# Research Papers — 2026-10 · bundle page 45 of 156

> Full-text markdown of papers #2201–2250 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/45
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/44.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/46.md)

### Comparing GenAI to Machine Learning and Manual Review for eDiscovery

Authors: Gordon V. Cormack, Maura R. Grossman, Jeremy Pickens
Published: 2026-10-12
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2610.16925v1

Keeling et al. (Keeling2026Generative) report on a case study recently conducted by Redgrave LLP in which they assert that Relativity's Generative AI Review tool (aiR) achieved 88% recall while Relativity Assisted Learning (RAL), its machine-learning tool, achieved 64% recall. These results are not comparable because the methods employed have different objectives, because of inter-assessor disagreement, and because they represent different recall-precision and cost-benefit trade-offs. Our analysis of the Redgrave data indicates that, when these differences are taken into account, aiR and manual review are comparable. Furthermore, established machine-learning models employing Continuous Active Learning (CAL) show state-of-the-art effectiveness, and superior efficiency, when trained only on a sample of 2,000 first-pass-reviewer responsiveness determinations.

---

### FidLIF: Parallel Training of High-Fidelity Spiking Neurons with Exact BPTT

Authors: Kaixiang He, Yujie Wu
Published: 2026-10-12
Categories: cs.NE
arXiv: https://arxiv.org/abs/2610.16924v1

Although spiking neural networks (SNNs) show promise in energy-efficient computing through event-driven computation and stateful temporal processing, their recurrent membrane dynamics render their training inherently sequential and inefficient for long sequences. Existing methods achieve full-sequence parallelism in SNNs through two main strategies: redesigning or approximating spiking dynamics to avoid reset-coupled temporal dependencies, or relying on iterative relaxed fixed-point solvers that suffer from excessive memory costs and iteration-dependent backward overhead. To address these limitations, we present FidLIF, a novel framework that reconciles the incremental update and hard-reset behavior of standard spiking LIF neurons with parallel forward propagation and BPTT-equivalent backward propagation. FidLIF iteratively recovers the full-sequence membrane-potential trajectory in parallel. By exploiting the lower bidiagonal structure induced by the local recurrence of LIF neurons, FidLIF formulates each forward trajectory correction and backward adjoint propagation as associative scans with an $O(\log T)$ temporal depth. This formulation also supports input-dependent neuronal parameters and allows the same neuron to perform full-sequence parallel training and incremental step-by-step inference at deployment. In our numerical convergence evaluation, FidLIF achieves a mean absolute error below $10^{-7}$ relative to the matched serial relaxed LIF dynamics, while yielding gradients numerically equivalent to exact BPTT. Our Triton implementation delivers favorable long-sequence latency and memory scaling, while achieving competitive performance on four sequential classification benchmarks. By reconciling parallel training with step-by-step execution, FidLIF enables high-fidelity spiking dynamics to benefit from parallel hardware without compromising incremental inference at deployment.

---

### Minimax Optimality of Shampoo for Nonstationary Stochastic Optimization

Authors: Abir Sarkar, Nirmalya Mandal, Martin T. Wells
Published: 2026-10-12
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.16923v1

We develop a comprehensive theoretical analysis of Matrix Shampoo for tracking time-varying optima in nonstationary stochastic optimization. We derive finite-horizon high-probability bounds for average tracking error that disentangle initialization, optimizer drift, momentum-induced drift penalty, stochastic noise, and adaptive preconditioning, with explicit dependence on momentum parameter \(β_1\) and stabilization parameter \(\varepsilon\). These bounds reveal an explicit drift--noise and stability--geometry tradeoffs: noise-dominated regimes favor larger $β_1$, which provides stronger first-moment averaging and greater suppression of gradient noise, whereas drift-dominated regimes favor smaller $β_1$, allowing faster adaptation to moving optimizer. Larger $\varepsilon$ reduces the preconditioner-perturbation term while weakening Shampoo's ability to exploit matrix geometry, thereby reducing adaptivity. We establish a matching minimax lower bound under squared path-variation constraint, proving the information-theoretic optimality of Shampoo over the class of causal optimization procedures. Under a constant stepsize, we establish high-probability bounds for the average projected stationarity gap along general nonstationary nonconvex objectives. We validate our theoretical findings on both synthetic and multiple real-world problems.

---

### Time Window Optimization for Motor Imagery Classification via Temporal Structure Embedded Reinforcement Learning

Authors: Huan Luo, Na Lu, Xiaopeng Wang, Ziyang Shang
Published: 2026-10-12
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2610.16921v1

Online motor imagery-based brain-computer interfaces (MI-BCIs) typically decode continuous EEG using fixed-length sliding windows that may be misaligned with neural events. Existing window optimization methods often evaluate windows independently, overlooking temporal dependencies and potentially producing fragmented or physiologically implausible selections. We propose Temporal Structure Embedded Reinforcement Learning (TSE-RL), a framework that incorporates prior knowledge of MI event structure into a constrained Markov decision process for adaptive window optimization. First, TSE-RL assigns each window an explicit semantic role through Discard, Onset, Sustain, or Offset actions, extending binary retain/discard decisions to event-level alignment. Second, a finite-state machine masks invalid actions to enforce the temporal order of MI phases and promote physiologically plausible window sequences. Third, a Transformer-based history encoder captures dependencies across windows, improving training stability and computational efficiency compared with recurrent architectures. TSE-RL is plug-and-play and can be integrated with diverse MI classifiers. Experiments on multiple benchmark datasets demonstrate consistent improvements in decoding performance in both cross-session and cross-subject settings. Visualization analyses further suggest that the learned window selection policy aligns with neurophysiological principles.

---

### ML Engineering Agents - A Data Management Perspective

Authors: Arnab Phani, Elias Strauss, Tim Schuster, Sebastian Schelter
Published: 2026-10-12
Categories: cs.DB, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2610.16919v1

Machine learning engineering (MLE) agents are emerging as a new paradigm for automating end-to-end ML pipeline development. Using large language models for code generation and predictive performance as a machine-gradable feedback signal, these agents iteratively synthesize, execute, and refine pipeline code. Yet current systems are largely evaluated on pre-built, single-table benchmarks that abstract away key data management challenges. This tutorial introduces the foundations of MLE agents and highlights research opportunities for the database community. We cover how agents combine program synthesis with iterative and evolutionary optimization, and discuss open challenges in efficient pipeline execution, data discovery and augmentation over heterogeneous sources, reliability and debugging, as well as fairness and compliance. We connect these challenges to existing data management techniques and conclude with a hands-on session using contemporary MLE agents.

---

### Transparent Information Flow Modeling for Role-Aware AI Act Assessment

Authors: Mattias Brännström, Themis Dimitra Xanthopoulou, Lili Jiang
Published: 2026-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.16916v1

The European Union's Artificial Intelligence Act introduces a structured framework for governing high-risk AI systems, emphasizing transparency, risk management, and role-specific accountability. However, current assessment practices often rely on monolithic system views or disconnected checklists, limiting their ability to capture the socio-technical complexity of real-world deployments. We explore the use of the Information Flow Methodology (IFM), a modeling-based approach to AI Act compliance assessment. IFM represents decision systems -- whether algorithmic, human, or hybrid -- as networks of information sites and transformation channels, enabling structured analysis of how information, decisions, and responsibilities flow across organizational and technical boundaries. We apply IFM in a real-world case involving a recruitment support tool used by a public-sector organization, evaluating both the Provider's system and the Deployer's recruitment process. Our results demonstrate that IFM can serve as a scaffold to bridge both component-based and holistic perspectives, and how technical systems are situated within socio-technical contexts. In doing so, IFM supports transparency, identifies risk pathways, and enables alignment analysis between intended and actual use. We argue that such modeling provides a foundational tool for effective, context-sensitive AI governance and accountability -- offering capabilities beyond conventional checklist-based assessments.

---

### FOCUS: A Subspecialty Foundation Model for Intraoperative Central Nervous System Pathology

Authors: Xing Liu, Yifan Guo, Hongtai Lv, Lei Lou, Yuyi Tan, Jiang Du, Xijia Zhang, Ming Zhang, Chao Pang, Minglei Li, Wei Liu, Xiaobo Zhu et al.
Published: 2026-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.16914v1

Intraoperative frozen-section diagnosis of central nervous system (CNS) lesions guides surgical decisions but is challenged by artefacts, diagnostic complexity and time constraints. Most pathology foundation models have limited exposure to CNS frozen tissue. Here we present FOCUS, a subspecialty foundation model pretrained on 27,930 frozen-sections enriched for CNS tissue. FOCUS led 11 internal diagnostic and 12 biomarker-prediction tasks, with mean AUCs of 0.969 and 0.877, respectively, retaining leading performance in temporal and external cohorts. To provide more comprehensive diagnostic information, we further organized ten diagnostic tasks into a WHO-aligned diagnostic hierarchy and separately evaluated FOCUS for lymphoma detection, a critical task for intraoperative surgical decision-making. In reader assessments by six neuropathologists, FOCUS assistance enabled junior readers to approach or exceed unassisted senior readers in hierarchical diagnosis and raised junior readers' lymphoma sensitivity from 81.6% to 94.7%. FOCUS could improve diagnostic accuracy and granularity, inform lymphoma-related resection decisions and provide provisional molecular information. Such capabilities highlight the potential of FOCUS to provide robust, clinically actionable support for intraoperative CNS pathology.

---

### Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given

Authors: Ben Slater, Ryan Lundqvist, Leo Richter, Kevin Wei
Published: 2026-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.16911v1

Does providing additional context to automated AI auditors improve their effectiveness? Using the Petri tool to audit LLM coding agents, we test the impact of providing two types of resources (an external codebase and benchmark transcripts) to LLM auditors, across four auditor-target LLM pairs and three behaviours (harmful compliance, reward hacking, sycophancy). (1) External codebase: We provide the auditor LLM with a fixed, external open source codebase, which prior work finds improves the realism of synthetic audits. Providing this resource suppresses reward hacking in both auditor-target pairs whose baseline rate is above the floor (4.8 to 1.3 and 3.9 to 1.8 on Petri's default 1-10 scale); the remaining two pairs sit at the floor throughout. The suppression recurs in three of four pairs under a different scenario and resource bundle. (2) External benchmark transcripts: We provide the auditor with transcripts of the target's performance on benchmarks measuring similar behaviours, intended to inform the auditor about the target's behavioural patterns. Providing this resource raises reward hacking scores in all four pairs (from 1.7 to 6.1 in one case). However, subsequent experiments show that supplying only the related benchmark's abstract, without transcripts, also increases reward hacking, and the effect is absent under a different framing of the same behaviour. Overall, we find no consistent effect of either resource outside reward hacking, but we find substantial variability in judge-scored behaviour across conditions. Our results underscore the importance of careful piloting with tools such as Petri, as the measured rate of target behaviour is highly sensitive to configuration decisions. We hope our results inspire more research into the reliability and robustness of automated alignment auditing.

---

### ConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder for End-to-End Autonomous Driving

Authors: Shengzhen Li, Yongkang Li, Hao Gao, Chenxi Wu, Yajing Sun, Lu Hou, Wenyu Liu, Xinggang Wang
Published: 2026-10-12
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2610.16908v1

End-to-end driving requires rich spatiotemporal representations to support scene understanding and trajectory planning under strict latency constraints. However, most systems initialize their visual encoders from generic image pretraining and densely process all patch tokens for each camera view and input frame, limiting both representation quality and inference efficiency. To address these challenges, we present ConDenseDrive, a knowledge-dense and token-sparse visual encoder for end-to-end autonomous driving. Our three-stage framework first makes the encoder knowledge-dense by distilling complementary visual, semantic, and geometric knowledge from three vision foundation models. It then adapts the distilled encoder to multi-frame end-to-end driving and integrates spatiotemporal context into register tokens for planning. Finally, it makes the encoder token-sparse by applying register-guided token compression, reducing redundant patch computation and yielding a 2.0$\times$ speedup while improving planning performance. ConDenseDrive achieves 94.5 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2, and reaches 37.4 HD-Score in zero-shot evaluation on HUGSIM. Extensive experiments and qualitative analyses demonstrate that visual encoder design provides an effective route to reliable and efficient end-to-end driving.

---

### Mining Cross-Modal Perception Gaps in Autonomous Driving: When Camera and LiDAR Disagree

Authors: Hongsen Cao, Mona Jaber, Shanxin Yuan, Ahmed Sayed
Published: 2026-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.16906v1

Multi-modal fusion for 3D object detection assumes that cameras and LiDAR are broadly complementary. In practice, how much each modality is trusted at a given location is decided by learned weights that are neither characterized nor auditable. We label every ground-truth object by which modalities detected it, then mine the resulting 0.4M-object database across nuScenes, KITTI, and Waymo. Because the patterns shift with distance from the ego vehicle, we read the mined model through Spatially Stratified Feature Attribution (SSFA), which conditions Shapley attribution on distance zones and exposes structure that global attribution averages away. Three assumptions built into the current fusion design do not hold. The modality-preference boundary tracks the object itself: a traffic cone is nearly six times as likely as a truck to be seen by the camera alone (16.8% vs. 2.9%), regardless of range. Camera-only detections peak at 10-30 m, inside the band usually ceded to LiDAR, and fall away on either side. The drivers of failure are not additive either: the distance - density interaction alone outweighs the entire main effect of viewing direction. We further find that modality dominance is directionally non-stationary, with objects behind the vehicle being markedly more LiDAR-dominant than those in front. We compile the mined structure into a Modality Reliability Map and inject it into four pretrained fusion detectors through a lightweight attention layer. This improves performance by up to 1.3 mean Average Precision (mAP) while fine-tuning under 4% of their parameters in 2-3 GPU-hours. Our work lifts reliability out of the weights and treats it as a quantity that can be examined before deployment. That is what a safety measure for multi-modal perception must rest on.

---

### Neural Bayesian Networks for Modular and Scalable Decision-Making Under Uncertainty

Authors: Giovanni Briglia, Marco Lippi, Stefano Mariani, Franco Zambonelli
Published: 2026-10-12
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.16902v1

Bayesian Networks (BNs) are established tools for letting agents reason under uncertainty in sequential decision-making. They split a joint distribution into local conditional mechanisms arranged on a directed acyclic graph, which makes them modular, interpretable, and ready to perform probabilistic inference. Their classical formulation, however, has limitations in both expressiveness and scale: each conditional is usually stored as a table or a linear-Gaussian form, and inference evaluates the graph one node and one query at a time. In this paper we introduce Neural Bayesian Networks (NBNs), in which each conditional is a differentiable, tensor-valued mechanism, while the graph and its factorization are unchanged. NBNs retain the modularity and local mechanisms of BNs, can represent any learnable conditional distribution, and run natively on GPUs. We also release NBN, a PyTorch-based library for learning and inference in NBNs, together with a public benchmark. Our evaluation shows gains in both expressiveness and scale: NBNs fit distributions that classical BN libraries struggle to represent, and on large networks and large batches of queries they run two orders of magnitude faster thanks to GPU parallelization. NBN is available at https://github.com/Giovannibriglia/NeuralBayesianNetworks.

---

### Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration

Authors: Adrián Szlatincsán, Filippo Ziliotto, Bruno Lepri, Luciano Serafini, Massimiliano Luca, Tommaso Campari
Published: 2026-10-12
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2610.16895v1

LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating a collaborator's actions in real-time teamwork without dialogue. We ask if observing the partner's state, exchanging object knowledge, and predicting the partner's next action, shape task outcomes and coordination when agents can share percepts but never intentions, plans, or task-level messages, and whether the two agents occupy symmetric roles. Using the Habitat-based PARTNR benchmark, we introduce a Decoupled Partial Observability regime that enforces strictly individual perception, and we augment decentralized zero-shot ReAct planners with Other Agent's State (OAS) observation, object Knowledge Exchange (KE) between co-located agents, and Other Agent's Next Action (OANA) prediction, evaluated on the full 2 x 2 x 2 grid with four planners on 1,000 validation tasks. OAS observation improves task quality, reducing extraneous effort for every planner, whereas KE primarily improves execution efficiency, cutting simulation steps by up to 25% with little change in success. The two are largely redundant for strong planners but complementary for the weakest, for which KE without the OAS is the worst configuration. OANA prediction lowers the success rate in 15 of 16 model x context pairs while raising explicit partner mentions to 55-100%, and its accuracy gains lie mainly in the coarse action type, partly because agents recognize the action the partner is already performing. The robot retrieves objects sooner and completes its tasks earlier than the simulated human. Shared context reduces total task time by shortening the remaining duration that the human works alone. Also, coordination benefits arise from responding to shared context, especially the OAS, rather than explicit anticipation, yielding shallow, planner-dependent partner modeling.

---

### Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers

Authors: Harvey Mannering, Zhiwu Huang, Adam Prügel-Bennett
Published: 2026-10-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.16892v1

Emotions are expressed on a continuum and are naturally described in the valence-arousal (VA) space. Existing VA-based image editors are typically training-based and domain-specific, limiting them to VA regions seen during training and making them brittle across datasets and domains. Meanwhile, despite producing high-quality edits, state-of-the-art foundation image editors are not continuous affective controllers: non-linear emotion representations in text encoders makes prompt interpolation poorly calibrated, so accurate and continuous VA control remains unreliable. To fill this gap, we introduce Barycentric Guidance, a training-free framework that turns pretrained foundation image editors into continuous affective controllers over VA, requiring no finetuning, extra data, or model changes. Our method maps any target VA point to simplex-based guidance weights, enabling VA controllability in three aspects: (i) accurate targeting of VA states, (ii) broad coverage across the VA plane, and (iii) continuous control. Across three face datasets, we improve VA target accuracy by 25-29%, expand VA-plane coverage by 28-50%, and increase expression diversity by 29-49%, over the strongest baseline. Unlike prior domain-specific methods, our training-free approach exploits the foundation model's inherent versatility, enabling generalization beyond human faces to animals, artworks, and complex scenes within a single framework. Code is available at https://github.com/harveymannering/BarycentricGuidance.

---

### AI-Assisted Tumor-Growth Law Discovery from Sparse Data: Refitting and LLM-Based Ranking

Authors: Yitian Lu, Weinan Wang
Published: 2026-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.16891v1

Inferring tumor-growth laws from sparse, noisy observations requires more than accurate curve fitting. We study an AI-assisted workflow involving symbolic regression, mathematical admissibility checks, coefficient refitting, and large language model (LLM) ranking. Synthetic Gompertz data allow trajectory fit, forecasting, and recovery of the governing growth law to be assessed separately. A dense noiseless control recovers the generating family, but sparse noisy sampling frequently leads to alternative forms. Among retained candidates in the tested configurations, physics-informed neural network refitting often increases growth-law error, whereas classical nonlinear least squares usually reduces it. A separate exploratory analysis of archived LLM rankings shows no consistent improvement over selection by training error and identifies errors in mathematical reasoning. Plausible saturation, accurate trajectory fits, and convincing explanations can therefore coexist with incorrect growth laws. Mathematical validity and law recovery require evaluation alongside predictive performance.

---

### FORGE: Procedural Weight Generation for Sparse MoE Inference

Authors: Chanyoung Moon, Travis Pence, Daisuke Yamada, Jiaqi Mo, Yanxin Zhang, Vikas Singh, Karthikeyan Sankaralingam
Published: 2026-10-12
Categories: cs.AR, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2610.16890v1

We introduce FORGE (Fast On-chip Rotor Generation for Experts), a procedural weight generation system for Sparse Mixture-of-Experts (MoE) inference. Rather than storing and loading every expert weight tensor from HBM, we show how a compact accelerator inside each Streaming Multiprocessor can regenerate them on-the-fly from $O(\log^2 d)$ rotor parameters per projection. Per replaced layer, gigabytes of stored expert weights are approximated with under a megabyte of seeds. This addresses the dual memory bottleneck of autoregressive Sparse MoE decode, where per-expert FFN operations are HBM-bandwidth-bound at small routed-token counts and the aggregate expert footprint forces multi-node Expert Parallelism (EP) with all-to-all traffic. We realize the approach as the Rotor Generation Unit (RGU), a fixed-function datapath that generates FFN weight tiles without competing with Tensor Core execution. With 30% of the MoE FFN layers replaced across five Sparse MoE models, we estimate 1.3-2.8x higher system throughput at matched GPU count and 1.10-1.15x lower per-user decode latency at short context. In exchange, downstream accuracy on three model families falls below that of the same model fine-tuned without rotor replacement, and the replacement ratio controls this tradeoff. FORGE also expands KV cache capacity by 1.2-2.6x. It is agnostic to the bit width at which weights are stored, so it can compose with quantization. The RGU is fully implemented/verified in SystemVerilog at ~0.9% SM area overhead (0.032 mm^2/SM, 7nm).

---

### Transparency as Answerability: Role-Dependent Information Flow Modeling

Authors: Mattias Brännström, Themis Dimitra Xanthopoulou, Lili Jiang
Published: 2026-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.16887v1

Transparency in AI-supported decision systems is widely required but poorly defined. Existing approaches treat transparency as a property of systems or components, producing characteristic failures: assessments that do not transfer across organizational boundaries, stakeholder questions that cannot be formulated within the available frame of analysis, and component-level findings that say nothing about system-level behavior. We propose treating transparency as a relation: a system is transparent to a stakeholder to the degree that their legitimate questions are answerable from its structure. We formalize this using information flow networks, in which transparency questions are expressed in terms of network structure and answerability is the condition that the system settles them. The framework supports three dimensions of analysis: structural answerability from the network alone, compositional answerability across organizational boundaries for deployed systems, and role-dependent answerability given a stakeholder's accessible sub-network. We demonstrate the framework on a real pre-integration assessment of an AI recruitment tool in a public sector municipality. The assessment uses participatory design and interviews to model the decision system structure. We show how structural and role-dependent transparency questions can be formally stated and analyzed across the Provider and Deployer boundary where the AI system is composed together with the deployer's decision process.

---

### Learning Operators for Symmetry Discovery: From Lie Groups to Local Symmetry Geometry

Authors: Pavan Karjol, Scindhiya Laxmi, Prathosh AP
Published: 2026-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.16884v1

Continuous symmetry discovery is typically formulated as a separate estimation problem for each function or dataset. We instead investigate whether the map from a function to its symmetry structure can be learned across a family of functions from finite observations. Using the infinitesimal differential characterization of continuous symmetries, we formulate this map as an inverse symmetry operator, analogous to an inverse PDE problem. For global Lie-group symmetries, we establish a representation-theoretic population characterization: the symmetry Lie algebra is the nullspace of a positive-semidefinite operator constructed from representation coefficients and the infinitesimal group action. We also show that the inverse symmetry operator is equivariant under coordinate changes through the adjoint action. This characterization separates the geometric symmetry map from finite-sample estimation, motivating a hybrid approach that amortizes statistically difficult components while retaining analytic structure. On SO(5) benchmarks, amortized equivariant estimation of harmonic coefficients improves symmetry recovery from sparse observations, whereas ordinary least squares suffices for SL(2,R). We extend this viewpoint to local symmetries, where symmetry directions form smoothly varying tangent distributions rather than a fixed Lie algebra. Under the Lie-bracket consistency condition, Frobenius' theorem guarantees local integral submanifolds along which observables remain unchanged. We recover this geometry using a hybrid estimator that learns observation weights while preserving analytic differential and geometric recovery. Across global, non-compact, local, and physically motivated synthetic benchmarks, our results support learning the statistically difficult finite-sample components while preserving the known geometric structure of symmetry recovery.

---

### Acceptable Misalignment

Authors: Maud van Lier, Ludovica Marinucci, Vieri Giuliano Santucci, Raja Chatila, Stéphane Doncieux, Émiland Garrabé, Richard Duro
Published: 2026-10-12
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2610.16881v1

There is a specific challenge designers face in developing autonomous robots capable of open-ended learning. This challenge is how one can develop such systems in an ethically sound way when there are many unknowns during design time about their manner of deployment, what they can and will learn, and how these systems will act on the basis of what they have learned. One response to this challenge is to align, as far as possible, the activities and goals of autonomous robots with human values, raising the question of how to make this alignment possible, a question known as the value alignment problem. We argue that the value alignment problem faces a number of challenges that show that full alignment is both theoretically and practically impossible, meaning that misalignment incidents will keep occurring. This undermines current alignment approaches, as the attempt to maximize alignment cannot properly deal with the possibility that the risk of misalignment that remains after alignment methods have been implemented might still be unacceptable to society. To overcome this difficulty, we argue that a shift in perspective is required from a focus on the maximization of alignment to the conditions under which misalignment incidents become acceptable. In this paper, we explore what this shift in perspective entails. We introduce the concept of acceptable misalignment, formulate normative requirements for alignment mechanisms aimed at bringing misalignment incidents to an acceptable level, and we conclude by presenting a new methodological framework that consists of alignment mechanisms that can meet these requirements.

---

### EviStress: Evidence Stress Learning for Generalizable Face Forgery Detection with Textual Explanations

Authors: Jiuyao Jing, Xuanyu Yi, Yu Zheng, Chunlei Peng
Published: 2026-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.16879v1

The rapid spread of face forgeries on the Web challenges the credibility of visual content. In practical Web environments, manipulated media originate from evolving generation pipelines and undergo diverse processing during dissemination, making reliable authenticity assessment under unseen manipulations and visual changes a critical challenge. We observe that a standard LoRA-adapted CLIP detector exhibits uneven patch-level decision dependence, concen trating a disproportionate share of class-specific relevance on a small fraction of visual patches. To improve robustness to variations in such highly dependent evidence, we propose EviStress, a two-stage framework for generalizable face forgery detection with textual explanations. In the first stage, Evidence-Targeted Patch Perturbation (ETPP) estimates patch dependence from global, relational, and semantic cues and assigns positively correlated perturbation probabilities, explicitly stress-testing highly dependent visual evidence during training. We further introduce Discriminative Variation Preservation (DVP), which constrains the residual between clean and perturbed representations to retain authenticity discriminative information. In the second stage, Intrinsic Evidence Instruction Tuning (IEIT) transfers the adapted CLIP encoder into LLaVA as its vision tower and performs parameter-efficient multimodal instruction tuning, enabling authenticity prediction and textual explanation directly from the learned forgery-sensitive representation without an external detector. Experiments demonstrate improved cross-dataset and cross-method generalization and corruption robustness, with the multimodal model providing authenticity predictions and human-readable explanations.

---

### Sequence Composition in EHR Foundation Model Pretraining

Authors: Joshua Placidi, Inigo Stibbe, Alfred J. Balston, Marek Rei, A. Aldo Faisal
Published: 2026-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.16878v1

Autoregressive electronic health record (EHR) foundation models predict the next event token in patient trajectories: sequences of structured medical events. A typical pretraining strategy is to concatenate all trajectories into a global stream and sample token windows from it. This gives patients with longer sequences more training exposure and allows tokens to attend across patient boundaries. We argue that these choices create a misalignment between pretraining and downstream clinical tasks. To explore this, we investigate how the composition of pretraining sequences affects clinical prediction performance. Using the global-stream approach as a baseline, we propose alternative sequence composition methods that control how patient trajectories contribute to pretraining sequences. Across four MIMIC-IV v2.2 tasks, our best method improves macro AUROC, AUPRC, F1, and balanced accuracy, with relative gains of 9.3% in F1 and 2.7% in AUPRC under a fixed training recipe. We find that these gains generalize across four additional evaluation settings, including the INSPIRE and eICU-CRD datasets, with improvements in macro AUROC, AUPRC, and F1 score. Our results show that simply changing how EHR data are presented to the model during pretraining can improve downstream performance, without changing the model or collecting additional data.

---

### CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives

Authors: Yuhan Wang, Rui Hu, Batian Di, Tan Jiang, Dongsheng Ma, Leichao Dong, Yuanzi Li, Yalin Feng
Published: 2026-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.16876v1

Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresent similar content without optimizing this balance; group-level methods face coarse units, predefined set-level validation signals, and costly or inaccurate mixture search. We propose CLIVO, a target-aware framework connecting fine-grained semantic allocation, automatically learned validation objectives, and differentiable mixture search. Specifically, semantic clusters provide independently adjustable shares at the hundred-cluster scale. Correlations between per-example merged-proxy losses and real probe performance identify target-relevant validation examples; learned nonnegative weights combine their losses into an objective. A single backward pass through the merged proxy supplies gradients for all shares, avoiding an additional mixture-response regression model. Selecting 100K instructions from an 8M pool, CLIVO attains 97.2% of the full-data four-target average score with only 1.25% of the data. It improves on the strongest evaluated selection baseline by 1.16 points using random within-cluster sampling; combining learned quotas with sample ranking increases this advantage to 1.55 points. Analyses show that finer units benefit most targets, short-trained experts preserve mixture responses, sample weighting retains useful validation information, and direct search consistently reduces the learned objective. CLIVO also supports interpretable allocation, modular selection, and reuse across targets and granularities.

---

### SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?

Authors: Zhiqing Zhong, Mingyu Chen, Aoyang Fang, Yuzhong Zhang, Haoye Tian, Lionel Briand, Boxi Yu, Pinjia He
Published: 2026-10-12
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2610.16870v1

As coding agents become more capable, tests remain the primary evidence for judging whether their code is correct. Yet passing available tests does not establish that an implementation satisfies its natural language specification. Reliable validation requires checks that faithfully capture the specification and scenarios that thoroughly exercise the code, but current benchmarks provide limited insight into whether agents can construct such evidence themselves. We introduce SpecGuardBench, a benchmark of 291 tasks from 13 real-world repositories, covering 8 types of verification logic such as functional postconditions and interaction protocols. Given a natural language specification, repository context, and a reference implementation, an agent constructs a validation harness comprising executable checks and test scenarios. The checks should reject implementations that violate the specification while accepting those that satisfy it, and the scenarios should thoroughly exercise the code. Across four proprietary and open-weight coding agents, none constructs a harness scored as faithful on the benchmark's implementations for more than 63% of the tasks. The bottleneck lies less in exploring test scenarios than in constructing checks that faithfully reflect the specification. Specifically, the agents show a clear tendency to write checks that mirror the reference implementation rather than the specification, and therefore reject implementations that the specification permits.

---

### From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon

Authors: Tom Jacobs, Rebekka Burkholz
Published: 2026-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.16868v1

Simplicity bias, which can arise from sequential feature learning during training, has been proposed as a general explanation for the success of deep learning. An important driver of this phenomenon is saddle-to-saddle behavior, in which the gradient flow trajectory remains close to a sequence of saddle manifolds while learning one feature at a time. However, Muon, a state-of-the-art optimizer based on spectral descent, does not exhibit such dynamics in the full-batch setting and instead learns features in parallel. How is it then that Muon is so successful in deep learning settings? We show that stochastic gradient noise fundamentally changes this behavior: small-batch noise restores sequential feature learning, providing a mechanism for simplicity bias that is absent from full-batch Muon. We explain this transition through stochastic smoothing of the spectral descent operator underlying Muon. When gradients are small relative to the noise scale, the expected spectral update becomes approximately proportional to the actual gradient, which restores gradient-flow-like dynamics. We formalize this mechanism for deep linear models by deriving the effective continuous dynamics of noisy spectral descent. Experiments on low-rank matrix reconstruction, vision transformers, and large language models (LLMs) support these findings.

---

### Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments

Authors: Xiaoyang Yuan, Ji Zhao, Xingyu Hu, Wenhan Wang, Yutao Hu, Qiaosheng Zhang, Pengfei Liu, Yu Qiao, Yi Bin, Wenqi Shao
Published: 2026-10-12
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.16867v1

Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved. Scaling either trajectory coverage or verification alone is insufficient as new environments introduce distinct states, rules, and dependencies that must also be reflected in the success criteria. To address this challenge, we introduce Davinci-Tool, a 30B tool-use model, and Davinci-ToolData, an execution-grounded dataset designed to scale environment coverage and outcome verification together. Davinci-ToolData preserves restorable states, execution traces, outcomes, and verifiers as a unified substrate for supervision. Two complementary pipelines populate this substrate: Execution-Grounded Task Synthesis (EGTS) derives verified demonstrations from independently authored systems, and Executable Environment Synthesis (EES) synthesizes auditable environments, state-grounded tasks, and executable verifiers across single and coordinated domains. These pipelines yield 30,395 verified trajectories spanning 2,260 invoked tool names. We first train on these demonstrations with supervised fine-tuning, then reuse EES states and verifiers to compare alternative actions and construct outcome-grounded preferences for Direct Preference Optimization. Davinci-Tool improves Qwen3-Coder-30B-A3B-Instruct from 52.4 to 88.2 on $τ^2$-bench, from 30.4 to 62.8 on BFCL v4 multi-turn, and from 16.9 to 56.2 on MCP-Atlas, outperforming Qwen3-Coder-480B-A35B-Instruct on all three benchmarks with only 1/16 of its total parameters. Code is available at https://github.com/MassLab-SII/Davinci-Tool.

---

### Efficient Resource-Shiftable RL Post-training with Generative Rewards

Authors: Yanfeng Zhao, Haoyang Li, Sheng Lin, Yuming Zhou, Jiawei Jiang, Bin Cui, Fangcheng Fu
Published: 2026-10-12
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2610.16866v1

Reinforcement learning (RL) post-training with generative reward models (GenRM) has become a central recipe for improving large language models (LLMs), and it is also increasingly resource-intensive: policy rollout, GenRM-based reward evaluation, and policy training all compete for GPU resources. However, existing colocated and disaggregated systems rely on static resource allocation for these roles. Such allocation cannot adapt as each role's workload changes during RL and therefore leaves a role's resources underutilized. We present PivotRL, an RL post-training system that dynamically shifts resources among different roles according to their runtime demands. PivotRL introduces a resource-shiftable runtime built on a Global Parameter Storage, together with a unified mechanism that efficiently shifts role-specific context. A shift-aware scheduler enables sequence migration upon a shift, while a planner considers the aggregate throughput benefit and the shift overhead to determine when and how to shift. We evaluate PivotRL on a 128-GPU cluster using four model groups spanning dense and mixture-of-experts models. PivotRL enables resource shifting within seconds and improves end-to-end throughput by 1.81-2.05 times over colocated deployment and 1.50-1.95 times over disaggregated deployment, while preserving RL convergence.

---

### Better together? A performance theory of human-machine skill policies under generalization difficulty

Authors: Riccardo Zanardelli
Published: 2026-10-12
Categories: cs.HC, cs.CY, cs.LG, econ.TH
arXiv: https://arxiv.org/abs/2610.16863v1

Organizations pairing a human and a machine on a task decide, often by default, which executes each instance and what happens when both do. We account for what this attains under the squared rule, with performance distributed over instances to capture generalization difficulty. A gross stake lies between the skills' mean and best per instance. It splits at the best single skill into a systematic part, known from separate assessments and secured by commitment, and a residual, the expected value of perfect information on which skill each instance favors, known only from paired observation and split further by classes. Skills set the stake; workflows decide the take, via two channels. Routing directs work, weighting or selecting responses; with binary truth it is capped by the best skill per instance. Reading responses as joint evidence is not routing; what they jointly reveal caps it. Synergy lets skills interact before responding; bounded by no skill either way, its lift over independent responses must clear a break-even and can fall below one. As algorithms, arrangements form a ladder stating what each reads, holds and records, and a procedure whose checks keep earlier gains when class means are known and lose little on finite records given a margin. The theory extends to many skills, each worth what it adds where it beats all others held, and to competing skills, where at parity a single failure's allowed cost decides. In a public chest-radiograph study with 227 radiologists, they are near parity with the model and the stake is mostly residual; assisted reading, no better on average originally, returned less than averaging both responses; recalibrating the model alone beats any deployable arrangement of raw responses. Organizations can learn from their records what is at stake, which arrangement collects it and what evidence each step needs; pricing costs and errors is future work.

---

### From Volpiano to Pixels: 30,000 Lines of OMR Ground Truth for Medieval Chant

Authors: Robert Klugseder
Published: 2026-10-12
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2610.16862v1

Optical music recognition (OMR) for medieval chant lacks training data linking manuscript images to musical symbols across notational families. Using existing Volpiano transcriptions from the Cantus Database, we created 30,567 image-target pairs from ten sources in eleven exports, including 339 verse fragments. Their target sequences contain 1,952,143 tokens. The pipeline locates staff systems, infers clefs and maps known pitches to staff positions. Six detector families handle the different layouts and notations. Where heuristics failed, two small U-Nets learned staff lines and clef letters from manual annotations. Reviews of sampled export lines found zero to four pitch or clef errors, but used different error definitions and do not provide a uniform audit of the corpus. A CRNN trained from scratch achieved a symbol error rate of 9.6 % on 3,086 test lines. The earlier model, trained mainly on Austrian sources of the 15th and 16th centuries, scored 45.3 %. In three separate training runs, each excluding one manuscript, error rates on the excluded manuscript were 21.5-31.0 %. Model-assisted alignment recovered a further 2,686 lines.

---

### GpFlash: Maximizing Speed and Minimizing Memory for Gaussian Process Training and Prediction

Authors: Andre Marchildon
Published: 2026-10-12
Categories: cs.LG, cs.MS, math.OC
arXiv: https://arxiv.org/abs/2610.16861v1

This paper presents GpFlash, a Gaussian process library that is focused on fast training and posterior evaluations, minimal memory usage, and scalability to high-dimensional problems. GpFlash was compared to the popular GP libraries scikit-learn, GPy, GPflow, GPyTorch, and SMT on a MacBook Pro and the supercomputer Trillium. GpFlash was found to use less memory and to be faster for training and posterior evaluations relative to the other GP libraries for all cases considered. For example, when using $\nx = 10^4$ training points in a 10-dimensional space GpFlash required 9.6 to 35 times less memory and was 2.6 to 54 times faster than the other GP libraries for the evaluation of the marginal log likelihood and its gradient. The memory reduction was achieved by only using one matrix of size $\nx \times \nx$ to store different symmetric matrices in its lower and upper triangular entries. The computational speedup was the result of designing algorithms to access memory efficiently, using BLAS and LAPACK methods extensively, and factoring kernel equations so that expensive exponential calculations could be reused. GpFlash was more than 440 times faster than all of the other GP libraries considered when evaluating the posterior mean together with its gradient for the case with $10^4$ training points and 10 dimensions. GpFlash is available at https://github.com/marchildon/gpflash.

---

### Vision Models Capture Complementary Representations in Children That Converge in Adults

Authors: Domenic Bersch, Timothy Schaumlöffel, Michela Proietti, Antonia Franaszek-Traczewska, Hannah Elisabeth Zwad, Siying Xie, Marlena Baldauf, Teresa Sylvester, Christina Maria Schätz, Bert Turtleton, Moritz Köster, Stefanie Höhl et al.
Published: 2026-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.16860v1

How the relationship between image-text aligned and vision-only models changes across development remains unknown. We applied time-resolved representational similarity analysis to EEG data from 8-year-olds, 12-year-olds, and adults. CLIP showed significant model-brain alignment already in children, whereas vision-only models aligned more strongly later in development. Residual analyses revealed complementary structure, with CLIP retaining alignment beyond an architecture-matched vision-only model from age 8. Much of the model-brain alignment reflected semantic structure, with EEG representations of category and animacy strengthening toward adulthood, while alignment with low-level image properties remained weak across age. Together, these findings suggest that image-text aligned and vision-only models capture complementary aspects of developing visual representations and may provide useful constraints for AI systems that aim to learn and adapt over time.

---

### ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding

Authors: Wenqiang Zhu, Xinping Lei, Zhiyi Lai, Zhengshuo Gong, Tianzhuang He, Songwei Yu, Weihao Li, Jingxuan Xu, Zihang Xu, Gang Wu, Zhongqiu Wang, Yuhui Bai et al.
Published: 2026-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.16859v2

For repository-grounded coding agents, a functionally correct patch is not necessarily an acceptable one: developers also constrain how the task must be carried out-modification scope, workflow order, validation, tool use, and reporting. This capability, which we call engineering constraint following, remains largely invisible to current evaluations. We introduce ANCHOR (Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding), a benchmark built on naturalistic, multilingual repository tasks spanning eight language groups. ANCHOR combines (i) a hierarchical taxonomy of 10 categories and 78 leaf types distilled from real developer interactions, (ii) an automated pipeline that instantiates task-grounded atomic constraints and composes them into typed AND/THEN/PRIORITY relations, and (iii) a trajectory-grounded evaluation framework that checks both the code diff and the execution trajectory with rule-based and LLM judges. Across 19 agent configurations spanning 2 scaffolds and 10 foundation models on 358 tasks, the strongest measured system, Claude Opus 4.8 under Cline, reaches 70.1% atomic compliance and 63.7% relation compliance, while 19.0% of tasks pass every scored checklist item under the strict all-item FCCR criterion. A five-engineer audit of constraints from 50 instances reports 94% feasibility, 94% repository consistency, and 96% realism. In the primary paired set (14 configurations), the mean signed change in task completion after adding constraints is +0.7 percentage points; individual changes vary in both directions. These results distinguish functional success from constraint compliance, with failures concentrated in workflow ordering, tool-use discipline, and reporting, and substantial interactions between models and scaffolds.

---

### Towards Cost-Efficient Video Dataset Construction with Large Language Models

Authors: Mohammed Shabot, Jonathan Adams, Jan Van den Stock, Joost Vennekens
Published: 2026-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.16857v1

Research on video classification models has witnessed significant growth recently, accompanied by a significant increase in the demand for datasets to train such models. Existing video dataset curation approaches share a common bottleneck: candidate videos must be downloaded before any relevance judgment is made, which results in storage, time and annotation costs. In this work, we present a filtering step, using Large Language Models (LLMs) to pre-screen videos based on their metadata, before actually downloading these videos, thereby saving on these costs. We evaluate the LLMs against a strict human majority vote derived from four independent annotators and validate the reliability of the annotations through inter-annotator agreement analysis (Gwet's AC1). We compare the LLM pre-filter against two no-LLM baselines, namely two keyword heuristics. Via a Leave-One-Rater-Out (LOO) mechanism and an Add-One-Rater-In (AORI), we evaluate the performance of the LLMs as virtual annotators. Finally, we report cost comparisons relative to existing approaches. To ensure reproducability, we made our implementation available on github.

---

### Radial Tail Repair: Post-Training Correction for Diffusion and Flow Models

Authors: Hamza Cherkaoui, Hélène Halconruy, Antonio Ocello
Published: 2026-10-12
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.16851v1

Diffusion and flow-matching models may struggle to accurately represent distributional tails, especially for heavy-tailed data. Existing approaches often use heavy-tailed noise or modify the generative dynamics, requiring dedicated retraining and more difficult estimation. We take a simpler approach: rather than relearning the full distribution, we correct only the model's behavior in the extreme regime. Our method builds on the radial-angular decomposition of multivariate heavy tails, where radius and direction become asymptotically independent. This allows us to preserve the directional structure learned by the pretrained model and correct only its radial tail. We estimate the tail onset from reference and generated samples, then rescale generated extremes so that their radial survival matches the target distribution. The resulting method is a lightweight post-training correction applied to a frozen diffusion or flow-matching model, requiring neither retraining nor changes to its sampling dynamics. Experiments on challenging synthetic heavy-tailed distributions and real weather and wildfire datasets show that this simple correction substantially improves extreme-tail coverage using only a small number of fitting samples.

---

### A Multi-Task Deep Learning Framework for Pose-Invariant Face Recognition and Facial Landmark Localization

Authors: Ali Ashkeyev, Zukhra Abdiakhmetova
Published: 2026-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.16849v1

Face recognition systems often experience performance degradation under large pose variations due to changes in facial appearance and visibility of discriminative features. This study presents a multi-task deep learning framework that jointly addresses pose-invariant face recognition and facial landmark localization within a unified architecture. To enable simultaneous optimization of identity recognition and facial structure learning, the original Cross-Pose Labeled Faces in the Wild (CPLFW) dataset was adapted into a multi-task learning dataset by associating facial images with identity labels and five-point landmark annotations. The proposed framework consists of two task-specific branches operating on a common facial input: a ResNet50-based branch for identity recognition and an EfficientNetV2B0-based branch with spatial attention for facial landmark localization. The two objectives are jointly optimized using a weighted multi-task loss, allowing the model to learn complementary semantic and spatial facial representations. The proposed framework was evaluated on the prepared CPLFW-based multi-task dataset. Unlike the original CPLFW benchmark, which focuses primarily on identity recognition, the proposed dataset adaptation incorporates five-point facial landmark annotations to enable joint recognition and localization learning. Experimental results demonstrate that the model achieves a validation recognition accuracy of 81.58% and a facial landmark localization mean squared error of 96.38. The results indicate that combining identity classification and landmark regression within a single optimization framework provides an effective approach for learning robust facial representations under cross-pose conditions The proposed method demonstrates the potential of multi-task learning and attention-based feature refinement for unconstrained facial analysis.

---

### Feature Normalization under Finite Training Budgets

Authors: Johan Larsson
Published: 2026-10-12
Categories: stat.ML, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2610.16845v1

Standardizing a rare feature can help stochastic gradient descent learn its effect within a finite budget, but it also changes the noise cost of learning. We characterize the lowest rare-subgroup risks attainable by standardized and unscaled training when each chooses a nonnegative constant learning rate and a deterministic stopping time under the same observation cap. For two independent binary features, we derive both optimized risks as prevalence vanishes while the expected number of rare observations remains finite. Uniform control over rates and stopping times reduces each limiting oracle to a scalar minimization. With positive noise, the preferred scaling changes exactly once as we move signal to the rare feature while the limiting risk at initialization stays fixed and positive. The formulas also explain how noise and budget affect the comparison. Separate finite-prevalence bounds favor standardization on a rare-dominant signal family and unscaled training on a common-dominant family. The results concern final iterates with population preprocessing and fresh observations. Exact-moment searches assess the approximation at finite prevalence. In a controlled study, both orderings persist under observation reuse, estimated preprocessing, and intercept fitting when tuning choices are fixed before evaluation. Selecting a predictor after observing training can reverse an ordering, even when selection uses exact population risk.

---

### Few-for-Many Best-Arm Identification in Multi-Objective Bandits

Authors: Bo Xue, Yilu Liu, Haodong Jing, Hongzong Li, Xi Lin, Shuang Qiu
Published: 2026-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.16840v1

Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling each option as an arm in a multi-objective bandit, we introduce \emph{few-for-many best-arm identification}, which seeks a small set of arms minimizing the worst weighted degradation from the objective-wise optima, rather than the best arm for every objective. We consider both known objective groups and latent groups specified only by a representative budget, and propose \textsc{GFM-Elim} and \textsc{AFM-Elim} with instance-dependent sample-complexity guarantees. For Gaussian rewards, we further derive a lower bound for the latent-group setting and show that it is asymptotically attainable with high probability by an oracle-based Track-and-Stop procedure. Our results show that sharing observations across objectives and ignoring irrelevant objective-wise distinctions can substantially reduce the sampling cost, as confirmed by experiments on synthetic and real-world tasks.

---

### Label Collapse in Diffusion Language Model In-Context Learning

Authors: Ziye Guo, Ye Yuan
Published: 2026-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.16839v1

In-context learning (ICL) applies large language models to new tasks by prepending a few labeled demonstrations to a query. Prior work has studied how demonstration ordering affects ICL, but the interaction between label arrangement patterns and model biases has not been systematically examined. We define label collapse as the failure mode in which the model generates query-independent labels, and show that it is architecturally universal at the tested 8-9B scale: five models spanning autoregressive (Llama-3, Qwen3.5) and discrete diffusion (LLaDA, iLLaDA, LLaDA-Instruct) families all exhibit label collapse even under the class-balanced alternating arrangement, with some label word pairs collapsing in virtually every tested condition and others flipping their collapse direction with arrangement. Critically, accuracy alone cannot detect this collapse: models can achieve near-chance accuracy while generating query-independent labels, a score indistinguishable from balanced performance, so the failure can persist undetected in deployment. We measure separation, the log-odds of the two label words at the query position (the quantity that label-bias calibration operates on), as a complementary diagnostic that exposes collapse hidden beneath surface accuracy, together with a measurement protocol that guards label extraction against tokenizer and formatting artifacts. For autoregressive models, collapse persists where the majority-label-bias account does not apply, and arrangement patterns can reverse the collapse direction; for diffusion models, we present a systematic evaluation of ICL failure modes, complementing contemporaneous studies of dLLM context comprehension and demonstration-order sensitivity, and identify open questions about how iterative denoising interacts with label biases.

---

### Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization

Authors: Huihao Jing, Shaojin Chen, Wenbin Hu, Yuxuan Liu, Haochen Shi, Zhongwei Xie, Haoran Li, Yangqiu Song
Published: 2026-10-12
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2610.16838v1

As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardrails are often placed in front of these actions, yet few evaluations ask whether their decisions follow authorization: blocking unauthorized actions while still allowing the same actions under valid permission. We introduce \bench{}, a benchmark that contrasts authorization evidence for the same operation in its language track. It combines expert-annotated natural-language scenarios with executed and verified operations, plus externally sourced native-policy requests. \bench{} checks each decision for correctness, usability and resulting effect, and tracks each request across guardrail changes. Our experiments show that many blocked operations stem from failed reviews, not correct denials. Repairing the output format restores usable decisions but changes which authorized requests are honored, and adding a second reviewer removes some errors while rejecting valid authorization. Guardrails should therefore be evaluated on both the unauthorized actions they stop and the authorized actions they let through.

---

### A Scaled-Up Empirical Study of Syntactic Language Models

Authors: Pengcheng Wang, Zhexuan Zhang, Chao Lou, Kewei Tu
Published: 2026-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.16837v1

Syntactic language models (SLMs) that generate sentences along with their syntactic tree structures have shown promise in both syntactic generalization and downstream tasks. Prior studies, however, have mostly evaluated smaller models trained on less pretraining data and tested on narrower task suites. In addition, the design space of tree linearization and attention masks remains underexplored. We conduct a large-scale empirical study of 12 controlled configurations---one terminal baseline and 11 SLM variants spanning different linearizations and masks---at scales up to 1B parameters and 100B training tokens, evaluated across 11 downstream tasks and two syntactic benchmarks. The experimental results show that SLMs with standard causal attention match or exceed structural-mask variants across downstream and syntactic benchmarks. They require no architectural modifications and remain compatible with FlashAttention. We also observe that when scaling up to the 1B-parameter scale, the top-performing SLM variant no longer shows a clear advantage over a compute-matched non-structural baseline, suggesting that SLMs may become less competitive with scale. Our code is available at https://github.com/qlwpc/TG-Interpolation.

---

### Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models

Authors: Jihye Kang, Jiwon Park, Namhyuk Ahn
Published: 2026-10-12
Categories: cs.CR, cs.CV
arXiv: https://arxiv.org/abs/2610.16835v1

Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection effectiveness, clean fidelity, compatibility, and tamper resistance. We incorporate long-horizon attack simulations to strengthen resistance to protection removal. Experiments with a single protection tool show improved resistance to re-alignment at a cost to clean fidelity, motivating further research toward practical model-side protection.

---

### The Bell Boundary of Shared Representations

Authors: Yang Wu, Hanyu Zhao, Yazhou Zhang, Yuexian Hou
Published: 2026-10-12
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.16828v1

When does a shared representation become insufficient for jointly supporting multiple tasks? This question lies at the heart of multi-task learning models. Although task interference in shared representations has been widely observed, its onset, measurable form, and capacity boundary remain poorly understood. In this paper, we revisit this problem through the lens of Bell's theorem. We show that if four binary task outcomes can be jointly represented by a common shared representation, their correlations must satisfy the classical CHSH bound $|S|\leq2$. We introduce NCnet, a controlled multi-task model for studying how representational capacity affects task compatibility. Experiments reveal a clear capacity-dependent transition. Once nontrivial task fitting emerges, constrained capacity can yield $|S|>2$. As capacity further increases, these exceedances progressively disappear and $S$ returns to the bounded region. This systematic pattern provides evidence that limited representational capacity is an important source of the observed incompatibility. We observe similar transitions across CNNs, PLMs, and LLMs, suggesting that the phenomenon extends beyond the controlled NCnet setting. We refer to this capacity-dependent transition as the Bell Boundary, providing a measurable diagnostic for representation bottlenecks, task incompatibility, and capacity allocation in multi-task models.

---

### Unsupervised Data Drift Monitoring for Deployed Deepfake Speech Detectors

Authors: Lukáš Prokeš, Vojtěch Staněk, Anton Firc, Kamil Malinka
Published: 2026-10-12
Categories: cs.SD, cs.AI, cs.CR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.16826v1

Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face evolving attacks, codecs, speakers, and recording conditions, with labels unavailable during operation. This makes it difficult to know when a detector operates in familiar conditions and can be relied on. We propose an unsupervised drift monitor that operates on the internal embeddings of a deployed detector. The monitor compares each input against bona fide and spoof references using regularized Mahalanobis distances. These distances define trusted, ambiguous, and novel regions of the detector embedding space, allowing unfamiliar inputs to be routed for review. We evaluate the monitor on four modern detectors on three datasets. The monitor raises alerts for dataset mismatches and substantially reduces the security-critical case of accepting deepfakes at the cost of reduced automatic coverage. The results also show that drift affects both classes: bona fide recordings can move away from the training reference, increasing alert rates even in in-domain settings. Our findings suggest that deployed deepfake speech detectors should be treated not only as a binary classification, but also as a reliability problem.

---

### Mean Accuracy Is the Wrong Estimand for a Release Decision

Authors: Jaewon Choi, Jihye Kang, Namhyuk Ahn
Published: 2026-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.16825v1

A release decision about a fine-tuned model is an operational commitment about the \emph{next} rerun of its training recipe. Yet standard benchmark reporting gives only the mean accuracy of past seeds. These target fundamentally different questions: release decisions depend on catastrophic tail risk, whereas standard evaluation reports only central tendency. Because fine-tuning induces bimodal mode collapse, high average accuracy frequently conceals severe failure rates. Auditing $2\,124$ fine-tuned models across eleven language models, we show that shipping models based on mean accuracy violates a $10\%$ deployment failure budget $48.0\%$ of the time. Common heuristics like $\bar b - 2σ$ prove equally dangerous: by underestimating variance on small samples, they become most permissive when evidence is weakest. We introduce \textbf{recipe cards}, an evaluation framework that directly certifies rerun tail failure rates using exact finite-sample binomial bounds. Recipe cards reduce held-out budget violations to $0.6\%$, enforce a mathematical sample floor ($N \ge 22$) that prevents certification on thin evidence, and explicitly refuse unverified claims under domain and task shifts.

---

### DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning

Authors: Yuxiang Zeng, Kun Xie, Yang Wang, Jigang Wen, Xiaocan Li, Guangxing Zhang, Gaogang Xie, Jiannong Cao
Published: 2026-10-12
Categories: cs.LG, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2610.16822v1

Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates. The key difficulty is that neural architectures are operation-labeled DAGs: edge direction defines computational flow, but existing predictors often treat direction as a local structural cue. We propose DTA-GT, a Direction- and Topology-Aware Graph Transformer based on encoder-wide directional consistency, which preserves directed computational semantics across node initialization, global spectral encoding, pairwise interaction, and feature update. DTA-GT realizes this principle with direction- and topology-aware node initialization, Magnetic Laplacian spectral encoding, direction-dual structural attention, and a Direction-Sensitive MoE-FFN. Across accuracy and latency prediction on NAS-Bench-101 and NAS-Bench-201, DTA-GT consistently outperforms representative sequence-, GNN-, Transformer-, and hybrid predictors under limited-budget settings. Ablations and Magnetic spectral controls show that the improvements come from coordinated direction-aware stages and edge-orientation-sensitive spectral information, while mechanistic diagnostics confirm that the modules exhibit the intended directional behavior. These results support encoder-wide directional consistency as an effective design principle for architecture DAG representation.

---

### Sample-Size Extrapolation in Simulation-Based Inference via Statistical Scaling

Authors: Shiyi Sun, Lei Fang, Geoff K Nicholls
Published: 2026-10-12
Categories: stat.ML, cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2610.16820v1

In simulation-based inference (SBI), neural posterior estimators trained on a bounded range of sample sizes can become inaccurate on larger datasets because their parameterizations do not specify how posterior location, uncertainty and shape must change as observations accumulate. We propose center-estimated NPE (CE-NPE), which combines a statistical center with an explicit contraction rate and learns a local center correction and residual densities in posterior-scale coordinates. The center is a statistical estimate, such as a closed-form statistic or a simulator-based moment match, which does not require an evaluable likelihood. Our analysis explains how contraction amplifies center error and decomposes Gaussian posterior error into shape, mean and covariance contributions. On six regular benchmarks, CE-NPE gives the best reference-posterior agreement of all tested amortized estimators at every out-of-range size, up to five times the largest training size, without retraining; it also fits better within the training range on most of them. Matched controls and nonregular examples characterize the scope of these gains and identify the conditions on which they depend: an appropriate contraction rate, an accurate center, and a stable residual representation.

---

### Calibrated $α$-Barycenters for Multiobjective $f$-Divergence Optimization

Authors: Dier Tang, Peijie Li, Xiaoyuan Zhang
Published: 2026-10-12
Categories: math.OC, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2610.16819v1

Matching one distribution to many targets can require repeated evaluations of every target. CAL-$α$-MODM aggregates a nonlinear predictor into one barycenter, calibrates its residual derivatives, and checks steps against the original $f$-divergence objective. Under smoothness assumptions, calibration controls parameter-step model error without requiring targets to be close to the model. Exact-oracle stationarity and local convergence guarantees are established. At common matching, canonical geometry cancels the leading quadratic iteration error, giving cubic convergence with second-order calibration and sufficiently accurate inner solves. High-precision experiments support this prediction. Sensitivity-based initialization also accelerates preference continuation along regular stationary branches. On 300-target Jensen--Shannon problems, CAL-p2 achieves median paired speedups of $3.15\times$ over L-BFGS and $1.10\times$ over second-order Direct-TR, across 23/25 and 24/25 objective-comparable stationary pairs. The savings arise when cheaper predictor queries offset calibration overhead.

---

### Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers

Authors: Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Andrea Dittadi, Karl Henrik Johansson, Kaitlin Maile, Johannes von Oswald, Stefan Bauer
Published: 2026-10-12
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.16817v1

Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large language models have renewed interest in this longstanding approach, demonstrating benefits for training efficiency and reasoning alongside changes in internal computations. However, how growing affects representation quality and computational patterns in self-supervised vision transformers remains unclear. In this work, we systematically investigate progressive depth growth in two popular self-supervised families, namely masked autoencoders (MAE) and DINOv3, and analyze how growing affects downstream performance, intermediate representations, and internal computations. Across global and dense tasks, we show that growing improves downstream performance while reducing training FLOPs by 13.9--24.8%, with ImageNet linear-probe accuracy gains of up to 3.36 percentage points. Growing also improves downstream performance at intermediate layers and reshapes internal computational patterns, introducing recurring alternations between global and localized attention in MAE and earlier local-to-global attention progression in self-distilled DINOv3. Together, these findings establish progressive depth growth as an effective and efficient pretraining strategy for improving downstream performance across global and dense visual tasks with less computation, and advance our understanding of how growing shapes visual computation.

---

### Statistical Downscaling of Daily Precipitation from ERA5 Atmospheric Fields to IMERG over West Africa

Authors: David Sagna, Redouane Lguensat, Samo Diatta
Published: 2026-10-12
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2610.16816v1

Global reanalyses are too coarse to resolve the convective systems that produce most West African monsoon rainfall. In this work, we use U-Net based architectures to downscale daily ERA5 fields (0.25°) to IMERG V07 satellite precipitation (0.1°) over West Africa for the June to October seasons of 2000 to 2024, using geopotential, temperature, humidity and wind at three pressure levels together with elevation and land fraction. Adding ERA5 precipitation as input slightly improves performance for this particular challenging region. We find that all the deterministic networks investigated for this work are too dry and lose almost all observed variance below a few hundred kilometers, which motivated our use of a GAN-based alternative. We also investigated permutation importance for the U-Net that ranks 500 hPa specific humidity first, consistent with the sensitivity of deep convection to mid-tropospheric moisture.

---

### On the Calibration of Crowdsourcing Aggregators

Authors: Gabriel Singer, Reda Arab, Maïssa Frikha, Samuel Gruffaz, Olivier Vo Van, Nicolas Vayatis, Argyris Kalogeratos
Published: 2026-10-12
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.16815v1

Calibration has been extensively studied for classifiers, but remains largely unexplored for crowdsourcing aggregation methods, which are increasingly used for making probabilistic decisions. To the best of our knowledge, we provide the first theoretical and empirical study of calibration in label aggregation. To our great surprise, we find that widely used aggregation methods can be severely miscalibrated, and in opposite directions: Majority Vote is underconfident while model-based aggregators are overconfident. We prove that the Bayesian aggregator is perfectly calibrated under its data-generating model. We also show that exact calibration of weighted majority votes requires highly restrictive conditions, which helps explain why Majority Vote is generally miscalibrated in realistic crowds. Empirically, we study calibration across $39$ human crowdsourcing datasets and LLM-based crowds. In both cases, we observe systematic miscalibration for aggregation models such as Majority Vote, Dawid--Skene, GLAD, and CrowdFM. Finally, we propose a post-hoc calibration procedure that \emph{aggregates the aggregators}: for any aggregation function $φ$, we introduce a transformation that first combines its predictive distribution with those of complementary aggregators, before applying temperature scaling. This simple and interpretable transformation makes temperature scaling more effective than when applied directly to $φ$. It improves calibration, especially in the high-redundancy regime where there are many annotations per item, while generally preserving or even improving accuracy.

---

### StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge

Authors: Anning Hu, Yangyu Li, Yuqi Huang, Shengchao Hu, Junchi Yan
Published: 2026-10-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.16814v1

Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recommendation. However, LLM-as-a-Judge pipelines are vulnerable to score-hijacking prompt injection embedded in evaluated content, which corrupts scoring signals and distorts induced rankings. Existing defenses often enforce robustness by modifying the judge model itself, making safety dependent on a specific model's scale and training and requiring repeated effort when the judge is updated or replaced. We propose StableJudge, a lightweight defense framework that externalizes prompt-injection mitigation as a reusable pre-scoring capability. StableJudge centers on a compact 0.13B Sentry that localizes injected spans and performs targeted sanitization prior to evaluation, and is trained using adversarially evolving attacks to improve robustness beyond a fixed prompt set. To stabilize measurement, StableJudge derives deterministic, fine-grained scalar scores from the judge's output distribution. Across held-out scientific abstracts and out-of-distribution attack variants, StableJudge improves score recovery under attack while largely preserving general-purpose performance, demonstrating that robust LLM-based judging can be achieved by decoupling safety from judge scale via reusable defense capabilities. Code and data will be released.

---

### Carve VFM: Carving Specialists out of Generalists, Automatic Task-Specific Compression of Vision Foundation Models

Authors: Lotfi Abdelkrim Mecharbat, Abdelrahman Elsayed, Ibrahim Almakky, Martin Takáč, Mohammad Yaqub
Published: 2026-10-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.16813v1

Vision foundation models (VFMs) provide transferable visual representations, but their inference cost limits deployment in many settings. Fine-tuning specializes a VFM without shrinking it; distillation shrinks it, but through expensive teacher-guided training. Structured pruning offers a more direct route by extracting a compact subnetwork from the VFM. However, as compression gets aggressive, existing methods fail because they treat subnetwork selection and recovery as separate axes. Across layers, capacity must follow task sensitivity rather than spread uniformly. Within a layer, a removal cannot be judged by importance alone; its impact also depends on how well the lost contribution can be recovered from what remains. Selection and recovery must therefore be decided jointly. We introduce Carve VFM, which resolves this interdependence. Given a VFM, a calibration set, and a parameter budget, it (i) searches for task-specific capacity allocations across layers; (ii) guides the search via an adaptive recovery-aware fitness criterion; and (iii) reconstructs removed behavior through iterative closed-form low-rank corrections merged into the surviving weights. The result is a dense encoder produced in minutes on a single GPU without backbone retraining. Across twelve benchmarks and four models from DINOv3 and MetaCLIP-2, Carve VFM achieves the highest reported mean accuracy in seven of eight backbone-budget configurations among the evaluated dense structured-pruning methods. Further fine-tuning surpasses the strongest evaluated edge model (88.1% vs. 85.8%), and carved models cut compute and memory while delivering 1.3-2.0x higher GPU throughput than the uncompressed one. These results show that the compact model you need is inside the VFM; it only has to be carved out.

---