# Research Papers — 2026-10 · bundle page 142 of 156 > Full-text markdown of papers #7051–7100 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/142 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/141.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/143.md) ### Any-scale Object Detection using Arbitrary-scaled Images Authors: Kazutoshi Akita, Norimichi Ukita Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.04346v1 This paper proposes any-scale object detection using arbitrary-scale super-resolution for continuously rescaling object images, while general multi-scale object detection uses discretely rescaled appearance representations. However, a naive usage of super-resolution produces many false-positive detections if many super-resolution images are independently fed into an object detector. Our method suppresses these false positives by predicting scale proposal maps, each of which represents a set of pixels appropriate for each super-resolution scale. --- ### System One Models for Wireless Decision-Making:Applications and Performance Evaluation Authors: Masoud Rahimi, S. M. Matin Alemohammad, Hamid Behroozi, Mahdi Nouri Published: 2026-10-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2610.04345v1 Many wireless control tasks require repeated selection of a single action from a finite feasible set under stringent latency and reliability constraints. While large language models (LLMs) have recently emerged as general-purpose decision engines, their autoregressive generation mechanism is not naturally aligned with such bounded control problems. This paper investigates System-One models, which directly learn probability distributions over explicitly defined decision spaces, as a lightweight alternative for wireless decision-making. We formalize their decision structure and learning objective, identify their applicability across physical-layer control, radio resource management, mobility, network slicing, and network operations, and evaluate their practical behavior through representative wireless case studies. Using Jev as a System-One implementation, we benchmark decision quality and client-observed latency against generative LLMs and conventional baselines. In receive-antenna selection, Jev delivers up to an 8.5x reduction in median response latency relative to the evaluated LLMs, although this gain comes with a loss in decision quality compared with stronger task-specific alternatives. More notably, in intent-conditioned RAN slicing, Jev achieves utility comparable to the evaluated LLMs while providing more than a 3.5x reduction in median response latency. Complementary evidence from edge-service orchestration further shows that faster decisions do not necessarily translate into lower end-to-end service latency. These results expose a fundamental quality/latency tradeoff and position System-One models not as replacements for numerical optimization, but as a promising decision interface for latency-sensitive, bounded, and intent-driven wireless control. --- ### Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry Authors: Qi Yu, Ruizhong Qiu, Zhichen Zeng, Xuying Ning, Yanjun Zhao, Dongqi Fu, Yinglong Xia, Hong Li, Hanghang Tong Published: 2026-10-03 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.04344v1 Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, group-based RLVR methods, such as GRPO, assign a uniform advantage to all tokens within rollouts of the same outcome. While existing works refine credit assignment of GRPO based on local signals such as token locations or entropy, they often fail to capture the global semantic novelty of a reasoning behavior relative to the current policy. In this work, we propose a hierarchical credit assignment approach for group-based RLVR methods, called HarA, which identifies and encourages semantically novel reasoning behaviors during RLVR. HarA represents each sampled rollout as a distribution over the hidden states and locations of tokens, and computes the Fused Gromov-Wasserstein (FGW) barycenters of all rollouts with the same outcome, capturing the internal reasoning patterns in the latent space under the current policy. The semantic novelty of a reasoning element can then be measured by its contribution to the FGW distance between the current rollout and the barycenter. While solving the FGW formulation is expensive, we introduce an anchor-guided linearization that turns it into a Wasserstein formulation solvable via the Sinkhorn algorithm efficiently. By reweighing token-level advantage of group-based RLVR methods based on the novelty signals, HarA highlights novel reasoning behaviors at flexible granularities to encourage fine-grained LLM exploration. Extensive experiments across three group-based RLVR methods show that our plug-and-play method effectively enhances the exploration of LLMs, outperforming existing methods across diverse reasoning benchmarks. --- ### A KKL Observer Perspective on Reservoir Computing Authors: Anastasia Bizyaeva, Fernando Castaños, Jaime A. Moreno Published: 2026-10-03 Categories: eess.SY, cs.LG, math.DS, math.OC arXiv: https://arxiv.org/abs/2610.04343v1 Reservoir computing (RC) is a machine learning technique for data-driven modeling of dynamics for forecasting and control, primarily studied in computer science and physics literature with promising applications in neural network learning, physical computing, and neuroscience. Why reservoirs learn and how to choose good reservoir architectures are considered important open questions. We show that the RC problem is mathematically an extension of a classic problem in systems and control theory, the Kazantzis-Kravaris-Luenberger (KKL) observer design problem. As a consequence, many of the questions considered open for RC stand to benefit from a large body of theory in the mature KKL literature, non-exhaustively including on questions of embedding, transverse stability, local and global uniqueness guarantees, and effective data-driven solution constructions. Elaborating on this connection, we show that the surprising forecasting ability of reservoirs is in fact a direct consequence of the well-known observer internal model principle, derive an upper bound on the prediction error over a fixed forecast horizon, and provide a partial explanation for why linear readout training in RC works reasonably well. This work illustrates how classical ideas from systems and control can provide strong theoretical backing and open new questions for modern machine learning methods. --- ### Asynchronous Tracking, Optical Communication and 3D Motion Capture using Event-based Sensors Authors: Ziwei Wang, Angus Apps, Holly Battisson, Iain Guilliard, Timothy Molloy, Robert Mahony Published: 2026-10-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.04342v1 Inter-robot communication is a key enabling technology in cooperative robotics applications. While wireless communication is ubiquitous, simple, and effective, it has inherent limitations: the receiving robot cannot easily localise the source of an incoming signal, clock synchronisation is challenging, and signals are broadcast to all nearby devices rather than targeted recipients. Optical communication provides a complementary channel that is inherently directional and spatially localised, directly addressing these limitations. Event cameras are bio-inspired dynamic vision sensors that respond to changes in image intensity with high temporal resolution, high dynamic range, and low latency, making them well-suited as receivers for high-rate optical communication in cooperative robotic systems. In this paper, we propose the Asynchronous Tracking and Optical Communication (ATOC) system, which integrates LED smart-beacon modulation, event-based detection, optical tracking, and event-data demodulation in a single pipeline. By simultaneously tracking and demodulating multiple LED smart beacons, ATOC transforms a conventional visual marker into a robust communication channel suitable for a wide range of high-impact robotics applications. We validate ATOC in a suite of laboratory studies and two 'applications': a smart-city demonstration and a 3D motion-capture system. --- ### ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine Authors: Jinhyuk Choi Published: 2026-10-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04339v1 ShadowMiner v1 is a system that automatically discovers research problems and generates hypotheses from AI papers. It is a nine-stage pipeline. It structures documents into a knowledge graph and finds graph gaps in it - structural blind spots in research. These graph gaps are included in the LLM generation prompt. Each generated hypothesis is then verified by checking whether it is already covered by existing research, scoring its quality, and checking that the facts it relies on are accurately drawn from its sources. This report does not propose a new generation or evaluation technique. It describes our experience of implementing and applying ideas from prior work, and measuring whether each one actually contributed. --- ### S$^3$N: A Spherical Spiral Scanning Network for Weather Forecasting Authors: Fan Yan, Chen Hui, Weisi Lin, Haiqi Zhu, Feng Jiang, Sun-Yuan Kung, Wei Zhang Published: 2026-10-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.04338v1 Machine learning-based weather prediction (MLWP) has achieved strong performance in global weather forecasting. Recent Hierarchical Equal Area isoLatitude Pixelation (HEALPix)-based methods use the HEALPix (HP) grid to avoid area distortion near the poles of conventional latitude-longitude (LL) grids. However, existing HP-based approaches often use pointwise mapping methods and process HP pixels within separate base faces or local windows. Consequently, the mapping may introduce reconstruction errors and cross-face communication depends on handcrafted boundary handling or shifted windows. We propose the Spherical Spiral Scanning Network (S$^3$N) to address both limitations. First, L2Proj provides a bidirectional method for mapping atmospheric fields between the LL and HP grids through an $L^2$ projection of their continuous finite-element representations. Second, the Attention-Guided Quad-Spiral State-Space Scanning (AQSS) block uses cross-latitude attention to guide selective state-space updates along four global pole-to-pole spiral paths. This design enables continuous information propagation across HP base-face boundaries without additional boundary-processing mechanisms. Experiments show that S$^3$N achieves better results at 4-, 7-, and 10-day lead times, and exhibits slower error growth in long-range forecasting. --- ### FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration Authors: Haopeng Deng, Shuo He, Dayuan Wang Published: 2026-10-03 Categories: physics.soc-ph, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2610.04337v1 Calibrating microscopic traffic models for digital twins is an expensive black-box optimization problem: tuning car-following and lane-changing parameters requires a full simulation run, affording only a tight budget per recalibration window. Matching raw trajectories yields a rugged objective that sparse surrogates cannot learn, reducing sequential acquisition to near-random probing. We present FLAT, which couples what to optimize with where to sample next. An eight-dimensional behavioral fingerprint smooths the parameter-error landscape, making the objective learnable from a few dozen samples; annealed lower-confidence-bound (LCB) acquisition then spends each remaining run where it most reduces error. The surrogate, interchangeable among a Gaussian process (GP), random forest (RF), or multi-layer-perceptron (MLP) ensemble, plugs into the same LCB loop. Across six heterogeneous real-world scenes, FLAT-GP achieves the lowest scene-averaged behavioral error, winning 6/6 scenes against SPSA, GA, and CMA-ES and 5/6 against TPE under the matched budget. Some baselines need up to 4.4 times more simulations to match. Ablations show objective choice shifts final behavioral error by 81% on average, removing sequential LCB raises the six-scene mean by 20%, and surrogate choice shifts it by at most 4.2%, confirming gains trace to objective geometry and sequential allocation rather than surrogate capacity. --- ### A differentiable Lagrangian-coupled 3D Gaussian Splatting-SPH model for forward simulation and inverse analysis in solid mechanics Authors: Tian Xu, Soroush Atashi, Tianju Xue Published: 2026-10-03 Categories: cs.CV, physics.comp-ph arXiv: https://arxiv.org/abs/2610.04336v1 Recent advances in generative world models have increased interest in digital models that reproduce both the appearance of real objects and their response to physical interaction. Three-dimensional reconstruction techniques, including 3D Gaussian Splatting, capture detailed surface geometry and appearance from images and videos. However, extending these representations beyond plausible animation to mechanically interpretable models for constitutive behavior, boundary conditions, and inverse parameter identification remains less explored. In this work, a differentiable Lagrangian-coupled 3DGS-smoothed particle hydrodynamics (SPH) model is proposed for forward simulation and inverse analysis of deformable solids. The observed object is first reconstructed from multi-view calibrated visual dataset as a 3DGS rendering model. An envelope-based procedure then generates an independent SPH support for the solid-mechanics model, avoiding the direct use of rendering primitives as mechanical particles. A reference-configuration Lagrangian transfer maps SPH deformation to Gaussian positions and covariances, thereby coupling the physical model and the image observation model while preserving a differentiable computational path. The SPH formulation supports linear elastic, hyperelastic, and Kelvin--Voigt viscoelastic responses, together with fixed, free, and Robin-type boundary conditions. Numerical studies validate the SPH response against finite-element results, assess accuracy and efficiency against a conventional model using Gaussian centers as surface SPH particles, and demonstrate forward simulations on beam, bridge, and liver-shaped examples. Inverse analyses further estimate constitutive and boundary parameters from rendered deformation observations, including noisy cases, demonstrating the feasibility of the proposed model for mechanics-based parameter identification from image data. --- ### Synthetic-to-Real ViT-Based Pose Estimation of a Noncooperative UAV Authors: Krishnanujam Srinivas, Hanish Acharla, Brij Agrawal, Leonardo Herrera Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.04335v1 Remote pose estimation of noncooperative Unmanned Aerial Vehicles (UAVs) from imagery is critical, as they cannot be influenced or instrumented in advance. Deep-learning-based approaches offer a promising solution; however, their development is constrained by the cost and difficulty of acquiring large-scale real-world datasets with accurate pose labels. Synthetic imagery provides an alternative, but models trained on synthetic data must overcome the synthetic-to-real domain gap to generalize to real-world imagery. This work investigates the inherent synthetic-to-real generalization capability of a Vision Transformer (ViT)-based model for monocular UAV pose estimation. The proposed approach employs a self-supervised DINOv2 backbone and is trained exclusively on labeled synthetic imagery while being evaluated on labeled real-world imagery. Pose ambiguity-aware strategies are incorporated during training and inference to address ambiguities arising from the projection of a three-dimensional target onto a two-dimensional image plane and from target symmetries. An $α$-$β$ filter is further integrated during inference to improve pose estimations. To assess the model under operational requirements, it is evaluated in terms of Mean Angular Error (MAE) and inference time, both before and after filtering, using a real-world dataset containing 77,077 labeled UAV images. Before filtering, the model achieves an MAE of $19.18^{\circ}$ and an inference time of $13.25$ ms, whereas after filtering, these values are $8.74^{\circ}$ and $13.42$ ms, respectively. --- ### Factorized Delayed Streams Modeling for LLM-based Streaming ASR Authors: Tatsunari Takagi, Kai Washizaki, Atsushi Kojima, Lianbo Liu, Koki Nikaido, Yui Sudo Published: 2026-10-03 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2610.04333v1 Delayed Streams Modeling (DSM) enables LLM-based streaming automatic speech recognition (ASR) by aligning acoustic and text streams on a common timeline. DSM adds the padding token <p> and the word-start token <w> to the LLM vocabulary and predicts them together with normal text tokens using the same softmax. We first show that <w> can be removed while maintaining competitive recognition performance. Based on this result, we propose Factorized DSM (F-DSM), which separates the waiting probability for <p> from the distribution over the original LLM vocabulary. This factorization removes ASR-specific tokens from the text prediction space and allows the large-vocabulary softmax to be skipped on waiting steps. Experiments on the Corpus of Spontaneous Japanese and LibriSpeech show that F-DSM achieves better recognition performance than DSM. It also greatly reduces GPU memory use while maintaining similar training throughput, provides a small inference speed improvement through softmax skipping, and reduces the degradation in text-only perplexity observed with DSM. --- ### Suppressing Pressure, Amplifying Evidence: Self-Guided Attention Steering to Mitigate Sycophancy and Stubbornness Authors: Yinghao He, Mengyu Xu, Haixiang Sun, Donghan Li, Yibo Wang, Lixu Wang, Kezhen Chen, Chi Li, Chunwei Liu, Bharat Bhargava, Chongyang Gao Published: 2026-10-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04329v1 Reliable language models should resist unsupported user pressure while effectively using objective contextual information. However, models may exhibit sycophancy by yielding to unsupported user pressure or contextual stubbornness by failing to update their answers when relevant contextual information warrants revision. Evaluating interventions for these failures separately can obscure whether mitigating one failure exacerbates the other. To assess this trade-off, we introduce CoPE-Bench with six conditions per question: a neutral baseline, correct or incorrect user pressure, contextual information consistent with or conflicting with the neutral answer, and a joint condition combining incorrect claims with conflicting contextual information. To regulate the influence of user pressure and contextual information, we propose SPAE (Suppressing Pressure, Amplifying Evidence), a training-free framework that uses the model's own judgments to identify relevant tokens, suppressing user pressure and amplifying contextual information through token-level attention steering. On average across five backbones, SPAE reduces pressure following by 18.8 percentage points and increases joint-condition updating by 5.5 percentage points relative to the strongest baseline in the main comparison. In two-turn dialogue, it improves joint-condition updating by an average of 13.2 percentage points over the strongest prompting baseline. The source data and codes can be found at https://github.com/03Grant/sycophancy-and-stubbornness. --- ### Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures Authors: Junbo Wang, Lidong Lu, Zhuoqun Li, Guiping Jiang, Xiangyu Wu, Tinghai Zhang, Tong Lu Published: 2026-10-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04328v1 Correction-based offline preference pipelines commonly treat model failures only as rejected responses under the original prompt. This supervision is incomplete for boundary failures: responses that violate the given instruction yet coherently satisfy a nearby intent or constraint setting. We introduce Bidirectional Preference Synthesis (BPS), a data-construction method for standard Direct Preference Optimization (DPO) that makes this missing prompt dependence explicit. For each validated boundary failure, BPS keeps the conventional forward pair under the original prompt and adds a reverse pair under a synthesized achieved prompt, so the same response is rejected where it is wrong and chosen where it is right, without changing the DPO objective, training a reward model, or requiring online sampling. On Qwen3-4B-Instruct-2507, BPS preserves original-side pairwise ranking while raising achieved-side ranking accuracy from 6.8% to 62.3% on held-out crossed anchors, with a similar shift under a Kimi-K2.6 cross-teacher probe. A blind human audit supports the intended reverse preference direction, and downstream evaluations show the clearest separation from Forward-DPO in multilingual multi-turn instruction following, with consistent capability-retention patterns on agentic, tool-use, and code checks. --- ### When Satellite and Street Views Disagree: Cross-View Complementarity in Disaster Damage Assessment Authors: Yifan Yang, Lei Zou Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.04327v2 Satellite and street-view imagery see different parts of a damaged building: roofs from above, facades and debris from the ground. Average accuracy hides whether fusion methods use this complementary evidence. We study the conflict cases, the samples on which independently trained single-view models disagree, as a diagnostic subset. On paired collections from the 2025 Eaton wildfire and Hurricanes Ian and Milton, conflicts make up 9.6-33.2% of the test data. Fusion improves conflict accuracy over either view, yet an oracle that selects the correct single view per conflict remains 0.19-0.32 above the best evaluated fusion method. A linear fusion gate over building-visibility features, calibrated confidences, and disagreement recovers part of this headroom where ground photographs are aimed at the building: on Eaton it beats end-to-end fusion by +0.072 conflict accuracy p < 10^-4 and calibrated averaging by +0.051 p = 0.0001; on the panoramic hurricane datasets it is indistinguishable from end-to-end fusion. Cropping panoramas toward the building raises the conflict gain of fusion, whereas random crops of the same size do not. The spatial density of conflicts, computed without labels, correlates with tile-level wildfire damage Spearman r = 0.615, 25 tiles. Conflict cases thus show how much complementary evidence fusion uses, which view it carries under each hazard and capture setting, and where current methods fall short. --- ### LyapuFlow: Controlling Generative Flows with Lyapunov Feedback for Inverse Problems Authors: Minseon Gwak, Hans Hao-Hsun Hsu, Danielle C. Maddix, N. Benjamin Erichson Published: 2026-10-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.04326v1 Pretrained flow models are now widely used as generative priors in science and vision, where inference-time guidance enables test-time constraints without retraining. Existing methods use projection, posterior sampling, or iterative optimization of the generative trajectory. We propose LyapuFlow, an alternative based on Lyapunov feedback control. At each sampling step, LyapuFlow predicts the terminal sample towards which the current flow is evolving, and evaluates the constraint violation on this prediction. Then, we compute the minimum-norm control that satisfies a prescribed Lyapunov decrease condition. The resulting control remains inactive when the uncontrolled dynamics already reduce the constraint violation at the prescribed rate. Otherwise, it provides a corrective update within a feedback trust region that prevents the control from dominating the pretrained dynamics. We demonstrate LyapuFlow in both data and latent spaces, outperforming alternatives spanning different mechanisms for test-time constraint enforcement in scientific machine learning and image inverse problems. --- ### GrayShield: Bit-Level Sanitization for Transformer Model Supply-Chain Security Authors: Armstrong Foundjem, Tsung-Hsien Chuang, Foutse Khomh, Mohamed Amine Merzouk Published: 2026-10-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.04319v1 Transformer models such as BERT and Vision Transformer~(ViT) achieve strong performance via densely parameterized attention backbones. However, the least significant bits~(LSBs) of their 32-bit floating-point weights can be abused as covert channels to conceal malicious payloads, posing a serious threat to the AI model supply chain. We propose \GS (\GSabbr), a lightweight, post-training, zero-data sanitization method that completely replaces the declared mantissa-LSB channel with a Gray-code-guided low-transition sequence. Complete payload-independent overwrite, whether keyed or public, makes the sanitized target bits independent of the embedded payload and gives that declared channel zero capacity. Gray coding supplies overwrite structure, while a keyed per-tensor phase supplies pattern diversity. Benchmarked against seven post-training defenses on four Transformer model presets and two real-world malware payloads, \GSabbr maintains sub-$1\%$ accuracy impact and achieves $49.96\pm0.66$ percentage-point Recovery Reduction (RR) under five implemented attacker variants. Because pre-defense recovery is effectively $100\%$, RR near 50 percentage points corresponds to post-sanitization bit accuracy at binary chance. Its main empirical advantage is stable near-chance sanitization with substantially smaller weight-distribution shift than the evaluated near-chance baselines PatternMask (PM) and Post-Training Quantization (PTQ). --- ### Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency Authors: Sixun Dong, Wei Li, Andong Deng, Qi Qian, Victor Zhu, Zhengping Ji, Chen Chen Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.04318v1 Efficient long-video understanding with vision-language models (VLMs) is often framed as selecting informative frames or visual tokens at a fixed native resolution. We show that per-frame resolution can instead be traded for denser temporal coverage, while front-end decoding latency depends on the size of the candidate pool rather than the final token budget. An empirical study across multiple VLMs and long-video benchmarks yields three findings: dense low-resolution sampling outperforms sparse native-resolution sampling at matched token budgets; resolution-sensitive tasks benefit from selected high-resolution frames; and front-end decoding dominates wall time for hour-long videos. Motivated by these findings, we introduce LoHi, a training-free, single-pass framework that combines a dense low-resolution video stream with sparse high-resolution image frames through the VLM's native video and image pathways. LoHi-Anchor selects high-resolution frames using codec I-frame metadata, while LoHi-SemDiv uses query relevance and visual diversity over CLIP features. Across three long-video benchmarks, LoHi improves average accuracy by 10.6 percentage points over the native-resolution baseline at a matched token budget and by 5.2 percentage points over the strongest prior efficiency method. It also reduces front-end decoding latency by up to 7x on hour-long videos. Project page: https://sixundong.com/projects/lohi --- ### From Latent Space to Jacobian Space: Measuring, Evading, and Training Against Safety-Content Accessibility Authors: Mohammad Mosafer Published: 2026-10-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04316v1 Output-only safety monitoring sees only the end of a model's computation, yet the model computes its answer before emitting it: what it is internally poised to say is safety-critical. Jacobian-space (J-space) readouts, linear maps from hidden states to the output vocabulary via the model's input-output Jacobian, have been proposed as a window on behaviorally accessible internal content, and a first safety protocol (JADR) showed that danger recognition is readable there. What remains unknown is how this accessible content relates to the latent-space safety geometry studied by representation engineering, and how safety training shapes it. We introduce two quantitative bridges: (i) a transport-amplification profile $A_\ell$, measuring how strongly a latent safety direction is carried toward output space by each layer's Jacobian, and (ii) a paired base-vs-tuned protocol that attributes accessibility to training provenance. Across four small model pairs (135M to 1.5B, three lens-fit seeds), tuned checkpoints concentrate recognition in upper-middle layers, and at 0.5B DPO installs refusal while J-space recognition drops to chance: training can widen the accessibility gap exactly where behavioral safety looks best. A deployment audit closes the loop: monitor-aware GCG-style suffixes suppress the prompt-side monitor at zero behavioral cost at every scale; only a learned monitor rung resists its own adaptive re-attack; the training-time defense fails its re-attack at every penalty weight; steering shows the amplification profile is descriptive, not causal; and continuous-prefix optimization fails where discrete search succeeds. Safety monitoring, training, and evaluation must operate on accessibility itself, not on outputs alone. --- ### MOIRA: Mass-Oriented Indexing with Ragged Attention for Long-Context Decoding Authors: Dich Nhat Minh Nguyen, Tran Dang Duong Nguyen Published: 2026-10-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04313v1 Long-context decoding is limited by memory bandwidth, because every output token reads the KV cache of every layer. Sparse decoding reduces this cost by reading only part of the KV cache. We observe that the number of pages a query needs varies widely across KV heads, layers and steps. Fixed budgets are simple, but they are sized for demanding cases and tuned per workload; adaptive budgets follow this variation more flexibly, but existing designs pay for it with extra selection cost or training. At the kernel level, FlashAttention-3 (FA3) and FlashInfer are designed for rows of similar length: with page lists whose length differs per KV head, they either pad the lists (forfeiting much of the sparse saving), leave thread blocks unbalanced, or rely on a host-side plan that runs outside the CUDA graph. We propose MOIRA, a training-free sparse decode path in vLLM whose budget adapts per KV head and per layer. For every request, layer, KV head and step, a coverage rule keeps the smallest set of pages whose estimated attention mass reaches a fraction $γ$. A new kernel, self-planning attention, lets each thread block derive its own share of the work from the list lengths, so the whole decode step stays inside the CUDA graph. On an H200, at RULER's 128k context, MOIRA with $γ=0.99$ matches dense accuracy while reading about 30% of the pages and reduces the time per output token (TPOT) by 2.2-2.5$\times$ relative to dense FA3; with $γ=0.98$ it reduces TPOT by 2.7$\times$ and stays within the noise of dense. Under high serving load it raises throughput by up to 51%. These results suggest that a budget adapted per head and layer, paired with a kernel that keeps such budgets inside the CUDA graph, makes sparse decoding both flexible and fast. --- ### Modeling Deletion Requests in Machine Unlearning Authors: Christian Cianfarani, Aloni Cohen Published: 2026-10-03 Categories: cs.LG, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2610.04310v1 Machine unlearning is seen as a promising approach to enable users to exercise the "right to erasure" in the context of AI models. We ask how users might influence the behavior of models when exercising this right. We define two types of behaviors that users might adopt when requesting the deletion of their data: adaptivity and collectivity. Drawing connections between the goals of users in this context and results in stochastic optimization, we demonstrate theoretical gaps between the potential effects of groups of users who do and do not display these behaviors. We then show how techniques from data valuation might be used to design deletion requesters that can significantly alter model behavior in realistic settings. In experiments on computer vision tasks, we demonstrate the differential effects of different models of user behavior and attempt to isolate the impacts of adaptivity and collectivity. --- ### ML-OPF-Bench: Benchmarking Machine Learning for Optimal Power Flow Authors: Xinyi Liu, Xuan He, Danny H. K. Tsang, Yize Chen Published: 2026-10-03 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2610.04307v1 Machine Learning (ML) methods promise a fast solution process for Optimal Power Flow (OPF). While inconsistent test cases, implementations, and evaluation metrics across existing studies make it challenging to determine which algorithmic advances are most critical for real-world deployment. To this end, we propose ML-OPF-Bench, a unified benchmark for AC- and DC-OPF that evaluates representative ML algorithms under a consistent pipeline, stress-tests them across system sizes, distribution shifts, and resource budgets, and ranks them with a multi-objective framework. We find that prediction accuracy alone is not a reliable indicator of operational feasibility. Under heavily loaded, congested conditions, even the strongest in-distribution performers lose their advantage, while feasibility is maintained largely by post-processing that enforces the target constraints rather than by the underlying pure ML predictor. Data scaling shows that prediction accuracy and constraint violations follow different trajectories, whereas compute scaling shows that returns diminish and that larger models do not consistently perform better. These results expose critical trade-offs among ML methods' speed, accuracy, and feasibility, and offer practical guidance for future ML-OPF design. We open-source the benchmark as an extensible Python package for integrating new learning-based OPF algorithms and evaluating them under the same standard as the existing baselines. --- ### Evaluating Modeling Approaches for Experience-Level Classification in Job Description Authors: Celia Liang, Eddie Wu, Shiqi Wang, Yonah You Published: 2026-10-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.04304v1 This paper investigates the task of predicting job experience levels in recruitment texts, aiming to automatically identify the qualifications required for positions. Unlike traditional text classification, recruitment texts typically possess explicit internal structures, with different paragraphs playing disproportionate roles in conveying experience clues. To address this, we propose a structure-aware Section-Aware BERT approach that segments and encodes key paragraphs (titles, responsibilities, requirements) for integrated modeling, building upon rule-based systems and classical baselines TF-IDF. Simultaneously, we evaluate large language models under both few-shot and fine-tuning settings on the same dataset to compare the capability boundaries of different modeling paradigms. Experimental results demonstrate that explicitly leveraging text structure significantly improves experience level prediction performance, particularly in scenarios with ambiguous job titles. Further error analysis reveals systemic challenges in this task, including confusion between Entry and Senior levels and the blurred boundaries of Mid-level positions. This research provides an effective modeling approach and analytical framework for understanding structured recruitment texts. --- ### What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle Authors: Peilin Wang, Feng Shiyang, Hongfu Gao, Cencheng Zhao, Di Yuan, Hui Chen, Guiguang Ding Published: 2026-10-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.04303v1 Recursive computation repeatedly compresses or reuses intermediate states, creating a simple tension: information that must remain useful across longer recursive paths is also exposed to more opportunities for loss before reaching the final prediction. Existing reconstruction or local-prediction objectives provide tractable supervision, but do not ensure that the retained information remains sufficient for subsequent recursive computation. We identify local predictive sufficiency with recursive predictive closure: controlling local predictive deficiencies at individual interfaces controls the resulting discrepancy at the root. We then turn this principle into a tractable training procedure. Starting from a variational characterization, we derive finite predictive tests and an empirical predictive deficiency that measures predictive value retained across compression. Its predictive sensitivities define margin-relaxed half-space constraints on parameter updates, and we project the host optimizer's proposed update onto their intersection only when predictive preservation would otherwise be violated. Across temporal graphs, language memory, vision-language-action control, and recursive self-improvement, the method matches or improves the corresponding host models under matched compression budgets, with larger gains under heavier recursive or memory demands, while better preserving predictive information across successive transformations. Crucially, the same task-agnostic predictive-preservation principle is instantiated across all four settings through host-compatible interventions while keeping the endpoint task, backbone, and evaluation protocol fixed. These results establish predictive preservation at recursive interfaces as a general training principle for recursive compression. --- ### EnvDreamer: Large-Scale Multimodal-to-Environment Generation for Embodied AI Authors: Kabir Swain, Sijie Han, Antonio Torralba Published: 2026-10-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04301v1 Large datasets and high capacity models have accelerated progress in vision and language. This work introduces a platform aimed at bringing comparable gains to embodied learning, world models, and robotics. We present EnvDreamer, a framework that uses large language and vision language models to generate Unreal Engine 5 environments for embodied AI and robot training. EnvDreamer enables sampling of large, diverse, interactive, customizable, and validator passed virtual environments for training and evaluation across navigation, interaction, and manipulation. We illustrate the platform with a large set of generated scenes and simple baselines. Policies trained on EnvDreamer generated environments, without explicit mapping or human task supervision, achieve competitive results on multiple embodied benchmarks spanning navigation, rearrangement, and manipulation. EnvDreamer also supports image-conditioned reconstruction for real-to-sim studies. Finally, we release EnvDreamer-20k, a dataset of 20,000 validator passed environments with task programs, scene graphs, trajectories, and metadata to support reproducible benchmarking. --- ### A Geometric-Transformation Feature-Adaptive Manifold Restoration Method for Open-Vocabulary Semantic Segmentation of Remote Sensing Images Authors: Jianzheng Wang, Huan Ni, Xiaonan Niu, Danfeng Hong, Haiyan Guan Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.04300v1 The semantic information of objects in remote sensing images is typically invariant to geometric transformations from the dihedral group D4. However, SAM3-based open-vocabulary semantic segmentation (OVSS) methods often exhibit inconsistent responses to different geometric transformations. To exploit this property and improve the stability of OVSS for remote sensing images, we propose a feature-adaptive manifold repair method based on dihedral-group geometric transformations. First, we introduce multi-scale harmonic-guided D4 view selection (MH-D4VS) to select complementary candidate views from a set of geometrically transformed views. Next, we propose original-view-anchored adaptive manifold repair (OAMR), which uses the original view as an anchor and reliable cross-view information to selectively repair locally unreliable visual features. Finally, we develop pixel decoder test-time adaptation (PD-TTA) for SAM3, which fine-tunes only the parameters of the GroupNorm layers online during inference, thereby enhancing the model's ability to adapt to sample-level distribution shifts. Experimental results show that the proposed method achieves an average mIoU of 55.6% across eight remote sensing semantic segmentation benchmarks and delivers consistent performance improvements under different SAM3-based inference frameworks. --- ### Questioning the Questions: Sustaining Self-Evolution in Reasoning Models Authors: Jinyuan Li, Chengsong Huang, Langlin Huang, Donghong Cai, Shiping Gao, Yuyi Yang, Jiaxin Huang Published: 2026-10-03 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04299v2 Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we investigate why performance deteriorates over successive rounds and how to sustain self-evolution. Our analysis identifies two recurring quality problems in self-generated questions: invalid questions and repeated variants of the same mathematical questions. First, invalid questions become more prevalent across rounds, and answer-consistency filtering further increases their proportion in training data. Second, existing question diversity controls based on lexical similarity can miss mathematically equivalent questions expressed in different ways, which leads to question diversity collapse in later training rounds. Building on these findings, we introduce R-Quest, which uses question validity and novelty feedback to guide self-evolution. We first train the solver to recognize and reject invalid questions, then use its judgments to guide questioner rewards and filter solver training data. To avoid question repetition, we use a frozen base model to compare sampled question pairs and provide novelty feedback. Empirically, our method consistently achieves the highest average performance on 12 benchmarks in mathematical reasoning, general-domain reasoning, and code generation across two model families. Additionally, R-Quest maintains stable performance gains over ten rounds of self-evolution, peaking in the final round and outperforming R-Zero by 17.32 points. --- ### Latent Safety Filters: When a Lossy Encoder Admits a Transferable Certificate Authors: Johannes Mootz, Zahra Nili Ahmadabadi, Reza Akhavian Published: 2026-10-03 Categories: eess.SY, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2610.04297v1 Latent safety filters certify safety on a learned low-dimensional representation of the state, enabling constraints that resist analytic description. Because the encoder is lossy, a filter can report safe while the physical state is unsafe, with no detectable model error. Existing transfer conditions leave the effect of discarded safety information implicit. We ask when a lossy encoder admits a safety certificate that transfers to the physical system, and show the answer is governed by the detectability of the discarded safety-relevant dynamics. We construct a system whose latent model is exact and whose latent signals always report safe, while the physical state becomes arbitrarily unsafe. For this system no certificate exists and no monitor downstream of the encoder can detect the failure. When the discarded dynamics contract, a latent barrier certifies true safety up to two explicit margins, one for the latent-model error and one for the variation of safety across states the encoder cannot distinguish. In the linear case and under boundedness and non-degeneracy conditions, every calibrated barrier transfers with a finite margin when the safety-relevant subspace is detectable, and none does otherwise. On learned cartpole encoders, the model error does not indicate for which representations the estimated bound is non-vacuous, while the second margin does. --- ### RRM-GPT: A Framework and Vision for Radio Resource Management Foundation Models Authors: Ahmed Aboulfotouh, Akram Bin Sediq, Koosha Pourtahmasi Roshandeh, Omar Mashaal, Ahmad M. Nagib, Jale Sadreddini, Hatem Abou-Zeid Published: 2026-10-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2610.04296v2 Learning-based models for radio resource management (RRM) are typically built for a single function and deployment, so each new setting repeats the development pipeline. RRM decisions, however, share a common structure: each is assembled from interdependent fields, defined by the standard, whose values are selected in view of the network state. We propose RRM-GPT, an autoregressive framework for RRM foundation models that generate these decisions as a language model generates text. An encoder maps heterogeneous network observations into a common token representation, and a decoder emits the decision one field at a time, each conditioned on the network state and the fields already committed. Pretraining on unannotated network logs teaches the model what makes a decision valid and how controllers choose among valid decisions; post-training then adapts it to deployment-specific operator objectives through imitation or reinforcement learning. The framework targets two forms of reuse: a function-specific model reused across deployments, and a model shared across RRM functions that generates their interdependent decisions as one sequence. In a 5G New Radio (NR) case study, we demonstrate that a single model generates complete scheduling grants spanning user selection, timing, link adaptation, resource allocation, and control signaling. The model captures dependencies among grant fields and transfers learned behavior to an unseen scenario without adaptation. --- ### Language-Conditioned Token and Reasoning Efficiency in Large Language Models: A Paired Cross-Lingual Study Protocol Authors: Genliang Zhu, Chu Wang Published: 2026-10-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04295v1 Large language models incur language-dependent representation and inference costs, but existing comparisons often conflate input language, assigned observable-trace language, and answer realization. We specify a prospective paired study that separates these interfaces while holding the semantic item, checkpoint, and answer oracle fixed. The initial design instantiates 240 exactly scored items rendered from templates in English and seven non-English languages, three distinct-lineage open-weight checkpoints, three trace-token budgets, 22 input- and trace-language conditions, a fixed answer reserve, and a separately counted delimiter: 47,520 initial core runs before prospective sample-size selection. RQ1-RQ3 estimate input and trace effects by intention-to-treat with failure-inclusive terminal accounting and test answer realization by cloning a sealed prefix and runtime-native KV state into eight crossed branches. Pre-freeze independent language review, fixed-form ASCII selectors, and code/surface/solver agreement constrain the realization test. H1-H5 share one Holm family and a global simultaneous component band. A secondary randomized experiment compares one-long-attempt and complete K-short-attempt policies at equal trace allowance under frozen seeds and oracle-blind aggregation; it is a full-policy contrast because answer capacity differs. Outcomes include exact token spans, correctness, latency, runtime-exposed memory, and qualified same-host operating-system-reported energy over prespecified hardware rails. The protocol separates tokenizer expansion, observable-trace cost, and answer-realization cost without treating visible traces as internal cognition or operating-system estimates as physical cross-device energy. No confirmatory model outcome is reported; result fields remain disabled until the frozen evidence ledger passes independent verification. --- ### LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures Authors: Jiateng Liu, Rushi Wang, Cheng Qian, Xuejun Zhang, Sun Li, Jiayu Liu, Yifan Shen, Xu Cao, Jiarui Yao, Bingxuan Li, Ruhi Sarikaya, Heng Ji Published: 2026-10-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04292v1 LLM-based agents are increasingly capable of generating complex 3D structures, with the potential to reshape how objects are designed and realized in the physical world. Yet, producing elegant geometry is fundamentally different from producing objects that can be built and perform their intended functions. Existing evaluations largely focus on geometric quality while overlooking physical realizability. We introduce LMBuild, a benchmark for evaluating LLM agents on generating buildable and functional structures. LMBuild represents generated objects as assembled structures comprising part decompositions, joints, materials, and sequences. To support reproducible evaluation, we provide a unified framework consisting of: (1) an interactive environment in which agents can use tools to retrieve, create, and place components to construct objects; (2) a curated benchmark that repurposes established CAD datasets and augments them with knowledge from Wikipedia; and (3) a evaluation framework covering structural soundness, functional affordance, design quality, and physical realization. Evaluations across 30 systems reveal several intriguing findings: (a) Soundness and alignment are no longer the primary bottlenecks for frontier closed-source models, while functional affordance and physical operability remain substantially more challenging; (b) stronger models more effectively create new components, whereas weaker models tend to rely on retrieval; and (c) providing functional specifications substantially improves part completeness, kinematics, and physical operability. These results show that generating real-world structures requires deeper reasoning about functional affordances, mechanics, and designing and creating novel components. We expect LMBuild to provide a foundation for measuring progress and incentivizing research toward agents that generate buildable and functional structures. --- ### Local Fisher Information Enables Sparse Causal Discovery Authors: Byeongguk Kang, Donghyeon Lee, Euijong Song, Gunwoong Park Published: 2026-10-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.04291v1 Sparse causal discovery calls for methods that exploit graph structure without estimating high-dimensional densities. We introduce Fisher Information Completion Search (FiCS), a source-first algorithm for additive noise models that uses one local Fisher score for both ordering and parent selection. Under regularity and nonconstant-parent conditions, we prove that a node's local Fisher information equals the noise Fisher information exactly when the conditioning set contains all parents, provided that it contains no descendants. This Fisher parent completion identifies the parent set as the unique minimal Fisher completion. With a maximum conditioning set size $q$ at least the maximum indegree $d$, population FiCS queries marginals of at most $q+1$ variables and recovers the true directed acyclic graph under a positive ordering margin. Bounded conditioning also has a population advantage: reducing $q$ toward $d$ cannot decrease, and can strictly increase, the ordering margin. A growing non-Gaussian family separates local Fisher selection from conditional-variance and leaf-first Fisher ordering. For the regularized kernel Stein estimator, we establish high-dimensional DAG consistency under $q\{1+\log(p/q)\}+\log p=o(n)$, uniform Fisher separation, local approximation, and compatible ridge and parent penalty parameters. Experiments show the strongest gains when $n$ is small relative to $p$, quantify the effect of the conditioning size, and demonstrate competitive reference-graph recovery on three real-data benchmarks. --- ### Scaling of Wireless Foundation Models via Representation Diversity and Multi-Branch Architectures Authors: Ahmed Mohamed, Ahmed Aboulfotouh, Hatem Abou-Zeid Published: 2026-10-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2610.04289v1 Wireless foundation models learn representations from unlabeled radio signals for reuse across downstream tasks. Scaling model capacity is a common strategy for learning richer representations and improving downstream performance. However, its gains are less consistent in wireless self-supervised learning when pretraining data are limited. We investigate objective diversity as an alternative scaling axis: different self-supervised objectives emphasize different signal properties, and combining their representations can preserve more information to enable diverse tasks. We develop a fusion framework that combines frozen representations from independent encoders trained through reconstructive, predictive, and contrastive learning. This provides a reference for the benefits of diversity, but requires the maintenance of multiple encoders. To retain these benefits within the parameter budget of a standard single-objective encoder, we introduce a jointly trained multi-branch architecture with a shared trunk and objective-specific branches. We pretrain on a heterogeneous corpus of spectrogram and channel state information data and evaluate six downstream tasks that span communication, sensing, and positioning. At an equal output embedding dimension, fusion outperforms the evaluated single-objective encoders on all six tasks while using roughly one-third of their parameters. The multi-branch architecture retains much of the fusion benefit within a single-encoder parameter budget. Representation analyses indicate complementary contributions across objectives, with much of the added benefit retained in components orthogonal to the reconstruction representation subspace. These findings support objective diversity as an effective strategy for scaling wireless foundation models. --- ### VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering Authors: Kang Li, Lu He, Sandarsita Guntupalli Published: 2026-10-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04287v1 Enterprise agents should improve from delayed feedback without allowing every correction to rewrite system behavior. We study continual harness learning for corpus-level spreadsheet question answering. Building on FiCo (Find-then-Compute), a static retrieval-and-execution backbone, we introduce VIGIL (Verifier-Informed Gated Improvement Loop). Within a question, VIGIL verifies and repairs diversely prompted Structured Query Language (SQL) candidates. Across episodes, delayed labels update only a contract calibrator and query/result-column selector. The base model, prompts, retriever, and recorded candidate pool remain fixed in the continual-learning protocol. With the gold workbook and expected type supplied, the ungated and dual-gated full-replay variants reach 82.4% and 82.0% forward accuracy over 79 documents, from a 75.8% static baseline. The dual gate has the larger retrospective gain (2.7 versus 2.3 points), and its 6.3-point forward gain has a 95% t-interval of 5.6-6.9. In a separate stricter split that excludes 16 documents and 380 questions from fitting and online promotion, the accuracy-only gate raises mean held-out accuracy across ten final harnesses from 80.3% to 86.7%. Calibrator-only adaptation gains 5.9 points, close to the combined 6.4-point gain. Yet three of 26 gate-approved updates reduce held-out accuracy relative to their incumbents, so replay-buffer non-regression does not imply held-out non-regression. MiMoTable and external-task case studies test within-task verification and reuse the same promote-or-retain discipline. Overall, the results support bounded, auditable harness adaptation while revealing where finite replay gates fail to generalize beyond their promotion buffers. --- ### CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks Authors: Damilola Popoola, Souradeep Bhattacharya, Manimaran Govindarasu Published: 2026-10-03 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.04286v1 Distributed Energy Resource (DER) environments rely on network communication protocols to coordinate control commands, measurements, and device states across edge assets and cloud systems. Edge anomaly detection systems (ADS) monitor this traffic to identify deviations from normal communication behavior, flagging suspicious flows for further investigation. When the ADS flags abnormal network traffic, a single attack label is often insufficient for operational response: the label reports the detector's selected class but does not expose alternative threat interpretations that may warrant investigation. This paper presents Cybersecurity Threat Reasoning with Explainable Artificial Intelligence (CyTReX), an evidence-grounded threat reasoning framework for DER security that transforms network-level anomaly alerts into ranked, analyst-facing threat hypotheses designed to support Security Operations Center (SOC) triage and investigation. CyTReX constrains large language model (LLM) reasoning through a structured evidence packet, defined as a consolidated record of detection outputs, model explanations, and cyber threat intelligence (CTI) context. The evidence packet integrates edge-layer anomaly detection evidence, cloud reasoning layer attack interpretation, Shapley Additive Explanations (SHAP) network-feature attributions, surrogate decision rules, and Model Context Protocol (MCP)-enabled CTI enrichment. This ensures that every ranked hypothesis and attack-tree branch is traceable to explicit evidence rather than free-form LLM inference, and that incomplete or conflicting evidence is communicated rather than suppressed. Evaluation across five configurations shows that additional reasoning components improve hypothesis specificity, evidence traceability, and analytical grounding, with the complete pipeline providing the richest evidence-grounded reasoning context. --- ### Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems Authors: Qi Feng, Gu Wang Published: 2026-10-03 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2610.04285v1 We develop an amortized, grid-free implementation of continuous Langevin dynamics based policy-value iteration for entropy-regularized, infinite-horizon relaxed stochastic control problems. The improvement rate of the exact iteration is a discounted aggregate of relative Fisher information between the policy and the Gibbs law of its Hamiltonian. The associated score residual is the velocity with which the control's Langevin dynamics transport its law. We project this velocity onto a conditional sampler shared across states, instead of one Langevin dynamics per state, and the value dynamics onto a parametric critic, estimating both projections at sampled states to obtain coupled actor--critic flows. The score loss measures the actor's agreement with the current critic, while the policy-evaluation residual measures the critic's agreement with the actor. We also derive gradient and Hessian residuals, including a Feynman--Kac representation for the gradient equation, to control errors not detected by the projected value iteration. An exact decomposition of the HJB residual combines these errors into a policy-suboptimality bound under verification and logarithmic Sobolev assumptions. In the linear-quadratic class, both projections are exact and recover the pointwise iteration, and we provide numerical experiments on general models to demonstrate the coupled actor--critic learning in high-dimensions. --- ### First-Order Steering: Translating Weight Adaptation into Activation Steering Authors: Sri Pranav Kunda, Alexander Kurz, Tomas Dominik, Uri Maoz Published: 2026-10-03 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04283v1 Activation steering exploits interpretable directions in the residual stream to enable inference-time manipulation of model behavior. Composing steering vectors to apply multiple target behaviors simultaneously is important in various fields-including AI alignment and safety-but remains a challenge for existing activation steering methods. In contrast, prior work in model merging shows that target behaviors represented by learned weight adaptations can be combined with high accuracy. A method that translates weight adaptations into activation steering vectors could therefore extend prior work in model merging to generate composable steering vectors that better enable simultaneous inference-time behavioral control. For this, we introduce First-Order Steering, a formulation of activation steering as a first-order approximation of weight update matrices parameterized by a vector of steering strengths, and establish theoretical bounds on the approximation error of first-order steering. We then develop a novel model merging procedure, HeRD-Merging, which minimizes the first-order approximation error terms to enable higher first-order steering accuracy. Together, our method produces steering vectors that control both individual and composed behaviors more accurately than existing activation steering methods. Furthermore, HeRD-Merging matches the performance of conventional model-merging baselines, while producing weight adaptations that admit more accurate first-order steering vectors. --- ### OctMesh: A Unified Octree-Hierarchical Framework for Lossless Triangle Mesh Compression Authors: Shiyu Feng, Xihua Sheng, Lingyu Zhu, Chunyang Fu, Shiqi Wang Published: 2026-10-03 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.04281v1 Lossless triangle mesh compression must preserve both vertex positions and connectivity. Octrees support learned point cloud geometry coding and progressive refinement, but extending them to meshes requires a compatible connectivity representation. Unlike the eight occupancy decisions of a voxel, a parent edge can develop into varied child connections, making edge refinement difficult to model with a compact prediction prior. We propose OctMesh, a learned framework that codes geometry and connectivity on a shared octree hierarchy. Its key observation is that octree pooling produces parents with either one child or two to eight children. Child edges are then grouped by their endpoint parents' types and whether the endpoints share a parent. Each candidate group contains children from just one parent or two connected parents. The resulting four categories define small, fixed-shape prediction tasks: connections uniquely determined by the parent graph are inherited without bits, while three neural predictors estimate probabilities for the remaining candidates. These probabilities guide arithmetic coding of the actual edge symbols. Binarized predictions of within-parent connections provide context for predicting connections between different parents. A graph-aware parent feature extractor combines local geometry, parent connectivity and global shape. The connectivity models use dedicated weights at coarse levels and share weights at fine levels. Residual edges and a finest-level face-selection payload complete the reconstruction. On 256 frames from eight MPEG V-DMC test sequences, OctMesh losslessly recovers the finest-level vertex-coordinate, edge and unoriented face sets at an average of 7.033 bits per face, 12.8% below V-Mesh. The same hierarchical representation supports nine levels of progressive vertex-and-edge refinement. --- ### Dense Neuro-Symbolic Reasoning in a Unified Geometry State Authors: Ruoran Xu, Wending Gao, Haoyu Cheng, Xiaoqiang Kang, Qiufeng Wang Published: 2026-10-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04280v1 Geometry reasoning is naturally stateful: solving a problem repeatedly alternates between structural proposals and exact deductions. We formulate this process as dense neural-symbolic coupling, in which neural guidance and symbolic execution share a typed state and communicate through executable actions at every search step. Neural proposals contribute theorem instances, constructions, and algebraic bridges; the symbolic runtime applies registered rules, propagates exact constraints, and records provenance. A nested controller allocates computation first between neural and symbolic proposal sources and then among admitted actions. We instantiate the framework in OmniGeo, a single solver for plane, analytic, and solid geometry. With Claude Sonnet 4.6, OmniGeo reaches 94.2%, 88.5%, and 89.8% on FormalGeo7K, Conic10K, and SolidFGeo, respectively (90.8% macro average), and solves 21/30 IMO-AG-30 problems. --- ### Do RUL explanations hold up? Faithfulness and stability of attributions on C-MAPSS Authors: Manh Hien Nguyen, Ngoc Thanh Nguyen, Isabella Mendoza Cortes, Tam Khuat, Thanh Pham, Nhat Quang Tran, Ushik Shrestha Khwakhali, Loan Do Published: 2026-10-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.04278v1 Deep remaining-useful-life (RUL) models on NASA C-MAPSS are now routine, and so are heatmaps that colour sensors and timesteps. A heatmap that looks mechanical is not the same as an explanation an engineer can act on. We train three standard architectures - a 1D CNN, an LSTM, and a small Transformer encoder - on the official FD001 and FD003 splits with the piecewise RUL cap of 125 cycles and the official PHM08 asymmetric score. We then attach three attribution maps (Integrated Gradients, occlusion, last-layer attention) and evaluate them with the checks the XAI-for-PdM literature still under-reports: deletion/insertion faithfulness, Spearman stability under sensor-scale noise, agreement across training seeds, and cosine consistency inside RUL bins. Prediction error is a prerequisite, not the claim. The headline is which explanation method moves the RUL output when its top cells are removed, and which map survives a 5% input perturbation. Integrated Gradients and occlusion are similarly faithful on the LSTM; Transformer attention is cheap and temporally smooth but weakly faithful. All three maps are almost unchanged under 5% input noise, yet IG/occlusion agree only moderately across two LSTM seeds - stability to sensor jitter is not the same as stability to retraining. A secondary tabular check on the AI4I 2020 failure dataset shows the same deletion pattern for tree importances. We recommend occlusion or IG for any C-MAPSS-style report that will be read by a maintenance engineer, and we treat raw attention weights as a visualisation only. --- ### Integrated Imputation-Classification for Supervised Learning with Missing Data Authors: Yue Liu, Ben Liang, Ali Tizghadam, Ilijc Albanese Published: 2026-10-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.04273v1 We study supervised classification problems with missing feature values. Existing approaches often decouple imputation from classification, producing imputations that may be plausible but uninformative for prediction. Instead, we propose the Integrated Imputation and Classification Network (IICN), which jointly trains an imputer and an ${(n{+}1)}$-classdiscriminator adversarially with a single class supervised classification objective, where the discriminator learns to distinguish among the $n$ true classes and an additional ``imputed" class. We prove that at the global optimum, the imputer and discriminator together implement marginalization over missing coordinates and yield a Bayes-optimal classifier. We evaluate IICN on FashionMNIST, CIFAR-10, and tabular datasets with naturally occurring missingness. IICN outperforms classical impute-then-classify pipelines and recent generative baselines, showing strong robustness and accuracy in challenging settings. --- ### Rethinking Self-Distillation for Multi-Teacher Capability Merging Authors: Roy Xie, Dan Friedman, Feng Nan, Yukun Huang, Zhichao Xu, Chengjiu Zhang, Jun Xu, Manaal Faruqui, Vivek Rathod, Bhuwan Dhingra Published: 2026-10-03 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.04272v1 Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-model post-training. Recent trends suggest that multi-teacher on-policy distillation (MOPD) outperforms conventional off-policy methods. However, despite the higher inference and environment interaction costs incurred by MOPD, we find that much of its reported accuracy gain is due to certain training design choices and hyperparameter optimization, rather than the algorithm itself. We conduct a controlled self-distillation study across two multi-teacher settings, four models, and eleven benchmarks, comparing off-policy methods, namely supervised fine-tuning (SFT) and soft-label distillation, to hybrid teacher-prefix distillation and MOPD. We found that all four methods achieve \textit{nearly identical} accuracy. However, MOPD uses $14.8$--$23.1\times$ SFT's training GPU-hours. We also revisit four recently published comparisons between on-policy and off-policy distillation and find that the reported on-policy gains shrink substantially when SFT baselines are trained on rejection-sampled teacher trajectories and use independently tuned hyperparameters. As a training-free alternative, we also find that simple weight-merging methods can recover expert capabilities with minutes of CPU merging time, although their accuracy degrades as model size decreases and task interference increases. Overall, our results question recent gains reported due to MOPD and suggest careful tuning of more efficient off-policy baselines as a viable alternative. --- ### Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience Authors: Zixuan Wang, Hao Li, Fengyu Gao, G. Edward Suh, Yi Zeng, Yevgeniy Vorobeychik, Ning Zhang, Chaowei Xiao Published: 2026-10-03 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.04269v1 Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection attacks that can hijack task objectives. Existing safety alignment methods rely on static expert trajectories or preference optimization, limiting their ability to generalize to adaptive attack patterns. In this work, we propose Self-Reflection Fine-Tuning (SRFT), a training framework that enables agents to improve robustness by learning from their own failure experiences under adversarial conditions. Instead of passively imitating expert behaviors, SRFT exposes the agent to compromised trajectories constructed via injected attacks, and leverages an expert model to generate structured self-reflection reasoning that contrasts unsafe and optimal actions. This reflective supervision teaches the agent to identify malicious instructions, reason about their consequences, and maintain alignment with the original user intent. We instantiate this framework in SR-Agent, built on Llama-3.1-8B-Instruct and Qwen3-8B, and evaluate it on both static and adaptive prompt injection benchmarks. Experimental results show that SRFT substantially reduces attack success rates while preserving task performance, and demonstrates strong generalization under adaptive attacks. These findings suggest that learning from failure via self-reflection is a promising direction for building robust and secure LLM agents. Our code is released at https://github.com/Eden-Wang1710/srft-repo. --- ### AI-Enabled Quality Assurance for Multiple-Choice Assessment Items Authors: Steven Moore, Nicholas Diana Published: 2026-10-03 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2610.04267v1 Generating multiple-choice questions is increasingly scalable, but establishing their assessment quality remains difficult. We present a focused narrative review of automated item-writing flaw detection, revision, psychometric screening, and NLP benchmark auditing. Database searches, citation retrieval, and nominated sources yield fourteen research reports reviewed in full text. We distinguish surface checks from content-sensitive judgments and map a 19-criterion rubric to detection methods and reported evidence. High label-level accuracy often coexists with weak positive case detection, while rubric definitions and reference standards vary. Revision evidence is mixed, and the associations reported in prior work do not establish the effects of repair. We propose evaluating quality assurance as a sequence of independently validated decisions, with criterion-specific reporting, calibrated human review, and outcome-based assessment of revisions. --- ### Adaptive Bregman Alternating Projections for Feasible Gromov-Wasserstein Learning Authors: Aoran Zhang, César A. Uribe Published: 2026-10-03 Categories: cs.LG, cs.CG, math.OC arXiv: https://arxiv.org/abs/2610.04264v1 The Gromov-Wasserstein (GW) problem compares structured distributions without requiring a shared feature space or known correspondences, but its nonconvex objective and coupled marginal constraints make computation challenging. Bregman alternating projected gradient (BAPG) uses inexpensive alternating row and column updates, yet its fixed-penalty relaxation leaves a persistent feasibility gap. We propose Adaptive KL-BAPG (A-KL-BAPG), which combines a finite fixed-penalty burn-in with a guarded increasing-penalty phase. At each tail iteration, the method reuses BAPG's alternating updates and backtracks a delayed-power step until a Sinkhorn-inspired projective-diameter safeguard is satisfied. We prove finite termination of the backtracking at each iteration and show that the feasibility gap vanishes asymptotically. We further establish a best-iterate $O(1/\log N)$ bound for the weighted squared corrected residual and, under a support regularity condition, the existence of a stationary accumulation point for the original GW problem. This distinguishes A-KL-BAPG from fixed-penalty BAPG, whose stationarity guarantees are given for the relaxed problem. Experiments show that A-KL-BAPG achieves a favorable balance of accuracy, objective value, feasibility, and stationarity relative to BAPG variants, projection-based methods, and task-specific baselines. For synthetic and real graph alignment problems, it closely matches the accuracy and objective value of fixed-penalty KL-BAPG while reducing the marginal feasibility gap by 62-99% and the projected stationarity residual by 28-98%. Heterogeneous domain adaptation experiments show a similar pattern: A-KL-BAPG maintains comparable target accuracy and objective values while achieving better feasibility and stationarity than fixed-penalty KL-BAPG. --- ### Multimodal Dual-Encoder Retrieval for Automated ICD Coding Authors: Abhinav Bohra, Anuj Bohra Published: 2026-10-03 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2610.04263v1 Accurate International Classification of Diseases (ICD) coding is crucial for large-scale clinical research, documentation, and billing. There are three primary problems with current ICD prediction methods: (1) They are unable to comprehend multimodal patient data because they rely on either structured EHR data or unstructured clinical notes. (2) They also struggle with scalability to a larger amount of ICD codes (9K+ codes in ICD-9), as traditional classifiers need dense output layers and often do not generalize well to long tail rare diseases. (3) They lack transparency for clinical use. To address these challenges, this research proposes a two-stage framework that first retrieves ICD codes using a multimodal dual-encoder retrieval model, where structured and unstructured patient data are integrated through gated fusion. The second stage refines the top-k retrieved candidates with an LLM-based re-ranker that provides ranked codes with clinically relevant explanations. Our experiments show that the proposed approach improves Micro-F1 and Precision over a multimodal dual-fusion classifier baseline. These improvements demonstrate that combining a gated multimodal retrieval system with LLM-based re-ranking is a practical alternative to dense multi-label classification for automated ICD coding. --- ### CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning Authors: Keyang Lu, Zhifei Yang, Tianao Dong, Mingzhe Xing, Zhen Xiao, Yikai Wang Published: 2026-10-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04262v1 Reconstructing editable parametric CAD models from a single-view image is of great practical value for modern manufacturing, yet remains challenging due to incomplete geometric observations and complex inter-part relationships. To address it, we propose CADForge, an agentic framework that progressively converts a single image into CadQuery programs. CADForge decomposes an object into CAD-meaningful components and performs explicit geometric reasoning for each component, a process that first identifies CAD-relevant constraints and then translates them into precise modeling parameters through mathematical code. The inferred parameters then drive component-wise synthesis of executable CadQuery programs, with a review agent evaluating the resulting geometry and providing targeted feedback for iterative refinement. To further improve robustness and efficiency, CADForge incorporates a failure-guided toolkit construction mechanism to distill accumulated experience into tools, and maintains a compact parametric CAD memory for retrieving modeling context on demand. Experiments on diverse single- and multi-part objects show that CADForge consistently outperforms existing baselines in reconstruction fidelity and perceptual quality, demonstrating an effective approach to accurate single-view CAD reconstruction. --- ### Playing social deduction games with reinforcement fine-tuned large language models Authors: Lingzhe Zhang, Yunpeng Zhai, Tong Jia, Kening Zheng, Chiming Duan, Minghua He, Zhaoyang Liu, Bolin Ding, Philip S. Yu, Ying Li Published: 2026-10-03 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.04261v1 Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deduction games to study how RFT changes LLMs' social behaviour. We let fine-tuned and base LLM agents play hidden-role games that require hidden-state inference, social reading and vote steering. Our results show that LLM agents do not reliably acquire social-deduction ability by directly optimizing terminal win--loss outcomes, suggesting that final game results provide a sparse and noisy signal for socially interactive learning. However, RFT is particularly effective at improving social reading, including tasks that require agents to infer hidden roles from public discussion, update beliefs over time and predict other agents' future decisions. We further show that RFT can also improve social influence, including tasks that require agents to steer votes, team approvals and collective decisions, although these gains depend more strongly on behaviourally specific rewards and structured interaction settings. Finally, we show that LLMs' ability to play social deduction games can be further improved through multi-agent social-cognitive reinforcement fine-tuning, which combines social-reading and social-influence signals during same-side multi-agent training. These learned behaviours also receive more favourable human evaluations of strategic competence, persuasiveness and social usefulness. Together, these results enrich our understanding of how RFT changes LLMs' social behaviour and provide a step toward a behavioural learning theory for machine social intelligence. --- ### Cross-Trait Transfer in Subliminal Learning Authors: Xingyu Zhao, Yiqiao Zhong Published: 2026-10-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.04260v1 Subliminal learning is a phenomenon where a student language model acquires a teacher model's behavioral traits by training on semantically unrelated outputs. It is a subtle statistical phenomenon as trait transmission relies on weak statistical patterns in the generated data. To understand trait transmission between teacher-student pairs, we study cross-trait transfer: how data generated under one teacher trait changes the student's preferences of other traits. To this end, we introduce a directed trait-transfer matrix that quantifies these effects using log-probability gains for student answers. We find that the trait-transfer matrix reveals clusters of related traits, with students sometimes developing preferences for traits similar, but not identical, to the teacher's trait. Such cross-trait structure can be partially captured by output distribution metrics and representation-based metrics. Further, we analyze trait development and interaction: learning dynamics shows a progression from broad shared shifts toward more trait-specific transfer, and multi-trait experiments suggest that opposed traits can enhance such differentiation. Together, our findings reveal salient statistical structures over trait transfer and competition, thus providing a broader view of how hidden preferences are transmitted in subliminal learning. --- ### FloVMos: Optical Flow-based Medical Video Mosaicking Authors: Jinyang Liu, Sandesh Ghimire, Chaman Singh, Jennifer Dy, Milind Rajadhyaksha, Dana H. Brooks, Octavia Camps, Kivanc Kose Published: 2026-10-03 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2610.04258v1 Biomedical imaging modalities often require a trade-off among resolution, field of view (FOV), and acquisition speed. Video mosaicking offers a strategy to overcome this limitation by computationally stitching sequential high-resolution frames into a wide-FOV composite. However, existing methods struggle with non-rigid deformations, and modality-specific artifacts arising in clinical and research imaging. Here, we present FloVMos, a generalizable, optical-flow-based deep learning framework for real-time video mosaicking across diverse biomedical imaging modalities. FloVMos achieves robust, pixel-level registration by fine-tuning an optical flow model on synthetic training data with ground-truth deformation fields. We introduce a pipeline for generating this training data, simulating realistic tissue motion and imaging distortions from existing mosaics or raw videos. Our automated synthetic data generation and optical flow model training based on this data allow users to adapt FloVMos to different imaging modalities. To demonstrate this, we applied FloVMos to seven diverse imaging modalities: reflection confocal microscopy, open-top light-sheet microscopy, fetoscopy, laparoscopy, dermoscopy, sparse spectral microscopy, and endoscopy. FloVMos outperforms conventional baselines in accuracy, robustness, and speed for all the tested modalities. This adaptable and training-efficient framework enables large-area visualization with real-time performance and may support broader use of video-based biomedical imaging in research and clinical workflows. --- ### A Hand-Checkable Proof That Two Hidden ReLU Layers Compute the Maximum of Six Numbers Authors: Dimitrios Myrisiotis Published: 2026-10-03 Categories: cs.LG, cs.CC arXiv: https://arxiv.org/abs/2610.04256v1 Exactly computing the maximum function is a standard test case for studying depth in ReLU networks. Two hidden layers are known to suffice for up to twelve inputs through computer-assisted constructions. For six real inputs, we give an explicit hexagon identity whose local structure yields a self-contained analytical proof of this depth bound. The identity was found by computer-assisted search; we prove it through explicit cancellations that can be checked entirely by hand, without executing a verification program. The identity also yields an explicit network with hidden widths $17$ and $41$, zero biases, and rational weights. ---