# Research Papers — 2026-10 · bundle page 117 of 156 > Full-text markdown of papers #5801–5850 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/117 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/116.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/118.md) ### Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents Authors: Ziyang Cai, Christos Ziakas, Vasilis Kontonis, Tim Pearce, Siddhartha Sen, Akshay Krishnamurthy, Shivam Garg, Dimitris Papailiopoulos Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07447v1 Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent experiments. We show that independent runs of the same agent on the same task often plateau at substantially different scores, with gaps that persist even after considerable additional compute. Embedding their candidate artifacts by functional similarity provides further evidence that trajectories remain in localized regions of the solution space, which we call idea basins. To help agents escape these basins, we study a simple periodic intervention, fork-and-flush. Our method forks the agent into parallel trajectories, each inheriting the accumulated workspace but starting with a fresh chat context. After running each trajectory for a fixed horizon, the agent continues from the highest-scoring one. Across 13 long-horizon research and engineering tasks, with individual agent runs lasting up to several days, fork-and-flush outperformed the single-run and best-of-N baselines by a relative improvement of 66.0% and 44.4%, respectively, on the min-max normalized average score under an equal compute budget. --- ### Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type? Authors: Aadi Chauhan, Arthur Ilyasov Published: 2026-10-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.07444v1 A GUI agent decides which action to take and where to take it; we ask how a small grounding model should receive the action type. Fine-tuning Qwen2-VL-2B with LoRA on Android in the Wild, we compare a flat baseline with five ways of supplying the type under matched data, compute, and decoding: an auxiliary loss, a hard-routed action word, an additive learned embedding, a prepended learned token, and the type written into the prompt. With five seeds, an episode-clustered bootstrap, and seed-level paired tests, the ranking on a mixed stream is clear: the auxiliary loss, the additive embedding, and the prompt word each gain five to seven hit@0.10 points over the baseline, while hard routing and the prepended token are not distinguishable from it. Much of that gain is protection from a preprocessing choice of ours rather than a spatial prior. Our serializer clamps the off-screen touch point AITW records for type events to the origin; that class degrades the baseline's click grounding, and removing it lifts the baseline by nearly seven points, after which no mechanism's hit rate beats it and the intervals exclude a two-point effect, though the auxiliary loss still shortens the average miss; on a stream of taps and swipes none helps. Whether this generalizes beyond one serialization is open. For deployment, the pipeline's margin over the baseline with predicted rather than gold types is not established (+0.016, 95% interval (-0.017, +0.052)), and a wrong type collapses every model conditioned at inference. The prepended token does not help at the shared learning rate, where its rows barely move from initialization; trained ten times faster it reaches the level of the other three, with a margin three seeds do not establish. We also document a silent failure: injecting conditioning through inputs_embeds makes Qwen2-VL fall back to 1-D positions for image tokens, costing nine points. --- ### Artifact removal improves electrodermal waveforms but not downstream classification in a virtual-reality balance task Authors: Haochen Chai, Qixu Zhu, Siyao Li, Fangfang Jiang Published: 2026-10-05 Categories: cs.HC, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2610.07438v1 Artifact removal routinely precedes the classification of electrodermal activity (EDA), on the assumption that a cleaner signal supports a better decision. We tested this assumption in a virtual-reality (VR) balance-disturbance task. A residual gating network was trained on a benchmark with expert-corrected EDA, frozen, and applied to VR recordings, where raw and gated signals were classified by five published time-series methods under identical leave-one-participant-out evaluation. On the benchmark the gate detected artifacts well (median record AUROC 0.94) and reduced error inside artifact regions by 17.8%. In the VR task it did not improve classification. Changes in balanced accuracy ranged from -1.35 to +0.93 percentage points, no classifier improved and two lost accuracy, and all five were equivalent to raw input within +/- 3.32 points. The benefit was lost between waveform and decision. The correction that lowered waveform error also reduced skin conductance response detection in all 43 benchmark records. Processing left 92.8% of predictions unchanged, and the predictions it did change were corrected and corrupted at similar rates. The VR recordings also carried little contamination (an estimated 4.6% of samples), and even perfect localization of deliberately injected artifacts recovered only 3.3 points in the most sensitive classifier. A pooled association between artifact level and accuracy (11.3 points) disappeared within participants (0.1 points), showing how differences between people can make cleaning look useful. Preprocessing should be judged by the decision it supports, against an unprocessed arm. --- ### When Does AI Supervision Help? A Role-Aware Study of Network Fraud Decision Management with Blockchain Auditability Authors: Saviz Changizi, Nasibeh Mohammadzadeh, Mohammad Shojafar, Rahim Tafazolli Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07434v1 When does a second artificial intelligence (AI) component improve a primary network-fraud decision rather than add operational burden? We study this question through a role-aware Decider-Supervisor (DS) framework with blockchain auditability, evaluating four directional configurations that combine centralised machine learning, a Federated Averaging (FedAvg)-trained federated meta-model, and Base or Quantized Low-Rank Adaptation (QLoRA) large language model variants. The analysis compares primary-only and supervised decisions using non-hard fraud performance, intervention burden, conditional calibration, traffic-mix and Review-capacity sensitivity, dependability tests, and blockchain lifecycle controls. The deterministic hard gate resolves 89.994% of fraudulent requests, leaving the non-hard population as the main AI decision setting. Conditional validation calibration does not produce a consistently transferable supervisory advantage on deployment replay. DS-3 QLoRA is the least disruptive supervised configuration, but it still underperforms its primary FedAvg stage in F1 and total errors. Across 36 reweighted traffic mixtures, supervision reduces total errors only for DS-4 Base in two extreme high-fraud scenarios. Blockchain tests support digest verification, tamper detection, authorisation, single-use review resolution, and post-finalisation integrity, while exposing a pre-finalisation single-write limitation. The results show that the value of AI supervision depends on role assignment, calibration, escalation policy, traffic composition, and lifecycle controls rather than on the presence of a second model alone. --- ### StaFIR: Convex Learning of Stationarity-Aware Causal Filters Authors: Lorena Egger, Mathis Linger Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07430v1 Reducing nonstationarity in a persistent time series entails deciding how much of its temporal dependence to remove. In finance, fractional differencing is often tuned using the Augmented Dickey--Fuller (ADF) test, limiting the search to a one-parameter family of lag profiles and addressing input preservation only indirectly. We propose StaFIR, a causal finite-impulse-response filter with a learned nonnegative mixture of exponential lag profiles. Its convex learning objective balances empirical stationarity with similarity to the input. We evaluate StaFIR on ARFIMA--GARCH controlled settings and rolling financial series, including a realized-volatility forecasting task. The experiments show that StaFIR adjusts its filtering strength to persistence while limiting unnecessary transformation in stationary regimes. In downstream forecasting, there is no clear accuracy difference from fixed half-order differencing, while StaFIR achieves higher measured similarity to the raw signal. A complementary direct forecasting experiment finds that greater input similarity is associated with smaller forecasting penalties, although the raw representation remains stronger. --- ### Adaptive Gait Biofeedback With Participant-Held-Out Modeling and Participant-Specific Updating in Chronic Ankle Instability Authors: Jaeyoon Kim, Veronika Lebisova, Jeniya Sultana, Jaeyoung Cho, Jaeho Jang Published: 2026-10-05 Categories: cs.AI, eess.SP arXiv: https://arxiv.org/abs/2610.07428v2 Adaptive gait biofeedback may support repeated practice in chronic ankle instability, but its evaluation must address model performance and human response. We evaluated a temporal convolutional classifier on protocol-defined, angle-derived GOOD/BAD gait-cycle labels using participant-held-out leave-one-subject-out (LOSO) cross-validation in 20 participants. Seven participants in the adaptive-intervention group completed nine sessions over three weeks, with one motion-capture recording analyzed per session. Models updated after failed sessions were compared offline with their parent models on the same-session validation subset used for candidate selection and the first subsequent adaptive-session recording. Frontal-plane ankle angle was compared between the adaptive group and 10 sequentially enrolled controls at Baseline, Post, and 7-day Retention. Across 20 held-out folds, mean fold-level area under the receiver operating characteristic curve (AUROC) was 0.948, sensitivity for angle-threshold-exceeding BAD cycles was 0.941, and specificity for angle-threshold-meeting GOOD cycles was 0.366. Mean BAD-class F1 was higher in candidate models by 0.187 on the same-session subset and 0.118 on the first subsequent recording. At Post, the adaptive group had a baseline-adjusted frontal-plane ankle angle 5.168 degrees lower than controls (95% confidence interval, 1.766-8.569 degrees lower); the Retention contrast was uncertain. These findings characterize population-model discrimination and offline participant-specific updating during repeated biofeedback use, alongside a nonrandomized Post frontal-plane ankle angle association. They do not establish independent clinical gait classification or a causal benefit of updating. --- ### AccentCL: Robust Accent Classification with Incremental Expansion Authors: Mu-Ruei Tseng, Waris Quamer, Ghady Nasrallah, Ricardo Gutierrez-Osuna Published: 2026-10-05 Categories: cs.CL, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2610.07426v1 Accent classifiers are typically trained with a fixed label inventory and cannot accommodate new accent categories as new data becomes available. Moreover, accented speech corpora often exhibit substantial class imbalance and/or domain shift due to differences in recording conditions across corpora. We present AccentCL, a class-incremental learning framework for English accent classification that is robust to class imbalance and cross-corpus domain shift. AccentCL extracts multi-layer representations from a frozen Whisper-Large-v3 encoder, optimized with an imbalance-aware cross-entropy loss to reduce bias toward the majority accent classes and a domain mean alignment loss that minimizes distributional mean shift across training corpora. The label space is then expanded via replay-based continual learning, using the frozen base model for knowledge retention and an old-to-new margin loss to reduce overprediction on newly added classes. On a five-class accent classification task, AccentCL achieves 77.1% balanced accuracy and a 76.9% macro-averaged F1 score. We further evaluate the model's ability to incrementally incorporate two new accent categories: Spanish-accented and Chinese-accented English. When adding Spanish-accented English to the pretrained model, AccentCL attains an F1 of 83.3% on the new class while retaining 77.3% balanced accuracy on the base classes. When subsequently adding Chinese-accented English, it achieves 61.8% F1 on the new class while preserving 77.6% balanced accuracy on the previously learned classes. These results show that AccentCL enables robust regional accent classification while allowing new accent categories to be added without full retraining. --- ### 2d-fet-bench: from spatial reasoning to fet design on flakes Authors: Dunzhi Zhou, Chengyu Zhu, Gang Qiu, Caiwen Ding Published: 2026-10-05 Categories: cs.AI, cond-mat.mes-hall, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2610.07423v1 Field-effect transistor (FET) layouts on exfoliated two-dimensional flakes are typically drawn by hand for each flake, placing contacts and gates to match its position and outline in optical micrographs. To our knowledge, no executable benchmark tests whether language-model agents can perform this flake-specific construction reliably. We introduce 2D-FET-Bench V2, a benchmark of 128 layout tasks built from microscopy-derived flake contours, including hole-containing flakes and multi-flake tasks. Each task supplies a textual device specification and contour coordinates. An agent generates typed polygon and path operations rendered to GDSII. A deterministic verifier checks geometric and structural requirements, and a separate integrity check verifies that the supplied contours remain unchanged. Scripted reference layouts pass all 128 tasks, showing that every task is solvable. We evaluate six models and seven workflow and scaffold variants of GPT5.6-Luna, with five attempts per task. The best-performing configuration in the six-model panel, GPT5.6-Luna with ReAct-3, passes 62.3% of attempts and solves 80.5% of tasks at least once (coverage) and 43.8% in all five attempts (consistency). ReAct-3 exceeds the one-pass Plan-and-Execute by 27.0 pass@1 points at 2.46 times the tokens. An expert audit of one sampled verifier-passing layout per covered task, across five ReAct-3 configurations, accepts 56.4% to 63.5% of them. The benchmark evaluates geometric and structural FET layout construction. --- ### Benchmarking Label-Revealed Online Updates for EEG BCI Decoding Authors: Bogdan Kozyrskiy, Artem Grachev, Abraham I. Camelo Guerrero Published: 2026-10-05 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2610.07420v1 Electroencephalography (EEG) signals drift over time, which can cause static brain-computer interface (BCI) models to degrade in practice. We present a benchmark for online adaptation and compare two widely used pipeline families, Common Spatial Patterns (CSP) and Riemannian covariance-based methods, under time-ordered prequential (test-then-train) evaluation. We examine (i) which pipelines benefit most from label-revealed updates, (ii) whether controlled forgetting of older data improves robustness, and (iii) how a minimal-calibration cold start compares with starting from a pretrained model. Across four datasets (three motor-imagery datasets and one movement-decoding dataset), label-revealed online updates improve 13 of 14 model/dataset pairs on the two largest streams, with relative accuracy gains of up to about 18% over a frozen model. A Shapley-based data-valuation analysis over temporal blocks assigns the largest mean value to the most recent block in each of the three analyzed datasets, while older blocks retain positive value. --- ### Learnable Spectral Activations Authors: Tamir Shor, Or Litany, Alex Bronstein Published: 2026-10-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.07419v1 Implicit neural representations (INRs) are shaped by the spectral structure induced by their input encodings and activation functions. Existing methods improve fitting primarily by modifying which frequencies are available to the network, through coordinate encodings or periodic nonlinearities. However, frequency access is not the only bottleneck: signals with localized or spatially varying structure require the network to efficiently compose frequencies into multi-harmonic internal responses. We introduce learnable spectral activations (LSA), which replace fixed neuron-level nonlinearities with a residual truncated Fourier series whose harmonic amplitudes are learned during training. LSA does not expand the asymptotic function class. Instead, it changes the factorization of the representation: linear weights select features while activation coefficients control spectral shaping, and the two are updated by separate gradients. Because the activation output is affine in the coefficients given fixed pre-activations, spectral tuning becomes a more direct subproblem compared to architectures where it is entangled with feature selection. Empirically, this factorization concentrates more target-signal energy in the leading eigenmodes of the neural tangent kernel, consistent with improved optimization behavior. Across audio, image, neural radiance field, and neural acoustic field tasks, LSA also improves reconstruction quality. --- ### Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds Authors: Davide Sartor, Meghan E. Huber, Donghyun Kim, Nathan Wycoff Published: 2026-10-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.07417v1 Bayesian Optimization (BO) has become an established methodology for minimizing black-box functions of a vector input. Often, however, this parameter vector arises from the discretization of an inherently functional relationship. Several recent articles have considered the Functional Bayesian Optimization (FBO) setting, in which the variable to be optimized is not a member of a finite dimensional vector space, but rather an infinite dimensional function space. In this work, we propose $L^0$ Manifold Optimization (L0MO), a simple approach to FBO which searches the subset of a Reproducing Kernel Hilbert Space (RKHS) consisting of functions with a sparse representation in the kernel functions, optimizing both the kernel locations and their coefficients. We discuss in detail the relationship between our method and existing ones, providing a unifying lens through which to view prior works. To assess our method against the state of the art, we conduct an extensive computational study, and along the way develop a novel set of benchmark test functions which port standard finite-dimensional ones to the infinite dimensional domain. Our experiments demonstrate that, on balance, the proposed method achieves superior performance across a wide range of test benchmarks. --- ### Simplified Swarm Optimization for Surrogate-Assisted Reliability Design of Insulated-Gate Bipolar Transistor Power Modules Using an Open-Source Process Finite-Element Model Authors: Wei-Chang Yeh Published: 2026-10-05 Categories: cs.NE, cs.CE, math.OC arXiv: https://arxiv.org/abs/2610.07412v1 Process-induced warpage, ceramic stress and solder strain limit the reliability of insulated-gate bipolar transistor (IGBT) modules on direct-bonded copper (DBC) substrates. Surrogate-assisted design studies train regression models on finite-element analysis (FEA) databases, but rarely check the optimized designs against new FEA or report how surrogate error interacts with the optimizer. This paper builds and evaluates an open pipeline: an open-source process finite-element model, surrogates tuned by Simplified Swarm Optimization (SSO), multi-objective design search, FEA confirmation of selected designs and confirmation-driven infill. The model starts at the second reflow and reproduces measured warpage within 18.2%, 33.6% and 15.3% at the reflow, housing and molding stages without fitted parameters. On a balanced 60-design database, all stochastic tuners reach the same test accuracy, outperform the published grid on cross-validated performance for every output but generalize better only for warpage; the cross-validated ranking of tuners does not transfer to the test set. With equal result reporting, multi-objective SSO and the non-dominated sorting genetic algorithm II give comparable Pareto fronts; a corrected multi-objective particle swarm optimizer trails both. FEA confirmation shows that warpage predictions hold (mean absolute error 0.5%), whereas at the design-space bounds reached by the optimizers the ceramic-stress surrogate is optimistic by up to 26%. Two confirmation-driven infill rounds reduce this error to 1-10% and halve the out-of-sample error; no confirmed design improves on the database in ceramic stress. Ceramic-stress results are indicative, as the metric is mesh-sensitive at production resolution. The model, database, scripts and pre-registered and post-registration results are released. --- ### Evaluation of Active Feature Acquisition Policies with Tabular Foundation Models Authors: Yuta Kobayashi, Divyam Madaan, Shalmali Joshi Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07406v1 Active feature acquisition learns policies that sequentially acquire features to maximize information about a target variable. We study how to learn and evaluate such policies from finite offline data using prior-data fitted networks (PFNs), which are off-the-shelf models that output posterior predictive distributions without task-specific training. We show that under the imbalanced coverage of offline data, using total predictive entropy as a reward creates an epistemic bias that penalizes acquiring sparsely observed features. Specifically, this reward conflates epistemic uncertainty (arising from lack of offline data) with aleatoric uncertainty (arising from uninformative features). To address this, we target the posterior expected (aleatoric) entropy instead of the total predictive entropy output by a PFN for evaluating feature acquisitions. Empirical evaluations on synthetic and real-world datasets demonstrate that our approach consistently reduces value estimation bias and yields credible intervals with strong empirical coverage, which can translate to improved downstream policy selection. --- ### What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training Authors: Subham Rath, Raj Dandekar, Rajat Dandekar, Sreedath Panat Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07405v1 pass@$k$, the fraction of problems a model solves within $k$ sampled attempts, is the field's default protocol for deciding whether reinforcement-learning (RL) post-training on verifiable rewards improved a model. At the population level, pass@$k$ depends only on a problem's probability of a correct sample, with no term for how it is distributed across outputs. We show this gap is not academic. Training Qwen2.5-1.5B-Instruct on grade-school math with Group Relative Policy Optimization (GRPO) and with rejection-sampling fine-tuning (RFT, training on the model's own shortest verifier-passed rollout) moves three complementary diversity measures (token-level entropy, answer-level entropy, unique answers per prompt) in opposite directions, with zero overlap across three seeds per arm. The gap survives restricting to verifier-correct completions only (lexical diversity among correct solutions is 15% lower for GRPO, after controlling for length) and a count-controlled check isolating diversity among incorrect answers alone, ruling out that GRPO's higher accuracy alone explains it. Yet pass@8 and pass@32 show no consistent winner on GSM8K, and a hard MATH-500 subset shows the same pattern: separation only at low $k$. Compared against the starting checkpoint, no trained arm significantly improves hard-problem coverage: RFT is significantly worse, while GRPO is statistically indistinguishable from it - so GRPO's pass@1 edge over RFT reflects a smaller loss relative to Base, not a capability gain, a missing-control issue, not a failure of pass@$k$. On GSM8K, only pass@1, with no role in detecting diversity by construction, separates the arms cleanly, rewarding the arm whose correct solutions are least diverse. We argue this is a concrete instance of a standard evaluation protocol missing a property it is routinely used to certify. --- ### Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy Authors: Ritvij Sharma, Russell Dlugosz, Ryan Zhou, Maheep Chaudhary Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07403v1 Long-term memory allows Large Language Models (LLMs) to maintain personalized context across interactions, but retrieved user history can induce memory-induced sycophancy, causing models to favor stored user beliefs over objective evidence. Existing defenses primarily operate on retrieved context and are rarely evaluated jointly with internal behavioral bias. We introduce a $2 \times 2$ defense-in-depth framework separating internal activation steering from external memory handling. We extract sycophancy steering directions from 100 paired prompts and evaluate four open-weight models across 10 steering coefficients and five memory-defense configurations on MemSyco-Bench (answers for all 1,550 items; defense conditions judged on a fixed 250-item subsample), with three LLM judges. Three of the five configurations are new (rewriting every memory, a Router Gate that keeps, rewrites, or drops each memory, and dropping all memory); the other two are MemSyco's baselines. Selective Router Gate filtering preserves substantially more of MemSyco's average accuracy than complete memory removal, and this separation persists when the models are steered toward sycophancy. On Llama 3.1 8B with Router Gate, mild inverse steering ($α= -1.5$) lowers judge-averaged sycophancy from 35.80% to 31.32% while average accuracy moves from 43.99% to 43.31%; this reduction has the same direction under all three judges but is not statistically significant (paired $p = 0.08$ to $0.63$ on 149 items). External memory filtering is the part of the design that holds up; our data do not show that inverse steering adds to it. --- ### Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering Authors: Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07399v1 Federated deep clustering seeks to learn clustering-friendly representations from decentralized unlabeled data while preserving client privacy. However, Deep Embedded Clustering (DEC)-style objectives depend on global soft-assignment statistics that require clients to reveal their sensitive information. We propose Fed-BRDECS, a privacy-preserving and heterogeneity-aware federated deep embedded clustering framework. Fed-BRDECS replaces the globally normalized clustering objective with a locally computable sample-stability loss, avoiding the transmission of local soft-assignment distributions. To tackle non-IID client distributions, we introduce prediction-balanced sampling, which oversamples locally rare predicted clusters without requiring ground-truth labels, and centroid-level restarting, which periodically refreshes biased or inactive centroids. Experiments on image and text clustering benchmarks show that Fed-BRDECS consistently outperforms representative federated clustering and deep clustering baselines under both IID and non-IID partitions. We further demonstrate its applicability to federated time-series anomaly detection, where it improves reconstruction-based detectors without adding inference-time cost. --- ### A perspective note on likelihood approximation and inference for complex simulation models using a chain of aggregated normalizing flows Authors: Getachew K Befekadu Published: 2026-10-05 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.07391v1 We present a new perspective on the problem of likelihood approximation within the framework of simulation-based inference that promotes scalable and controllable simulation routines for large-scale data analysis, allows efficient parameter space exploration or smooth interpolation in high-dimensions and, thus, supports valid statistical treatments of hypothesis testings as well as uncertainty quantification. In particular, we consider a chain of $n$-aggregated normalizing flows for likelihood approximation scheme, where a set of upfront replicated observation datasets from the forward complex simulation model pass through the first set of bijective transformations, and then subsequently pass to the other sets of bijective transformations. Here, we assume that, for any $k \in \{1,\,2, \ldots, n\}$, the parameters corresponding to the first $k$ sets of bijective transformations are estimated sequentially, in some sense of optimality, for constructing flexible probability distributions, regardless of the remaining $(n-k)$ sets of bijective transformations. Moreover, our objects of interest are to highlight two complementary mathematical arguments that leverage an informatics-theoretic formalization, based-on empirical likelihood estimators under moment restrictions, and a sequential decision-making paradigm, with mixing distributions, for updating and aggregating the estimated parameters of the overall normalizing flows. As a by-product, the framework provides a reliable surrogate model, conditioned on the model parameters defining the forward computational simulation, that allows samples generation, with statistical powers, and facilitates computationally tractable scheme in the Bayesian paradigm for inference, hypothesis testings and uncertainty quantification. --- ### Inference and learning in sparse autoencoders as natural gradient flow Authors: Hadi Vafaii, Tejas Rao, David Chanin, Thomas Fel, Jacob L. Yates, Bruno Olshausen, David Klindt, Dileep George, Miguel Lázaro-Gredilla Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07389v1 Sparse autoencoders are widely used to uncover interpretable features in neural networks, yet reliable recovery remains difficult when features overlap or activate infrequently. These challenges involve both inferring which features explain an input and learning the dictionary that represents them. Here, we unify inference and dictionary learning as natural-gradient flows on a shared variational free energy. We instantiate this framework as BeFOND, an encoder-free sparse coding model with closed-form inference and learning dynamics. We show how recurrent explaining away reduces interference between overlapping features, while Fisher preconditioning can compensate for the slow learning of rare features. On synthetic data, BeFOND improves dictionary recovery and rare-feature detection, with a growing advantage over amortized baselines as superposition increases. On language-model activations, it improves single-feature concept detection and selective intervention, outperforming pretrained reference SAEs with substantially less training data. Its feature quality continues to improve with dictionary width, whereas the evaluated baselines largely plateau. Together, these results show how improving inference and learning within a unified probabilistic framework can make better use of data and dictionary capacity to interpret and intervene on neural representations. --- ### DeepAJM: Deep Association Joint Model for Irregularly Sampled data Authors: Barsha Halder, Jeffrey A. Thompson Published: 2026-10-05 Categories: stat.AP, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.07388v2 Joint Models simultaneously model longitudinal and survival outcomes, leveraging patterns in patients' longitudinal trajectory to improve the prediction of survival outcomes. The classical parametric joint models, however, rely on fixed parametric assumptions, making them susceptible to bias under model misspecification and smaller sample sizes. We propose a deep joint model, DeepAJM, that does not require any parametric assumptions, while retaining a partially interpretable, per-longitudinal-outcome association structure. The joint model uses an encoder-decoder (sequence-to-sequence) architecture to learn the latent structure in patients' time-varying covariate trajectories. The model links the longitudinal processes to the survival processes through a learned interpretable association structure, in which each longitudinal output from the decoder gets remodulated by baseline covariates before it contributes to the risk scores from the survival head of the architecture. The model was evaluated on three datasets ( a cardiovascular-disease EHR cohort, a primary biliary cirrhosis (PBC2) dataset, and a simulated dataset) against a classical parametric joint model, TransformerJM, DA-LSTM and a Cox-based survival-only model. All models were assessed using C-index, integrated brier score (IBS), time-dependent AUROC, and time-dependent AUPRC. Our model achieved the best discrimination in terms of the C-index, time-dependent AUROC, and AUPRC across all datasets. --- ### Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-Tuning Authors: Suguru Onda, Matthew Bailey, Ryan Farrell Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07385v1 Fine-tuning vision-language models (VLMs) is typically evaluated at a single downstream checkpoint, obscuring whether a semantic capability was never acquired or emerged earlier and later declined during specialization. We ask how semantic capabilities are acquired, when they peak, how well they transfer, and what remains at deployment. We study these dynamics as a semantic capability trajectory, tracking identity- and attribute-based capabilities over training. We formulate a trajectory-based framework that separates capability acquisition, capability-specific optima, and later specialization, and introduce Structured Semantic Routing (SSR) to study how the representation of supervision shapes what is acquired. Across six pretrained backbones spanning DFN, MetaCLIP, and OpenAI CLIP, we show that fine-tuning can acquire semantic capability beyond the pretrained state, including gains observed on held-out evaluations. Unstructured name-and-attribute supervision produces strong name-and-attribute retrieval with comparatively weak name-free attribute-profile retrieval, whereas SSR yields substantially stronger name-free attribute-profile retrieval and is further strengthened by stochastic name-branch dropout. Different capabilities can peak at different stages, so a checkpoint selected by target class-name retrieval need not coincide with a transferable semantic optimum. Continued optimization can therefore preserve strong target class-name retrieval while reducing previously acquired transferable semantic capability. In a representative diagnostic study, this late specialization is consistent with reduced cross-modal semantic accessibility while substantial image-only class structure remains available. --- ### WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification Authors: Turhan Can Kargin, Piotr Kubaty, Ekaterina Rostovskaya, Izabela Wierzbowska, Bartosz Zieliński, Marcin Przewięźlikowski Published: 2026-10-05 Categories: cs.CV, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.07384v1 Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wildlife monitoring: a query image must retrieve the correct individual from a reference set of known animals. This requires computer vision models to recognize distinctive local patterns in fur, skin, or other visual markings. Current approaches either learn global embeddings as a classification problem, requiring many labeled images per individual while largely ignoring local evidence, or apply off-the-shelf, domain-agnostic image matchers. Although such matchers are pretrained on large and diverse image collections, adapting them to wildlife imagery is challenging because available datasets are small and lack correspondence-level annotations. We study weakly supervised adaptation of a pretrained keypoint matcher using only identity labels, without keypoint-level or geometric correspondence ground truth. We mine informative image pairs with the pretrained matcher, derive weak positive and negative supervision from identity agreement, and contrastively fine-tune the matching network to strengthen correspondences for same-identity pairs and suppress them for different identities. Across open-source wildlife re-identification datasets, our approach improves accuracy over off-the-shelf matchers and a state-of-the-art local--global fusion method. Under an open-world protocol with held-out individuals, it learns a transferable correspondence prior rather than memorizing training identities. To our knowledge, this is the first study of matcher-level, identity-supervised adaptation for animal re-identification. Our method enables data-efficient specialization of image matching models to wildlife domains using identity annotations already available in typical monitoring datasets. --- ### HyperNSDE: Personalized Neural SDEs for Joint Static-Longitudinal Clinical Data Generation Authors: Perrine Chassat, Agathe Guilloux Published: 2026-10-05 Categories: stat.ML, cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2610.07383v1 Synthetic patient data generation is a promising solution to the dual challenge of data scarcity and privacy constraints in healthcare machine learning. Realistic synthesis of patient-level clinical data requires jointly modeling heterogeneous static covariates, irregularly sampled longitudinal trajectories, and informative observation times - three tightly coupled components in practice yet rarely addressed together. We propose HyperNSDE, a continuous-time generative model that conditions a latent Neural SDE on static patient representations through a hypernetwork, allowing baseline characteristics to shape trajectory evolution beyond the initial condition without requiring a trajectory encoder, while stochastic latent dynamics capture realistic variability in generated paths. Observation times are modeled jointly through a latent-state-dependent intensity process, and training on irregular stochastic paths is stabilized via a deterministic-stochastic path decomposition with a non-adversarial signature-kernel objective. Experiments on simulated and real clinical datasets show improved observation-time fidelity and competitive performance, while matched-grid analyses reveal that forecasting and correlation metrics are affected by observation-grid regularity and trajectory smoothness. --- ### GeoWM: Efficient Direct World Modeling in Explicit Geometry Authors: Mehrdad Noori, Guile Wu, Sam Hosseini, Dongfeng Bai Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07381v1 Modeling 3D scene geometry and its evolution over time is essential for autonomous driving and robotics. A common paradigm is to use world models to predict future images or latent representations of the environment and subsequently recover geometry from these predictions. However, this paradigm does not explicitly model geometric structure and typically relies on recursive rollouts to reach longer prediction horizons, leading to error accumulation and increasing computational cost. To address these limitations, we present GeoWM, a geometry world model that directly forecasts future scene geometry at specified future horizons without recursive rollout. The key idea is to leverage a geometry foundation model to transform observed RGB frames into a geometric history, which conditions a flow-matching transformer to predict the scene geometry at a specified future horizon. We further show that a lightweight camera-motion predictor can accurately estimate the future viewpoint, and that projecting the observed geometry into the predicted viewpoint provides an effective geometric prior for future geometry forecasting. Extensive experiments on four datasets spanning urban driving, aerial flight, and dynamic manipulation demonstrate that GeoWM outperforms the evaluated world models in forecasting depth, camera pose, and 3D scene geometry, while substantially reducing inference time at longer horizons. --- ### SimCortex v2: Joint Cortical Surface Reconstruction with Near-Zero Collisions and Self-Intersections Authors: Kaveh Moradkhani, Sylvain Bouix Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07378v1 Reconstructing cortical WM and pial surfaces from structural magnetic resonance imaging (MRI) is a prerequisite for surface-based neuroanatomical analysis, yet remains challenging because the cortex is thin and tightly folded. Reconstruction methods can produce geometric artifacts such as mesh self-intersections and collisions between cortical surfaces, and although recent deep learning methods have reduced reconstruction time from hours to minutes, these artifacts persist. We propose SimCortex v2, a deep learning framework for simultaneous reconstruction of the left and right WM and pial surfaces from T1-weighted MRI. SimCortex v2 estimates topologically correct initial surfaces from a volumetric segmentation and refines all four jointly using multi-scale stationary velocity fields predicted by a ribbon-conditioned, U-Net-like network. We evaluated SimCortex v2 on 560 cases from 14 cohorts, thirteen of them unseen during training, spanning ages 6-89, healthy and clinical populations, and scanners from three vendors. SimCortex v2 matched the surface-distance accuracy of the strongest baseline (average symmetric surface distance 0.253 mm) while showing no detected inter-surface collision in 92.14% of cases and the lowest self-intersection fraction (0.044%) among learning-based methods, whereas every baseline produced at least one collision in every case. Source code, configuration files, pretrained weights, preprocessed data, and the exact evaluation splits are publicly released. --- ### MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments Authors: Xinting Liao, Siyan Liu, Rabab K. Ward, Holger R. Roth, Xiaoxiao Li Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07376v1 Large language model (LLM) agents increasingly operate in interactive environments, where they need to make sequential decisions through observation, action, and feedback. Although memory can help agents reuse experience, existing work designs memory in isolation, where collecting enough trajectories to populate it is expensive. Existing shared-memory approaches mitigate isolated experience by pooling episodic memories across tasks and environments. However, retrieving shared memory is challenged by the granularity, where retrieved memories can be either too specific to preserve current grounding or too coarse to support the next action. In this work, we propose MemCo, a memory-centric collaboration framework for generalizing LLM agents to unseen interactive environments. It maintains complementary local and global memory spaces, preserving environment-specific details locally while promoting transferable workflows induced from local trajectories to global memory. During online interaction, MemCo routes relevant local and global memories in terms of the agent's current state and decision phase, enabling agents to reuse the experience of other agents without blindly transferring environment-specific details. Experiments on interactive decision-making benchmarks show that MemCo improves task success and reduces redundant exploration compared with isolate-memory and shared-memory baselines. Our code is available at https://github.com/SYannL/nvdamas. --- ### Multigroup Fairness and Omniprediction: Separations and Equivalences Authors: Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold, Konstantinos Stavropoulos, Pranay Tankala Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07374v1 Omniprediction is a learning guarantee which requires a single predictor to be competitive relative to the best hypothesis from a benchmark class for any loss chosen from a family of loss functions. Loss Outcome Indistinguishability (loss OI for short) is a stronger notion that implies omniprediction. It requires the predicted distribution on labels to be indistinguishable from the true distribution to tests that depend on the loss functions and the benchmark class. Multiaccuracy and multicalibration are multigroup fairness notions that generalize classical notions of calibration and accuracy in expectation. Most known learning algorithms for omniprediction (both for the standard notion and for strengthenings like loss OI) rely on some version of these multigroup fairness notions, or on an intermediate notion called calibrated multiaccuracy. We ask if this is necessary: Does omniprediction require some form of multigroup fairness? We show that the answer is no for (plain) omniprediction, and yes for loss OI. First, a sequence of works shows that multicalibration or calibrated multiaccuracy imply omniprediction. We rule out even a weak converse, by showing that omniprediction for proper losses does not imply even accuracy in expectation, a much weaker notion than any of calibration, multiaccuracy, or multicalibration. Second, prior work showed how to achieve loss OI from a combination of calibration and multiaccuracy. We show a converse: loss OI is equivalent to a form of calibrated multiaccuracy. --- ### Identity-Conditioned Score Fusion for Open-Set Person Re-Identification Authors: Manyi Yao, Jurijs Nazarovs, Eunji Chong, Abhishek Sharma, Rohan Sarkar, Yue Guo, Christian R. Shelton, Amit K. Roy-Chowdhury, Debashish Pal Published: 2026-10-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.07366v1 Robust person re-identification often combines complementary cues such as face, gait, and body shape. While adaptive fusion typically targets query quality, model strength also varies across identities. We introduce identity-conditioned score fusion, a framework that tailors weights to each gallery identity without training. By contrasting intra-identity consistency against cross-identity impostors, it extracts identity-specific profiles that couple with query-conditioned adaptation via a parameter-free rule. This widens the separation between true and false matches while preserving score calibration. Evaluations on three clothes-changing person re-identification benchmarks show that our method consistently outperforms statistical, rank-based, and learned baselines, achieving up to an 8.8% absolute reduction in the false non-identification rate and demonstrating the value of identity-conditioned fusion in open-set person re-identification. --- ### Who Wrote It Is Not Enough: Detecting Who Contributed the Insight Authors: Zhuoyang Zou, Abolfazl Ansari, Jiaxi Yang, Delvin Ce Zhang, Qian Chen, Dongwon Lee, Wenpeng Yin Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.07365v1 As LLMs increasingly assist scientific writing and peer review, detecting who wrote the text is no longer sufficient: we need to determine who contributed the underlying insight. We introduce Insight Provenance, the task of identifying whether a review insight originates from a human, an LLM, or their hybrid contribution. We construct InsightProv-v0 from 4,057 scientific papers and 12,660 human reviews, simulating different levels of LLM involvement with GPT-4o, Gemini, and DeepSeek and annotating provenance at the sentence level. We show that strong performance on raw data can be misleading, as models exploit linguistic and textual-authorship shortcuts that degrade substantially under progressively debiased evaluation. We therefore propose a two-stage adversarial framework that suppresses shortcut signals while preserving provenance-relevant information. Beyond detection, extensive analyses reveal what makes intellectual authorship identifiable: paper grounding and neighboring review context provide complementary provenance signals, while human, hybrid, and AI insights systematically differ in their information sources and failure modes. Most strikingly, AI insights predominantly remain close to generic or paper-provided information, whereas human insights more often introduce external knowledge and independent judgment. These findings suggest that while wording can be rewritten by an LLM, the provenance of an idea leaves a deeper and more persistent signal. --- ### Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints Authors: Shai Feldman, Yaniv Romano Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07362v1 We evaluate large language models (LLMs) in multi-turn interactions through their time-to-event: the number of interaction steps required to produce an event of interest, such as a successful jailbreak or agentic task completion. Under limited compute, interactions may be terminated before the event occurs, so that event times are only partially observed (censored). Existing allocation methods for calibrating time-to-event bounds satisfy the budget only in expectation and can exceed the available budget on a particular evaluation run. Enforcing a hard constraint is particularly challenging as the cost of a trajectory is initially unknown. We introduce Hard-budget Allocation with Reflow for Predictive calibration (HARP), a budget allocation that satisfies hard resource constraints and adaptively reallocates unused budget. We show how to use HARP to construct lower predictive bounds (LPBs) on the time-to-event and to estimate evaluation metrics such as the jailbreak rate on a fixed benchmark. Although HARP induces dependence in acquisition decisions across different trajectories, we prove that HARP never exceeds the target budget, that its LPBs have finite-sample coverage guarantees, and that its metric estimates are unbiased. Experiments on agentic task success, LLM jailbreaks, toxic content generation, and RAG hallucinations show that HARP achieves coverage close to the nominal level with low variance, while never exceeding the given budget. --- ### Redundancy and synergy in multivariate Gaussians via the Blackwell order Authors: Artemy Kolchinsky Published: 2026-10-05 Categories: cs.IT, stat.ML arXiv: https://arxiv.org/abs/2610.07360v1 The goal of the partial information decomposition (PID) is to quantify the redundant and synergistic information that multiple sources provide about a target. PID has many applications in machine learning, neuroscience, and other fields, but defining and computing it for high-dimensional continuous systems remains challenging. Here, we define a PID for multivariate Gaussian systems based on the Blackwell order, which formalizes when one channel is more informative than another. We prove that Gaussian channels are optimal for extracting both redundant and union information, yielding an intuitive geometric interpretation and an efficient numerical algorithm for the PID. Our union information and synergy coincide with the well-known BROJA measures, and we derive closed-form expressions for both in the case of two sources. We also argue that Blackwell redundancy (which differs from BROJA) is the only existing redundancy measure that satisfies a set of natural desiderata. We demonstrate the scalability of our method on systems with up to a thousand dimensions or sources. Our approach is illustrated on an optimal control problem, where it identifies redundant and synergistic interactions between sensor and memory. --- ### Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently? Authors: Chenglin Yang Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07359v1 Runtime gates for agent tool calls are stacked on the assumption that their errors multiply. We test it on 1,119 labelled agent actions from three corpora, without an adaptive adversary. The stack has one deterministic rule layer and four LLM judges, three of them re-collected with the served model recorded on every call. We read each stack as a number of multiplication-equivalent layers, n_mult, with its floor under perfect coupling. Under the STRICT miss definition (escalation to a human scored as not stopped), any two judges compose to about 1.2 to 1.4 layers (φ median +0.430, 6 of 6 pairs significant, floors 1.02 to 1.17). The rule layer plus one judge composes to 1.86 to 2.09 layers (φ median +0.014, 0 of 4 significant, floors 1.01 to 1.09). Under PRIMARY (escalation scored as caught) the bands are 1.21 to 1.57 and 1.80 to 2.13. Intervals separate on the pooled data, point estimates split on each corpus, and a third-vendor judge lands in the judge band. Solo accuracy does not predict what a layer adds: a cloud rule pack lowers the rule layer's solo miss rate by 20% and adds no new joint coverage. The difficulty share of judge coupling is not identifiable: 31.8% to 61.8% depending on the probe and the miss definition. One judge tier was served by an unrequested model version in 50 of 112 batches, concentrated on the external corpus. That event overturned a pre-declared analysis rule, and the scoring of review verdicts reversed five conclusions. We report both. --- ### Towards Explainable Benchmarking for Data-driven Post-Wildfire Debris Flow Prediction Authors: Zhisheng Qi, Li Zhu, Utkarsh Sahu, Douglas Tommey, Josh Roering, Yu Wang Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07358v1 Post-wildfire debris flows (PFDFs) are destructive sediment-laden hazards triggered when intense rainfall strikes recently burned terrain, destabilizing hillslopes and threatening infrastructure, local economies, and community safety. Data-driven methods have been proposed to learn predictive patterns directly from historical PFDF observations. However, the current research landscape of data-driven PFDF prediction remains highly fragmented across feature spaces, model architectures, and evaluation protocols, making rigorous comparison and the derivation of scientific insights difficult. Moreover, existing studies lack a systematic investigation into the relative importance of heterogeneous factors (e.g., meteorological conditions, terrain characteristics, soil properties, and burn severity) in triggering PFDF. To address these limitations, we present a unified benchmark for data-driven PFDF prediction, enabling fair and comprehensive evaluation across diverse models and feature configurations. Furthermore, to better understand the underlying drivers of PFDF formation, we propose a reinforcement learning-based feature selection framework that identifies factors whose perturbations render positive and negative events indistinguishable, thereby discovering the regional underlying mechanisms of PFDF occurrence across regions. Our code and benchmark are publicly available at https://github.com/KINDLab-Fly/PFDF-Benchmark. --- ### A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models Authors: Ardalan Aryashad, Yan Jin Published: 2026-10-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.07356v1 Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that they use the same elements and remain consistent with one another. Large language models can generate diagrams as text or code, which makes it possible to create system diagrams automatically. However, their ability to generate coherent sets of diagrams is not well understood, and existing datasets and benchmarks do not directly measure this ability at scale. We introduce SEMAADB (Systems Engineering Modeling Assistant with AI Dataset and Benchmark), a dataset of 3,000 engineering contexts and 15,000 diagrams. Each context contains five connected SysML views: Requirement, Block Definition, Activity, State Machine, and Sequence. Here, a view is a diagram that presents one aspect of a system. We checked the diagram sets for consistency and valid rendering. A set of 100 contexts is also human-verified and forms the benchmark test set. We evaluate three language models on two tasks. In diagram repair, the strongest model repairs 64.3% of semantic errors . In cross-diagram update the best propagation F1 is 80.7% when a model applies one change across related diagrams. The results show that syntax repair is nearly solved, but semantic repair and consistency across diagrams are still challenging tasks for models. SEMAADB therefore provides both a large diagram resource and a set of benchmarks for measuring coherent multi-diagram SysML generation. --- ### Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object Authors: Peng Xie, Amr Alanwar Published: 2026-10-05 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2610.07355v1 Video world models track objects they can see; we ask what they keep of objects they cannot. We hide an object from a frozen V-JEPA 2 predictor and compare its prediction for the hidden region with the encoder's representation of two worlds that differ only inside that region. The predictor's decision keeps a stationary object in part and one carried inside a container not at all, and loses a moving one within 0.3 s (0.5 s under V-JEPA's own tube mask; ViT-H keeps it to 1.1 s at pretraining's 90% masking ratio); in projection a trace remains, below the midpoint, at 14-60% of what a baseline copying the last view retains. The information is there: the encoder reads the object's presence at 1.00 and keeps a closed container's contents decodable for 3.5 s, while the predictor's output, read with the encoder's own probe, contains the ball in 2% of scenes once the box has been closed for half a second. On rendered scenes, permanence is missing on the predictor's side, and training installs it cheaply as a prior: three thousand predictor-only steps on synthetic containers take this belief from 0.05 to 1.00 against two matched controls. They also raise IntPhys-2019 from 84.2% to 93.3%, but so does a curriculum without containers, and which training habit the benchmark credits changes with its scoring rule. Continued training with tube masks produces 1.1-1.6 s of moving-object carry-over on manipulation and internet-style video, so the deficit is not intrinsic to latent prediction. VideoMAE keeps almost nothing, and Cosmos's next-token prediction keeps a stationary hidden object but not one carried inside a moving container. --- ### Evaluating Escalation Signals for LLM Routing: Targets, Controls, and Five Ways to Fool Yourself Authors: Ramin Pishehvar, Andrea Morandi, Mahesh Viswanathan Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07354v1 Deciding when to escalate a query from a small language model to a larger one requires a cheap signal that predicts, before the large model is called, whether escalating would help. Semantic entropy, originally developed to detect hallucinations, is a natural candidate: it measures how much a model's sampled answers disagree in meaning, and high disagreement often signals an unreliable answer. We test it across three benchmarks and two model families. On GSM8K, with a small/large pair about twelve times apart in size, semantic entropy reliably distinguishes the small model's mistakes (AUROC 0.871) and improves routed accuracy over random escalation by up to nine points at matched cost. An earlier strong-looking result on a synthetic benchmark proved misleading: a simple rule based only on question difficulty, with no model involved, matched semantic entropy almost exactly. This paper's main contribution is a set of checks that catch this before it is reported as real. We show that scoring a cheap, question-only difficulty estimate alongside any signal reveals whether the signal adds real information or just tracks how hard a question looks; that two reasonable definitions of "escalation worked" can produce very different results on the same data; that a benchmark can leave almost no room for any signal to beat simply always using the large model; and that the true cost of live sampling can make routing more expensive than calling the large model directly. For a cheaper alternative that reuses cached past outcomes, we show how to predict whether it will work on a new dataset -- confirmed by correctly forecasting a collapse from AUROC 0.908 to chance level (0.518) ahead of time. We offer these as a general checklist for evaluating escalation signals. --- ### Trajectory-Retrieval Speculative Decoding: When Does a Model's Own History Help? Authors: Yuyang Dai, Yushun Dong Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07350v1 Long chain-of-thought reasoning increases sequential decoding cost while creating a growing history of potentially reusable continuations. We investigate when this history supplies useful drafts and complements an existing drafter. Controlled source comparisons reveal trajectory-specific reuse, motivating our method Trajectory-Local Adaptive Retrieval (TLAR). TLAR retrieves approximately matched continuations from the current trajectory and uses recent verification outcomes to adapt retrieval activation and candidate width. TLAR combines retrieved continuations with model-generated drafts in a shared candidate tree, preserving the target model's output distribution through exact verification. Across code debugging, mathematics, and open-ended writing, our evaluation connects source reuse, incremental acceptance, and execution cost. Combining TLAR with strong retrieval baselines improves token acceptance under matched verification budgets and increases end-to-end throughput over the draft-model baseline. These findings support generated trajectories as runtime memory for adaptive inference. --- ### RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents Authors: Sayak Chakrabarti, Sathish Reddy Indurthi Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07349v1 Group Relative Policy Optimization (GRPO) avoids a separate critic by estimating advantages from rollout groups. For multi-turn agents, however, trajectory-level supervision provides coarse, noisy credit: terminal rewards do not locate errors and can penalize useful actions alongside mistakes. Group-in-Group Policy Optimization (GiGPO) and subsequent methods refine supervision through state-conditioned comparisons, but their credit estimates remain sensitive to downstream decisions and outcomes. We introduce RELACE, Retrospective Likelihood-based Action, a critic-free framework that integrates retrospective action assessment with state-conditioned advantage estimation. RELACE evaluates executed actions through teacher-forced likelihood scoring under both their original contexts and outcome-augmented contexts. Comparing these likelihoods yields a trajectory-normalized retrospective factor that captures outcome-dependent changes in action plausibility, rather than hindsight plausibility alone. We use this factor to reweight discounted task returns and construct local advantages by comparing weighted returns among actions from equivalent states within a task. This couples retrospective relevance with observed reward, producing fine-grained credit that complements trajectory-level GRPO supervision. Temporal smoothing and success-protecting masking further stabilize the local signal. RELACE requires neither auxiliary value nor reward models nor additional autoregressive rollouts for credit estimation. Experiments on ALFWorld and WebShop with Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct demonstrate substantial improvements over GRPO, GiGPO, and HCAPO. With the 1.5B model, RELACE achieves $96.35\%$ success on ALFWorld and $79.43\%$ on WebShop, surpassing GiGPO by $5.47$ and $5.60$ percentage points, respectively. --- ### Stepped MoE: Segment-Level Routing with Configurable Inference Complexity Authors: Arnav Kundu, Zhaoyang Xu, Bairu Hou, Chang Gao, Reed Li, Tao Lei Published: 2026-10-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.07348v1 Training large language models (LLMs) is resource-intensive, and adapting them for diverse deployment scenarios with varying computational constraints remains challenging. While elastic architectures enable flexible model deployment and sparsely activated models allow input-adaptive computation, existing approaches treat these dimensions independently. Moreover, models catered towards on-device edge inference need to conform to the memory and compute limitations of the serving devices. In this paper, we introduce a unified framework that combines elastic structures with sparsely gated architectures to create models that adapt simultaneously to both deployment constraints and task requirements. Our approach employs a model backbone that conditions on both the context and target efficiency specifications, enabling fine-grained control over the accuracy-efficiency trade-off at inference time. The model learns to activate task-relevant parameters within elastically-nested sub-networks, allowing a single model to span multiple capacity points while maintaining input-adaptive routing. Through experiments we demonstrate that we can create a model that allows the flexibility to use 1,2,3,4 billion parameters while being more accurate than their dense counter-parts (2-5\% on knowledge-intensive benchmarks) and at par with their static versions while delivering similar latency metrics as dense models. Overall, we save on device disk space by sharing the model parameters, allow flexibility of serving based on DRAM and compute available while delivering more accurate results. --- ### Evaluating Behavioral Context for Interpretable IAM Policy Risk Scoring in Cloud Environments Authors: Yassin Elsharkawy Published: 2026-10-05 Categories: cs.CR, cs.DC, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2610.07345v1 IAM policy analysis typically emphasizes the authorization capabilities encoded in a policy, but security analyst review priority may also depend on the behavioral and environmental context surrounding a policy event. This paper evaluates whether contextual information provides measurable incremental value for interpretable IAM policy risk prioritization beyond policy and effective-authorization information. AWS is used as the experimental cloud provider because its IAM and audit-telemetry ecosystem enables controlled evaluation using AWS IAM Context Bench, a benchmark containing 534 real AWS experimental observations across policy, environment, and behavioral scenarios, including matched cases where policy and environment remain fixed while behavioral context changes. Three Explainable Boosting Machine models are evaluated under the same leakage-controlled grouped cross-validation protocol: a policy-centric baseline, a policy-plus-environment model, and a full-context model incorporating CloudTrail telemetry. The full-context model substantially reduces analyst-priority prediction error relative to the policy-centric baseline and closely tracks the reference priority ordering. In matched same-policy context pairs, the policy-centric model remains invariant, whereas the full-context model separates benign and suspicious behavioral conditions with high directional accuracy. The results also show improved concentration of high-priority cases at the top of simulated analyst review queues. These findings indicate that behavioral and environmental context can provide useful incremental information for analyst-oriented IAM risk prioritization while preserving an interpretable additive model structure. The formulation is applicable beyond AWS conceptually, although cross-provider validation remains future work. --- ### Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding Authors: Hoang Phan, Minh Pham, Chau Pham, Chinmay Hegde, Trung Le, Qi Lei Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07342v1 On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectiveness is often limited by reward sparsity: when a model fails to discover correct trajectories for difficult problems, the optimization process receives little useful signal and may stagnate. Existing approaches mitigate this issue by incorporating off-policy demonstrations, expert traces, or model-generated solutions, but they typically require the auxiliary data to match the format of the reinforcement-learning task, often relying on rejection sampling from stronger models to obtain suitable training trajectories. We introduce Rationale-Guided Policy Optimization (RGPO), a framework that adaptively leverages ground-truth rationale information according to the model's current capability while preserving its freedom to explore. Rather than treating reference solutions as fixed imitation targets, RGPO uses them as temporary scaffolds: rationales help the model generate improved responses, after which only higher-reward, model-generated solutions are transferred back to the original unguided setting. This design allows training to exploit available ground-truth information without requiring off-policy data to follow the same format as the RL task. Across both language-only and vision-language reasoning settings, RGPO consistently improves performance over RLVR baselines, and ablation studies show that adaptive rationale guidance is a key contributor to these gains. These results suggest that RGPO offers a practical and general approach for reducing reward sparsity, stabilizing reinforcement learning, and improving reasoning performance in both text-only and multimodal models. --- ### CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening Authors: Loka Li, Jin Tian, Kun Zhang Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07340v1 Protein-molecule virtual screening is increasingly cast as a problem of representation learning in a shared embedding space. Existing methods rely on dense holistic alignment, entangling invariant binding determinants with nuisance correlations and limiting transfer to new targets. It has been noted that binding in protein-molecule systems involves sparse cross-modality interactions: binding is governed by a small contact interface and a few decisive local interactions (e.g., hydrogen bonds, hydrophobic contacts, and salt bridges) rather than the global structures of the protein and molecule. We hypothesize that uncovering and leveraging sparse interaction patterns is critical for generalization beyond the training data, as these patterns are reusable and expected to improve performance across different scenarios. In this paper, we aim to identify and leverage sparse interaction patterns, and verify our hypothesis. Since the training data contain only observed binding pairs, we formalize this prior via a V-structure causal model under Heckman-style selection, and establish three theoretical results: (i) the latent concepts of interacting proteins and molecules are not identifiable without appropriate sparsity constraints; (ii) these concepts and their sparse interactions are component-wise identifiable under structural sparsity conditions; and (iii) a low-rank relaxation of these conditions yields subspace identifiability of the concepts and interactions. Inspired by these principles, we propose CausalBind with three implementation variants. Extensive experiments on DUD-E and LIT-PCBA benchmarks show that all variants consistently outperform strong retrieval baselines, with the largest gains on LIT-PCBA early enrichment, and further generalize to target- and scaffold-level out-of-distribution splits. Code is available at https://github.com/lokali/CausalBind. --- ### A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care Authors: Junseob Kim, Jade Chng, Ayman Ali, Victor Moas, Yichun Lee, Po-Chun Chin, Sunil Hwang, Rishikesan Kamaleswaran Published: 2026-10-05 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.07339v1 Tactical Combat Casualty Care (TC3) requires responders to connect visual observations of injuries and interventions with established clinical guidance. Developing vision-language models to support this process requires supervision that links visible evidence to traceable doctrine. We present TC3-VQA, a dataset constructed from public instructional and field TC3 videos and authoritative TC3 documents. It contains 581 items spanning 11 concepts, with 1,860 questions covering intervention recognition, doctrine, clinical reasoning, procedural guidance, and refusal when visual information is insufficient. Doctrine-based answers preserve verbatim source passages and character offsets. Construction combines visual annotation, passage retrieval, entailment checks, and verification across model families. Equipment boxes, anatomical labels, temporal segments, and source metadata accompany the question-answer pairs. Automated audits and ratings by two physicians and two medical students characterize annotation quality, with human ratings available for 88 retained items. The dataset provides a resource for adapting vision-language models to TC3, studying the connection between visual evidence and clinical knowledge, and evaluating recognition, doctrine recall, and abstention. --- ### Logbook: Extremely Long-form Audio Event Understanding Authors: Kwanghee Choi, Suwon Shon, Dmitriy Serdyuk, Guitang Lan, Chao-Wei Huang, Mohammad Sadegh Rasooli, Sangeeta Srivastava, Zhaojiang Lin, Saurabh Adya, Ming Sun Published: 2026-10-05 Categories: eess.AS, cs.AI, cs.CL, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2610.07338v1 Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies. To close this gap, we introduce Logbook, a benchmark for hour-scale audio understanding, with recordings ranging from ten minutes to six days. Given a continuous audio recording and an event label vocabulary, a system must predict a gap-free segmentation with an event label and a description per segment. We compare 52 systems, end-to-end and cascaded, and ablate fine-tuning, context length, and reasoning budget. We find the task tractable, though the best systems remain below the human reference. Also, over-segmentation is pervasive, and fine-tuning partially mitigates it. Finally, end-to-end are often better than cascaded systems, but degrades with longer context. --- ### Compositional Concept Erasure in Text-to-Image Diffusion Models via Hierarchically Grounded Semantic Surgery Authors: Chen Dai, Ganyu Zou, Nathan Self, Kevin Piper, Ramachandra Rao Seethiraju, Karthik Shyamsunder, Chang-Tien Lu, Naren Ramakrishnan Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07337v1 Removing copyrighted, unsafe, or user-specified concepts from a deployed text-to-image diffusion model is now a practical requirement. Weight-editing methods can suppress fixed targets, but they require per-target retraining and modify the model checkpoint. Training-free methods, on the other hand, are deployment-friendly, but they suffer from text-side routing failures on compositional prompts. In such prompts, the erase target may be invoked through a related class rather than its lexical name, and its modifiers may migrate onto preserved objects. This paper proposes Hierarchically Grounded Semantic Surgery (HGSS), a training-free framework for compositional concept erasure. The framework lifts both the routing signal and the edit operator used by text-side erasure. First, hierarchical span grounding resolves erase-target spans through lexical, taxonomic, and semantic evidence, while guarding against broad-hypernym and compound-head false positives. Second, dynamic attribute binding refines the text conditioning during early denoising via a counterfactual reference and a preserve-aware cross-attention objective, keeping surviving attribute-noun bindings intact. HGSS selectively removes the erase target without updating model weights or adding learned parameters. On SEE, HGSS cuts hierarchical evasion from 29.54 to 10.02 and roughly halves pairwise attribute leakage, achieving the best Neighbor E and AttrP scores among the reported erasure methods. On UnlearnCanvas, HGSS slightly improves the six-metric average over the matched Semantic Surgery baseline, reaching state-of-the-art. --- ### Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making Authors: Heewon Park, Somin Im, Minhae Kwon Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07335v1 Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous agents interacting with complex environments, early mistakes can propagate through trajectories and cause cascading failures. Recent approaches improve reliability by incorporating external critique or deliberation, but invoking these mechanisms at every step substantially increases token consumption and latency, limiting practical deployment. We propose SAG (Self-improving Agent with Gated critique), a cost-aware framework that formulates critique invocation as a step-wise decision problem during long-horizon interaction. SAG introduces a lightweight, training-free gating mechanism that estimates the utility of critique using action-level ambiguity signals--global entropy and local top-2 margin--computed over admissible actions. From a decision-theoretic perspective, this mechanism approximates the Value of Information (VoI) of critique, enabling the agent to selectively allocate expensive feedback only when its expected benefit justifies the cost. SAG further incorporates online bootstrapped self-improvement, allowing the actor to internalize critic-assisted behaviors and progressively reduce reliance on critique. Across three long-horizon interactive benchmarks and multiple backbone models, SAG substantially improves the performance-cost trade-off compared with both no-critique and always-on critique agents. On ALFWorld, SAG increases task success from 24.6% to 78.4% while maintaining a token budget comparable to ReAct, yielding a $3.1\times$ improvement in normalized token efficiency. Moreover, a 7B actor with a lightweight 3B critic achieves performance comparable to a 14B actor without critique, showing that selective critique can recover most of the reliability benefits of deliberation while dramatically reducing inference cost. --- ### Weight Oracles: Reading Neural Network Weights with Language Models Authors: Krishna Kabra, Constantin Venhoff, Christian Schroeder de Witt Published: 2026-10-05 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.07334v1 Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring known inputs to find hidden capabilities such as backdoors. We propose Weight Oracles, fine-tuned language models that diagnose properties of a target network by reading its raw weights directly, without behavioural testing. We investigate this paradigm in two phases. Phase I establishes feasibility: through a staged curriculum and an external chain-of-computation that delegates parameter-free operations to deterministic code, an explainer LLM learns to simulate the forward pass of small transformers from their weights, achieving 99% holdout accuracy on unseen targets. Phase II repurposes this infrastructure for safety auditing. We train an oracle on natural language diagnostic questions about weight anomalies using only benign pathologies as training signal, and evaluate it zero-shot on backdoors absent from training. The oracle achieves AUROC 0.93 on attention-routed backdoors and 0.81 across a diversified threat distribution including stealth and adversarially regularized variants. Hand-crafted statistical detectors are sharp on the threat models they implicitly target but collapse on threat-model shift, while the oracle remains uniformly competent across attack types. Scaling to realistic model sizes remains the principal open challenge. --- ### Memory-Efficient Expert Routing for Distributed MoE Training Authors: Arnab Kanti Tarafder, Jaume Guasch-Martí, Gokcen Kestor, Jie Ren Published: 2026-10-05 Categories: cs.DC, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2610.07333v1 As Mixture-of-Experts (MoE) models scale toward hundreds of experts and higher top-$k$ routing, memory efficiency in distributed training becomes a critical bottleneck. Peak memory is dominated by the MoE block, not attention: every intermediate buffer in the MoE dispatch pipeline is individually scaled by top-k routing. The standard all-to-all dispatcher sends all routed tokens in a single collective step, requiring the full top-$k$-expanded buffer to be constructed at once. In this work, we propose RelayMoE, a ring-based MoE execution model that computes locally as expert weights or tokens circulate, avoiding full top-$k$-expanded dispatch buffers. RelayMoE selects between expert and token routing according to communication volume and overlaps transfers with computation. The ring structure naturally supports memory-efficient MoE recomputation during backward: each hop reconstructs expert intermediates, uses them to compute gradients, and releases them before the next hop. The saved memory supports longer sequences and larger batches, or retains more attention activations to reduce attention recomputation and improve training throughput. We evaluate RelayMoE on 30B$-$57B production MoE models and varied expert configurations. In single-layer MoE experiments, RelayMoE achieves a $2\times$ average speedup over Megatron-LM. In full-model training under the same GPU memory budget, it improves throughput by up to $2.02\times$ and extends the largest tested trainable sequence length by up to $2.85\times$. --- ### Structuring MoE Expert Selection for Agentic Reinforcement Learning Authors: Bolian Li, Ting-Yao Hu, Cheng-Yu Hsieh, Sanjoy Chowdhury, Oncel Tuzel, Raviteja Vemulapalli Published: 2026-10-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.07332v1 Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structures remains underexplored. In this work, we comprehensively study the connections between agentic post-training and MoE expert selection. In off-the-shelf MoE models, we observe expert selection exhibits a specialized structure that naturally aligns with agentic trajectories. Specifically, expert routing overlaps more between turns where the agent performs semantically similar operations (e.g., READ, UPDATE) than between turns with differing operations. However, standard RL algorithms ignore this specialization, allowing the MoE routing to go uncontrolled during training, which empirically limit task performance and inference efficiency. To address this, we introduce a hierarchical routing control framework for agentic tasks. We explicitly encourage turn-level expert selections to align with agentic operations while regularizing token-level expert selections to maintain local consistency. To resolve stability issues that arise during post-training with the proposed methods, we further introduce an entropy-gated control mechanism. Overall, our routing control framework achieves over 10-point improvements in success rate on all evaluated benchmarks. These results demonstrate that agentic trajectory structure provides an effective signal for optimizing MoE capacity during RL post-training. --- ### Advantage of Entangled Learning Rules in Quantum Measurement Class Learning Authors: Arka Prabha Das, Abram Magner Published: 2026-10-05 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2610.07328v1 Learning with data in the form of quantum states is of current interest and has led to a variety of problems that boil down to interaction with the available data via quantum measurement and classical post-processing of observed classical outcomes. In quantum measurement PAC learning, one is given a sequence of unknown, prepared quantum states and classical labels, along with a hypothesis class of candidate measurements. The task is to select a measurement from the hypothesis class that minimizes a fixed notion of error in prediction of the classical labels via measurement of a new state by the selected hypothesis. In this work, we consider the advantage of interacting with the given data in the measurement learning framework using learning rules given by measurements that cannot be implemented using local operations and classical communication (LOCC), as opposed to single-copy learning rules. We provide a construction showing that there exist learning scenarios wherein single-copy learning rules are asymptotically suboptimal compared to optimal ones. We then show that learning rules based on entangled measurements enjoy at most a polynomial sample complexity advantage over single-copy learning rules in the PAC learning setting (under a natural joint measurability covering assumption). --- ### SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents Authors: Naoki Wake, Justin Wagle Published: 2026-10-05 Categories: cs.RO, cs.CL arXiv: https://arxiv.org/abs/2610.07327v1 Agent tasks require sequences of interdependent decisions. Autoregressive models support more flexible decision interfaces than conventional classifiers but incur the latency of token-by-token generation. Recent shared-prefix methods reduce this cost by reusing encoded context and scoring multiple decisions in parallel, but do not model decision dependencies or verify execution. We propose SharedKV-BT, where each active node of a behavior tree (BT) exposes stage-local fields and candidates, and Shared-KV scores the candidates in parallel and passes the selected decision to a separate execution system. We tested SharedKV-BT on robot manipulation, mobile navigation, and computer-use tasks. Across three tasks, SharedKV-BT made typed decisions 2.36-4.15 times faster than prompt-matched autoregressive decoding. On the manipulation task, node-local Shared-KV improved joint decision accuracy from 75% to 94% and closed-loop success from 0% to 60%. Fixed-score policy replay showed that stage gating prevented out-of-order actions and external postconditions prevented premature completion. ---