories: cs.LG, q-fin.ST
arXiv: https://arxiv.org/abs/2610.07006v1

Learning effective representations helps characterize the structure and dynamics of equity markets from financial data with a low signal-to-noise ratio. Black-box deep models can capture complex patterns but may overfit sample noise and lack explicit economic structure. Meanwhile, classic linear financial models provide interpretable references, but their oversimplified assumptions leave non-linear signals uncaptured. To combine the strengths of these two directions, we propose Stock-JEPA, a joint-embedding predictive framework that learns predictable incremental revisions relative to a point-in-time financial prior. First, we leverage a low-complexity financial model to produce fixed statistics summarizing multi-horizon return and risk. A prior projector then maps these statistics into the target encoder's latent space as an anchor. Second, we design a context-conditioned revision predictor to estimate the future representation's predictable displacement from the anchor. Separate losses update the two branches: the anchor learns from prior statistics, while the revision captures additional predictable information from historical context. Third, we freeze all representation modules and train a downstream readout, evaluating its forecasts through cross-sectional ranking and portfolio performance. Theoretically, we prove that optimal revision reduces the prior anchor's expected squared error for the same future representation by exactly $\mathbb{E}(\|\boldsymbolΔ\|_2^2)$. This non-negative gain is the expected squared magnitude of the additional signal predictable from historical context. Experimentally, Stock-JEPA outperforms 13 strong baselines across large-scale China and U.S. equity universes on 5 key evaluation metrics. Ablation studies and representation analysis further demonstrate the value of the learned revisions for representation learning in equity markets.

---

### Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio

Authors: Boyuan Chen, Minseok Kim, Sohaila Abdulsattar, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad Shafique
Published: 2026-10-04
Categories: cs.SD, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2610.07005v1

We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio. The protocol masks frequency components of the perturbation in the short-time Fourier transform (STFT) domain and measures attack success and audio-span representations. On 520 AdvBench prompts, the primary judge labels 76.7% of adversarial inputs as jailbreaks. A condition-blind, single-annotator validation yields a Rogan-Gladen sensitivity estimate of 0.87 for this condition (about 0.83-0.95 with validation-rate uncertainty); this correction is not applied to masked conditions. The apparent frequency ranking depends on the partition: energy share alone predicts the standard eight-band ranking (Spearman's rho = 0.95), and equal-Hz and equal-energy partitions show that masking any tested band can sharply reduce attack success. At a finer 16-band equal-energy resolution, however, masking the narrow 7520-7960 Hz band leaves ASR at 0.10, which remains unresolved without a matched control. Matched-energy scattered-removal tests show that contiguous removal is more damaging in lower bands, while both forms approach the floor in upper bands. Global rescaling leaves ASR near baseline but tests amplitude sensitivity rather than frequency location. In a re-optimization pilot (n = 20), tested single- and two-band supports reach ASRs of 0.00, 0.25, and 0.40, while random supports covering about half the STFT bins reach a mean of 0.86. In a prompt- and energy-adjusted model, audio-span divergence is associated with band necessity, with the coefficient rising from +0.63 at the projector output to +0.93 at layer 30 (contrast +0.293, 95% CI (0.11, 0.51)). This association is not a causal localization, and single-layer patching does not establish a causal layer. The results support partition-aware auditing of frequency claims, leaving the fine-resolution top-band result and broader generality open.

---

### Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents

Authors: Sen Zhao, Jia Tang, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Ding Zou, Xinyu He, Xu Zhang, Junwei Han
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07004v1

Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for sequential or directed acyclic graph (DAG)-like structures, they struggle with workflow patterns such as verification-correction loops, convergent branch merging, and reusable intermediate states that arise naturally in real-world tool orchestration. We present TopoPlanner, a topology-consistent planning framework that lifts tool dependency graphs into cellular workflow complexes and uses them as topologyaware context for LLM tool planning. TopoPlanner retrieves a request-relevant closed subcomplex through cosheaf-consistent cellular retrieval, performs multidimensional structural reasoning over the retrieved topology, and interfaces the resulting cellular representation with the planner LLM for tool-sequence generation. Experiments on four tool-planning benchmarks with topology-guided loop, merge, and loop-merge workflows show consistent improvements over prompt-based and graph-enhanced baselines across different local LLM backbones.

---

### Should We Skip Diffusion?

Authors: Yiping Ji, James Martens, Simon Lucey
Published: 2026-10-04
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2610.07002v1

Diffusion models learn semantic representations while generating images. In the Decoupled Diffusion Transformer (DDT), a condition encoder provides features that guide a velocity decoder in denoising. To enable effective denoising at all noise levels, these features must capture both high-level abstract structures and low-level details. However, skip/residual connections in the encoder allow shallow features to bypass successive transformations, which may limit progressive abstraction, or at least make it difficult to disentangle different levels of abstraction. We propose DDT-RFE, which removes the residual connections around the Self-Attention and MLP operations in each encoder block while maintaining stable training. To retain the information that abstraction discards but that the decoder still needs, we fuse the input patch embedding with intermediate and final encoder features to form the encoder output. The decoder thus has access to information from multiple encoder depths, while each encoder block is able to learn more abstract representations. DDT-RFE achieves overall improvements over DDT across visual understanding tasks, including image classification, semantic segmentation, object discovery, and semantic correspondence, while using fewer encoder blocks. It also achieves a lower FID for image generation on ImageNet.

---

### Mask-Guided KV Cache Eviction in Block Diffusion Language Models

Authors: Gleb Molodtsov, Ekaterina Alimaskina, Evgeny Uskov, Artur Zagitov, Aleksandr Beznosikov
Published: 2026-10-04
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.06996v1

Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both memory capacity and generation speed. Reducing these costs requires deciding which past tokens to use for denoising the current block (selection) and which to keep in memory for future blocks (eviction). We propose MaskAhead, a training-free method that solves both tasks with a single mask-query-based ranking mechanism. Current-block masks guide selection, while probes of upcoming masked blocks guide eviction. Both rank KV entries by their estimated contribution to the attention output. Our quantized variant, Q-MaskAhead, computes selection and attention directly from low-bit KV, largely preserving the selected entries. Experiments on Fast-dLLM-v2, DreamReasoner, and LLaDA2.0-mini cover long-generation reasoning, long-prompt question answering, and needle-in-a-haystack retrieval. On long-prompt QA, MaskAhead reduces KV memory by $9.5\times$ on average with a 1.2-point mean F1 loss relative to dense inference. Q-MaskAhead increases the reduction to $20.1\times$ with a 2.3-point mean F1 loss. In a batch-32 systems profile, MaskAhead achieves $1.23\times$ end-to-end and $1.68\times$ decode-stage speedups over dense inference.

---

### Joint upper-bound coverage and route-choice utility: an empirical evaluation on two urban proxy tasks

Authors: Jianing Long, Xiaobin Li, Wuming Lei, Weiguang Wang
Published: 2026-10-04
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2610.06995v1

Whether more accurate traffic forecasts or higher uncertainty coverage improve route decisions is unclear. We evaluate this question with a frozen protocol that separates speed error, joint candidate path upper bound coverage, route selection, and realized loss. Using processed road speed data from Beijing and Chengdu, we construct offline proxy tasks with 150 origin destination pairs, three candidate paths, and 14 test days per city. We compare raw 90th percentile path time bounds with jointly calibrated upper bounds under minimum bound route choice. Joint coverage rises from 83.19% to 92.26% in Beijing M1, from 75.14% to 88.33% in Chengdu M1, and from 74.01% to 90.64% in Chengdu M2. Yet C2 increases lateness by 0.1633, 0.7848, and 0.9200 percentage points, respectively, and mean travel time by 0.588, 3.082, and 4.418 seconds. In a separate Chengdu predictor comparison, a 14.91% reduction in speed mean absolute error accompanies a 1.4571 percentage point reduction in lateness under C0. Joint coverage is therefore not a surrogate for downstream route utility in these frozen tasks the offline results do not establish online or causal benefits.

---

### TARE: Weigh a Never-Poisoned Twin Before Reading Backdoor-Defense Costs

Authors: Ruizhi Xu, Wei Xu, Sibo Zhu
Published: 2026-10-04
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.06994v1

Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate removal from what the defense does to any model, and inherits the victim's start, which for three of BackdoorBench's sixteen attacks is a configuration file: WaNet, BPP and Input-Aware ship a MultiStepLR that never fires, so their victims never anneal and are the least accurate in 30/31 public CIFAR cells at $\leq$5%. On PreAct-ResNet18, fine-tuning-family defenses return a low start to their own level, so there the published cost is negative, the benchmark's rating clips the "gain" to zero, and 2 of 48 citing defense papers we read rest a no-cost claim on those cells; TSBD and CGD, re-run with their code, "gain" on a never-poisoned model too. A $2\times2$ editing only that scheduler line isolates the cause, its swapped arms self-registered before they ran: the sign of the fine-tuning family's clean-model cost reverses both ways while its published gain on the annealed victim only shrinks toward zero, 44/44 seeds following the schedule, replicated on BPP, FT-SAM, CIFAR-100 and VGG19-BN and induced in a second toolkit. TARE runs the same defense on a never-poisoned twin of the same recipe, schedule and seed (on BackdoorBench, $\leq$10 poisoned images, admitted only below 5% attack success); what the twin loses is the tare. On the BadNets grid seven of eight defenses charge the twin (Neural Cleanse only where its detector fires), +0.13 (fine-tuning) to +5.70 points (I-BAU); the eighth, ABL, destroys it. Within an attack the start cancels from rankings, so the tare re-orders nothing there; what poisoning adds beyond it is printed under two estimators and not corrected, its removal share unidentified. We ship the three-key patch, a signed tare column (7 attacks $\times$ 8 defenses) and TARE-Z, a twin-free estimator for seed-stable defenses.

---

### DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies

Authors: Zhishen Sun, Hongzhan Wang, Sizhe Dang, Guang Dai, Haishan Ye
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.06993v1

Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However, standard ES uniformly averages rewards across problems and compresses problem level population feedback into a single scalar, making it difficult to capture how the learning value of each problem changes with model capability. To address this limitation, we propose Difficulty-Aware Reweighting and Targeted Replay for Evolution Strategies (DART-ES). DART-ES estimates the local solvability of each problem from its pass rate across the perturbation population and aggregates historical observations to construct a dynamic difficulty state. This shared state jointly guides continuous difficulty reweighting and rare solvable sample replay, thereby improving perturbation direction evaluation and training data allocation without introducing an additional difficulty model or backpropagation. Extensive experiments show that DART-ES achieves good fine-tuning performance. DART-ES outperforms ES on all five base models and improves the average accuracy from 72.07\% to 73.53\%, exceeding the 73.26\% achieved by GRPO on GSM8K. Across five challenging mathematical reasoning benchmarks, DART-ES achieves an average accuracy of 49.20\%, compared with 48.34\% for ES and remains competitive with strong 7B models trained with RL. Further experiments show consistent gains in instruction tuning, code generation and the Countdown task with a 14B model, demonstrating strong generalization across tasks and scalability to larger models. Beyond performance gains, DART-ES also shows clear advantages in system efficiency. It reduces runtime per step by 15.2\%--50.2\% and peak memory usage per GPU by 21.1\%--51.1\% compared with GRPO. Despite performing full parameter fine-tuning, DART-ES also requires less runtime and GPU memory than GRPO+LoRA.

---

### When better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value

Authors: Jianing Long, Xiaobin Li, Wuming Lei, Weiguang Wang
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06992v1

Improved traffic forecasts do not necessarily yield better signal-control decisions. We investigate this gap through a layered diagnostic study using 29 days of reconstructed demand from Xuancheng, China, with seven dates reserved for testing. The framework evaluates point forecasts, conformal intervals, dependence-aware scenarios, and matched closed-loop controllers. Entry-level and movement-level forecasts reduce mean absolute error by 4.03% and 3.92%, respectively, relative to historical means. A nominal 90% conformal interval achieves 90.72% marginal coverage but only 75.66% on an ex-post high-demand subset. Interface audits identify decision-time leakage and reveal that only two of nine controlled intersections offer multiple effective actions. We correct the temporal interface and compare causal forecasts with a five-second event oracle using exhaustive joint-action search. A synthetic positive control demonstrates that future information can reduce the internal rollout cost by 61.5%. On the frozen test dates, however, causal forecasts and the event oracle increase queue vehicle?seconds by 6.09% and 3.39% relative to the matched no-future rollout, while the oracle reduces spillback exposure by 3.78%; paired-day bootstrap intervals cross zero. These findings indicate that forecast value depends on temporal observability, action identifiability, dynamics consistency, and objective alignment. The proposed protocol provides a practical way to diagnose where predictive improvements fail to translate into operational benefits.

---

### State-Aware Interaction MIL for Rare Joint Molecular Phenotype Prediction in Colorectal Cancer and Lung Adenocarcinoma

Authors: Dasari Naga Raju, Tripti Bameta
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.06991v1

Joint molecular phenotype prediction is complicated by small joint-positive populations and overlapping histological features across alternative molecular states. Existing computational pathology approaches typically predict biomarkers independently or formulate the joint-positive phenotype as a binary endpoint. Independent prediction does not model interactions between biomarker-specific histological representations, whereas binary joint prediction collapses the double-negative and two single-positive configurations into a single negative class. We propose State-Aware Interaction MIL, a weakly supervised method that preserves biomarker-specific histological representations, models their interaction, and supervises the complete four-state molecular configuration. We evaluate the proposed approach for joint BRAF+/MSI+ prediction in colorectal cancer and EGFR+/TP53+ prediction in lung adenocarcinoma using frozen UNI2-h and CONCH pathology foundation-model representations. With UNI2-h, State-Aware Interaction MIL achieved an average precision of 0.5566 in colorectal cancer (joint-positive prevalence 6.8%) compared with 0.5161 for NaiveMTL, and 0.2784 in lung adenocarcinoma (joint-positive prevalence 8.6%) compared with 0.2525 for IndependentPair. With CONCH, State-Aware achieved an average precision of 0.4410 compared with 0.3932 for DirectJoint in colorectal cancer and 0.1659 compared with 0.1226 for DirectJoint in lung adenocarcinoma. These results indicate that pathology foundation-model representations contain predictive information for rare joint molecular phenotypes and that preserving biomarker-specific representations within a structured molecular-state formulation can improve prediction of these phenotypes from histopathology.

---

### Repair Lot Skyline: A Weighted Constraint Satisfaction Approach to Pavement Repair Optimization from Geospatial Hazard Density

Authors: Takato Yasuno, Keita Kobayashi, Ryuta Sakaguchi, Takuya Okamoto
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.06989v1

Pavement agencies must translate a spatially distributed distress inventory into a bounded, actionable repair-lot plan: accident-critical defects (potholes) must always be addressed, lower-risk defects (cracks) should be included only when their benefit justifies the repair cost, and historical patch locations signal re-degradation risk without themselves triggering repair. We formalize this as a Repair Lot Skyline problem: a Weighted Constraint Satisfaction Problem (WCSP) defined over chainage (distance along the road) rather than over time, so that it requires only a single-epoch distress survey and makes no claim about future deterioration. The WCSP identifies 143 candidate hazard clusters (61 hard, 82 soft), of which 106 are merged into a final repair plan totaling 1,997.4 m---83.7% of the 2,385.9 m that would be required if every soft candidate were included regardless of cost. This plan covers 100% of observed potholes (138/138) and 91.6% of observed cracks (404/441), capturing 93.6% (542/579) of the total hazard benefit available in the full candidate set. The skyline frontier shows pronounced diminishing returns beyond this point: the remaining 37 excluded soft candidates would add only 6.8% additional benefit for a 19.4% increase in repair length. We further formalize the minimum-lot-length $L_{\min}$ and historical-context radius $κ$ as a joint, four-objective hyperparameter search over this WCSP; on the same case study, the recommended configuration ($L_{\min} = 14.7$ m, $κ= 10$ m) reduces repair-crew mobilizations by 7.1% relative to an untuned default, at the cost of a 12.9% larger budget and a 1.1-percentage-point lower crack coverage.

---

### An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing

Authors: Houru Jiang, Zixi Wang, Tengteng Cheng, Xueyi Li, Mingliang Hou, Jiaqi Zheng, Renqiang Luo, Teng Guo, Zitao Liu
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.06988v1

Knowledge tracing (KT) models are predominantly evaluated using aggregate metrics such as area under the curve (AUC) and accuracy. However, these global scores obscure where the remaining errors originate and fail to indicate whether a benchmark is approaching saturation. While estimating a global theoretical performance limit is challenging in realistic KT settings, it is possible to quantify local predictability. To address this, we propose an information-theoretic evaluation framework for KT benchmark diagnosis. We use Context Tree Weighting (CTW) on item-response histories and current-item queries as an operational causal uncertainty coordinate, while distinguishing it from the unobserved Local Irreducible Uncertainty (LIU) under the full KT information set. By projecting predictions onto this shared uncertainty coordinate, we evaluate model performance gains across distinct entropy bands rather than only at the global level. Comprehensive evaluations on NIPS Task 3/4 and Algebra 2005 reveal that model improvements are highly non-uniform. Modern KT models show substantial gains in high-entropy regions, and additional item-aware references, log-loss, and equal-frequency analyses support this localization. The framework also flags regions where apparent gains require checks for noise-sensitive behavior. By surfacing these local modeling failures alongside genuine gains, this approach provides a diagnostic tool for studying both residual predictive structure and the limitations of current KT benchmarks and models.

---

### EPOCH: Reliable Discovery through Evidence-Governed Search

Authors: Binjie Guo, Aisheng Mo, Ruitong Li, Xinle Deng
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06986v1

AI research agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize evaluator feedback without adequately governing how that feedback is interpreted, challenged, and reused. As a result, promising but fragile candidates can be promoted as discoveries, while benchmark improvements, finite certificates, and theorem-level claims are too easily conflated. We introduce EPOCH, an evidence-governed architecture designed to close this gap. EPOCH implements an evidence-governed discovery loop by combining explicit task contracts, typed memory, active falsification, admission checks, and independent replay, so that each candidate is evaluated against the strength and scope of the claim it supports. EPOCH achieves state-of-the-art aggregate performance on AlgoTune, substantially exceeding the strongest baseline in mean normalized score (0.65 vs. 0.53), and attains the highest mean score on the internal Math14 suite (0.57). It further shows favorable held-out behavior under official-test replay and leads the descriptive aggregate on AgentHPO. Across ten discovery problems, EPOCH delivers substantial task-specific advances, including improved executable constructions, optimized algorithms, counterexamples, and proof-supported results. These advances demonstrate its ability to convert search into concrete progress across mathematical and computational domains. Together, the results suggest that evidence governance is a necessary step toward AI research agents that produce not only stronger solutions, but also more trustworthy scientific discoveries.

---

### CrystalJev: calibrated foundation-model probabilities decide what to compute next in materials discovery

Authors: Peng Kang, Yaxuan Sun, Zhen Li, Yu Liu, Lei Zheng, Huibin Xu
Published: 2026-10-04
Categories: cond-mat.mtrl-sci, cs.AI, physics.comp-ph
arXiv: https://arxiv.org/abs/2610.06985v2

Atomistic foundation models screen hypothetical crystals by thresholding predicted energies, an output that states neither how likely a candidate is to be stable nor whether more computation would change the decision. CrystalJev reads one forward pass of a frozen potential on the unrelaxed structure and returns calibrated probabilities, conformal guarantees and a rule for escalating candidates to relaxation or density-functional theory (DFT). Across 65 Matbench Discovery models, threshold calls hide cost assumptions, and ordering slower computation by its value for the decision, rather than by probability, recovers most of its benefit at a tenth of its cost. In a registered prospective test with 2,100 DFT calculations on ionic substitutions, forecasts calibrated on existing data over-stated the stable fraction of new candidates by 0.9--2.2 percentage points, because the population had shifted, not the labelling protocol; a few hundred labels from the new pool removed this bias more reliably than label-free corrections.

---

### A Data-Driven Framework for Unsupervised Monitoring of Transmission Systems Using End-of-Line Testing Data: A Case Study at Ford Motor Company

Authors: Mohammad N. Bisheh, Mehrdad Moradi, Parinaz Farajiparvar, Colin Brady, Rajesh Gupta, Xueling Li, Javad Navaei, Milad Parvaneh, Kamran Paynabar
Published: 2026-10-04
Categories: cs.LG, stat.AP, stat.CO
arXiv: https://arxiv.org/abs/2610.06980v1

Sensing technologies have advanced rapidly across industries ranging from energy to automotive manufacturing. These systems generate high-dimensional (HD) data characterized by complex nonlinear patterns and strong temporal dependencies. Traditional statistical monitoring methods are often limited in their ability to capture such nonlinear structure. Likewise, many analytical approaches used in End-of-Line testing rely on predefined thresholds and heuristic rules, which restrict their ability to detect informative anomaly signatures in HD temporal data. In contrast, while modern deep learning and generative AI models offer strong predictive capabilities, they are often unsuitable in applications where data are costly to collect and where the monitoring system must remain interpretable, low-latency, computationally efficient, and usable by non-technical practitioners. To overcome these limitations, we propose an advanced multivariate monitoring framework for HD data. The framework operates in two stages. In the first stage, the data are preprocessed to remove incomplete and non-informative samples and to temporally align time series data. In the second stage, nonlinear dimensionality reduction is performed, followed by anomaly detection through a control chart based phase I monitoring procedure. The framework can be used in both unsupervised and supervised settings, depending on the availability of ground truth labels during training. Moreover, its flexible and modular structure allows practitioners to adapt its components to different domains and operational requirements. We evaluate the proposed framework on real production data from an automotive manufacturing environment at Ford Motor Company. The proposed method achieves higher accuracy, recall, and F1 score than the company's existing model, improving these metrics from 0.50, 0.30, and 0.429 to 0.625, 1.00, and 0.769, respectively.

---

### Hierarchy-GBP: Accelerating Factor Graph Inference via Abstraction and Recovery

Authors: Yuzhou Cheng, Tom Yates, Ignacio Alzugaray, Danyal Akarca, Pedro A. M. Mediano, Andrew J. Davison
Published: 2026-10-04
Categories: cs.CV, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2610.06978v1

Gaussian Belief Propagation (GBP) is a distributed inference algorithm that passes messages in graphical models, making it attractive for scalable spatial intelligence. However, we find GBP most effective locally: it rapidly smooths message errors that vary sharply between neighbor variables, but corrects global errors across distant graph regions incrementally through long-range message propagations. We propose Hierarchy-GBP (H-GBP), an iterative, two-stage framework that accelerates GBP by first solving these global errors with a coarse graph approximation (abstraction) and projecting the results back to the original graph (recovery), then refining the remaining local errors with GBP. We prove H-GBP convergence to the optimum by deriving the combined matrix operator of our abstraction and recovery steps and analyzing its spectral radius. Experiments on linear sparse graphs show that H-GBP converges fundamentally faster than standard GBP. Moreover, we validate H-GBP on two important spatial problems: Pose Graph Optimization (PGO) and Bundle Adjustment (BA). H-GBP markedly accelerates large-scale PGO and achieves state-of-the-art runtime across all tested BA scales.

---

### Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs

Authors: Xiaojun Jia, Simeng Qin, Yiming Li, Jie Liao, Sensen Gao, Ke Ma, Yang Liu, Xiaochun Cao
Published: 2026-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.06977v1

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-source surrogate models are accessible. Existing targeted transfer attacks mainly align adversarial and target samples using global image-level features, such as encoder (CLS) embeddings. However, such coarse alignment insufficiently exploits patch-level visual structures, limiting transferability across heterogeneous closed-source MLLMs. We propose IAU-FOA, a visual-invariance-augmented feature optimal alignment attack with adaptive unbalanced transport, to improve targeted transferability against closed-source MLLMs. IAU-FOA aligns adversarial and target samples at both global and local levels: a cosine-based objective narrows their global semantic gap, while patch tokens are clustered into compact local patterns and matched through optimal transport for fine-grained feature alignment. Balanced optimal transport enforces fixed marginal masses even for local clusters without reliable counterparts, potentially introducing misleading alignment gradients. We therefore introduce confidence-adaptive unbalanced transport to relax these constraints for weakly matched clusters, aiming to reduce unreliable local alignment and improve adversarial transferability. We further study the effect of input transformations and propose visual-invariance augmentation, which applies bidirectional pixel-intensity rescaling and per-channel white-balance adjustment to simulate exposure, contrast, illumination, and color-temperature variations. This strategy encourages adversarial perturbations to generalize across different visual encoders. Extensive experiments on open-source and closed-source MLLMs show that IAU-FOA consistently outperforms state-of-the-art transferable attack methods. Code is available at https://github.com/jiaxiaojunQAQ/IAU-FOA.

---

### The GenAI4IDN Benchmark 3.0 - a Public Tool to Assess Generative AI Tools for the Design of Interactive Digital Narratives

Authors: Hartmut Koenitz, Jonathan Barbara, Mirjam Palosaari Eladhari
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05633v1

This paper presents GENAI4IDN Benchmark 3.0, the third iteration of an evaluation framework to assess Generative AI tools for creating Interactive Digital Narratives (IDNs). Moving beyond manual testing, this iteration introduces AI-assisted evaluation through a publicly accessible web application (https://genai4idn.com), enabling the community to run benchmarks on demand, add new models, and propose new tasks. The revised evaluation framework is "blinded" to avoid model-bias, and can handle complex media such as music, videos, and full IDNs that previously required human raters. A significant addition - responding to concerns raised during ICIDS 2025 - is the addition of fact-checking and bias detection with dedicated tasks and rubrics, validated by human raters with lived experience in the depicted contexts. Findings from a diverse range of models report on maturing creative capabilities while observing runaway thinking and overzealous safety filters as limitations. Fact-checking reliably caught subtle historical inaccuracies, anachronisms, and fabricated claims while the bias rater consistently exposed structural assumptions, tropes, and marginalized group erasures.

---

### Delay-coordinate reconstruction and conditional-moment causal diagnostics in stochastic systems

Authors: Jun Ohkubo
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05632v1

Partial observation and delay-coordinate reconstruction are rooted in deterministic dynamical-systems theory, whereas there are many systems with intrinsic stochasticity. We propose a conditional-moment interpretation of delay-coordinate reconstruction for stochastic systems, in which a delay vector is used to reconstruct conditional moments of a future distribution rather than a unique future sample path. Two complementary arguments motivate this viewpoint. First, the probability density of a stochastic differential equation obeys a deterministic Fokker-Planck equation and, under certain assumptions, is represented by an infinite deterministic hierarchy of moments. Hence, a finite-moment closure suggests a Takens-like finite-dimensional approximation. Second, a discussion based on the Koopman operator theory clarifies that the time evolution of an observable in the Mori-Zwanzig formalism yields a conditional expectation in stochastic systems. Then, the orthogonal "noise" term in the coefficient-space Mori-Zwanzig equation vanishes in the stochastic cases; this result is consistent with the moment-based argument. As an application of this stochastic delay-reconstruction viewpoint, we revisit convergent cross mapping (CCM) for diagnosing certain causal relationships. Although CCM based on the embedding theorem cannot generally be applied to stochastic systems, it is possible to examine certain types of causal relationships by using conditional moments. Using coupled logistic systems with additive and multiplicative coupling mechanisms, we discuss how causal relationships are embedded in stochastic systems.

---

### Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection

Authors: Nallathambi Vethiappan, Derya Soydaner, Gijs Wijnholds
Published: 2026-10-04
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2610.05630v1

Visual entailment (VE) asks whether an image supports, contradicts, or leaves undecided a textual hypothesis. Strong results come from fine-tuning large vision-language models on labelled data, while zero-shot and hybrid approaches remain far behind. A VE hypothesis often bundles several visual claims, yet existing zero-shot methods reason over it as a single unit. We propose Atomic Visual Entailment (AVE), which decomposes the hypothesis into atomic facts, produces candidate predictions from both the full hypothesis and its facts using frozen vision-language models, and predicts the final label with a lightweight classifier trained only on how those candidates behave. We find that decomposition helps only when the hypothesis context is preserved: judging facts in isolation is worse than not decomposing at all. Full-hypothesis and atomic prediction make complementary errors, and learning which to trust recovers far more of that complementarity than majority voting, reaching 0.803 test accuracy on SNLI-VE without fine-tuning any vision-language model. AVE also localises the visual evidence behind its prediction without region-level supervision. These results suggest that learning which candidate prediction to trust can close much of the gap to fine-tuned systems, offering a practical alternative where fine-tuning a vision-language model directly would need more labelled data or compute than is available.

---

### A Framework for Automated Multi-Source Satellite Data Analytics and LLM-Based Report Generation

Authors: Hind Yousif Alhammadi, Isam Mashhour Al Jawarneh
Published: 2026-10-04
Categories: cs.AI, astro-ph.IM
arXiv: https://arxiv.org/abs/2610.05625v1

This paper presents the workflow for building an automated ArcGIS Pro tool using ArcPy to extract the Land Surface Temperature (LST) from Landsat 7, 8 and 9 datasets. The tool eliminates the need for manual band selection and repetitive raster computations by automating the multi-step workflow of radiometric calibration, NDVI-based emissivity correction, and thermal conversion. In addition to supporting batch and single-scene processing, the tool has an optional Large Language Model (LLM) for statistical result interpretation and reporting. Depending on batch size, the tool reduced the processing time from around 11-58 minutes when done manually to around 4-11 minutes using the tool. We tested the tool with data from Ras Al Khaimah (RAK) in the UAE, and the LST obtained for Ras Al Khaimah ranged from approximately 25C to 50C, demonstrating an accurate LST mapping compatible with the weather conditions of RAK. In summary, our tool reduces human errors and improves processing accuracy and efficiency for thermal and environmental remote sensing applications, in addition to providing an interactive LLM-based interface for result interpretation.

---

### UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

Authors: Dolly Sah, Tanmay Sah, Harshul Jain, Tanya Sah
Published: 2026-10-04
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2610.05622v1

Tool-using AI agents are increasingly deployed across enterprise software systems, yet widely used benchmarks primarily evaluate nominal task completion, conflating baseline planning competence with operational fault recovery. We introduce UndoBench, a benchmark spanning 36 base workflows and 36 fault scenarios across 8 enterprise domains, decoupling task competence from recovery capability via counterfactual paired trials under identical seeds alongside wire-level effect-history and environment-state oracles. On 12 held-out TEST workflows across two open-weight models, two frameworks, and three recovery paradigms (5,760 executions / 2,880 paired trials) in the frozen lost-acknowledgment study, nominal competence reached 83.54% while conditional recovery success rate (CRSR) fell to 46.72%, with naive retry producing duplicate external effects in 53.33% of trials. Extensions to commercial API models reproduced this competence-recovery separation. Evaluations across complementary execution boundaries show that recovery is phase-dependent: before mutation, methods perform similarly without duplicate effects among capable trials; during partial mutation, naive retry, per-call idempotency, and zero-privilege journaling collapse on the evaluated composite workflows; after commit but before acknowledgment, verification and server-side idempotency substantially improve safety. These findings demonstrate that evaluating nominal completion alone masks critical, phase-dependent recovery vulnerabilities in autonomous agents.

---

### Causal Lag Structure Discovery in Confounded Time Series via Orthogonalized Adaptive Estimation

Authors: Hong Kiat Tan, Isaac-Neil Zanoria, James Chen, Haoyang Lyu, Mihai Cucuringu
Published: 2026-10-04
Categories: stat.ME, cs.LG, econ.EM
arXiv: https://arxiv.org/abs/2610.05618v1

Finding which variables cause which others in multivariate time series, and at what lags, is central to science and policy, yet existing methods force a choice between flexible confounder adjustment, data-driven lag selection, and inference that controls the false discovery rate (FDR). ORACLE-VARX does all three in one pipeline. First, double/debiased machine learning (DML) removes nonlinear confounder effects from the outcomes and the lagged series. Second, adaptive causal lag estimation (ACLE) picks the lag order at each time step by sequential significance tests, tracking regime changes. Third, entry-wise $z$-tests with Benjamini--Hochberg correction select directed edges at a target FDR. We prove that in each rolling window, the debiased coefficients are asymptotically normal around a window-averaged target, so their $z$-tests are asymptotically valid. On a synthetic benchmark with time-varying structure and nonlinear confounding, ORACLE-VARX (LightGBM) tracks the true lag order best (RMSE $0.96$ vs $1.1$--$1.5$), has edge FDR $0.047$, close to PCMCI ($0.045$) and below VAR ($0.129$) and VAR-LiNGAM ($0.187$), and forecasts better than all three. On nine U.S. sector ETFs with macroeconomic confounders, it yields interpretable causal graphs whose lag order rises in high-volatility regimes.

---

### DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate

Authors: Khanh-Binh Nguyen, Van Dai Do, Tien Anh Nguyen, Svetha Venkatesh, Hung Le
Published: 2026-10-04
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2610.05615v3

Multi-agent debate (MAD) has emerged as an effective paradigm to improve the reasoning capabilities of large language models (LLMs) and is increasingly being extended to multimodal settings. However, existing multimodal MAD frameworks typically expose agents to the same fixed visual input, ignoring substantial variation in the visual scale needed across samples and agents. In addition, these frameworks frequently suffer from groupthink, a phenomenon where agents prematurely abandon correct deductions to conform with confident but hallucinated peer responses. To address these bottlenecks, we introduce DREAM (Dynamic Resolution Assignment For Multimodal Multi-Agent Debate), which operates via two core components: (1) Dynamic Resolution Assignment, a zero-shot probe round where agents test multiple resolutions, quantify uncertainty using Average Normalized Log-Likelihood (ANLL), and use an adaptive threshold to assign each agent to its empirically optimal resolution; (2) Uncertainty-Guided Rollback Aggregation counters groupthink by tracking each agent's uncertainty over rounds and restoring early low-uncertainty answers overridden by group pressure. On six multimodal datasets, DREAM improves the accuracy-token trade-off over multi-agent debate baselines by 1.5-3.2% accuracy without dataset-specific tuning.

---

### SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays

Authors: Sonal Kumar, Sinan Hersek, Artem Dementyev, Mengzhen Pan, Ishan Chatterjee, Anurag Kumar, Ramani Duraiswami, Dinesh Manocha, Andrea Colaco
Published: 2026-10-04
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2610.05610v2

Embodied, ego-centric intelligence fundamentally requires the ability to comprehend spatial audio within complex environments. While large audio-language models excel at mono-channel reasoning, they lack spatial awareness, discarding critical spatial cues that enable sound localization and that can improve the disentanglement of overlapping sound sources. To address this, we present SEA-LM, a Spatial Audio Understanding model. First, we introduce FOACODER, a layout-flexible spatial audio encoder trained on source localization and ego-centric voice activity detection objectives to encode First Order Ambisonics derived from variable-count, variable-position smart-glasses arrays via beamforming. We train a Multimodal Large Language Model (MLLM) to understand these spatial audio embeddings through a two-stage curriculum spanning six tasks, including sound localization and spatially selective transcription in settings with multiple speakers and overlapping sounds. To prevent the transcription outputs from dominating the next token prediction loss and overwhelming the direction predictions, we introduce a Spatio-temporal Weighted Cross-Entropy Loss. On our evaluation set, SEA-LM achieves lower azimuth and elevation MAE, higher temporal IoU, lower external-source hallucination and missing-source rates, and lower WER on most transcription tasks than compared baselines, while remaining robust across 1,211 smart-glasses array configurations with 4 to 9 microphones.

---

### Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Authors: Team Kandinsky, Julia Agafonova, Bulat Akhmatov, Mikhail Aksyutin, Grigorii Alekseenko, Anastasia Aliaskina, Olga Androsova, Vladimir Arkhipkin, Anna Averchenkova, Alexander Belykh, Serafima Bocharova, Sofiya Bogakovskaya et al.
Published: 2026-10-04
Categories: cs.CV, cs.AI, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2610.05608v1

We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video Lite (3B parameters) and Kandinsky 6.0 Video Pro (29B parameters). Both models generate 5-second video clips with synchronized 44 kHz audio, including lip-sync, in text-to-audio-video (T2AV) and image-to-audio-video (I2AV) modes; a built-in super-resolution model raises the output resolution to Full-HD (1920$\times$1080). Building on the video generation capabilities of Kandinsky 5.0, Kandinsky 6.0 Video employs a dual-stream CrossDiT architecture that connects a pretrained video stream and a newly trained audio stream through bidirectional cross-attention for temporal and semantic alignment. Our continuous pretraining strategy first trains the audio stream from scratch on large-scale audio corpora and then trains both streams jointly on paired audio-video data while preserving unimodal fidelity; pretraining is followed by supervised fine-tuning, reinforcement-learning-based post-training, and distillation. In side-by-side human evaluation, Kandinsky 6.0 Video Pro clearly outperforms its predecessor, Kandinsky 5.0 Video Pro, and remains competitive with leading audio-video generation models, particularly in speech quality. To accelerate open research and deployment in multimedia generation, we release the code, model checkpoints, and diffusers integration under the MIT license.

---

### EchoDino: A pediatric foundation model for transferable echocardiographic analysis across the lifespan

Authors: Sheng Cheng, Donnchadh M. O'Sullivan, Daniel J. Penny, Craig G. Rusin, Minh B. Nguyen, Devika Subramanian
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05603v2

Echocardiography is the most widely used cardiac imaging modality, yet interpretation demands integrating visual evidence across global anatomy, localized structures and dynamic cardiac motion. Machine-learning models have automated individual tasks, but they are typically built for a single purpose and depend on expensively labeled datasets - a barrier particularly acute in pediatric care, where data are scarce and anatomy changes with age. Here we present EchoDino, a self-supervised foundation model for echocardiography, created by adapting the DINOv3 framework to 3.7 million frames from 1.7 million unlabeled pediatric echocardiography videos. With its encoder frozen, EchoDino produces representations that capture global context, local anatomy, and dense spatial detail. We introduce Motion-biased Entropy Maximization Sampling (MEMS) to select the most informative frames for video-level analysis. Across nine pediatric and adult datasets, EchoDino outperformed strong baseline models, raising view-classification accuracy from 0.609 to 0.889 and the area under the receiver operating characteristic curve for structural-heart-disease detection from 0.811 to 0.872, while also cutting age-estimation error from 3.857 to 1.389 years, achieving the best segmentation accuracy and lowering ejection-fraction errors. By generalizing from label-free pediatric data to adult echocardiography, EchoDino offers a versatile foundation for cardiac image analysis across the lifespan.

---

### Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models

Authors: Kaiyuan Deng, Yuchen Li, Yang Xiao, Bo Hui, Geng Yuan, Xiaolong Ma
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.05601v1

Existing attacks on unlearned diffusion models assume that the erased concepts are known in advance and focus on recovering them. In practice, however, model providers may not disclose which concepts have been removed, and even with access to the original base model, an adversary may still lack a clear target to attack. In this paper, we aim to answer the following critical but overlooked questions: which concepts have been erased from the model, and how many have been erased in total? To this end, we present Tracer, a framework that rapidly and accurately identifies erased concepts and estimates their number. Tracer efficiently identifies erased concepts without generating and classifying images. By combining lightweight spectral analysis of weight footprints, it enables efficient search over large candidate vocabularies. To distinguish multiple erased concepts, we introduce a footprint coverage objective that guides sequential discovery. Tracer estimates the number of erased concepts by detecting a sharp decline in candidate confidence as the selected concepts account for the erasure footprint, without requiring labeled examples for calibration. The framework requires only lightweight linear algebra and limited forward probes, with no prior knowledge of the unlearning algorithm. Experiments across text-to-image and text-to-video backbones and diverse unlearning methods demonstrate that Tracer identifies erased concepts and estimates their number in seconds, achieving 150 to 137,000 times and 133 to 20,000 times speedups over MIA and brute-force search on image and video models, respectively, with substantially higher identification accuracy.

---

### An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection

Authors: Xinyuan Wang, Deepti Agrawal, Yanjie Fu
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.05600v1

High-dimensional bioinformatics data, characterized by a large number of features relative to the number of samples, pose major challenges such as the ``curse of dimensionality,'' leading to overfitting, high computational cost, and poor generalization. Traditional feature selection methods often suffer from limited scalability and adaptability in such domains. We propose an LLM-in-the-loop reinforcement learning (RL) framework for bioinformatics feature selection, where the RL agent formulates feature selection as a sequential decision-making task, while the large language model (LLM) enhances the process in two ways: (1) guiding exploration through domain-informed advice, and (2) providing hybrid rewards that integrate data-driven performance with knowledge-driven evaluation. The LLM also produces explanations to improve interpretability for human experts without altering the RL policy update. Experiments on diverse bioinformatics datasets show that the LLM-in-the-loop framework outperforms baselines, achieves stable performance across downstream models, and converges faster than pure RL.

---

### Gaussian Limits for SGD Without Stationary Moments

Authors: Xiaoli Li, Wei Biao Wu
Published: 2026-10-04
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.05599v1

Temporal dependence can separate the Gaussian approximation of stochastic gradient descent from its stationary moments. For unmodified least-squares SGD, we construct a design with standard Gaussian marginals whose stationary error has every positive moment infinite. Independent observations with the same marginals instead give finite stationary variance. Both regimes retain a Gaussian small-step limit. Our general theory establishes pathwise contraction from a finite second design moment, then uses score cancellation and localization to obtain stationary Gaussian and Ornstein--Uhlenbeck limits. Independent Gaussian regression errors yield an exact conditional Gaussian law and total-variation convergence under the same design integrability. Stronger design conditions identify a positive first-order total-variation constant and a deterministic covariance correction with $o(a)$ error. A scalar coverage expansion translates this correction into its inference consequence. Experiments examine distributional error, coverage, and calibration with dependent scores. Together, these results establish precise probability-law approximation beyond moment-based stationary analysis.

---

### When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data

Authors: Ahmadreza Eslaminia, Klara Nahrstedt, Chenhui Shao
Published: 2026-10-04
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2610.05598v1

An organization often holds too little labeled data to train a model that generalizes, and the records that would supply the rest sit with organizations that cannot release them. Cross-silo federated learning offers a way through, since participants exchange model parameters rather than records, but it ordinarily settles two aspects of the arrangement in advance, the participating sites and the classes the model can predict, and deployment can breach both. A new site joins after training, once the established sites have finished their engagement and gone offline, and its records arrive unlabeled, mixing conditions the model already recognizes with conditions no participant has observed. We present an autonomous three-stage procedure that expands the model entirely at the joining site: reconstruction experts screen for novelty, clustering separates the flagged records into candidate conditions, and class means describe the old classes, all inside one shared representation. Those classes were learned from records that never leave their owners, so the usual defenses against forgetting are unavailable, and the procedure supplies the evidence they would have carried from either of two dissimilar sources, prototypes held by the federation or records held by the joining site. On a real industrial condition-monitoring dataset, run end to end with no label consulted, either source holds old-class accuracy at 0.868 or above with forgetting at most 0.063, and the two differ by 0.021, so a configuration can be chosen by the disclosure it permits rather than the accuracy it delivers. Both keep old- and new-class accuracy in balance where every alternative we measure gives up one for the other, and both retain more of the old classes than distillation- and regularization-based baselines. The balance still holds with only 6 labeled records per arriving condition and 3 retained per old class.

---

### More Than Words: Compositional Tokenization for Efficient Language Models

Authors: Yuval Reif, Guy Kaplan, Roy Schwartz
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.05597v1

Language models process and generate text sequentially in token units, and the tokenizer determines how much text each inference step covers. Under standard tokenization, a short English phrase such as "On the table." is usually produced as four separate predictions for the preposition (On), article (the), noun (table), and punctuation (.), where each consumes a sequence position and adds inference cost. We introduce CoBPE, a compositional tokenization approach that represents such phrases as a lexical base token (table) attached with a small set of reusable surface modifiers, composed in embedding space at input and predicted jointly at output. In controlled pretraining from scratch at 780M and 1.3B scales, CoBPE shortens sequences by 30% and improves average downstream performance by 1.2 points relative to standard BPE under matched training compute. Our results suggest that part of what is now expressed through token sequences can instead be modeled through structured representations, opening a broad design space for more token-efficient and capable language models.

---

### Moment-Accurate Gaussian Mixtures for Constant-Step Stochastic Approximation

Authors: Xiaoli Li, Wei Biao Wu
Published: 2026-10-04
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.05595v1

Local Gaussian models of constant-step learning predict output variability and expected losses, but weak convergence alone does not justify these moment predictions. We establish moment-accurate Gaussian mixtures by matching stationary energy with local Ornstein--Uhlenbeck limits, ruling out quadratic tail mass invisible to weak convergence. For step size $a$, the second-order Wasserstein error is $o(\sqrt a)$, uniformly over invariant laws, using each law's actual root weights. The assumptions combine confinement, descent, finitely many hyperbolic equilibria and root continuity with finite-variance innovations. The result yields observable covariances, expected objective gaps and first-order mean shifts, while allowing singular covariances, compatible saddles and weights without a limit. For additive noise given by a fixed invertible transform of independent standardized Student $t_3$ coordinates, symmetry gives an order-sharp $\sqrt a$ smooth-test bound. Numerical transport calculations demonstrate the value of root-specific covariances; controlled SGD studies assess observable predictions across step sizes, batch sizes and model geometries.

---

### What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining

Authors: Yekun Chai, Haoyi Xiong
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.05591v1

As pretraining increasingly repeats data, every run faces three questions: how many epochs to take, how that number should change with model size, and whether anything besides the epoch count matters. We answer them by pricing a repeated token against two references: one epoch on the same data, which gives its value, and fresh data at equal compute, which gives its cost. Against fresh data, the cost of repetition follows a single variable, the number of extra epochs divided by the unique tokens per parameter. Against the same data, a second epoch is worth nearly as much as a fresh one, and repeated tokens fall to half the value of fresh ones after a critical epoch count that grows with the training budget per parameter but hardly with model size. With unique data fixed, the predicted compute-optimal run grows model size and epochs together until loss stops improving, near the critical epoch count. The same variable accounts for the direction of size trends that appear to conflict: larger models tolerate fewer epochs when the corpus is fixed, from about 15 at 127M to 4 at 2B parameters, but not when unique data grow with the model. Counts alone do not determine loss: at identical counts, replaying shards consecutively raises loss by up to 0.46~bits per byte, concentrating repeats on fewer samples also raises it, lower-entropy sources degrade faster with repetition, and re-tokenizing repeats helps only under heavy repetition. These results offer an empirical guide to pretraining when unique data, rather than compute, are the binding constraint.

---

### ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction

Authors: Jiheng Liang, Chen Zhao, Di Wu, Chenyang Bu, Yunpeng Hong, Xingquan Zhu, Yi He
Published: 2026-10-04
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.05590v1

Cold-start drug-drug interaction (DDI) prediction tests whether models can identify clinically significant interactions for drugs without training-time interaction history. Existing benchmarks mostly report aggregate edge-prediction scores, leaving a key evaluation question unanswered: when models receive molecular, textual, or knowledge-graph (KG) evidence, do they actually use the evidence that pharmacologically supports the interaction? We introduce ColdDDI, a reconstructible diagnostic benchmark built from DrugBank 5.1.13, with 1,900 approved small-molecule drugs and 565,731 positive DDI pairs. ColdDDI evaluates pairs with zero, one, or two unseen drugs. It also annotates each interaction by whether it changes drug exposure or drug effect, and by whether the biomedical knowledge graph contains shared enzymes, transporters, or targets that can plausibly mediate the interaction. These annotations separate evidence availability from predictive dependence. We evaluate eight conventional DDI methods and 13 LLMs; for open-weight LLMs, we test five prompt patterns and use masking, drug replacement, and channel-sensitivity metrics to probe knowledge utilization. ColdDDI exposes that, in the hardest split where both drugs are unseen, the main performance divide is mediator availability. A fine-tuned 1B LLM recovers 89-93% of interactions with a shared enzyme, transporter, or target, but only 40-62% without such a mediator. More importantly, KG-provided evidence is not always used; several KG-augmented baselines change little when the shared mediator is masked or disrupted, whereas fine-tuned LLMs respond strongly to this intervention. Thus, ColdDDI evaluates knowledge utilization rather than knowledge access alone, showing where cold-start DDI models rely on mechanistic evidence and where they fail despite receiving it. Code is available at https://github.com/0217ljh/ColdDDI-NeurIPS2026.

---

### Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife

Authors: Yuzhuo Li, Di Zhao, Xinyu Zhang, Daniel Wilson, Yun Sing Koh
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05587v1

Individual-level wildlife identification often suffers from data scarcity, as varying observations of the same animal under diverse poses, viewpoints, and motions are rarely available. Image-to-video (I2V) generation offers a promising way to mitigate this limitation by synthesizing additional observations from a single reference image. However, existing I2V models mainly emphasize global layout, semantics, and motion, and therefore often fail to preserve fine-grained local appearance cues that distinguish one wildlife individual from another, such as fur texture, stripe boundaries, spot configurations, and contour transitions. We observe that these identity-critical cues are closely related to high-frequency information. To address this challenge, we propose WildIcon, a high-frequency-guided I2V framework for wildlife individual consistency. Specifically, WildIcon introduces a frequency-aware identity encoding branch that extracts individual-specific high-frequency cues from the reference image. Combined with isolated foreground information, the resulting identity tokens are then injected into cross-attention blocks as identity conditioning. Building on a frozen backbone with lightweight identity adaptation, WildIcon preserves fine-grained identity cues visible in the reference image while retaining the motion controllability and semantic fidelity of the base I2V model. In addition, to support the training and evaluation of wildlife individual-consistent I2V, we construct WildlifeVid, a wildlife-centric video dataset with high-quality, temporally coherent clips and individual-level identity labels. Experiments on I2V generation and downstream animal re-identification (ReID) show that WildIcon achieves stronger individual consistency than existing baselines, and that its filtered outputs can serve as useful candidate training augmentations for downstream ReID.

---

### AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search

Authors: Jianing Wen, Tianshi Li
Published: 2026-10-04
Categories: cs.CR, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2610.05586v1

As Large Language Models (LLMs) gain tool use capabilities such as web search, they can retrieve and cross-reference public information, creating privacy risks beyond memorization. One manifestation is re-identification: linking an anonymized interview transcript to a named individual. Yet without ground-truth identities, the coverage of such attacks and the protection offered by a defense cannot be reliably measured. We introduce AgentDOXX, an evaluation suite of 822 synthetic interview transcripts grounded in public information about real individuals with known identities. We evaluate fifteen configurations of open-weight and proprietary models, isolating the effect of web search, and analyze their search trajectories to distinguish retrieval-driven from parametric identifications. Ground-truth identities reveal that re-identification risk is distributed across an agent's execution: retrieval and parametric recall both contribute, with open-weight models identifying 15-28% of transcripts without search; identification succeeds in over 88% of cases once the target appears in a retrieved result; entity masking leaves at least one attacker successful on 85.3% of a stratified sample; and privacy instructions suppress naming but not retrieval, with configurations scoring 0% accuracy yet retrieving the subject in up to 62% of transcripts. We further show that observed attack trajectories can provide supervision for localizing identifying spans, offering a path toward attack-informed anonymization.

---

### Expanding LLM Reasoning

Authors: Rian Atri, Evan Luo
Published: 2026-10-04
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.05584v1

Extra inference compute is usually spent on sampling more reasoning chains. We study where inside an existing chain an additional continuation should begin. We define expansion utility, the change in correctness from restarting a chain at a stored step, and measure it at every eligible step for nine models on six benchmarks (41 model and benchmark cells). Restart position matters: steps selected on one set of continuations beat uniform placement when scored on disjoint ones, in held-out audits on 5, 16, and 38 cells (+4.25 points (+2.51, +6.63) in a fresh five-cell audit). A fixed rule that restarts from the last eligible steps, always-last, is a strong baseline: our learned router beats uniform placement but shows no detected gain over it, and on DeepSeek-R1-Distill-Qwen-14B/MATH-500 always-last exceeds the exact self-consistency frontier at matched aggregate generated output by +0.052 (+0.008, +0.098), using 0.774x the aggregate generated output of four-sample self-consistency. Cross-fitted oracle selection still finds held-out headroom beyond declared positional classes, a target for future selectors. Finally, breaking step-label ties by earliest index flips the sign of a pointwise selector's gain over uniform placement in every seed of a five-seed diagnostic with four rollouts per step; randomized ties remove the bias.

---

### Rethinking Streaming-Perception Evaluation on Heterogeneous Edge Platforms

Authors: Misun Yu, Jinyoung Moon, Jemin Lee
Published: 2026-10-04
Categories: cs.DC, cs.CV
arXiv: https://arxiv.org/abs/2610.05578v1

Multi-camera streaming perception is increasingly deployed on heterogeneous edge platforms shared with co-resident workloads, yet accelerator placement is often evaluated using isolated single-stream experiments and mean streaming average precision (sAP). Using two end-to-end pipelines on a single GPU--NPU platform, we show that isolated evaluation can mis-rank deployment-time placement. Although the GPU pipeline is preferred in isolation, GPU-localized contention introduces deadline misses that make detections stale and can reverse the preferred placement before full GPU saturation. The NPU pipeline is less accurate than the GPU pipeline on small and medium objects in isolation, but nearly matches it on large objects. The largest absolute sAP losses in our latency and contention experiments occur for large objects. In our four-stream experiments, the preferred placement depends on which path becomes stale, and increasing GPU-side contention shifts the best placement from All-GPU to All-NPU. Under a GPU-saturating vision--language co-tenant, All-NPU achieves $5.2\times$ the worst-stream sAP of All-GPU. Because mean sAP can hide severe single-stream degradation, evaluation should report contention sweeps, deadline-miss rates on both paths, and worst-stream sAP alongside mean sAP.

---

### What Does an Observability Foundation Model Know?

Authors: Dhyey Dharmendrakumar Mavani, Rian Atri, Tairan Ji
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.05577v1

A linear probe can show that a label is recoverable from a model's hidden states, but not whether that goes beyond what the input already reveals, or whether the model uses it. We audit Toto, an observability forecasting foundation model, on the Benchmark of Observability Metrics (BOOM) across five series-disjoint resplits, comparing linear probes on its frozen residual stream with models that read the raw input window and with Toto's architecture stripped of its trained configuration. Short-vs-medium cadence and metric type are more linearly recoverable from Toto's residuals than from the strongest raw-window model in every resplit (macro-F1 0.766 vs. 0.633 and 0.545 vs. 0.498). Domain is nearly tied, and series cardinality is recovered far better from the raw window. MOMENT-base shows related cadence, metric-type, and domain readouts. Recoverability is not use: exchanging Toto's residuals with those of high-burst donors moves a future-burstiness readout as intended but does not make forecasts consistently burstier than a randomized donor. A BOOM-trained coordination probe has negative zero-shot R^2 on the tested external benchmarks. We report each label against its strongest baseline.

---

### SteadySplats: Resampling of Low-Variance Gaussians for High-Fidelity Stochastic Rendering

Authors: Felix Windisch, Thomas Köhler, Lukas Radl, Chris Wyman, Georgios Kopanas, Bernhard Kerbl, Markus Steinberger
Published: 2026-10-04
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2610.05576v2

Stochastic order-independent transparency enables efficient and elegant rendering of primitive-based radiance fields like 3D Gaussian Splatting models, but remains impractical due to the inherent visible noise in the output. We propose a principled approach to minimize high-frequency noise, addressing its sources at the representation and image synthesis level. During stochastic rendering, our history-based spatial resampling scheme drastically accelerates image convergence, while temporal importance resampling ensures coherence under camera movement. During training, a color regularizer implicitly reduces the variance along view rays in the 3DGS models. With these properties, our optimized, Vulkan-based renderer effectively mitigates output noise at low and high sample counts, achieving a substantial 13~dB PSNR increase in quality over previous stochastic methods at 1 sample per pixel and quickly converging to sorted 3DGS with an average L1 error of less than $10^{-4}$.

---

### Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters

Authors: Abdul Rehman, Jian-Jun Zhang, Xiaosong Yang
Published: 2026-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.05575v1

Much of expressive text-to-speech research rests on an untested assumption that written text carries enough information to select an appropriate prosodic style for its delivery. Text-predicted style models improve listener preference, and expressive-appropriateness evaluation presupposes that context constrains style, yet neither measures the assumption itself. This paper tests it as a falsifiable hypothesis against style labels derived from acoustics alone. For each of six speakers in a 1,200-hour conversational corpus, utterances are clustered in the spaces of five speech models, including a prosody-only control, and the cluster of held-out utterances is predicted from twelve text embedding models. Three controls are applied: utterance length is erased from the speech embeddings; accuracy is scored against the majority-class floor of unbalanced clusters rather than uniform chance; and a bag-of-words baseline measures word identity alone. Text predicts the cluster above that floor for all six speakers (+0.111 top-3 accuracy), but bag-of-words achieves three quarters of this. Sentence embeddings add only +0.026, largest for encoders not trained for sentence semantics and reversed by tree-based probes for all others. Acoustic clusters are not compact in text embedding space in any of 360 configurations. The prosody-only space weakens the association for five speakers, but not for the speaker showing it most strongly. Text thus informs these delivery clusters mainly through word choice, whether as a cue to prosody or as a marker of topic and recording situation, and reference-free style selection cannot assume more.

---

### Better Retrieval, Limited Clustering Gains: A Controlled Study of Multilingual Company Entity Resolution

Authors: Yijiashun Qi, Yuxuan Li, Hanzhe Guo
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05573v1

Improved name retrieval may have little effect on company clusters when the pair classifier remains unchanged. We examine this dependency by adapting multilingual E5 encoders under fixed candidate budgets and downstream decision rules. Random-negative and hard-negative training use identical positive schedules. Checkpoints are selected before collecting a new GLEIF sample of 3,633 names, 2,880 source identities and 882 silver-positive pairs. At 72,660 candidate edges, adaptation with a multi-view selector increases direct pair recall from 53.74% to 76.98%. The primary matcher adds only seven correct and two incorrect co-cluster pairs: cluster recall rises from 32.54% to 33.33%, while precision falls from 95.99% to 95.45%. Of 208 newly retrieved silver-positive pairs, 202 fall below its decision threshold. Random-negative and hard-negative training produce identical final partitions. An AI-assisted, single-reviewer audit of 137 pairs supports the observed pattern, although its predominantly LEI-derived evidence does not establish independent gold labels. The results locate the immediate loss of retrieval gains at the existing confirmation stage and show why encoder evaluation must also measure final cluster quality.

---

### Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction

Authors: Mohsen EsfandyariDoulabi, Lawrence Arkoh, Biruk Tadesse, Vaishvi Patel, Mehul Sharma, Marcelo d'Amorim, Wesley Assunção
Published: 2026-10-04
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2610.05572v1

Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution. Recent approaches report strong predictive performance, often with AUROC values between 0.85 and 0.94. However, predictors are typically trained by pooling runs from many tasks. We hypothesize that part of this performance comes from recognizing that some tasks are harder than others, rather than detecting whether a particular run is heading toward failure. This distinction matters because task-level difficulty supports decisions about where to allocate computation, while run-level prediction is needed to decide whether to intervene in an ongoing trajectory. We study benchmarks with repeated attempts of the same task by the same agent and separate cross-unit comparisons from comparisons between successful and failed runs of the same model-task unit. Across the evaluated corpora, more than 99.93% of the positive-negative pairs underlying pooled AUROC are cross-unit. Accordingly, predictors that never observe the current run can achieve high pooled performance, including a difficulty oracle with AUROC up to 0.945, while remaining at chance within task. Early run-level discrimination is consistently weak across trajectory predictors, released monitors, and hidden-state probes, although it improves later in execution and is stronger for weaker agents. Under fixed token budgets, task-level allocation outperforms abort-only strategies, while early stopping becomes beneficial only when within-task AUROC reaches about 0.84-0.93, far above the 0.50-0.55 range observed for early monitors. These results show that failure prediction should be evaluated not only by outcome accuracy, but by whether the captured signal supports the intended deployment decision.

---

### Scenario-Based Compositional Statistical Model Checking for Safety Specifications

Authors: Abhinav Pomalapally, Arya Raeesi, Kevin Kai-Chun Chang, Beyazit Yalcinkaya, Sanjit A. Seshia
Published: 2026-10-04
Categories: cs.LO, cs.AI, cs.RO, cs.SE, eess.SY
arXiv: https://arxiv.org/abs/2610.05571v1

In safety-critical domains such as autonomous driving, systems must be evaluated across a large number of environment conditions, often represented as composite scenarios built from primitive scenarios. Existing statistical model checking (SMC) approaches analyze each composite scenario independently, requiring many expensive simulations and resulting in substantial redundant computation when scenarios share common structure. This work introduces a scenario-based compositional SMC framework for safety and co-safety specifications, enabling efficient analysis of composite scenarios. Our approach decomposes scenarios into primitives and specifications into sub-specifications, verifies each primitive independently, and composes the resulting statistical estimates using importance sampling and kernel density estimation. Our empirical evaluation shows that the proposed framework can accurately answer verification queries for previously unseen composite scenarios while reducing simulation cost through parallelization and trace reuse.

---