# Research Papers — 2026-10 · bundle page 76 of 156 > Full-text markdown of papers #3751–3800 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/76 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/75.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/77.md) ### Large Language Models, Machine-Assisted Cultural Analytics, and the Agentic Turn Authors: Andres Karjus Published: 2026-10-08 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2610.12792v1 Technologies like large language models make it easier to convert cultural material into analyzable variables, while LLM-driven agentic systems extend machine assistance to other parts of the research workflow. Rather than a full how-to guide or an exhaustive review of recent LLM use cases, this chapter looks at some crucial aspects of this new paradigm as well as the bigger picture. I argue that these technologies expand the scale, methodological range, and scope for delegation, while the basic logic by which those measurements support cultural claims remains mostly unchanged. --- ### EvoBelief: Falsifiable World Models for Self-Improving LLM Agents Authors: Janet Wang, Jiang Guo, Yi Xiang, Jiaqing Yuan, Mingwen Dong, Hideo Kobayashi, Shuaichen Chang, Chandan K. Reddy, Jiarong Jiang Published: 2026-10-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.12789v1 Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can fail when their beliefs about environment dynamics are incomplete, incorrect, or outdated. We study a complementary axis of self-evolution: evolving those beliefs during deployment. Such beliefs can support multiple tasks, but incorrect ones can also propagate across them. We introduce EvoBelief, a self-evolving world model that represents environment knowledge as falsifiable hypotheses. Unexpected outcomes and decision-relevant unknowns trigger hypothesis formation. Later observations and controlled experiments provide independent validation before a rule can guide predictions or plans within its supported scope. Counterexamples narrow or retire rules as the environment changes. The language model remains frozen, and each rule remains linked to its evidence and the decisions it changes. Across four benchmarks spanning static dynamics, hidden drift, and scientific discovery, EvoBelief improves task performance and reuses learned rules across tasks. On ALFWorld without actor-side transition memory, it improves success over the matched Frozen World Model by 23.9% and 31.3% with Claude Haiku 4.5 and GPT-5.4, respectively. On MiniGrid, it revises stale rules and recovers after unannounced dynamics changes. In DiscoveryWorld's Reactor Lab, it discovers and validates quantitative laws, completing 83.3% of Normal-tier and 58.3% of Challenge-tier instances, versus 0% for each evaluated baseline. These results demonstrate self-improvement through testable, revisable environment knowledge rather than model-parameter updates. --- ### Domain Adaptation of SAM 2.1 for Building-Component Segmentation in Image-Based 3D Reconstruction Authors: Ehsan Agha Ebrahimi, Yong-Cheol Lee, Keith G. Mills Published: 2026-10-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.12786v1 3D reconstruction of building components using image-based scanning requires appropriate segmentation of the objects in the 2D building images. In order to benefit from consistent grouping of the 2D masks in 3D environments, vision foundation models such as the Segment Anything Model have been utilized by Group Anything with Radiance Fields (GARField) to perform 3D segmentation. This study fine-tuned SAM 2.1 on the HBD dataset, consisting of 2,679 annotated images from 42 buildings, to enhance multi-class segmentation of 2D building images, covering 11 classes (Wall, Window, Ceiling, Door, Column, Beam, Floor, Opening, Curtain Wall, Roof, and Lift). The model was evaluated using per-class IoU, Dice, and mIoU metrics, and the results show an improvement in mIoU from 49.9% to 69.6%, indicating a meaningful improvement in class segmentation and providing a more accurate model for distilling the masks in 3D. SegFormer was then used as a baseline, generating per-class masks for comparison with SAM 2.1, which indicates improvement in some object classes with larger surface area. The masks in the building images were grouped in the neural radiance field, and the pretrained SAM 2.1 was compared with the fine-tuned SAM 2.1 in the newly rendered images. This comparison shows that fine-tuning improves the grouping of building components at a user-selected grouping scale. This advances the application of Group Anything with Radiance Fields (GARField) in 3D, enabling better segmentation of building structures for 3D auto-reconstruction. --- ### Shift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual Segmentation Authors: Kun Li, Sami Sebastian Brandt, Michael Ying Yang Published: 2026-10-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.12783v1 Referring Audio--Visual Segmentation (Ref-AVS) is an emergent multimodal task requiring the precise identification and segmentation of a specific object based on a natural language expression grounded in both visual and auditory cues. Unlike traditional AVS, which segments generic sound sources, or referring video object segmentation (Ref-VOS), which relies solely on visual--textual grounding, Ref-AVS necessitates fine-grained tri-modal interaction across vision, audio, and language. However, existing methods often fail to maintain consistency when subjected to target shift, a phenomenon where the model erroneously transfers its focus between objects due to transient occlusions, acoustic fading, or identity ambiguities. To address this, we propose a novel Shift-Aware Identity-guided Latent (SAIL) refinement framework. It introduces a dual-token strategy that decouples frame-level dynamics from a global semantic anchor to explicitly model target-shift cues. We design a shift-aware refinement module that rectifies drift by aligning tokens with domain-specific evidence. Finally, we leverage a decoder that integrates the refined embeddings with a continuous memory update to maintain spatio-temporal coherence and identity consistency throughout the video sequence. Extensive experiments conducted on two Ref-AVS benchmarks demonstrate the effectiveness of our proposed method, significantly outperforming existing AVS, Ref-VOS, and Ref-AVS approaches. The code will be released after publication. --- ### Representation Alignment from a Few Paired Data via Distilled Optimal Transport Authors: Julien Kordes, Reuben Dorent Published: 2026-10-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.12781v1 Aligning two independently pretrained unimodal encoders typically demands millions of paired examples. In this paper, we study the regime where only $N \sim 100$--$500$ pairs are available, while unpaired data on either side is abundant. Our method expresses every representation by its similarities to the $N$ paired anchors, which places both modalities in a common coordinate system; matches the two point clouds with a single entropic optimal transport problem solved over the entire pool, whose marginal constraints counteract the hubness that defeats nearest-neighbor matching; and distills the resulting plan into two lightweight encoders, so that the correspondence becomes inductive. We additionally put this marginal constraint in relation with the one-step hub corrections of the bilingual lexicon induction literature. Pairing is required only for the anchors: the unpaired collections may be drawn independently from the two marginals, so that no item outside the anchor set needs to have both of its modalities observed. We evaluate on image-text and molecule-text alignment, where our method outperforms existing approaches at the same anchor budget on Flickr30k, MS-COCO and ChEBI-20. --- ### Coordinate-Free Automatic Differentiation Authors: Alex Guerra, Joshua Aduol, Yaqian Tang, Daniel Williams, Ryan P. Adams, Peter Orbanz Published: 2026-10-08 Categories: cs.LG, cs.MS, math.DG arXiv: https://arxiv.org/abs/2610.12776v1 Automatic differentiation (AD) is a cornerstone of modern machine learning. Since all AD frameworks implicitly fix a basis of Euclidean space to define gradients and Jacobians, they natively process mathematical objects that are arrays of a fixed set of coordinates. This makes it awkward to express objects such as rotations, volume forms, and curvatures that arise, for example, in applications of AI to science. Bespoke workarounds lack reusability. We show that (i) a single, basis-independent derivative operator can represent many geometric differential operations, and (ii) this operator can be expressed entirely in terms of existing AD primitives. This reusable transformation can be composed with JAX batching, compilation, and hardware acceleration. Geometry enters as algebraic data. We experimentally demonstrate its reuse across different manifold operators, its composition through a spacetime inverse-problem pipeline, and its use in optimization over different rotor subgroups. --- ### Credit Attribution in Timestamped Soccer Networks Using Multivariate Hawkes Processes Authors: Phillip W. Kornberg, Kevin S. Xu Published: 2026-10-08 Categories: cs.SI, cs.LG, physics.soc-ph, stat.AP arXiv: https://arxiv.org/abs/2610.12775v1 The two main traditional player statistics used in soccer are goals scored and assists, with an assist credited when a player's pass immediately leads to a teammate scoring. Attributing credit solely to the player who makes the final pass before a goal fails to account for the contributions of multiple players in the buildup to the goal. Consequently, traditional statistics provide only a limited view of player involvement. In this paper, we use multivariate Hawkes processes (MHPs) to model timestamped sequences of passes and shots, which form continuous-time networks. MHPs provide a branching mechanism where an event (a pass or shot) can be generated as a child of a previous event, which allows us to quantify each pass's contribution to a subsequent pass or shot. This approach distributes credit across multiple passes within an attacking sequence, making it applicable across a wide range of situations. Building on this framework, we propose expected goal involvements (xGI), a metric that measures a player's involvement in creating goal scoring opportunities based on their passes. This metric identifies players who play key roles in creating goal scoring opportunities even if they do not make the final pass, offering a more comprehensive measure of attacking involvement and player performance. --- ### REDaCT: Collapse-Free Unlearning in Large Reasoning Models Authors: Joshua Maccoby, Wendy Hui Wang Published: 2026-10-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.12769v1 Unlearning in large reasoning models (LRMs) requires removing forget-set information from both the reasoning trace and the final answer. Existing approaches achieve this objective at the cost of reasoning collapse, where the model fails to produce a coherent chain-of-thought (CoT) and does not properly terminate its reasoning process. To address this challenge, we propose REDaCT (REgenerate via Detection and Corrective Tuning), an inference-time unlearning framework for LRMs. REDaCT consists of two key components: (1) a binary leak detector that identifies sentences in the reasoning trace that leak forget-set information, and (2) an embedding optimization module that learns a corrective embedding offline, such that when injected at the first detected leak during inference, it guides subsequent reasoning towards sentences that do not leak forget-set information. Experimental results show that REDaCT completely avoids reasoning collapse, substantially improving reasoning preservation compared to state-of-the-art unlearning methods while maintaining perfect answer forgetting and near-perfect CoT forgetting. Our code is available at: https://github.com/jmaccoby/redact. --- ### Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries Authors: Oktie Hassanzadeh, Dharmashankar Subramanian Published: 2026-10-08 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2610.12768v1 Semantic query engines evaluate natural-language filters with a large language model, and every evaluation is a costly oracle call. Optimizers that reduce these calls face a dilemma: cascades that trust a cheap proxy miss their precision and recall targets on many queries, methods with finite-sample guarantees save little, and all of them discard the oracle's labels when the query ends. We present SemViews, a certified semantic filter that orders tuples by signals that cost no oracle calls (the labels that earlier queries left behind as semantic views, a local embedding, and a helper model's score), refines that order with labels it must pay for anyway, and certifies its answer with fresh stratified oracle samples. The answer meets user precision and recall targets with probability at least $1-δ$ for every workload and every catalog, so a stale or misleading view can cost oracle calls but never accuracy. On four workloads replayed against 725,000 recorded oracle labels, SemViews meets both targets on 99.63% of queries and saves 28%-45% of the oracle calls, whereas the only prior method in our study with the same guarantee needs 1.32x-1.71x as many calls. When a question returns in different words, views cut its calls by a further 27%-36%, with both targets met on at least 99.8% of such queries; similarity caches and entailment-based reuse meet them on only 17%-47%. --- ### Provenance-grouped protocol for evaluating machine learning in perovskite photovoltaics Authors: Qiwei Han, Chi Zhou Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12766v1 Machine-learning models for perovskite solar cells are typically evaluated using random data splits, which we show systematically leak information through massive internal duplication. Because nearly two-thirds of curated devices share their exact recipe with another, random splits primarily reward the mere recall of historical data rather than testing true physical generalisation. To solve this, we mapped the institutional provenance of the Perovskite Database and established a rigorous hierarchy of grouped splits that progressively isolate duplicate devices, publications, and institutions. Benchmarking thirteen models establishes new state-of-the-art performance across all splits and reveals a critical regime shift: while tree ensembles dominate random splits by recognising familiar recipes, their ranking collapses on genuinely unseen institutions and future discoveries, where composition-aware neural architectures excel. Furthermore, feature importance demonstrates that the device architecture and fabrication methodology dictate final efficiency just as strongly as the absorber chemistry. This standardised protocol empowers the community to separate memorisation from true physical discovery. --- ### Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs Authors: Haotian Qiao, Robert P. Dick Published: 2026-10-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.12762v1 Hardware datasheets contain engineering specifications essential for component selection, system integration, and hardware compatibility verification. However, manual inspection is tedious and error-prone because datasheets are lengthy and heterogeneous, with dense information fragmented across tables, figures, and text. Although large language models (LLMs) can automate this process, naïve one-shot processing omits relevant specifications even when the document fits within the model's context window. We present an automated LLM-driven pipeline that transforms hardware datasheets into general-purpose hierarchical hardware knowledge graphs through chunk-based property extraction, hierarchical routing, and iterative refinement. The framework uses LLMs for information extraction and semantic reasoning while preserving source provenance and applying graph updates through validated instructions and deterministic local execution. This staged design reduces per-query context and maintains traceable intermediate representations. The resulting knowledge graphs provide semantically organized, source-grounded hardware properties for downstream retrieval and reasoning. We evaluate the framework on 20 hardware datasheets spanning diverse component types and document lengths. We assess property faithfulness and introduce inter-graph completeness to measure relative semantic coverage without exhaustive ground truth. Our framework achieves 98.8% property faithfulness compared with 76.1% for the one-shot baseline, while fully covering 83.6% of faithful baseline properties; in the reverse direction, the baseline fully covers only 10.5% of ours. These improvements provide more reliable and comprehensive engineering information for downstream hardware design and verification, reducing the risk of overlooked constraints and incorrect decisions. --- ### DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models Authors: Drew Rein, Patrick Oathout, Vishal Kumar, Udari Madhushani Sehwag Published: 2026-10-08 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2610.12758v1 Language models have been adopted faster than evaluation practices that reliably assess their risks, and a growing share of use is affective rather than informational. Within that traffic users disclose suicide and self-harm (SSH) crises. Existing safety benchmarks score models primarily on refusal, but refusal is not the desired behavior here; the conversation requires a substantive supportive response. We introduce DistressBench, 718 English conversations with clinician-authored user turns spanning 23 SSH subcategories, each paired with a task-specific rubric of weighted atomic criteria across seven dimensions of crisis support and a clinician reference response. A model's score is the weighted average over the criteria its reply satisfies, reading directly as the fraction of required care delivered. The best of 25 frontier models satisfies 88.4% of weighted criteria and the median model 71.4%, against 98.7% for clinician references scored on the same criteria. Pooled across all 25 models, in 35.3% of conversations where a model satisfied every criterion for recognizing the crisis, it failed to route the user toward human help. The shortfall concentrates in the dimensions requiring the model to act rather than withhold. Contrasting each dimension's median model against its best separates capability limits from choices: de-escalation reaches 74.6% in the strongest model against a median of 46.0%, and safety disclaimers 84.6% against 8.3%. Multi-turn conversations score below single-turn ones (68.5% against 74.2%). We release the corpus, rubrics, judge calibration labels, and a companion annex of 20 long-horizon red-team transcripts. These results argue for evaluating crisis safety on the care a model delivers rather than on what it declines to say, and for treating de-escalation and resource routing as deployment requirements. --- ### MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents Authors: Arkajyoti Chakraborty, Adam Zernik, Ishika Kulkarni, Mudit Arora, Hugo Lin, Justin Chiu, Alessandro Di Bari, Neha Gupta, Andreas Stolcke Published: 2026-10-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.12757v1 Task-oriented conversational agents remain fragile under realistic conditions, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks underrepresent adversarial conversation trajectories, thereby limiting the training resources available for developing robust agents. We present MADS (Multi-Agent Dialog Simulation), a synthetic data generation pipeline that produces structured, diverse dialogue trajectories. We inject adversarial conversation, producing validated conversation trajectories that capture realistic, unhappy paths. Using MADS, we construct MADS-Bench: a benchmark spanning six domains, 55 personas, and 1095 conversations, with approximately 66% of conversations containing failure-prone conversation scenarios. We evaluate the robustness of the trained models using a two-stage training approach that combines supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). --- ### NV-Tesseract-AD: Curriculum-Enhanced Conditional Diffusion for Multivariate Time-Series Anomaly Detection Authors: Aditi Gautam, Manikandan Ravikiran, Saira Qureshi, Sena Fatma Ekiz, Charan Jagwani, Mahmoud Elhadidy, Sanjeev Roka Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12754v1 We propose NV-Tesseract-AD, a curriculum learning-enhanced conditional diffusion framework for multivariate time-series anomaly detection. Our central hypothesis is that reconstruction difficulty can be explicitly structured along two complementary axes, masking severity and diffusion noise level, and that training from easier to harder tasks along both axes simultaneously stabilizes optimization and improves residual discriminability. We integrate a Transformer-based diffusion backbone with a three-stage dual curriculum over masking ratios and diffusion timesteps, retaining anomalous samples throughout training and relying on structured corruption to drive self-supervised representation learning. We evaluate NV-Tesseract-AD under two regimes: in-distribution training on the TSB-UAD-M corpus and strict zero-shot transfer to ten EasyTSAD benchmark families without per-dataset tuning. The dual-axis curriculum produces masking-invariant reconstruction, confirmed by a near-zero loss gap between complementary masking strategies within the first training stage, and yields an approximately 3.7-fold improvement in F1 and a 56 percent reduction in MSE relative to a non-curriculum baseline. Zero-shot performance reaches F1 = 0.984 on NAB and F1 = 0.948 on NormA. Weaker results on heterogeneous families are traced to unsupervised threshold calibration rather than reconstruction quality, identifying calibration as the dominant remaining detection bottleneck. Accelerated inference via DPM-Solver++ reduces sampling cost by a factor of 3.5 to 5.7 at the dataset level but couples to thresholding behavior, establishing that the sampler and threshold must be validated jointly. Together, these findings demonstrate that aligning diffusion denoising difficulty with curriculum learning principles provides a principled and practical approach for robust anomaly detection in complex multivariate time series. --- ### Trajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data Authors: Shuo Zhang, Aman Sunesh, Semiha Ergan, Kaan Ozbay Published: 2026-10-08 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.12747v1 Ego-trajectory prediction in urban roadway work zones remains an underexplored topic in autonomous-driving research, with limited dedicated data and systematic evaluation. Roadway work zones involve temporary changes in the lane layouts and connectivity of the roads, complicating interactions with surrounding vehicles and workers. These changes make future vehicle trajectories difficult to predict. To address these challenges, we collect WZDrive-Data, a multimodal dataset comprising 1,183 work-zone driving segments from 33 drivers, using a human-in-the-loop driving simulator with prerecorded worker animations and VR-controlled workers. Driver control and gaze signals are recorded from human participants, while vehicle trajectories and scene information are obtained from the simulator. Our proposed multimodal ego-trajectory predictor, WZDrive, achieves a mean minADE (K=6) of 1.09 m and minFDE (K=6) of 2.12 m. Compared with the best-performing state-of-the-art baseline for each metric in our benchmark, WZDrive reduces minADE (K=6) by 7.18% and minFDE (K=6) by 13.18%. This research addresses a gap in autonomous-driving research on urban work zones by combining human-in-the-loop data collection with multimodal learning from human driving signals and in the context of work zones. --- ### Static Gradient Attribution Underperforms a Density-Matched Random Mask on Loss-Based Forgetting Within LoRA B-Matrix Authors: Yu Sun, Junwei Zhou, Zuodong Xiang, Yike Zhang, Pengcheng Xu, Xinyu Guan, Ruoyun Ma, Hailu Xu Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12744v1 Parameter-efficient continual learning updates a restricted subset of adapter parameters to incorporate sequential tasks while limiting catastrophic forgetting. Gradient attribution is a common rule for selecting that subset, but it requires an additional backward pass over calibration data. We identify a parameter-pool confound in comparisons between initialization-time gradient masks and unrestricted random masks under standard zero-initialized LoRA ($B=0$): the gradient with respect to $A$ is identically zero ($\partial\mathcal{L}/\partial A=0$), so gradient masks select strictly from the $B$ matrix whereas unrestricted random masks draw from both $A$ and $B$. Such a comparison changes both the selection rule and the candidate parameter pool. Isolating the selection criterion by restricting both approaches to the same parameter pool, we find a negative result: a uniform random mask consistently achieves lower loss-based backward transfer than gradient attribution across seven seeds on Qwen2.5-3B. The effect is concentrated on the medical task, which contributes 80\% of the aggregate; code and math move in the same direction, and legal shows no reliable difference. This advantage is consistent with a stability--plasticity trade-off under the tested task sequence, in which random masking slightly reduces single-task fitting. On the two discrete-option tasks (Medical and Legal), the mean accuracy-BWT difference is not statistically distinguishable from zero. --- ### U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction Authors: Ahmad Abbas, Hussein Mazeh, Chadi Abou Chakra, Aya Jouni, Mohammad Ballout, Fadi A. Zaraket Published: 2026-10-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.12742v1 This paper details our submission to KnowledgeGraphEval 2026 Subtask 2 on directed Arabic relation extraction. We explored encoder-based and large language model approaches for predicting one of 40 relations or no_relation from an Arabic sentence and a subject-object pair. Our encoder systems use typed entity markers and separate relation-existence and relation-classification heads, while our LLM systems fine-tune Yehia and Qwen3.5 with QLoRA and ontology-constrained prediction. Our best system, an ensemble of Yehia-RE, Qwen-RE, and TypedPair, achieved a micro-F1 score of 94.06 and ranked 1st in Subtask 2. Yehia-RE (full-vocabulary) achieved 92.98, while the best encoder and Qwen-RE achieved 92.69 and 91.94 respectively. Our results highlight the importance of constrained prediction and complementary modeling approaches for Arabic relation extraction. --- ### Neural expectation-maximization and meta-models Authors: Zhuolin Fu Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12741v1 We interpret Transformer networks as learned approximations to a hybrid probabilistic-inference procedure that combines max-product Loopy Belief Propagation (LBP) with Expectation--Maximization (EM). In this view, a Transformer performs inference in partially observed Markov Random Fields (MRFs) whose structure and parameters are not given a priori but are inferred from data. We show that self-attention implements a differentiable approximation to max-product LBP on an input-conditioned, dynamically structured MRF, with attention weights encoding learned structural affinities. We further establish an EM correspondence at the level of depth: each layer updates latent representations in an E-step-like forward pass, while the transition $θ^{(l)} \to θ^{(l+1)}$ across layers acts as an implicit M-step. Building on this interpretation, we introduce \emph{meta-models}, a design paradigm in which inputs generate instance-specific parameters, unifying mechanisms such as self-attention, mixture-of-experts, and gated units within a single framework. Empirical results support the proposed perspective. --- ### Minimax Rates for Estimating Powered Sliced Wasserstein Functionals Authors: Binh Thuan Tran Published: 2026-10-08 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.12740v1 We study the two-sample estimation of the powered Sliced Wasserstein functional under projected $r$-th moment assumptions. Let $N=n\wedge m$, where $n$ and $m$ are two sample sizes. We establish the minimax rates in the noncritical regimes. When $p<r<2p$, the minimax risk is of order $N^{-(r-p)/r}$, while for $r>2p$ it is of order $N^{-1/2}$. In both cases, the natural plug-in estimator is minimax rate-optimal. At the endpoint $r=p$, the minimax risk is bounded away from zero, so uniformly consistent estimation is impossible. At the critical order $r=2p$, we obtain the exact worst-case rate of the plug-in estimator and a lower bound for the minimax risk, leaving a logarithmic gap between the lower and upper bounds. The exact minimax rate in this critical case remains open. --- ### KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting Authors: Jonas Petersen, Pratik Jawahar, Riccardo Maggioni, Gian-Alessandro Lombardi, Matteo Cozzi, Marek Gajewski, Federico Martelli, Camilla Mazzoleni, Philipp Christian Petersen Published: 2026-10-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.12738v1 Forecasting rare, high-cost events in multivariate time-series systems is hard because their precursors are seldom observed, so a purely data-driven model has little to learn from. The engineers who run these systems, however, hold knowledge that precedes such events, information absent from the scarce labels. We call this a semantic prior and inject it into a self-supervised event forecaster through two switchable mechanisms, a covariate mechanism and an attention-bias mechanism, each the identity at its null, so one architecture serves every prior type with no per-dataset architecture search. A prior helps when it supplies information the observed window does not already contain: in a short context an informative prior beats no prior in-domain (pooled h-AUROC over the no-prior baseline: a periodicity clock +14%, p<0.001; a conservation residual +47% at a 0.25 label fraction), and a working prior transfers out-of-domain (+53%), substituting for feature transfer, while priors the window already recovers stay inert and the attention-bias mechanism shows no measurable gain. KITE is a switchable, attributable route to contextual conditioning, and a substrate for scaling toward cross-domain, pretrained time-series foundation world models that carry their governing structure explicitly. --- ### Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability Authors: Davide Wiest, Ahanaf Hasan Ariq, Abdul Monaf Chowdhury Published: 2026-10-08 Categories: cs.LG, cs.CV, stat.ML arXiv: https://arxiv.org/abs/2610.12737v1 Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensive, while static importance scores discard input dependence. We derive KPSA (Kernelized Parameter Sensitivity Atlas) from a block decomposition of the empirical neural tangent kernel. It measures normalized parameter-group sensitivity, embeds those sources in an explicit query space, and uses a lightweight kernel to estimate sensitivities for unseen inputs. We derive bounds that separate finite-source from irreducible representation error and give margin-based top-$k$ recovery. This paper studies two interpretability applications. Firstly, KPSA identifies parameter groups with high susceptibility to perturbations across vision, forecasting, and protein-modeling setups. Across a fivefold range of parameter budgets ($0.02$-$0.1\%$), its selected groups attain $39$-$85\%$ of the perturbation susceptibility of a first-order backpropagation oracle. In vision and forecasting, these parameter groups form sparse sensitivity circuits that extend across depth and vary systematically with the input. Secondly, we use KPSA on an activation-attribution problem for MLP features in transformers. It retains $81\%$ of the gap between a backpropagation oracle and a constant-sensitivity baseline on vision while increasing batched query-time throughput from 551 to 2,041 images/s and reducing peak GPU memory from 4.55 to 0.44GB. On the protein-modeling task, it recovers $68\%$ of this gap. An ablation of KPSA's kernel aggregation shows that nearest-neighbor retrieval in KPSA space can remain competitive. The empirics show that compact kernel atlases can store useful input-dependent parameter sensitivity while amortizing repeated gradient attribution, a step toward scalable conditional interpretability. Code can be found at https://github.com/Axym-Labs/kpsa . --- ### Reference-Free Food Volume Estimation from Egocentric Stereo Video Authors: Vivan Kumar, Gautham Vinod, Fengqing Zhu Published: 2026-10-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.12735v1 Current stereo vision-based approaches for food portion estimation are hindered by the user burden of using a mobile phone to capture multiple images or placing a reference object in the scene for scale calibration. As a step towards passive dietary intake monitoring, we introduce a method that uses stereo video from a wearable egocentric device to reconstruct food items in true physical scale to accurately estimate volume. By utilizing FoundationStereo for zero-shot stereo matching, SAM 2 for food segmentation, and TSDF fusion over a set of keyframes, our method yields a visually and metrically accurate 3D mesh of any plated food item from a single stereo recording. We leverage the unique offerings of wearables, such as a factory-calibrated stereo baseline and camera poses estimated on-device via visual-inertial odometry (VIO), to perform fully automatic reconstruction without a scale reference object in the scene. We show strong initial volume estimation results across five recorded food items, achieving a mean absolute percentage error of 9.1%. --- ### StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras Authors: Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita Published: 2026-10-08 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.12734v1 Stereo vision is increasingly used for robotic manipulation, with a growing body of work incorporating it into Vision-Language-Action (VLA) models. However, the scarcity of large-scale, real-world stereo datasets remains a fundamental bottleneck for scaling such policies. Recent generative monocular-to-stereo methods target settings such as VR content and autonomous driving. No prior work produces realistic synthetic stereo data for robotic manipulation, where stereo supervision has come predominantly from simulation. We propose StereoEngine, which introduces two complementary methods to synthesize stereo data for robotic manipulation. In the first, we warp a monocular (left) video into the right view using estimated depth and inpaint the disoccluded regions with a video diffusion model, lifting monocular demonstrations into stereo pairs without training on real stereo. In the second, we render a stereo pair in simulation and jointly generate both photorealistic views, producing consistent left-right data without any real video as input. StereoEngine outperforms existing baselines in generated stereo quality, and using its synthetic data for policy mid-training or task-specific fine-tuning substantially improves downstream bimanual manipulation. Project website: https://stereoengine.github.io --- ### A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges Authors: Xiaoyu Li, Zhizhou Sha, Chiwun Yang, Dai Shi Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12728v1 Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and benchmark score. We compare them as maps. A pretrained checkpoint is a base point in weight space, and a weight-space method is a smooth map from a small parameter space that starts at that point. These maps form a slice category in which the frozen model is initial and full fine-tuning terminal. Three invariants of the map do most of the work. Its image near the base point governs expressivity, through the first-order image, the dimension, a min-cut bound on rank and whether that point is smooth or an apex. Its fibres, with the optimizer's metric, govern training dynamics. Base change moves the base point and covers splitting initialisations, quantisation, restarts and merging. We prove, for example, that zero-initialised LoRA, and Householder reflection adaptation at its default start under stated rank and parity conditions, begin at the apex of a cone; that no exact initialisation lets LoRA reach an update of rank above twice its own; that exactly orthogonal methods never change a weight's singular values in exact arithmetic, however often they are merged; that under Adam with no epsilon, weight decay or clipping and one shared schedule, LoRA+ from the standard zero initialisation follows exactly the trajectory of plain LoRA with its scale multiplied by the learning-rate ratio; that Adam with shared hyperparameters respects only the signed permutations inside LoRA's continuous symmetry group of full-rank factors; and that the activation function decides when a scaling adapter folds into preceding weights. We classify 382 methods from 138 papers by seven coordinates read off their formulas, with 403 simulation arrows and 485 obstructions. Every numbered result is proved in full, and results due to others are credited where we re-derive them. --- ### Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction Authors: Utkarsh Saxena, Ruijing Yang, Mehdi Rezagholizadeh, Akash Haridas, Vikram Appia, Emad Barsoum Published: 2026-10-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.12727v1 Feed-forward 3D foundation models reconstruct scenes from unposed images, but the quadratic cost of global attention limits their scalability to large view sets. We present Zebra3D, a layerwise sparse-linear hybrid attention framework that improves the efficiency of pretrained 3D foundation models without training from scratch. Across VGGT, HunyuanWorld-Mirror, and $π^3$, we observe a broadly consistent depth-wise pattern: early stages are relatively tolerant to linear replacement, while sensitive middle-to-late stages tend to exhibit more concentrated attention. Zebra3D exploits this structure by assigning linear-centered attention to tolerant stages and tile-sparse attention to sensitive stages, using landmark summaries to preserve unselected context. Closed-form affine fitting enables training-free conversion, while optional post-conversion training combines task supervision with output and relational feature distillation. Across all three backbones, Zebra3D achieves strong reconstruction and camera-pose accuracy at high attention sparsity, with training-free variants remaining close to their dense counterparts. End-to-end speedups increase with input view count, reaching up to $7.1\times$ at 1,024 views. After post-conversion training, Zebra3D-VGGT reaches 80.5\% RealEstate10K AUC@30 at 94\% mean attention sparsity, within 1.1 percentage points of dense VGGT fine-tuned on the same data and schedule. --- ### Spatial Context or Memory? Sizing the Inputs of Neural Surrogates for Partially Observed Fields Authors: Ruige Kong Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12723v2 Neural surrogates that forecast a physical field from sparse, noisy sensors read a window of nearby sensors and a history of past snapshots. Practitioners choose both by comparing fitted models with each other. Such comparisons cannot tell a model's shortfall from missing information. We measure the trade-off between window and history against the Bayes-optimal error of the same readings. An exact Gaussian analysis shows that noisy or sparse observation of a field with local dynamics makes the optimal forecast read distant sensors only through spatial correlation. On a forced linear field with a known optimum, trained models that read only the window come within 1% of it. We then train such models on viscous Burgers flow and the chaotic Kuramoto-Sivashinsky (KS) equation, with every deciding comparison fixed before any test evaluation. In every field except KS, eight snapshots remove a smaller fraction of the one-snapshot error as the lead time, the number of steps to the forecast target, grows. In KS, for windows up to one correlation length, they remove a larger fraction. This lead-time inversion persists across sensor densities, three architectures and a two-dimensional domain. It shrinks as damping lowers the Lyapunov exponent. Damping also removes the linear instability of KS. We therefore tie the inversion to instability and leave chaos and linear amplification unseparated. For surrogate design the results give two rules. Size the window in correlation lengths of the field. Split a fixed input budget between window and history for the lead time the model will serve, because the best split moves toward wider windows as the lead time grows. In Burgers flow the split chosen at lead time one ends with 13.5 times the best error at lead time eight. --- ### A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models Authors: David García-Lorite, Raul Merino Published: 2026-10-08 Categories: q-fin.RM, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.12718v1 Large language models are stochastic by nature. Repeated executions under the same experimental conditions may produce different responses. We propose a framework that can be applied across the model lifecycle, from task design to residual behavior and continuous monitoring. The method consists of building an empirical response distribution estimated through Monte Carlo simulation. Semantic interventions are introduced to study how these distributions change. We illustrate the framework with two different tasks, borrower classification and music album recommendation, and quantify the resulting distributional changes. The framework is linked to model risk management and governance by measuring robustness and control effectiveness, and characterizing residual behavior. Since it relies only on observed responses, it can also be applied to black-box models accessed through commercial APIs. --- ### Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing Authors: Kai Li, Hanlin Cai, Zihao Liu, Yichen Li, Jose Alcaraz Calero, Wei Ni, Falko Dressler, Özgür B. Akan Published: 2026-10-08 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.12711v1 Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is vulnerable to Byzantine attacks that corrupt semantic consistency and factual resilience through malicious model updates. This paper presents a new resilience strategy that prevents semantically corrupted knowledge from propagating during federated aggregation. A defense problem is formulated to jointly maximize global accuracy and suppress manipulated model updates, enabling trustworthy knowledge aggregation without accessing private local data. To strengthen the resilience of FedLLMs, we develop a novel Hypergraph Message Passing Graph Autoencoder (HMP-GAE) framework, where low-rank model updates are represented as nodes in a hypergraph and high-order semantic relationships among multiple agents are exploited through iterative message passing. By leveraging historical checkpoints and cross-agent relational reasoning, HMP-GAE identifies and suppresses semantically inconsistent updates while preserving knowledge alignment among agents throughout federated training. HMP-GAE is implemented using Qwen-2.5 and Llama-3.2 as pretrained FedLLM backbones and evaluated on AG News and Yahoo! Answers datasets. Compared to existing defenses, HMP-GAE improves global accuracy by $1.21$\%, reduces final-model classification semantic entropy by $44.08$\%, and lowers perplexity by $13.34$\%. HMP-GAE outperforms the GAE-based defense by improving the accuracy $1.39$\%, reducing the semantic entropy by $54.5$\%, and lowering perplexity by $35.5$\%. --- ### Unsupervised Multimodal Reward Modeling Authors: Yueying Li, Jingxuan Fan, Kianté Brantley, Sham M. Kakade, Hanlin Zhang Published: 2026-10-08 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.12707v1 Vision-language reward models are trained on annotated preference pairs, which are expensive to collect, can disagree, and are ranked by benchmark accuracy. We build one with no human preference label: a linear head on an intermediate layer of a frozen Qwen3-VL backbone, trained to score a web caption above a perturbed version of the same caption; labeled data enters only to select the layer. The layer is the decisive choice, worth 5.8 points over the last layer, and one recipe transferred without re-tuning beats or at least matches GPT-4o on three benchmarks at 32B, 6.6 points ahead on VL-RewardBench, from a few thousand parameters at about a thousandth of fine-tuning compute. At an equal pair budget, perturbations teach a frozen head 3 to 5 points more than curated RLAIF-V pairs. Because the backbone is frozen, the objective is convex, and the perturbation sampler specifies the reward, which the benchmark does not identify: two heads trained on disjoint halves of the same perturbations tie on the benchmark and differ by 6.4 points in hallucination judging. Retraining the head on the policy's own verifier-labeled candidates cuts caption hallucination by 5.1 CHAIR points and lifts image-generation pass rate by 5.4, while scoring lower on every reward benchmark. Together, an intermediate-layer probe, free same-image perturbations, and a verifier-driven bootstrap turn give a recipe for multimodal reward modeling that needs no annotator, costs a fraction of fine-tuning, and is specified by the comparisons it is trained on rather than by a benchmark rank. --- ### PVBRF-ID: Private, Verifiable and Byzantine-Robust Federated Intrusion Detection for Oilfield Enterprise Networks Authors: Mustafa S. Aljumaily, Ali Ataeemh Allami, Mustafa N. Mnati, Nawar S. Alseelawi, Shahab Abdulla Published: 2026-10-08 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2610.12704v1 Federated learning allows dispersed oilfield sites to train a shared intrusion detector without pooling network traffic, yet its aggregation step forces a choice between privacy and robustness. Byzantine-robust rules must read each update in the clear, whereas secure aggregation hides updates from the checks that detect poisoning. We present PVBRF-ID, a two-server protocol in which sites secret-share their updates and the servers jointly test each update's norm and its cosine similarity to a reference computed on a small clean root set, revealing one accept bit per site. Commitments, Merkle roots and a homomorphic audit make the inclusion of accepted updates publicly verifiable. On a 15-class Edge-IIoTset task with ten sites holding differently distributed data and ten random seeds, PVBRF-ID matched FedAvg on clean data (macro-F1 0.708 vs. 0.706) and withstood sign-flip attacks (0.696 vs. 0.091). Against an adaptive attacker controlling 30% of sites, PVBRF-ID with secure clipping reached 0.641, whereas FedAvg fell to 0.046; plaintext multi-Krum remained higher by 0.052. An update-inference attacker recovered each site's class mix from plaintext updates (Spearman correlation 0.81) but not from one server's view. Backdoors passed the filter, and noise-based mitigation gave only heuristic protection. The implementation uses Python 3.13, NumPy 2.3, 30 rounds and 10 seeds. --- ### Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation Authors: Marco Stefani, Edoardo Parpaiola, Matteo Bino, Gianluca Caregnato, Francesco Roncolato, Daniel Fusaro, Loris Nanni, Alberto Pretto Published: 2026-10-08 Categories: cs.CV, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2610.12703v1 High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation across Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Vision Mamba (ViM). Unlike predominantly qualitative studies, we quantify the alignment between model attention and human visual perception using eye-tracking ground truth. We formalize this comparison via a standardized normalization pipeline mapping post-hoc attribution maps and gaze heatmaps onto spatial probability distributions. Alignment is evaluated across fine-grained classification, medical imaging, and emotion recognition using architecture-specific XAI methods. We measure fidelity using Jensen-Shannon similarity, Chi-square similarity, and Pearson correlation, three complementary estimators capturing support overlap, mass discrepancy, and structural co-variation. Our results reveal distinct attention dynamics: CNNs tend to exhibit a more global focus, with spatially more diffuse saliency maps that correlate well with human perception in general contexts, while ViTs demonstrate fine-grained, patch-level attention, often focused on discriminative microfeatures. The Mamba architecture shows biased behavior: it achieves strong explainability in medical tasks but exhibits divergent intensity distributions in natural images; our analytical characterization of the metrics makes this dissociation explicit, since near-unit support overlap is attained simultaneously with a vanishing linear correlation. We further analyze the effect of backbone freezing and ensemble strategies on model interpretability. The results highlight how architectural and training choices influence the alignment between model saliency and human visual attention. --- ### Product Monte Carlo: Expectation Under a Product of Densities Authors: Pietro Carlotti, Sifan Liu, Yuling Yao Published: 2026-10-08 Categories: stat.ME, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2610.12702v1 Aggregating independently computed sub-sample inferences is a well-known challenge in large-scale Bayesian computation, federated learning, and opinion pooling. The core problem is to approximate a distribution whose density is proportional to a product of individual densities. We propose Product Monte Carlo (PMC), an algorithm for computing arbitrary expectations under a product of densities using only Monte Carlo draws from individual densities. We turn the intractable product expectation into a regression problem by expressing it through a family of computable conditional expectations. Besides the point estimate, our fully Bayesian regression formulation provides coherent uncertainty quantification and principled diagnostics. We establish theoretical guarantees on consistency and characterize convergence rates for the PMC estimator. Across simulated and real-data experiments varying the number, dimensionality, and heterogeneity of the component distributions, PMC achieves higher estimation accuracy, better-calibrated uncertainty coverage, and improved scalability at a lower computational cost than existing methods. In addition, PMC requires no density evaluation, making it applicable to simulation-based inference, as we demonstrate in an application with protein images. --- ### Activating the Annotator: Operationalising Lived Experience in Data Annotation Authors: Sheza Munir, Ramaravind Kommiya Mothilal, Syed Ishtiaque Ahmed Published: 2026-10-08 Categories: cs.CL, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2610.12701v1 Perspectivist NLP has established that annotator positionality shapes labels for subjective tasks, but the field still lacks methods for operationalising it. Positionality is typically operationalised as a demographic form completed at recruitment: a static attribute recorded once and treated as a covariate, on the assumption that the knowledge it indexes is active when the annotator reads an item. This paper treats that assumption as a design problem and asks whether lived experience can instead be primed by the task itself. We introduce AXLE, a pre-annotation stage in which a scenario vignette anchors a short, axis-guided conversation that is synthesised into a first-person micro-narrative and returned to the annotator before labelling begins. In a 2x2 between-subjects study (104 annotators, 30 items, 1,040 annotations) on ambiguous hate speech spanning immigration, religion and gender, elicitation was associated with higher identity resonance and higher sensitivity to harm. It also increased label entropy and lowered inter-annotator agreement: the stage appears to surface plurality rather than manufacture consensus, which distinguishes it from annotator training, whose success criterion is convergence. --- ### Primal-Dual Flow Matching for Sample-Wise Constrained Generation Authors: Zhengyan Huan, Peter Y. Lu, Shuchin Aeron Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12699v1 We consider the problem of learning to generate data while satisfying a prescribed \emph{sample-wise} constraint with a user-specified probability of constraint satisfaction. Starting with a population-level constrained negative log-likelihood minimization and using a flow-matching (FM) parameterization, under regularity assumptions and sufficient expressivity of the velocity field family, we derive guarantees on the probability of constraint satisfaction for the corresponding primal-dual optimization algorithm. We provide a practical implementation of this approach, called Primal-Dual Flow Matching (PDFM), which has direct control over constraint satisfaction rate and requires only binary membership oracle feedback for constraint satisfaction, avoiding the need for differentiable distances, projections, or special structure of the constraint set, such as convexity. We show that PDFM improves constraint satisfaction over vanilla FM and achieves competitive performance against constraint-aware baselines while maintaining distributional fidelity. Our code is available at https://github.com/ZhengyanHuan/PDFM. --- ### Toward Maximizing Algebraic Connectivity via Density-Dependent Backbone Construction and Reinforcement Learning Completion Authors: Zeru Zhu, Marco Gamarra, Ji Liu Published: 2026-10-08 Categories: math.OC, cs.LG, math.CO arXiv: https://arxiv.org/abs/2610.12697v1 This paper studies an open network design problem of constructing graph topologies with maximum algebraic connectivity under fixed numbers of vertices and edges. A density-dependent approach is proposed that decomposes the design task into two stages: a high-quality, low-cost structural backbone construction and a reinforcement learning completion stage. The method selects the backbone based on density, using complete multipartite graphs in dense regimes and Cayley graphs in low-to-intermediate regimes, and then refines the remaining edges through a learning-based procedure. Numerical results show that the proposed method achieves high algebraic connectivity with favorable runtime scalability, outperforming existing methods. These results support a structural-family-first strategy for scalable network design. --- ### Critical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built On Authors: Tomo Oga, Devesh Shah, Cailum M. K. Stienstra, Gabriel Asher, Antonio H. de O. Fonseca, Niall O'Connor, Michael Widrich Published: 2026-10-08 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2610.12694v1 Molecular machine learning evaluates out-of-distribution performance with structure disjoint splits, a construction rule fixed once at the scale its library happened to have: threshold a pairwise distance, then assign whole connected components to folds. For predicting structures from mass spectra, the field has converged on single-linkage clustering under the myopic Maximum Common Edge Subgraph (MCES) distance at a threshold of 10. This convention was set on 29,000 molecules but public libraries now hold 227,690 molecules. MCES is NP-hard per pair over a quadratically growing set, and so the criterion has never been evaluated at that scale. We propose an optimized version of this criterion, allowing for computationally feasible application on the public libraries: Admissible bounds and a union-find skip reduce $2.6 \times 10^{10}$ molecular pairs to only $1.15 \times 10^{7}$ integer programs, a $2{,}259\times$ saving, while provably producing the lossless partition. We find that at this scale the graph percolates. A single component holds $95.5\%$ of the library, capping any test set at $4.5\%$. What remains is not merely smaller, but systematically different: a held-out compound outweighs a training compound 88.1\% of the time, because a fixed absolute budget is a tighter relative tolerance on a larger molecule. Large library benchmarks using this splitting rule naively therefore conflate structural novelty with extrapolation to larger, more complex chemistry. --- ### Expert-level detection of low-voltage intervals in EEG as a robust biomarker of neonatal encephalopathy Authors: John M. O'Toole, Sean R. Mathieson, Aurel Luca, Soraia Ventura, Sean Griffin, Geraldine B. Boylan, Robert Hogan Published: 2026-10-08 Categories: cs.LG, eess.SP, physics.med-ph arXiv: https://arxiv.org/abs/2610.12680v1 Background: Discontinuity in neonatal EEG is a critical marker of brain dysfunction but can be difficult to quantify visually. Inter-burst intervals (IBIs) are a key characteristic of discontinuity, yet their definition does not easily translate to AI detection. Objectives: To introduce low-voltage intervals (LVIs), defined exclusively by amplitude and duration, as a context-independent alternative to IBIs, develop an AI detection method for LVIs, and assess their clinical utility as a marker of brain injury. Methods: We developed a ConvNeXt model to detect LVIs and compared its performance with existing methods. We then tested the clinical relevance of detected LVIs across four applications: 1) grading background EEG abnormalities on an open benchmark dataset, 2) classifying clinical hypoxic-ischaemic encephalopathy (HIE) grades and comparing with a normal EEG dataset, 3) seizure prediction, and 4) association with seizure burden. Results: For training and validation, 654 hours of per-channel EEG from 123 neonates were reviewed and 51,162 LVIs were annotated. On held-out validation, ConvNeXt had an AUC of 0.996 and a Matthews correlation coefficient of 0.926. Model-reader agreement exceeded inter-reader agreement ($Δκ= 0.025$, 95% CI: 0.007 to 0.045, $p<0.001$), attaining expert-level equivalence. On a combined dataset of 444 neonates, percentage LVI showed a strong association with EEG grades (Spearman's $ρ=0.801$), a moderate association with HIE grades ($ρ=0.384$), a weaker association with seizure burden ($ρ=0.244$), and a strong seizure prediction capacity (AUC $=0.872$). Conclusion: AI detection of LVIs achieves expert-level equivalence, whereas quantitative features do not. Automated LVI quantification provides a robust clinical biomarker of neonatal encephalopathy associated with background EEG activity, HIE severity, and seizure risk. --- ### Amortised Inference through One-Step Implicit Sampling Authors: Vincent Pauline, Kirill Tamogashev, Arran Carter, Sanghyeok Choi, Stefan Bauer, Esmeralda S. Whitammer Published: 2026-10-08 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.12679v1 Efficient sampling from Bayesian posterior distributions in high dimensions remains a hard problem, despite advances in theory and algorithms. Multiple steps are usually required to draw unbiased samples, for example, iterations of an MCMC algorithm or integration steps in a diffusion-based amortised sampler. However, scalable one-step amortised inference remains a challenging open problem. In this work, we build upon recent progress in data-driven generative modelling to offer a possible solution for one-step amortised sampling. Our one-step implicit sampler (OSIS) uses short-time MCMC dynamics to define a local target for the evolution of an implicitly modelled distribution. In the asymptotic limit, the modelled distribution is a fixed point of the MCMC kernel and thus samples from the target. We analyse the convergence properties of OSIS and show connections with other generative modelling and sampling algorithms. We study various design choices and show that OSIS performs well compared to multi-step amortised samplers and non-amortised MCMC baselines while being far more efficient at sampling time. --- ### WoodBR-Cross: A public wood-image dataset and individual-tree-disjoint benchmark for species identification Authors: Daniel Casanova, Alexandre Bahia Gontijo, Arnaldo Candido Junior, Silvana Nisgoski, Pedro Luiz de Paula Filho Published: 2026-10-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.12676v1 Wood-image benchmarks can yield optimistic estimates when images from the same tree occur in both training and test sets. WoodBR-Cross contains 4,875 transverse-surface images in 38 operational taxonomic classes, linked to 303 distinct trees identified by numeric catalogue witness codes (codigos-testemunho) in the Brazilian Forest Service collection. A species-level subset comprises 3,406 images, 20 classes and 214 trees. Three tasks compare duplicate-aware image partitions for all classes (A), image partitions for the species subset (B1), and individual-tree-disjoint partitions for that subset (B2). In B2, all images from each tree are kept together, so no tree is shared across training, validation or test within a fold. ResNet-50, ConvNeXt-Tiny and ViT-B/16 were evaluated with three outer folds, internal validation and five training seeds. Handcrafted and frozen-feature baselines complement border-only and randomized-label controls. Validation-selected ConvNeXt-Tiny achieved B2 tree-level macro-F1 of 0.8621 +/- 0.0317; frozen DINOv2 features yielded 0.9000 +/- 0.0722. Values are means and standard deviations across three seed-averaged fold means. Results estimate performance on previously unseen trees from this collection. --- ### GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks Authors: Amirhossein Vahdat, Thierry Badard, Luc Lamontagne Published: 2026-10-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.12669v1 Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. This omission is critical as retrieval oriented geo-analytic tasks cannot be supported reliably without first identifying the necessary datasets and constraints. GeoFitBench-LLM is introduced as a benchmark for assessing whether LLMs can infer the datasets, the supporting resources and the constraints required by geo-analytic requests in natural language. The benchmark is structured around two reasoning dimensions, Spatio-Temporal Relational and Semantic Grounding, reflecting long-standing challenges in geospatial information retrieval and related natural language tasks. Ground truth requirements are encoded in a fixed, provider-independent schema for reproducible evaluation of resource identification and attribute-level specification. Experiments on seven models under minimal prompting indicate that identifying the necessary resources is often achievable, with GPT-5.4 Thinking achieving the best result by recovering the complete set of resources in 66.67% of benchmark requests. Results further indicate that accurate fitness-for-use specification remains more difficult as inferential demands increase. --- ### Recurrent Harness for Agentic Continual Learning Authors: Yuxin Xiao, Zhiyun Lu, Jianyu Wang, Yangtian Zhang, Yang Song, Qifan Wang, Bailin Wang Published: 2026-10-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.12668v1 Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or validation data for harness optimization. To address this, we propose ReHarness, a recurrent harness framework for agentic continual learning that complements forward read and write with backward revision under a strictly online streaming protocol. We ask what information could have been captured differently in the harness state to better inform the current instance in the stream. Specifically, after each instance, we leverage the resulting trajectory as feedback to revise the reflections retrieved for that instance, thereby propagating feedback backward through the textual harness state. Across three continual learning benchmarks and three language model backbones, ReHarness consistently outperforms strong raw-context baselines, memory- and reflection-based methods, and prompt optimization approaches. Further analysis shows that ReHarness produces source-grounded and meaningful revisions, corrects overgeneralized or outdated experience under distribution shifts, and improves both stability and plasticity during continual learning. --- ### perturber: A Stateless Service for Semantics-Preserving Text Perturbations Authors: Khoi-Nguyen Tran Published: 2026-10-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.12667v1 Large language model (LLM) evaluations on clean benchmarks overstate model robustness: real inputs arrive perturbed, and these meaning-preserving variants routinely move model answers. Studying this systematically requires applying perturbations one at a time, reproducibly, and identically wherever they run, yet existing tools couple them to a benchmarking stack rather than packaging them as a reusable transform layer. We present perturber, a stateless service and Python library that applies exactly one semantics-preserving perturbation per call, drawn from a first-party catalog of 68 perturbations across 11 families. It turns on a single primitive, with composition left to the caller chaining calls, so the service and the library produce identical output by construction. We evaluate the tool itself, its correctness, reproducibility, and cost, rather than any model's robustness, measuring meaning-preservation per perturbation rather than assuming it. The demonstration adds a live playground, an introspectable catalog for benchmark selection, and a one-command reproducible evaluation. --- ### Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision Support Authors: Federico Mazzoni, Andrea Failla Published: 2026-10-08 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2610.12666v1 We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conventional RAG systems, relying on static Knowledge Bases (KBs), our proposal addresses settings where the KB is initially empty and is progressively populated through human decisions. The system stores previous decisions as retrievable precedents and moves from silent observation to evidence-grounded contestation and, finally, to autonomous handling with abstention. Against an independent baseline, iRAG matches final-decision error under 10% drift without retrieval decay and reduces it under 40% drift across all configurations. Retrieval decay improves performance on changed knowledge while increasing error on stable knowledge, evidencing a stability--plasticity trade-off rather than a general advantage. Human oversight is an architectural provision of the workflow; its usability with real human users remains to be evaluated. --- ### MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis Authors: Ximing Lu, Aviral Kumar, Jan Kautz, Yejin Choi, David Acuna Published: 2026-10-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.12659v1 Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether the dataset provides a useful learning signal for a target policy. To guide the synthesis of effective RLVR data, we experimentally characterize dataset effectiveness as a function of its problems, the target policy, and the training rollout budget. Under this characterization, we show that a large open-source math corpus pooled from widely used RLVR datasets falls almost entirely into a zero-advantage trap: for a fixed target policy and rollout budget, roughly 88% of its problems are solved in every rollout or failed in every rollout. Filtering concentrates what remains, but it can only select, discarding the hard problems. Effective synthetic problems should therefore require the reasoning operations and compositions required to solve those hard problems. Yet their difficulty must be calibrated, so that some rollouts succeed, some fail, and at least one correct solution fits within the training budget. Prompting a teacher to vary hard problems directly does not achieve this. Guided by these empirical principles, we introduce MagicBeanStalk, a top-down decomposition and bottom-up recursive data-synthesis algorithm that grows seed problems into families of substantively new, policy- and budget-calibrated training problems while preserving the seeds' reasoning blueprints. Across 8 math benchmarks, continual RLVR on MagicBeanStalk problems improves gpt-oss-120b from 61.2 to 69.8 (+8.6) and DeepSeek v4Flash from 72.4 to 77.9 (+5.4) on a 16K-token budget. Training on the full 78K source corpus improves by only +1.1 and its best filtered real data subset by +5.8. In finance, we synthesize over 14K verifiable problems from only 340 solutions and improve over base by 6.9 and 2.4 points on SecQue and FinanceBench, respectively. --- ### Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK Authors: Talha Ansar, Waqar Muhammad Ashraf, Alejandro Coca-Castro, Manvendra Janmaijaya, Ramit Debnath, J. Scott Hosking Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12658v1 We develop a data-driven sensor-placement framework and apply it to aerosol monitoring in the United Kingdom (UK). A trained convolutional Gaussian neural process is embedded within the DeepSensor optimisation framework. Genetic optimisation with lazy evaluation and caching reduces mean computational time by 60\% (10$\pm$3 versus 25$\pm$7 minutes) while producing sequential placement performance comparable to the greedy solver. Using the CAMS reference field to construct a retrospective oracle benchmark, Joint NLL improves by about 22\% for Joint-MI-driven genetic placement after five locations for aerosol stations are identified. Seasonal and wind-regime analyses show that agreement between model-based criteria and oracle benchmarks varies with meteorological transport conditions. These results show a computationally efficient approach for data-informed expansion of environmental observing systems. --- ### Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization Authors: Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh, Vahid Partovi Nia, Parsa Omidi Published: 2026-10-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.12657v1 Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model depth. Existing approaches such as Multi-Query Attention (MQA), Grouped-Query Attention (GQA), Multi-Head Latent Attention (MLA), and Tensor Product Attention (TPA) reduce this cost through different trade-offs, but often sacrifice expressivity, require additional positional-encoding machinery, or impose restrictive low-rank structure. We propose Kronecker Product Attention (KPA), which represents key and value activations as sums of Kronecker products of compact, token-dependent matrix factors. KPA strictly generalizes TPA: rank-one vector-outer-product factorization arises as a degenerate Kronecker split, while non-degenerate matrix factors can represent richer block-structured patterns. We further show that a structured rotary embedding operator matched to the Kronecker representation preserves the relative-position property of RoPE while rotating only the compact factors, removing the need for a decoupled RoPE branch as in MLA. Empirically, KPA matches or exceeds TPA, MHA, MQA, GQA, and MLA across four model scales and nine downstream benchmarks under identical training conditions, while achieving up to 10x KV cache compression. The Kronecker head split is a tuneable hyperparameter that allows practitioners to navigate the compression-accuracy trade-off at design time without architectural changes. --- ### CLEAT: Learning Value-Guided Clarification for Interactive Agents Authors: Jiatan Huang, Zheyuan Zhang, Ziming Li, Tianyi Ma, Mingchen Li, Yanfang Ye, Chuxu Zhang Published: 2026-10-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.12655v1 LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users may leave unstated. We study this problem as interactive intent alignment through clarification. Yet clarification is useful only when the agent can turn the answer into better decisions. As training changes how the agent handles incomplete information and uses additional answers, the same clarification can become more or less useful. We introduce CLEAT (CLarification through valuE-guided Agent co-Training), a framework that co-trains a clarification-value controller and the task policy from shared interaction outcomes. We formulate residual query value to measure the task utility gained by asking rather than proceeding under the current policy, and estimate it through paired rollouts from the same interaction history. These paired returns train the controller to predict clarification value and the task policy to select useful questions and act on the answers. The controller guides subsequent rollout collection, while outcomes from the updated agent provide new value labels that allow clarification guidance to adapt as the agent learns. With Qwen3-4B, CLEAT achieves the highest mean score in all ten evaluation settings across four benchmarks. Gains over the strongest baseline reach 13.2 and 6.5 percentage points on UserGym Travel and IN3 underspecification judgment accuracy, respectively. Ablations show that co-training improves the task policy even when the controller is removed at inference, while adapting clarification guidance to the evolving policy yields further gains. --- ### SynAct: Synergistic Active Feedback Learning for LLM Agents Authors: Ning Liu, Ian Li, Kristina Klinkner Published: 2026-10-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.12651v1 LLM agents executing multi-step workflows fail in two fundamentally different ways: recoverable slips, which further attempts can repair, and knowledge gaps, which retrying cannot resolve. Expert feedback can address the latter, but expert attention is scarce. The key challenge is therefore not whether to ask for feedback, but where feedback can change the outcome. Existing approaches either avoid expert feedback, allowing agents to reinforce their own errors, or allocate feedback at the task level without identifying consequential decisions. We present SynAct, an active learning framework that treats expert attention as the binding constraint and allocates feedback at the level of individual decisions. SynAct ranks decisions by the mutual information between the selected action and the terminal outcome across repeated rollouts, queries an expert at the highest-value decisions, and distills the resulting corrections into transferable rules that the agent can reuse without expert access at deployment. We theoretically characterize what this signal identifies under finite repeated sampling: with k rollouts and at least m observations per action, outcome-constant decisions have zero mutual information, while outcome-separating decisions have mutual information at least H2(m/k) bits, yielding exact separation for any threshold t in (0,H2(m/k)). This also explains why success-based acquisition can be blind when all rollouts fail: success is constant even when failed runs reach different outcomes. Across four agent benchmarks and four models spanning three families, SynAct improves held-out accuracy in all 16 evaluated settings, by +11.7pp on average. The same signal transfers to inference-time routing, where SynAct outperforms budget-matched cascade, uncertainty, and expert-judge routers in 15 of 16 settings, while a single targeted correction outperforms seven additional unaimed retries. --- ### Feature Competition and Its Representational Origins in Vision Language Models: Evidence from the Stroop Paradigm Authors: Nurbüke Teker, Rui Xiao, Zeynep Akata, Shuchen Wu Published: 2026-10-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.12650v1 When you ask a vision-language model (VLM) a question with an image, it answers your question based on the image. But to act means to choose: saying one thing means choosing to respond not say another. This becomes an issue when the image contains multiple features that equally relate to the question at hand: how would VLMs choose to respond? This problem is precisely studied by the classical Stroop task in psychology: among a set of deliberately designed images whose text and color conflicts (e.g., \textcolor{blue}{RED}), participants are instructed to report the color. We adapt this psychological paradigm to a benchmark and prompted a range of contrastive and generative VLMs on their behavior. Across models, we observe a persistent bias toward the feature of text in Stroop images: when text and color disagree, models preferentially generate responses centered to the text rather than color. We then opened the black box and examined the source of this bias and why certain features influences the model's behavior more than others. In the embedding space, we found that textual cues are represented more strongly and separably than color cues. This representational asymmetry predicts intervention success: steering models toward text-related directions is substantially easier than steering them toward color-related directions. Using a classical psychological paradigm, we demonstrate, at both behavioral and representational levels, that distinct features within the same image can exert unequal influence on VLM behavior. Our findings suggest that VLMs assign different degrees of saliency to different features within the same image, highlighting the need to understand how cue-specific saliency shapes their performance in widely used downstream applications. --- ### Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller Authors: Tahmid Imtiaz Imu, Emama Nahid, Prodipta Sen Amartya, Ahsanul Jobayer, Yutong Song, Jiang Wu, Pengfei Zhang, Honghui Xu Published: 2026-10-08 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.12644v1 Backdoor Attacks on Large Language Models (LLMs) typically follow a trigger-response pattern, where satisfying a trigger condition activates a single terminal behavior. However, this single-point backdoor activation does not explore attacks in which malicious behavior develops gradually through multiple intermediate stages before reaching the terminal activation stage. We present Cancerous Backdoor Attack, that gradually corrupts an LLM's reasoning over a sequence of interactions by leveraging invisible tokens and a stage controller. Specifically, invisible tokens provide hidden stages to the model without appearing in the user's visible request and the stage controller tracks the attack's progression during inference to realize gradual activation. We evaluate Cancerous Backdoor Attack across several reasoning datasets. The attack consistently produces gradual reasoning corruption across models and tasks. We compare Cancerous Backdoor Attack with prior backdoor attack baselines to demonstrate our proposed attack outperforms the baselines. Our results indicate that reasoning corruption can develop gradually before it becomes visible, making answer accuracy alone insufficient for detecting backdoor attacks. ---