# Research Papers — 2026-10 · bundle page 55 of 156

> Full-text markdown of papers #2701–2750 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/55
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/54.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/56.md)

### Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments

Authors: Marthe Ballon, Arne Vanhoyweghen, Seorin Kim, Francesca Carlon, Lynn Delcon, Melika Mobini, Vincent Holst, Lukas Van de Voorde, Tibo Vanleke, Mathieu Louis, Bert Verbruggen, Brecht F. Verbeken et al.
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15634v1

Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribute to research synthesis, evaluation, and decision-making. A reliable model should revise its judgement when a user identifies a genuine flaw, but should resist pushback based on fallacies, emotion, or irrelevant appeals to authority. While sycophancy is usually measured on questions with a verifiable answer, the evaluative tasks in which it is most difficult to detect have no such ground truth. We introduce Big-Big-SycoBench, which measures sycophancy through argument discernment: the ability to revise an evaluation after valid criticism while resisting invalid pressure. The benchmark consists of 450 text artefacts with 5,400 arguments for raising or lowering their quality scores, each reviewed by one or more of twelve human annotators. An LLM scores each artefact twenty times to establish its baseline score and uncertainty. The model is then given a valid or invalid argument and asked to update its score. We only count a revision if it exceeds the model's own baseline variability. We use the resulting score delta to distinguish responsiveness to valid arguments from compliance with invalid ones. Across ten models, responsiveness is 88-95\% for seven, 76-77\% for Kimi K3 and GLM-5.3, and 32\% for Opus 5.5. Compliance ranges from 0.2\% for GPT-6 Astra to 95\% for GPT-4o. Big-Big-SycoBench is intended to guide the development of models whose judgements can be corrected by sound arguments, but not displaced by unsupported pressure.

---

### The Price of Precision: A Calibrated Cost Model for Mixed-Precision LLM Serving

Authors: Mukund Athmaram, Manoj Rao, Liang Ma
Published: 2026-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.15629v1

Choosing a mixed-precision configuration for large language model (LLM) serving trades speed against accuracy. Allocators that use average bit-width or a memory budget as a speed proxy can miss changes in the resource that limits execution. We argue that served speed can be limited by compute, weight loading, or key-value (KV) cache access, depending on the phase, batch size, and context length. A byte-based proxy does not capture all of these costs, so fewer bits do not always mean faster serving. To address this gap, we build a cost model that accounts for the binding resource and use it in two ways. First, as a predictor: given a configuration and operating point, it estimates serving latency using constants calibrated for the model, GPU, and serving stack. We evaluate its accuracy across three hardware classes. Second, as an allocator: we combine modeled time costs with measured per-tensor accuracy costs and use a dynamic program to select a configuration under a latency or accuracy budget. We compare its configurations against byte-aware and sensitivity-only allocation.

---

### Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging

Authors: Tristan Malatyński, Joanna Jaworek-Korjakowska
Published: 2026-10-11
Categories: cs.CV, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2610.15628v1

Deep learning is now central to radiology, helping detect changes on X-rays, CTs, and MRIs. However, these systems are highly vulnerable to adversarial attacks - small, crafted perturbations that mislead models while appearing unchanged to humans. Such errors risk missed cancers or false positives. Studies show over 90% attack success on medical scans. Almost 30% of US hospitals use AI in imaging in 2023. Thus, an effective method of detecting such attacks and their directionality is crucial to ensure the credibility and reliability of medical systems based on DNNs. We propose a novel detection framework that leverages subsequent attacks using random noise to identify adversarial perturbations. Our approach uses the analysis of variations in the Sigmoid function to distinguish genuine medical images from adversarially manipulated ones. Specifically, we compare prediction differences between clean and attacked images, as well as between different adversarially altered versions, to improve detection accuracy. We evaluated our method on three popular medical datasets including 'Chest X-Ray Images for Classification', 'Retinal Fundus Multi-disease Image Dataset' and 'Brain Tumor Dataset' under various attack scenarios, including random noise. Our framework achieved up to 99.8% ACC in identifying adversarial directional attacks, significantly outperforming existing defense mechanisms. It consistently identified adversarial samples across varying attack strengths while keeping false positives low, showing strong reliability and potential for clinical use. Furthermore, our proposal highlights its potential for real-world deployment.

---

### 1Step-WAM: Your World Action Model but Faster using 1-Step Action Generation

Authors: Rundong Su, Pengtao Chen, Haohan Geng, Sha Zhang, Zhihang Yuan, Yicheng Rong, Chong Yu, Hao Huang, Tao Chen
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15625v1

World Action Models (WAMs) unify visual world modeling and action generation, yet their real-world deployment is heavily bottlenecked by iterative action denoising and the sequential execution of visual prefilling and action prediction. We demonstrate that the action-denoising trajectories in WAMs are approximately straight, rendering the first-step velocity a strong estimate of the final action direction. Building on this observation, we introduce 1Step-WAM, a framework that transforms multi-step action denoising into one single forward. Specifically, we employ a lightweight calibrator to directly correct the first step velocity, and use bandwidth-constrained action decoding to further reduce errors in the calibrated one-step actions. Compressing action generation into a single step enables it to execute in parallel with visual prefilling, completely breaking the sequential bottleneck of the traditional imagination-then-action paradigm. Evaluations on RoboTwin and LIBERO show that 1Step-WAM largely preserves multi-step task success with only about 13.4M trainable parameters, while achieving inference speedups of $7.44\times$, $5.98\times$, and $24.84\times$ for FastWAM, ImageWAM and Kairos, respectively. Furthermore, real-world robotic deployments using the FastWAM backbone confirm a consistent 7.44$\times$ speedup while maintaining close success rate to the multi-step baseline. Code is avaliable at https://github.com/changdong1687/1Step-WAM.

---

### Adaptive Role Assignment and Controlled Feature Reconstruction for Federated Image Semantic Communication

Authors: Yuxuan Chen, Jiao Bie, Hang Qi, Jingjin Wu
Published: 2026-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.15623v1

Hybrid federated semantic communication enables user equipment (UEs) to contribute model updates or semantic features under a shared training framework. However, heterogeneous role costs and the interaction between model aggregation and feature reconstruction (FR) remain key challenges in practical radio access network (RAN) deployment. To address these issues, we propose ARC-FedSC, a RAN-aware framework that coordinates UE role assignment and server-side controlled FR under a fixed communication budget. Within ARC-FedSC, RAN Aware Role-Bandit learns the historical contribution of UEs in different roles together with current uplink conditions, while Temporal Consistency Alignment (TCA) regulates FR according to recent model aggregation directions. Experiments on CIFAR-10 with time-varying RAN channels show that ARC-FedSC outperforms baselines across all five tested role configurations in the later training stage, with the best configurations achieving about 24.17 dB average PSNR over the last 20 rounds. Component level results further show that Role-Bandit maintains an average rolling UE coverage of 85.3%, compared with about 65.7% for baseline, while TCA reduces the probability of harmful FR events from 0.245 to 0.093, corresponding to a 62.0% reduction. Ablation and sensitivity studies further support the effectiveness and robustness of the proposed design.

---

### From Stages to States: Unified Iterative Reasoning for MLLMs

Authors: Chuang Yu, Xuefei Ma, Yuanhao Feng, Wuxiong Zeng, Bo Wang, Minghong Cai, Dongming Wu, Fei Zhou, Chen Tang, Wenwen Tong, Lewei Lu, Xiangyu Yue
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15620v1

Multimodal Chain-of-Thought (MCoT) substantially enhances the complex reasoning capabilities of Multimodal Large Language Models (MLLMs) by explicitly modeling intermediate reasoning processes. However, most learning-based MCoT methods follow a stage-centric paradigm, where different reasoning behaviors are assigned to predefined stages and optimized separately. This results in fragmented reasoning and a training-inference reasoning-state gap. To address these limitations, we propose ReState, a unified iterative reasoning framework that reformulates multimodal reasoning from a stage-driven pipeline into a state-driven dynamic process. It comprises two complementary components: Unified Reasoning State Modeling (URSM) and Closed-Loop Reasoning-State Learning (CRSL). URSM unifies reasoning construction, correct reasoning preservation, and erroneous reasoning correction as reasoning-state transitions within a shared state space, enabling these heterogeneous reasoning behaviors to be learned jointly. CRSL further incorporates self-generated historical reasoning states during training and recursively updates the current state during inference, thereby mitigating the reasoning-state gap and enabling iterative self-refinement without requiring an additional reflection module, critic, or independent correction stage. Furthermore, we construct VersaCoT-10K, a high-quality CoT dataset spanning eight visual reasoning domains, which provides diverse supervision for multi-domain reasoning and reasoning-state refinement. Extensive experiments demonstrate that ReState exhibits strong adaptability across different MLLM backbones and achieves strong performance on multiple public reasoning benchmarks, supporting the shift from stage-centric reasoning toward state-centric reasoning. Our data and code are available at https://github.com/YuChuang1205/ReState

---

### Screening Collapse under Recursive Synthetic Data

Authors: Jia Zhang, Xin Chen
Published: 2026-10-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.15617v1

Recursive synthetic-data training can degrade a fitted model, but its effects on the variable-screening stage that precedes model fitting are less understood. When each generation labels data for the next, a marginal screener ranks variables against the current pseudo-label target rather than the original response. Across generations, this target drift can erode or reverse the active--inactive score margin and cause screening to discard variables that clean-label screening would retain. We call this process \emph{screening collapse}. In a Gaussian linear model with minimum-norm recursive generators, we establish finite-sample screening bounds, characterize a late-generation information-loss limit, and derive a minimax impossibility result. Screening collapse can precede and compound ordinary model collapse: omitted variables incur a covariance-weighted loss that no refit restricted to the selected variables can eliminate, while recursive labels further degrade estimation on the retained variables. We also examine two approaches to mitigating screening collapse. Fixed-fraction real-label retention preserves a clean-label component but leaves resolution fixed, whereas data accumulation can avoid screening collapse if the pooled target preserves a positive margin and the growing sample resolves it. Numerical experiments on gene-expression data support the theoretical findings.

---

### ProML: Progressive Multi-label Learning

Authors: Yi Kou, Jieting Wang, Yuhua Qian
Published: 2026-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.15614v1

Multi-label learning typically pursues model construction through the joint optimization of label fitting, correlation modeling, and structural regularization. While empirically effective, such a coupled paradigm imposes multiple learning objectives on a single predictive parameter matrix, forcing it to simultaneously fit observed labels and encode structural priors. This coupling may induce ill-conditioned optimization geometry, increase hyper-parameter sensitivity, and complicate capacity control. To address the these issues, this paper proposes a Progressive Multi-Label Learning (ProML) framework, which decouples direct label fitting from predictor learning via the introduction of an auxiliary predictive variable. This auxiliary variable admits a closed-form solution, yielding an equivalent profiled objective in which the supervised fitting term is scaled by a trade-off parameter. This result provides a unified view of ProML and conventional coupled learning, with the latter recovered as a limiting case. We theoretically analyze the optimization geometry of ProML and show that, under quadratic positive semidefinite structural regularization, ProML attenuates the dominant curvature of the fitting term, enlarges the stable learning rate range, and provides a controllable fidelity-regularization trade-off. Further, we instantiate the ProML for multi-label feature selection task by integrating global-local label priors and row-sparse regularization. Extensive experiments and controlled optimization analyses on 12 benchmark datasets empirically corroborate the theoretical analysis and demonstrate the robust and competitive performance of the proposed method.

---

### Joint Contrastive-Adversarial Representation Learning for Unsupervised Domain Adaptation

Authors: Yuling Jiao, Lican Kang, Jerry Zhijian Yang, Zhou Yu, Fusheng Zhou
Published: 2026-10-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.15613v1

Effective unsupervised domain adaptation (UDA) requires a representation that captures transferable structure from both the labeled source domain and the unlabeled target domain. We introduce Joint Contrastive-Adversarial Representation Learning (JCAR), a two-stage framework that learns a common representation from the union of unlabeled source and target samples by combining contrastive learning with adversarial domain alignment, and then freezes the representation to fit a source-supervised predictor. We establish a non-asymptotic excess-risk bound for this procedure that couples representation and domain-discriminator estimation while separating downstream prediction, with explicit neural-network approximation errors. Under the stated assumptions and common Hölder smoothness $β\geq1$, the bound identifies a sufficiently large unlabeled-sample regime in which the downstream rate is $\widetilde{\mathcal{O}}(m^{-β/(2β+d)})$, where $m$ counts labeled source samples and logarithmic factors are suppressed. The labeled-sample exponent is governed by the latent dimension $d$ rather than the ambient dimension $p$, which enters the pretraining cost. Experiments on Office-31, Office-Home, and DomainNet demonstrate clear transfer gains across diverse domain shifts, with particularly strong performance when representations are learned from scratch.

---

### Lesion-Aware Attention for Mammography Segmentation with Heterogeneous Supervision

Authors: Di Dai, Bo Liu, Liwei Wang
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15612v1

Accurate lesion segmentation in mammography is important for computer-aided breast cancer diagnosis, but dense pixel-level annotations remain costly and limited. Existing public segmentation datasets usually cover only a small set of lesion types with manually delineated masks, whereas larger mammography datasets often provide only image-level diagnostic labels. This annotation mismatch makes it difficult to train segmentation models that can generalize to rare or weakly annotated lesion categories. To address this problem, we study open-vocabulary mammographic lesion segmentation under a mixed-supervision setting, where pixel-level masks are available for base lesion categories and image-level labels are available for a broader set of categories. We propose a two-branch framework that jointly learns from segmentation data and classification data. The segmentation branch learns lesion boundaries from annotated masks, while the classification branch introduces additional image-level semantic supervision. To better transfer image-level supervision to lesion-relevant regions, we further introduce a Lesion-wise Attentive Classifier that maintains category-specific feature prototypes and generates lesion-aware attention maps for foreground feature pooling. This design reduces the influence of background tissue and encourages more compact lesion representations. Experiments on multiple mammography datasets show that the proposed method consistently improves open-vocabulary segmentation baselines on both base and novel lesion categories, while reducing the gap to fully supervised models that require dense target-domain masks. Qualitative results further indicate that our method produces more complete lesion localization for small, low-contrast, and visually subtle mammographic findings.

---

### Squeeze-Aware-YOLO: Early Channel Recalibration and Multi-Scale Fusion for Real-Time Traffic Sign Detection

Authors: Mizbaul Haque Maruf, Syed Samin Sadaf, Syed Tamzid Bakht, Md. Hasanul Kabir, Sabbir Ahmed
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15604v1

Traffic sign detection plays a vital role in intelligent transportation systems, supporting the safe operation of advanced driver assistance systems and autonomous vehicles. Despite significant progress in real-time object detection, accurately identifying traffic signs under challenging conditions remains difficult. Variations in lighting, adverse weather, motion blur, and partial occlusion often reduce detection performance, especially for small or visually degraded signs where important spatial information can be lost. To address these challenges, we propose Squeeze-Aware-YOLO, a lightweight traffic sign detection framework that introduces a multi-branch bottleneck module combining convolutional kernels of different sizes with a Squeeze-and-Excitation mechanism to improve feature extraction and adaptive channel weighting. In addition, we integrate the Multi-Branch Auxiliary Feature Pyramid Network and Re-parameterized Heterogeneous Multi-Scale modules to strengthen multi-scale feature representation and feature fusion while preserving real-time inference efficiency for practical deployment. The proposed approach is evaluated on the Bangladeshi Traffic Sign Detection Dataset, the CSUST Chinese Traffic Sign Detection Benchmark 2021, and the German Traffic Sign Detection Benchmark, achieving mAP@0.5 scores of 74.7%, 79.4%, and 84.0%, respectively, while consistently outperforming recent state-of-the-art YOLO-based traffic sign detectors. These findings demonstrate that combining multi-scale receptive fields, channel attention, and enhanced feature fusion enables more accurate and robust traffic sign detection while maintaining the computational efficiency required for real-world deployment.

---

### CondMSP: Condition-Informed and Resource-Aware Inorganic Materials Synthesis Planning

Authors: Heewoong Noh, Gyoung S. Na, Elton Pan, Namkyeong Lee, Chanyoung Park
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15603v1

Materials synthesis planning (MSP) connects AI-driven materials discovery to experimental realization by proposing precursors, synthesis operations, and processing conditions for a target material. Existing approaches predict these components separately or in pairs and treat conditions only as a prediction target. Consequently, MSP remains centered on recipe prediction: it leaves unexplored how conditions can serve as process context for constructing synthesis routes, and it does not address which candidate routes should be executed under limited experimental resources. We propose CondMSP, which extends MSP from recipe prediction to execution-aware planning. CondMSP predicts temperature, time, and atmosphere by combining a joint predictor with variable-specific experts, and then uses these predictions both as process context, grounding the generation and retrieval of operation sequences, and as execution requirements, specifying which thermal stages can share a furnace run and at what cost. This specification is held fixed across all compared methods; within it, CondMSP ranks routes across precursor sets by a common utility and, under furnace budgets, jointly selects routes and allocates their thermal stages by constrained optimization. CondMSP improves condition and operation prediction and, under this shared constraint, raises reference-recipe recovery from 27.9% to 32.9% at three simulated furnace runs per target and from 34.7% to 40.0% at 30 trials, while a new evaluation set of 2,344 targets supports generalization beyond oxide-dominated training chemistry.

---

### FireNav: Decision-Oriented Reconstruction Evidence Routing for Vision-Language Navigation in Indoor Fire Environments

Authors: Hongbo Ding, Xiang Chen, Jiangxin Dong, Jinshan Pan
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15595v1

In real-world indoor fire environments, visual degradation severely impairs instruction grounding, waypoint prediction, and long-horizon exploration in vision-language navigation (VLN). Although image restoration offers a natural means to mitigate such visual degradation, existing methods primarily optimize reconstruction fidelity, which does not necessarily translate into better navigation decisions and may even corrupt task-critical cues when applied indiscriminately. In this paper, we present FireNav, a decision-oriented reconstruction evidence routing framework that aligns visual restoration with navigation utility in VLN. To advance this task, we first contribute FireVLN-Bench, a paired indoor fire navigation benchmark with clean references preserving task semantics, safety supervision, and matched settings for continuous navigation and robot execution with simulated dynamics. Our FireNav retains native visual tokens and treats latent reconstruction features as auxiliary evidence, where a lightweight router leverages visual features, task context, and prior execution states to determine whether such evidence should be admitted and how strongly it should contribute to the visual tokens. To learn when reconstruction is beneficial, we further introduce decision utility calibration, which compares action prediction losses with and without candidate evidence under the same state, thereby supervising evidence selection according to its contribution to waypoint, heading, and arrival prediction. Experiments demonstrate that FireNav consistently outperforms state-of-the-art baselines in both navigation success and path efficiency across evaluation settings.

---

### An Attention-Guided Graph Neural Network Surrogate for Boundary Integral Computation in Physical Field Reconstruction

Authors: RongZe Gao, YuWei Wu, XinRan Ji, XingYue Ren
Published: 2026-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.15590v1

In practical engineering and scientific computing, a real physical system can be reduced to a boundary value problem, and the adequate boundary information to determine the interior spatial distribution and evolutionary state of the physical field can be solved with linear equations, alternatively, the the real physical problem can be treated with boundary problems with in adequate information problems in field of machine learning. This paper proposes a deep learning framework for the recovery of missing boundary information using an attention-guided graph neural network (GNN) surrogate. The framework extracts features from the physical information on the discretized boundary into a latent space, and the missing boundary quantities are then predicted by the network. Thus, the nonlinear mapping from known boundary quantities to missing boundary quantities is learned using a variational autoencoder (VAE) architecture, while an attention mechanism is incorporated to better model the correlations among different types of boundary information. Furthermore, the interior physical field can be reconstructed using the conventional boundary element method (BEM) integral formulation. The effectiveness of the GNN-BEM framework is evaluated using numerical examples of the two-dimensional Laplace and Poisson equations, which demonstrate good performance in reconstruction accuracy, local detail preservation, and model stability. The results show that GNN-BEM provides a feasible computational framework for boundary information recovery and fast interior physical field reconstruction for partial differential equations under complex boundary conditions.

---

### The Gradient That Top-k Distillation Never Computes

Authors: Rasul Khanbayov, Hasan Kurban
Published: 2026-10-11
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.15589v1

Many deployed distillation pipelines show the student a truncated view of the teacher: keep the top-k probabilities, renormalize, and minimize a divergence on what remains. Renormalization is assumed to account for the missing mass. We prove that it removes the visibility of tail mass, not the freedom to move it. The renormalized objective depends only on log-odds among the retained tokens, so at each position its gradient along the directions that control tail mass is exactly zero; on a real teacher that component measures $2$-$3\times10^{-15}$ of the gradient. The full-vocabulary gradient equals the truncated gradient plus a residual weighted by the tail masses, and training acts only on the first term. Without the cross-entropy term, a top-k student's tail mass drifts away from the teacher's while a full-vocabulary control moves slightly toward it; with it, the gap shrinks about fourfold but persists. On seven open-weight teachers, the retained set determines the teacher's distribution only from $k=d+1$ ($d$ the hidden dimension): recovery is exact from there on all seven, and commonly cached sizes sit below it. In our off-policy runs the practical effect is real but smaller than the choice of teacher-student pair. Renormalization is a normalization, not a safeguard. The code is available at https://github.com/KurbanIntelligenceLab/top-k-distillation.

---

### Inverse Garment Design with Visual Agents

Authors: Nanxiang Jiang, Yunuo Chen, Zeng Tao, Zizhang Li, Qi Guo, Jiajun Wu, Yin Yang, Chenfanfu Jiang
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15582v1

We study the problem of inverse garment design, reconstructing simulation-ready 3D outfits with arbitrary layers from a single image, with visual agents. Unlike differentiable optimization that is time-consuming, or feed-forward methods limited by training data, we introduce DressAgent, a hierarchical agentic system that recovers garment sewing patterns through planning and closed-loop refinement grounded in physical simulation. To this end, we first present an enhanced representation based on GarmentCode for diverse styles and arbitrary dressing layers, and build the first multi-layer sewing pattern dataset with over 15K outfits for supervision and benchmarking. Inverse design then proceeds coarse to fine: In layer planning and coarse estimation, agents infer layer order and relations, peel each layer into its own view, and estimate coarse patterns. In fine-grained refinement, an agentic trio of Tailor, Critic, and Orchestrator refines patterns in a closed loop of editing, simulating, and judging against the reference with visual and measured evidence. Carefully designed tools and an evolving memory make this refinement converge on the target geometry. We also design an agentic generation method for high-fidelity textures. DressAgent outperforms feed-forward methods by a large margin, surpasses or matches differentiable optimization in a fraction of the time, and generalizes to complex layering, diverse poses, and body shapes.

---

### Ellipsoids from Tangents

Authors: Efrat Dahan, Michael Werman
Published: 2026-10-11
Categories: cs.CV, cs.CG
arXiv: https://arxiv.org/abs/2610.15580v1

This paper presents an algorithm for detecting and fitting multiple ellipsoids in 2D, 3D and higher-dimensional data. The representation is based on tangents to the ellipsoid together with their contact points, rather than on points alone. A tangent contributes d independent equations where a point contributes one, so each hypothesis needs fewer samples, which in turn reduces the number of iterations required to recover every ellipsoid. The problem is posed as sets of linear equations whose solutions -- the ellipsoid parameters -- are recovered robustly by clustering in parameter space. The algorithm works in all dimensions and outperforms the state of the art in 2D. The approach applies in general to the robust solution of linear equations, and so has utility beyond ellipsoid fitting.

---

### Towards Robust Calibration Dataset for Domain-General Mixture of Experts Pruning

Authors: Luis Frentzen Salim, Chia-Chun Wu, Tran Van Nhiem, Lun-Wei Ku, Yung-Hui Li
Published: 2026-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.15578v1

Post-training expert pruning is a promising deployment technique for Mixture-of-Experts (MoE) models. The calibration set is an integral part of the pruning process, however, its correlation with evaluation performance is largely misunderstood and unintuitive. In this work, we present an empirical study of the robustness of calibration perturbations, specifically in MoE models. Showing how calibration size, language, and data distribution affect layer-wise expert pruning for gpt-oss-20b. Our findings reveal that (1) domain-general pruning quality receives minimal benefit from scaling calibration data beyond small sample sizes, (2) cross-lingual calibration transfers effectively, with English-only calibration maintaining strong performance across seven languages of varying typologies and scripts, and (3) a diverse calibration data resembling the pretraining distribution can yield comparable or superior performance to test-distribution data. Ultimately, we provide practical insights as a recipe for better understanding calibration for more effective domain-general expert pruning.

---

### Self-Representation Alignment in Diffusion Models for Video Background Music Generation

Authors: Jincheng Zhang, György Fazekas, Charalampos Saitis
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15575v1

Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learned in the diffusion models' denoising process are insufficiently meaningful, which can hinder the generation performance. To address this, we propose a novel diffusion U-Net architecture enhanced by explicitly aligning the weaker representation from the earlier layer conditioned on higher noise with the better representation from the later layer conditioned on lower noise during training, which we use for the challenging multimodal task of video background music generation. Our diffusion U-Net Self-Representation Alignment (U-SRA) employs an alignment loss to effectively guide our diffusion model to learn good internal representations, thereby enabling it to produce higher-quality symbolic music conditioned on video features. We employ a cross-attention mechanism to synchronize music with video segments. Experiments on a benchmark video-music dataset demonstrate that the proposed U-SRA approach for video background music generation surpasses the state-of-the-art across key evaluation metrics, including video-music alignment and overall music quality.

---

### The Fragility and Dynamics of LLM Pruning-Recovery Steps

Authors: Luis Frentzen Salim, Komang Rinartha, Chia-Chun Wu, Tran Van Nhiem, Lun-Wei Ku, Yung-Hui Li
Published: 2026-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.15574v1

Structural pruning followed by a recovery stage is the standard recipe for compressing large language models (LLMs), yet the two stages are typically designed and tuned in isolation. In this work, we study how their interaction shapes the compressed model, sweeping ordering, the data that drives each stage, and the alignment of their training objectives. We find that instruction-following is the first capability to collapse under pruning, well before knowledge, reasoning, or core language modeling, and that much of the pruning in-domain loss is likely not knowledge loss but a domain-agnostic failure to respond coherently to the prompt. We find in our setting that in-domain data is the strongest pruning signal, whereas instruction-style data recovers the most. Stage order matters little, but only marginally. We further analyze how the importance ranking drifts before and after pruning. Together these results give practitioners a concrete recipe for composing pruning and recovery.

---

### Latent-Space Importance Weighting under Covariate Shift

Authors: Yuling Jiao, Lican Kang, Yang Xiang, Jerry Zhijian Yang, Fusheng Zhou
Published: 2026-10-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.15571v1

In this work, we propose a transfer learning algorithm for covariate shift, integrating sample reweighting with representation learning. A key feature of our approach is the use of a lower-dimensional latent space for modeling, in contrast to conventional methods that operate directly in the high-dimensional ambient space. Our method estimates the density ratio of learned latent features for downstream weighted prediction. We establish explicit target-domain excess-risk rates with independent data folds for strictly sufficient learned representations with regular learned-space prediction scores and density ratios. We give dimension comparisons under stated smoothness conditions and a variance comparison for true weights and a fixed predictor. General finite-sample inequalities retain representation-quality errors. Experiments on simulated and real-world datasets demonstrate gains from combining learned representations and latent weighting, and reveal sensitivity to initialization and domain choice.

---

### Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem

Authors: Rasul Khanbayov, Hasan Kurban
Published: 2026-10-11
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2610.15570v1

Settling one comparison between two truncation samplers has cost six thousand A100-hours, and nothing says in advance how far apart two samplers can be. We observe that almost every deployed truncation rule keeps a prefix of the probability-sorted vocabulary, so any two such rules are nested at every decoding step. Nesting yields a closed-form per-step distance and a coupling under which both samplers emit identical text until they first disagree. Accumulated over a generation, this gives a separation certificate that bounds the difference between two samplers on any bounded outcome, is computable from logs a comparison already produces, and equals their sequence-level total variation distance exactly when neither rule ever overtakes the other. Two consequences follow without measurement: exactness is fragile, and certifying a small difference requires the two retained masses to agree to very high precision at every step. On six open-weight models over four math and science benchmarks, the certificate for every hyperparameter grid we tested is at least 0.998, so a bound alone rarely settles a comparison, although two members of one family can be far closer. What remains useful is the coupling, which gives an unbiased paired estimator that cuts variance $1.2$-$3.8\times$ against prompt-level pairing. Read against benchmark sizes at the default pair's variance and our point estimate of its between-prompt component, resolving a one-point difference needs 8 to 32 samples per prompt on GSM8K, MATH-500 and GPQA-Diamond and about 210 on AIME 2025; at that component's upper confidence bound GPQA-Diamond needs more than 32 and AIME 2025 cannot be resolved at any sample count. Choosing a truncation sampler is a measurement problem at least as much as a design one. The code is available at https://github.com/KurbanIntelligenceLab/truncation-samplers.

---

### Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning

Authors: Fan Yang, Lifeng Chen, Yipu Wang, Han Wang, Feilong Chen, Yidong Ma, Zhiyang Chen, Chaoyang Zhao, Lingxiang Wu, Hanqi Jiang, Yibo Chen, Xu Tang et al.
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15565v1

Recent multimodal large language models achieve promising results on visual reasoning tasks, approaching human-level performance on existing STEM benchmarks. However, these capabilities degrade under complex real-world scenes. We identify that chain-of-thought reasoning remains largely confined to the linguistic space, rarely anchoring each step in visual evidence. The main cause is the absence of such data during training. In this work, we introduce a training data augmentation pipeline, \textbf{Visual Augmentation Primitives} (VAP), which leverages state-of-the-art vision generative models to synthesize diverse photorealistic training samples and corresponding reasoning text. VAP introduces some basic operators and applies them to a seed image and gets a variant. It also constructs coherent multimodal reasoning chains throughout the generation process. Such training data force models to perceive visual content and perform logical reasoning according to them at every step. We further introduce multimodal chain-of-thought rubric-based reinforcement learning to enhance this. It rewards not only text reasoning but also visual reasoning by scoring intermediate reasoning steps for logical validity, completeness, and consistency. Moreover, we construct the UNREAL benchmark to systematically evaluate visual reasoning on hyperrealistic scenes across controllable difficulty levels. Experiments show that a 4B model built on this framework surpasses 8B baselines, with performance improving consistently as the model scales to 32B, validating the scaling law for visual reasoning.

---

### UNISON: A Unified Framework for Learning from Scored Bags

Authors: Ofek Kirshenboim, Or Shkuri, Shani Finkelshtein, Yoram Louzoun
Published: 2026-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.15564v1

We introduce UNISON, a unified framework that bridges multiple instance learning and recommendation systems by treating both as instances of learning from scored bag collections of (item, score) pairs. Unlike traditional approaches that address bag-level classification and personalized recommendation as separate problems, UNISON decomposes learning into three interconnected stages: (1) learning universal item representations, (2) modeling bag-specific preference patterns through lightweight personalized parameters, and (3) inferring bag-level characteristics from learned preferences. We justify the architectural choice of linear bag-specific scoring through a first-order analysis: when item embeddings are sufficiently smooth in the score, a linear function approximates the score up to a Taylor remainder controlled by the curvature of the underlying preference function. For cold-start scenarios, we show that the cold-bag fitting problem reduces to ridge-less linear regression with a closed-form solution, and provide convergence guarantees for the iterative variant. Empirically, UNISON matches or outperforms state-of-the-art approaches across diverse domains: entertainment (books, movies), immunology (T cell receptor (TCR) based classification), and microbiome, offering superior computational efficiency and interpretability. A controlled synthetic experiment further confirms that the bag-specific parameters ($w_j, b_j$) recover the latent factors that drive item scores even when the projection $φ$ has no access to the original scoring mechanism (AUC > 0.998). UNISON is available at https://github.com/louzounlab/UNISON.

---

### A Plausible Future Is Not a Causal Future: Can Video Models Generate How the World Unfolds?

Authors: Jialiang Li, Zhengning Xu, Zongyang Ma, Shaobo Cui
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15562v1

Large-scale video generation models are increasingly viewed as a promising path toward world models, yet their ability to capture causally coherent physical dynamics remains poorly understood. Existing evaluations largely emphasize visual quality, prompt adherence, or broad physical plausibility, leaving open whether a model can faithfully realize a complete causal cascade, in which an initiating event propagates through causally dependent interactions to a terminal outcome. We introduce CausalCascade, a simulator-grounded benchmark centered on 50 event-rich Blender scenes with structured event graphs, graph-grounded diagnostic VQA, three levels of future-event specification, and 2,832 controlled counterfactual variants, and use it to evaluate nine image-to-video models with complementary motion-, event-, and counterfactual-level diagnostics. Across the evaluated models, generated motion is more reliably localized spatially than realized with correct spatiotemporal evolution, while richer future-event specification improves event recovery but leaves physical realization limited. Counterfactual evaluation further reveals weak selective responsiveness to physical interventions, while most audited failures are foundational, arising at scene consistency or event occurrence. Together, these results position causal cascade generation as a process-level test of world modeling and highlight the need to jointly recover the intended future, faithfully realize its physical evolution, selectively respond to physical interventions, and maintain a coherent physical world over time. Code and dataset are available at https://github.com/SJTU-DeepDeltaLab/CausalCascade .

---

### Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors

Authors: Yeonseok Lee
Published: 2026-10-11
Categories: cs.LO, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2610.15556v1

Vision-Language-Action (VLA) models commonly generate robot actions token by token through Large Language Model (LLM) decoders, causing inference latency to grow with action sequence length and limiting closed-loop control frequency. We present Goal-Conditioned Vision-Predictor-Action (VPA), which replaces autoregressive decoders with a lightweight latent control loop. A shared vision encoder and a frozen text encoder embed observations, goal images, and instructions; a neuro-symbolic selector chooses a discrete skill; a Joint-Embedding Predictive Architecture (JEPA) predictor forecasts the next latent state; and a flow-matching solver generates an entire action chunk in a few integration steps, so that sequential network evaluations per decision step do not depend on the action horizon. We analyze inference complexity, regularization against representation collapse, and conditions under which latent sub-goal thresholding limits error accumulation across task phases. As an initial proof of concept, we evaluated VPA on the LIBERO-10 suite. The trainable model has under 20M parameters (checkpoint under 75 MB, excluding a frozen 63.4M-parameter CLIP text encoder); a decision step of a single-camera reference configuration takes 10-14 ms on an Apple M4; and trained only on LIBERO-10 demonstrations in under three hours on a single GPU, a two-camera policy succeeded in 40.0% of 200 evaluation episodes. These preliminary results from a single training run suggest the approach is workable. Code and weights are available at https://github.com/ylee-sling/Vision-Predictor-Action and https://huggingface.co/ylee-sling/vpa-libero10, and archived at https://doi.org/10.5281/zenodo.22960920.

---

### ELECT: Settling Identity Before Rendering for Scalable Story Visualization

Authors: Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana, Aniket Joarder, Mahmudul Hasan, Abir Chakraborty Partha, Md. Ahasanul Alam, Redwan Ahmed Rizvee, Md. Fahim Arefin, Md Mahmudur Rahman, Md. Tanvir Alam, Md Mosaddek Khan
Published: 2026-10-11
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.15555v1

Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing methods typically maintain consistency by conditioning each frame on other frames of the same story, coupling generation time, VRAM, or both to story length. We introduce ELECT, which instead settles cross-frame identity before final rendering through a language-guided scene-entity mapping and stationary anchors elected from the model's own drafts. This makes the per-frame cost of the final rendering pass independent of story length. Joint attention exceeds 96 GB of VRAM at 32 scenes, whereas ELECT remains at 8.3 s per frame and under 20 GB VRAM from 10 to 1000 scenes. On the Story50 long-story benchmark, ELECT reaches 0.833 average Character Consistency Similarity (aCCS), compared with 0.826 for ten-round refinement, at one seventh of its generation cost, with lower text alignment (0.327 vs. 0.340). At 1000 scenes, to our knowledge, the first evaluation of training-free story visualization at this length, ELECT exceeds ten-round refinement by 0.017 aCCS and the nearest flat-cost baseline by 0.091, while also surpassing refinement in text alignment at one twenty-fourth of its generation time. These results show that long-horizon consistency need not require increasingly expensive inter-frame conditioning as stories grow.

---

### An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays

Authors: Uday Bindal, Ishaan Karan, Manan Garg, Ekansh Goyal, Rahul Mishra, Rajakrishnan Rajkumar
Published: 2026-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.15544v1

We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. {\em Does Uniform Information Density (UID) predict salient scenes?} 2. {\em What other linguistic properties distinguish salient scenes from non-salient background?} We answer both questions through a controlled corpus study on the MENSA corpus, paired with a Linguistically-Grounded Salience Model (LGSM), a dual-stream classifier that fuses a frozen BERT encoder with explicit linguistic features through adaptive gating. The UID picture is layered in long-form discourse. Per-scene UID summaries carry no independent signal once length is controlled, but at the token level salient scenes match non-salient material in the bulk while specifically suppressing the rarest, hardest-to-predict tokens in the upper tail. UID therefore lives at the within-scene token level rather than as a per-scene aggregate. Salient scenes also show a moderate and sustained cast of central characters (following an inverted-U pattern), strong third-person usage, syntactically simpler language, and more abstract vocabulary about motivation and conflict. LGSM exploits this signature and improves recall on salient scenes over a strong semantic baseline while yielding better downstream summaries.

---

### Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning

Authors: Yuriy Dorn, Dmitrii Vishovan, Kirill Novoselov, Ilya Kuruzov, Darina Dvinskikh, Alexander Gasnikov
Published: 2026-10-11
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2610.15543v1

We study federated learning from continuously arriving data: each client samples from its own distribution, these distributions drift over time, and the server must track the minimizer of the clients' weighted average loss. Clients are not alike as they collect data at different rates, with different noise, and change at different speeds. The main question is how much history should each one keep? A single shared window must serve every client at once, and so makes a fast-changing client carry the sampling noise of a slow, nearly stationary one. We give each client a memory of its own, sized to that client's noise, arrival rate, and drift, and refresh it by restarted accelerated method that starts from a common point. The tracking error is then bounded by \( R\left(\sum_m w_m^{3/2}\,σ_m\sqrt{γ_m/λ_m}\right)^{2/3}, \) for clients with weight $w_m$, noise $σ_m$, arrival rate $λ_m$, and drift rate $γ_m$ on a domain of diameter $R$. This is never worse than what any common window can achieve, and strictly better whenever noise and drift are spread unevenly across clients. A lower bound that puts different groups of clients on different drift clocks shows this quantity is the right one. The two bounds agree up to a constant whenever the clients occupy boundedly many refresh scales, and in general differ only by the sixth root of the number of scales. Experiments show the gain comes from the memory rather than from the solver: it persists across accelerated, stochastic-gradient, and one-step methods, and against a separately tuned common-memory baseline.

---

### Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

Authors: Project Apertus, :, Yixuan Xu, Yassine Turki, Vinko Sabolčec, Valentina Pyatkin, Tommy Chu, Sven Najem-Meyer, Sean F. Carroll, Robert Smith, Raphael Kreft, Oscar Alessandro Tazza et al.
Published: 2026-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.15542v1

Language models are becoming infrastructure, and infrastructure built in the open, by public institutions, on documented data, is the alternative to dependence on a few providers; Apertus shows this is viable at scale. Apertus 1.5 extends the fully open Apertus family from text to multimodal reasoning. Continued pretraining of the Apertus 1.0 models, on 4T additional tokens for the 8B and 2T for the 70B, adds image and audio understanding and extends the context window fourfold to 262,144 tokens; multimodality enters through the tokenizer, the language-model head remains restricted to text, and the architecture is unchanged. Supervised finetuning, long-context finetuning, reinforcement learning with verifiable rewards, and preference alignment complete the released models. Thinking is a flag of the chat template rather than a separate model, and lifts mathematical reasoning by up to 20 points on the 8B model. The released models improve over their predecessors on nearly every benchmark; among fully open models of its class, the 8B leads on knowledge, instruction following, and cultural benchmarks, and its instruction following surpasses all compared models, including open-weight ones. On image and audio understanding, a first for the family, the models are competitive with fully open multimodal models, strongest on document understanding and long-form and lower-resource speech recognition, while specialized vision and audio models remain ahead on perception and transcription of English and other high-resource languages. As in Apertus 1.0, we train only on openly available data, respect crawler opt-outs retroactively, and exclude restrictively licensed material. We release the model weights, data preparation and training recipes, and evaluation suites under permissive licenses; openness extends to values, with the Apertus charter guiding alignment stages published alongside the models.

---

### Sensitivity Fidelity Reveals Physical Dependencies Beyond Forecast Accuracy in Deep-Learning Earth-System Models

Authors: Qi Chen, Peng Zhan, Hongxing Cui, Wenqing Cui, Ibrahim Hoteit
Published: 2026-10-11
Categories: cs.LG, physics.ao-ph, physics.geo-ph
arXiv: https://arxiv.org/abs/2610.15540v1

Deep-learning models increasingly rival numerical simulation in Earth-system forecasting, yet forecast error alone cannot determine whether their learned input-output dependencies are physically consistent. Here we introduce sensitivity fidelity as an additional criterion: alongside prediction error, model responses to input perturbations should be examined against a trusted reference or established physical knowledge. In an idealized Rayleigh-Bénard convection benchmark, four surrogate architectures achieved low forecast errors yet encoded markedly different sensitivities. Quantitative comparison with a matched adjoint distinguished the models far more sharply than forecast accuracy and showed that predictive skill and sensitivity fidelity need not coincide, while finite-perturbation experiments further linked these differences to the propagation of initial-condition uncertainty. We then applied this strategy to El Niño-Southern Oscillation prediction, where no adjoint reference exists and learned sensitivities showed event-wise robustness, validity under finite perturbations, and consistency with established precursors. These results identify gradient-based evaluation as a discriminating complement to forecast-error metrics, providing a practical test of whether data-driven Earth-system models learn physically credible dependencies.

---

### Poisoned into Action: Context Attacks on Typed Decision Workflows

Authors: Chenkai Wu, Xing Chang, Jun Yan
Published: 2026-10-11
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2610.15537v1

Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating context poisoning thus requires connecting model decisions to execution outcomes while accounting for legitimate automation retained by defenses. We introduce an execution-aware protocol tracing poisoned evidence through retrieval, model choice, automated action, and persisted state. We evaluate it with 1,659 fresh calls to Jev-1.13.0 across 20 development tasks in two synthetic workflows, using three repetitions per condition. Under natural retrieval, a standalone payload reaches all 60 trials and produces five security-violating executions, while a carrier-payload pair exposes the payload in 57 trials and produces one violation. An initial source-exclusion gate blocks the pair's observed violation but also withholds ten otherwise correct attacked decisions and sixteen correct clean decisions. Correcting its empty-scope behavior restores twelve clean decisions without additional model calls. Factorial controls show that adding correct evidence reduces wrong executions from 119/120 to 55/120 in the semantic arm and from 60/120 to zero in the neutral arm, suggesting that much of the improvement reflects general evidence value rather than attack-specific protection. Three prespecified contrasts are not statistically supported after Holm correction, so the findings remain exploratory. The protocol provides an auditable framework for studying which poisoning-induced errors reach execution and how much correct automation defenses preserve. Code is available at https://github.com/WuXixiong/jev-poisoning-bench.

---

### UMAS3D: Unified Mask-Free 3D Editing with Region-Adaptive Source Preservation

Authors: Xianlin Zeng, Xiaolong Shen, Ruijie Quan, Yi Yang
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15533v1

3D editing aims to modify an existing 3D asset according to user intent while preserving geometry and appearance outside the intended edit region. Existing methods often rely on task-specific training, source-3D inversion, or external 3D masks, and lack a unified framework for diverse editing conditions and tasks. We propose UMAS3D, a unified 3D editing framework that is training-free, inversion-free, and free from external 3D masks. UMAS3D converts text, bounding boxes, reference images, and their combinations into common target-view guidance, after which addition, deletion, modification, appearance, and pose editing share the same downstream 3D generation process. Our key insight is to couple online edit-region estimation with region-aware source preservation. Mask-Free Adaptive Region Modeling (MARM) initializes an Edit/Keep prior from source-target visual differences and progressively refines it as the target structure evolves, while Source-Guided Preservation Steering (SGPS) constrains the current Keep-region states to retain source geometry and appearance without suppressing target-driven changes. Experiments show that UMAS3D supports addition, deletion, modification, appearance, and pose editing while effectively preserving unedited source content. These advances make UMAS3D a unified framework for flexible and source-preserving 3D editing across diverse editing conditions.

---

### Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems

Authors: Xiuming Liu, Le Gai, Zhiyuan Chang, Peiyang Li, Bin Zhu, Shuo Wang, Chao Feng
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15529v2

Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected by a later agent or propagated into a consequential task decision. Measuring local exploitability alone leaves this difference unresolved and provides limited evidence about which participant caused the final outcome. We present Agent-Canary-Mas, an end-to-end evaluation system that follows protocol risk through long-horizon multi-agent tasks. It covers five risk classes and 13 subclasses across A2A, ANP, and BCS, with 975 matched malicious--benign task pairs in five business domains. A shared OpenClaw framework runs autonomous, tool-using agents under different underlying models while preserving the task and execution setup. Matched runs separate local protocol success from downstream consequences; retained evidence connects participant selection, message consumption, tool activity, and task-state changes. We further evaluate a protocol-context Guard that checks an object's authority at consequential handoffs. Across three model conditions, local attack success is frequently at or above 90%, while consequence conversion ranges from 7.1% to 100.0%. Cross-agent evidence raises macro-averaged Audit-F1 from 29.7% to 95.5%. On Finance tasks, the Guard lowers average ASR from 86.1% to 53.8% and PTCR from 65.5% to 31.2%, with a measurable completion tradeoff. These results show that protocol risk depends on how agents use exchanged objects throughout the task, and that evaluating this path supports more informative risk assessment, attribution, and defense.

---

### A Step in the Right Place: Understanding and Optimizing Timestep Placement in Continuous Diffusion Language Models

Authors: Shutian Zheng, Zhihong Yu, Linye Wei, Zeyang Zhang, Meng Li
Published: 2026-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.15527v1

Continuous diffusion language models represent an emerging paradigm for language modeling. They generate text in parallel by iteratively refining continuous representations and mapping them back to tokens through a decoder. However, realizing the efficiency advantage of parallel generation requires maintaining generation quality with only a few denoising steps. Even when the number of steps is fixed, their placement along the denoising trajectory remains flexible. In this paper, we demonstrate that changing timestep placement alone can substantially alter the final latent representations and thereby affect the decoded token distributions. Building on these findings, we introduce StepTune, an algorithm that searches for timestep placements that improve generation quality. The search is conducted on a small calibration set and guided by a language-aware objective, with the model and sampling budget fixed. Once calibrated, the timestep placement is fixed and reused across inputs. Experiments demonstrate consistent improvements in unconditional generation perplexity and conditional task metrics across all evaluated sampling budgets. In particular, StepTune enables 16-step sampling with a frozen model to outperform its native 64-step baseline on both XSum summarization and WMT14 translation and reduces end-to-end latency by approximately $3.8\times$. These results establish timestep placement as a practical means of improving the quality-efficiency trade-off in continuous diffusion language models.

---

### GNFormer: Gaussian Neural Field Transformer for Efficient Camera-based Occupancy Prediction

Authors: Guangcheng Chen, Li He, Hong Zhang
Published: 2026-10-11
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2610.15522v1

Camera-based occupancy prediction provides geometric and semantic scene understanding for robot perception and has been adopted in autonomous vehicle and UAV perception systems. Gaussian primitives offer a promising alternative by potentially representing only occupied regions, thereby concentrating computation and representational capacity where needed and reducing wasted computation and memory in empty space. However, existing Gaussian-based methods suffer from poor primitive utilization, as ineffective training objectives leave some Gaussians in empty space, while the limited expressiveness of Gaussian functions restricts their ability to model complex shapes. To address these limitations, we propose a novel 3D representation, Gaussian Neural Field (GNF), which can accurately map voxel positions to semantic occupancies. In GNF, Gaussians and a neural network jointly parameterize the field, where the Gaussians define its spatial support and provide features for neural decoding, while the neural network enables more expressive occupancy modeling than Gaussian functions alone. We further develop the Gaussian Neural Field Transformer (GNFormer), a streamlined and flexible method that predicts GNFs for camera-based occupancy prediction. Across Occ-ScanNet, SSCBench-KITTI-360, and nuScenes-SurroundOcc benchmarks, GNFormer achieves the highest IoU and mIoU and the fastest inference among the compared single-frame methods. In the experiments, GNFormer can represent indoor and outdoor scenes with only 256 and 1024 Gaussians, respectively, substantially fewer primitives than prior Gaussian-based methods. The code will be released.

---

### Improving the Bounds on Approximating Weighted Maximin Share for Chores

Authors: Trung Thanh Nguyen, Khaled Elbassioni, Jörg Rothe
Published: 2026-10-11
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2610.15520v1

We investigate the problem of allocating indivisible chores among agents with arbitrary positive weights and additive nonnegative cost functions. An allocation is said to be $α$-weighted-maximin-share (WMMS) fair if the cost incurred by each agent is at most $α$ times her weighted maximin share. We establish that every instance admits a $4.124234528$-WMMS allocation. Moreover, for instances in which all weights and costs are rational numbers represented in binary, we give an algorithm that computes a $4.12424$-WMMS allocation in time polynomial in the number of agents, the number of chores, and the total binary encoding length of the input. Complementing these upper bounds, we construct a family of instances with strictly positive, identically ordered costs for which the optimal WMMS approximation factors converge to $e$. Together, our results substantially narrow the previously best-known gap of $(2,12)$ established by Li et al.~\cite{LWX26} to $(e,4.12424)$.

---

### OceanFlow: Coherent Flow Matching for Probabilistic Ocean Modeling

Authors: Yuan Gao, Fan Xu, Hao Wu, Xiaomeng Huang
Published: 2026-10-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.15518v1

Probabilistic ocean modeling is essential for risk-aware marine operations, climate analysis, and scientific decision-making, where downstream decisions depend on the conditional distribution of future ocean states rather than a single deterministic trajectory. Recent data-driven ocean models have made deterministic global ocean modeling increasingly accurate and efficient, but probabilistic ocean modeling remains underdeveloped. Specifically, perturbation-driven ensembles can create spread without explicitly optimizing the joint distribution of their members, often yielding poor calibration and physical inconsistency. To address these issues, we propose OceanFlow, a coherent flow matching framework for probabilistic global ocean modeling. OceanFlow first establishes a sharp, stable mean anchor for the conditional ensemble. Flow matching then learns a coherent state-conditioned pathwise law that jointly reshapes the residual distribution around this anchor at each transition, preserving the predictive center while refining state-dependent uncertainty. We further introduce a Factorized Dynamics Operator (FDO), which combines factorized transitions with a learned state-conditioned response to parameterize the mean anchor and residual-flow velocity. Extensive experiments show that OceanFlow improves ensemble-mean accuracy, probabilistic reliability, and physical-consistency diagnostics over competitive baselines, supporting coherent flow matching as an effective route toward data-driven probabilistic ocean modeling. Code is available at https://github.com/YuanGao-YG/OceanFlow.

---

### Semantically Steerable Image Tokenization

Authors: Danilo de Goede, Mohammad Mahdi Derakhshani, Yuki M. Asano, Cees G. M. Snoek
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15515v1

Adaptive image tokenizers compress an image into a variable number of tokens matched to its complexity, and recent work makes this allocation controllable: conditioned on a target reconstruction error, the tokenizer itself decides how many tokens an image needs. However, the fidelity measure guiding this allocation shapes which aspects of the image are preserved under compression. The pixel-wise error used in prior work is blind to the spatial structure that carries an image's meaning, and under heavy compression such tokenizers are prone to abruptly discarding tokens that encode essential content. We introduce GIST (Guided Image Semantic Tokenizer), an adaptive tokenizer that can be steered toward a requested semantic fidelity. Its token allocation is jointly controlled by pixel-level and semantic target errors, with semantic error measured in the feature space of a frozen DINOv3 encoder. This joint control enables semantic protection: with the semantic target fixed at zero, the reconstruction target can be relaxed to discard pixel detail while preserving what the image depicts. In a controlled comparison on ImageNet-100, GIST outperforms its pixel-controlled counterpart KARL at every token count, with up to $30\%$ lower LPIPS and $37\%$ lower DreamSim. On average, lowering its semantic target reduces LPIPS $2\times$ faster per token than lowering the reconstruction target, and up to $5\times$ in the low-token regime. Semantic fidelity is thus an effective control signal for adaptive tokenization: it lets a tokenizer see, and so preserve, what an image depicts.

---

### SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning

Authors: Sankar Behera, Dhruv Singh, Satyadev Ahlawat, Yamuna Prasad
Published: 2026-10-11
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.15514v1

Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-agnostic speedup. Existing post-training methods couple neuron selection and weight reconstruction through a shared calibration dataset, introducing domain bias and out-of-memory failures at high sparsity. We propose SARATHI, a framework that decouples these two stages. A data-free \emph{NMF Residual Subspace Probe} scores neurons using intrinsic weight geometry, without accessing any calibration data, and carries a formal connection to Robust PCA. \emph{Adaptive OBS} then reconstructs the pruned weights with a localized calibration batch, operating in $\mathcal{O}(d^2)$ peak memory per layer and eliminating the global memory bottleneck of coupled methods. A \emph{Bias Shift Compensation} step corrects systematic activation drift in post-LayerNorm architectures that would otherwise cause perplexity collapse at high sparsity. Experiments across six models from two architecture families (gated and non-gated FFN) at 15--40\% sparsity show that SARATHI achieves competitive perplexity and matches or exceeds existing structured pruning baselines on zero-shot accuracy.

---

### REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming

Authors: Abrar Alotaibi, Moataz Ahmed
Published: 2026-10-11
Categories: cs.CL, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2610.15513v1

Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming methods either require privileged access unavailable in production, rely on manually engineered per-model templates, or optimize a single objective without population-level diversity. We present REPRO (Reflective Evolutionary Prompt Optimization), a pure black-box framework that discovers adversarial prompts through evolutionary optimization driven entirely by a compressed open-weight 7B reflective model on a single consumer GPU. REPRO introduces two mechanisms absent from prior work, both isolated in a component ablation: semantic crossover, an LLM-guided multi-parent recombination operator, and Bayesian strategy selection via Thompson Sampling informed by structured failure analysis. We catalog REPRO's behavior on AdvBench, JailbreakBench, and HarmBench across 36 target models from 11 families, including GPT-5-nano, Claude-3.5-Sonnet, Gemini-2.5-Pro, and Grok-4.1. Under our protocol REPRO reaches 100\% attack success rate (ASR) on every evaluated target in a single turn, at a median of 24 target queries per behavior. Two properties of the protocol qualify that figure. The judge scoring candidates during optimization also produces the reported ASR, and search halts when it accepts, so ASR reports whether search succeeded within the iteration budget rather than success at a fixed budget. All baseline figures are transcribed from their original papers, which use different judges, budgets, and model versions. We therefore present this as a catalog of model coverage under one protocol rather than a head-to-head ranking, and develop both qualifications in the paper.

---

### Structured Stateful Relational Scripts with a High-Quality Dataset for Multi-Shot Audio-Visual Video Generation

Authors: Chen Zhao, Lehan Shen, Qilong Huang, Hongyu Li, Zhuoliang Kang, Xiaoming Wei, Jian Yang, Ying Tai
Published: 2026-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.15512v1

Coherent multi-shot audio-visual video generation requires maintaining consistent identities while depicting evolving states and coordinating sounds across shot boundaries. Although dense captions describe individual shots in detail, they rarely specify which entities persist, how their states change, or which entities and actions produce sounds. To address this limitation, we propose Structured Stateful Relational Scripts (SSRS), a textual supervision representation that separates persistent entity and voice identities from shot-specific visual and auditory states. SSRS explicitly encodes sound-source bindings and temporal relations, while a global audio-visual event sequence connects local actions and sounds, including events that continue across shot boundaries. We further introduce MSAV-Script-100K, a large-scale dataset of curated multi-shot audio-visual videos paired with detailed SSRS annotations, enabling models to learn identity persistence, state transitions, and event continuity from structured supervision. Experiments demonstrate improvements in cross-shot consistency, adherence to specified state changes, and audio-visual alignment, highlighting the effectiveness of our SSRS and MSAV-Script-100K for coherent multi-shot audio-visual generation. Our proposed dataset is available at \href{https://huggingface.co/datasets/shenlehan/MSAV-Script-100K}{MSAV-Script-100K}.

---

### CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff

Authors: Haomiao Qiu, Yining Tang, Zijia Song, Ruizi Han, Ziyue Qiao, Miao Zhang
Published: 2026-10-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.15509v1

KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again. We study \emph{zero-prefill cross-model context handoff}: translating a sender cache into a receiver-compatible state so that the receiver can continue directly without prefilling same context. Existing affine transport methods show that receiver KV states can be substantially reconstructed from sender caches. However, through extensive analyses, we find that reconstruction fidelity is a poor proxy for receiver utility. Similar K/V reconstruction errors can lead to substantially different attention patterns, predictive distributions, and downstream accuracy, because conventional reconstruction objectives overlook the query-dependent functional importance of K and V in receiver attention. We thus introduce CACHELINK, which learns a coupled K/V correction through the receiver behavior directly. Across four independently trained sender--receiver pairs and seven evaluation panels, CACHELINK improves the equal-weight mean over all methods for every pair. In matched diagnostics, CACHELINK changes K/V squared error by less than 0.4% while substantially changing receiver attention and next-token behavior. At 32K context, it reduces handoff latency by up to $7.27\times$ relative to receiver re-prefill. Our findings verify that reconstruction fidelity alone is insufficient and that preserving the receiver computation induced by the transported cache is important for effective cross-model KV transport.

---

### Data Portability Revisited: Toward the Human-Centric, AI-Driven Data Ecosystems of Tomorrow

Authors: Mark Fenwick, Michael Fertik, Paulius Jurcys, Timo Minssen
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15503v1

This Article critically examines the contemporary regulatory framework and discourse surrounding data portability in the United States. Using recent regulatory developments in the European Union as an illustration, this Article suggests that although data access and portability are identified as vital issues in multiple policy instruments, in its current iteration, at least, legal conceptions of portability continue to reinforce the interests of service providers and data controller enterprises rather than individual end users. This Article argues that a paradigm shift toward a more human-centric data approach to data governance must occur, under which data would be recognized as fundamental to an individual's identity in a digital age. Therefore, it should be placed in the hands of individuals rather than service providers or data controller enterprises. This Article considers technical and market trends in the European Union that reveal and facilitate such a change. It suggests that regulatory frameworks should better align with these technological and market developments to encourage change-inducing trends among market actors. In short, this Article identifies a transformative approach to data portability that empowers individuals with the freedom and ability to aggregate their data in secure personal spaces under their control or dominion. Such a human-centric perspective on data portability is crucial in building Artificial Intelligence (AI)-powered applications for individual consumers that can pave the way for the human-centric, AI-driven data ecosystems of the future.

---

### Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers

Authors: Ziyi Chen, Yan Zhang, Jianhui Wei, Jianing Yin, Daoan Zhang
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15501v1

Large language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does not explicitly expose decision probabilities. Existing task-specific classifiers require per-task training and offer limited generalization to unseen decision schemas. We propose Large Decision Models (LDMs), repurposing language models to return explicit probabilities over labels specified at run time using one prefill forward pass. We first adapt models to this interface through Diverse Decision Supervision (DDS), covering varied domains, rules and labels. To further narrow the performance gap to a reasoning model, Self-Posed Reasoning Distillation (SPRD) adds tasks generated by a frozen teacher, filters them for answer consistency, and trains on label distributions obtained from repeated teacher reasoning. We evaluate on DecisionVista, pairing new-schema tests with held-out human-labelled sources. Across three base models, the recipe improves accuracy over a step-matched baseline by 1.8 and 1.5 percentage points, respectively, achieving a 182-fold speedup in latency over reasoning rollout on Gemma-4-31B. Reasoning remains stronger on the new-schema test, motivating a confidence router for uncertain decisions. On development sets, routing recovers a median 92% of reasoning's accuracy advantage while generating 27-58% of its tokens. Code is available at https://github.com/JianhuiWei7/LDM.

---

### The Imperishable Record, Forgiveness, and the Future of Criminal Justice

Authors: Mark Fenwick, Paulius Jurcys, Sebastian Porsdam Mann
Published: 2026-10-11
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2610.15499v1

Digital technologies can preserve records of wrongdoing indefinitely, and AI can give those records continuing influence over a person's future. We describe this condition as the eternal data present and argue that it threatens the possibility of forgiveness. In criminal justice, formal punishment has an end, whereas the harms caused by the continued use of criminal records may not. Drawing on Hegel's account of the "hard heart" and Arendt's account of the irreversibility of action, we distinguish two dangers that digital systems can combine. People may be permanently identified with what they have done, and acts that cannot be undone may continue to determine what happens to them. We propose a right to remain unfinished, supported by rights to limits on the weight given to older records, to re-evaluation in light of personal change, to reassessment of inferences that affect their lives, and to time limits on the use of records in specified decisions. These proposals extend the ethics of AI beyond accuracy, transparency, and non-discrimination to address how long past wrongdoing should be allowed to govern a person's life.

---

### Revisited Support Vector Machines: A Unified Joint Optimization Framework with Nyström Approximation for Scalable Adaptive Learning

Authors: Nassou Gongon Benjamin, Noulapeu Ngaffo, Patrick Njionou Sadjang
Published: 2026-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.15498v1

The theoretical elegance of Support Vector Machines (SVMs), grounded in statistical learning theory, establishes them as a reference for robust classification. However, in the era of Big Data, classical SVMs face two major bottlenecks: the prohibitive cubic complexity $\mathcal{O}(N^3)$ of training and the rigidity of static kernels. Traditional methodologies treat kernel selection as a discrete, "brute-force" GridSearch problem, effectively decoupling the learning of data representation from the optimization of the decision boundary. This paper proposes a paradigm shift with a so-called "Revisited SVM", a unified framework that recasts the learning process as a continuous %bi-level joint optimization problem. We derive a novel objective function $J(α, θ)$ that allows for the simultaneous optimization of dual Lagrange multipliers and kernel hyper-parameters. To solve this challenging non-convex problem efficiently, we introduce a hybrid Block Coordinate Ascent (BCA) algorithm, tightly integrated with Nyström-based low-rank approximation, which drastically reduces computational complexity to $\mathcal{O}(Nm)$. Extensive experiments conducted across four heterogeneous domains (Bioinformatics, Finance, Cybersecurity, and Computer Vision) demonstrate that our approach not only matches but often exceeds exhaustive GridSearch accuracy, while delivering training speedups of up to 100x. Notably, on the complex NSL-KDD intrusion detection dataset, our adaptive kernel approach achieves 96.25\% accuracy compared to a mere 50\% for standard baselines, proving its unique ability to model complex non-linear manifolds in high-dimensional spaces. We validate our results using rigorous statistical tests and provide a theoretical convergence analysis of the proposed algorithm.

---

### Concept Representations in Vector Space: Quantifying Sharedness and Idiosyncrasy of Meaning

Authors: Simon Josef Durstewitz, Denis Buehler
Published: 2026-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.15496v1

Concepts are the basic units through which we navigate the world and communicate meaning. But do you and I really mean the same thing when we think or speak about a concept? The present study develops a measurement framework for modeling and analyzing interindividual variation in concept representations through sentence embeddings, dense vector representations mapping entire utterances into a shared geometric space. The framework is developed in a theoretical argument and validated, demonstrated, and subjected to robustness checks in a pre-registered study. Short personal definitions, elicited from $N = 125$ participants, are encoded as sentence embeddings and submitted pairwise to a crossed random effects model yielding two concept-level quantities: sharedness ($S_b$), the expected dissimilarity between two randomly drawn individuals, and idiosyncrasy ($I_b$), the person-specific share of total dyadic variance. Two validity tests support the approach: the embedding space fully recovers concept and domain organization from participant definitions even with the target word excluded, and a parameter-free classifier achieves 0.630 accuracy in a within-participant extensional prediction task against a chance baseline of 0.500 and a consistency ceiling of 0.893. The framework finds theoretically interpretable variation in $S_b$ and establishes $I_b$ as a reliable source of dyadic variance across concepts. Results replicate across three encoders varying in architecture and capacity, providing a reproducible and scalable instrument for the empirical study of meaning variation.

---

### RF Fingerprinting of DSP Implementations using Machine Learning: An Over-the-Air Case Study

Authors: Stefan Scholl
Published: 2026-10-11
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2610.15494v1

Radio frequency fingerprinting aims to identify transmitters by exploiting small differences in the emitted signal waveform. Common approaches exploit hardware-dependent imperfections for that purpose. This work instead investigates whether differences between digital signal processing implementations of a transmitter can be identified from their radiated signals. As a practical case study, five different software-based DSP implementations for generating a 2-FSK RTTY communication waveform are considered. In a monitoring receiver, a classifier can identify these DSP implementations using convolutional neural networks that are trained on augmented software-generated signals represented as raw IQ, power spectrum or instantaneous frequency. The trained networks are evaluated on over-the-air recordings obtained using a shortwave transceiver and a software-defined radio receiver. The best neural network combines IQ and the power spectrum representation and achieves an accuracy of up to 90%. The study further examines the influence of the signal SNR and the observation bandwidth on the classification accuracy. The results demonstrate that DSP implementations leave distinguishable characteristics in the transmitted signals and suggest that DSP-dependent fingerprinting can provide complementary information for specific emitter identification systems.

---

### When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization

Authors: Haomiao Qiu, Yining Tang, Hongyi Wan, Changfeng Sun, Ziyue Qiao, Miao Zhang
Published: 2026-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.15492v1

Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing language-model agents to execute them without retrieving or reinjecting skill descriptions at inference time. Yet when new skills are learned continually, whether previously internalized skills remain usable is still poorly understood. We study forgetting in continual skill internalization and uncover a clear hierarchical structure. Early in subsequent training, a model may lose the ability to invoke an old skill from the raw request, while supplying only the correct canonical skill name substantially restores the learned behavior; with further optimization, this conditional execution also degrades. We call these two stages skill-addressing forgetting and skill-execution forgetting. Guided by this finding, we introduce Factorized Skill Memory (FSM), which separates continual skill memory into a plastic Address Memory and a stable Execution Memory. At each stage, FSM trains a new LoRA executor using only current-stage data, freezes it after acquisition, and appends it to Execution Memory; in parallel, Address Memory incrementally learns to map current requests to executors without replaying historical requests or execution trajectories. At inference time, Address Memory selects one executor from the raw request, and only that frozen executor performs a single language-model generation. On a five-stage benchmark built from 100 TaskBench skills, FSM achieves 65.95% mean exact match and 93.38% addressing accuracy across two task orders, improving over the strongest replay-free parameter-isolation baseline by 14.3 percentage points while remaining within 1.9 points of Replay, which retains historical training examples.

---