# Research Papers — 2026-10 · bundle page 14 of 156 > Full-text markdown of papers #651–700 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/14 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/13.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/15.md) ### Prune the Summary, Not the History: Source-Judged Compaction for Long-Horizon Agents Authors: Guanghui Min, Chen Chen Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.20927v1 Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-language summary. We show that these summaries contain more than a record of what happened. Compaction prompts ask for decisions and next steps, so each summary mixes facts established by the environment with reasoning written by the compressor, and the agent cannot tell the two apart afterwards. In an analysis of a widely used structured compressor, 83% of failed runs trace back to an action that carries out a specific summary entry, most of which no environment output supports. We propose Source-Judged Compaction (SJC), a training-free post-processing step that scores each summary entry for whether it has a source in the environment outputs or the previous summary, and removes the entries that do not. It changes neither the agent nor the compressor and adds one inexpensive judge request per compaction. The judge is Jev, a non-generative decision model that answers the source question with a calibrated probability instead of text. On AppWorld and OfficeBench with two agent models, SJC improves cross-run reliability over the underlying compressor by 2.1%-8.9% without increasing the agent's token usage. --- ### SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills Authors: Enze Ma, Chunyu Miao, Yankai Chen, Jie Yang, Liancheng Fang, Kening Zheng, Hanrong Zhang, Muyao Xu, Xinle Yu, Chengze Li, Wei-Chieh Huang, Ziwei Ren et al. Published: 2026-10-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.20926v1 Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iteratively improves skills using execution feedback. However, improvement may require several interdependent edits, so low-reward versions can still be worth developing. Requiring immediate reward gains can discard useful partial repairs before their benefits emerge. Non-elitist evolution allows new versions to receive further edits despite scoring below earlier ones. For agent skills, this calls for evidence of what to preserve and repair next. We introduce SkillNEO (Non-Elitist Evolutionary Optimization for Agent Skills), which separately selects a version to use and versions to keep improving. Comparing how related versions perform the same task reveals working steps to preserve and remaining failures to fix. It can also revisit and revise earlier versions using later evidence. Across 86 SkillsBench tasks in eight domains, including software engineering and office work, SkillNEO raises GPT-5.4 Mini's average reward from 49.1% to 66.4%, within GPT-5.5 and GPT-5.6 Luna's original-skill range. Mini executes tasks, proposes revisions, and edits skills; final evaluation uses the same task instances. Gains span all eight domains. The same skills improve stronger models without further editing. On the 41 tasks with modified skills, reuse improves Luna by 10.5 percentage points and places GPT-5.5 10.6 points above its published original-skill reference. Execution records show these skills can benefit stronger models even when Mini still fails some task requirements. Search histories also show lower-scoring versions leading to skills ultimately selected for use. Together, these findings show that skill evolution can turn a weaker model's partial progress into reusable procedural knowledge for improving more capable agents. --- ### Planning to Learn: Real-Time Robust Adaptive Control on the GPU with Guaranteed Future Learning Authors: Anutam Srinivasan, Siddhant Panse, Glen Chou Published: 2026-10-14 Categories: cs.RO, cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2610.20925v1 Robust adaptive control is vital for keeping robots safe while actively reducing uncertainty in unfamiliar settings. However, traditional methods are often conservative since they fail to account for guaranteed future parameter learning during planning and struggle to scale to high-dimensional systems. In this work, we present A-SLS, a learning-aware robust adaptive model predictive control (RAMPC) framework based on system-level synthesis. A-SLS forecasts future parameter uncertainty and preserves correlations between process disturbances, parameter error, and estimate updates to construct tight, guaranteed reachable sets that account for future information gain. We also develop a GPU-accelerated A-SLS solver to enable real-time performance. Across nonlinear robotic systems, A-SLS reduces reachable-tube conservativeness, maintains real-time performance, and scales to whole-body control for a quadruped with 61 states, 8 uncertain parameters, and 12 control inputs. We further demonstrate the approach on hardware, where a physical Crazyflie drone learns an uncertain dynamics parameter online to stabilize on the fly. --- ### Defining and Generating Compositional Structure Authors: Eric Elmoznino, Tejas Kasetty, Blaise Agüera y Arcas, Yoshua Bengio, Guillaume Lajoie Published: 2026-10-14 Categories: cs.AI, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2610.20922v1 Compositional structure is pervasive in nature and across scales: atoms combine into molecules, molecules into cells, and cells into organisms, while further compositional hierarchies appear within each level. More broadly, compositionality, the reuse and recombination of parts into novel structures, is a fundamental source of interesting complexity in both natural and artificial systems. Yet despite its importance, and despite our apparent ease in recognizing it, mathematical accounts capturing what we intuitively mean by compositional structure remain limited. Here, we fill this gap by formalizing a simple idea: compositional structure emerges when parts, considered together, reveal shared structure that is not captured when those parts are modeled separately. We express this idea using algorithmic information theory, the mathematics of information and compression, which provides a natural way to identify structure in arbitrary data without specifying in advance what that structure must look like. Applied across scales, our definition informs where and how compositional structure emerges within an object. Using tractable approximations, we then invert the framework to generate compositional objects: we specify the desired form of their compositional structure without prescribing their particular content, and optimize directly over strings and images. The resulting objects exhibit readily recognizable hierarchical reuse and part-whole organization, suggesting that the definition captures compositional structure rather than merely complexity, regularity, or shared information. Finally, we discuss implications for machine learning, including a new perspective on depth in neural architectures and principles for constructing compositional data curricula capable of supporting open-ended learning. --- ### A Multi-Tiered AI Accessibility Model (MAIAM): Proportionate Access and Capability Limits for Comprehensive Frontier AI Safety Authors: Chai K. Toh, Vasu Raj Jain Published: 2026-10-14 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.20921v1 Most debate about releasing capable AI systems treats the choice as binary: keep the model behind an API, or publish the weights. That framing runs together two separate decisions. One is how capable a system may become. The other is who may obtain a given capability, and on what terms. This paper is about the second decision. We propose a Multi-Tiered AI Accessibility Model (MAIAM) that sorts access by purpose, safety, and capability instead of by release artifact. Tier 1, AI for Learning, is broadly accessible and deliberately capability-bounded. Tier 2, AI for Exploration, serves research and development under registration, identity, and usage controls that tighten as capability rises. Tier 3, Full-Scale Frontier AI, is available only through structured, recorded, and accountable access. The principle behind the tiers is that accessibility should be proportional to capability, safety, and risk. We show why publishing frontier-class weights forfeits every safety lever a developer has after release, and, using evidence that safety fine-tuning can be stripped from open weights for a few hundred dollars, why an evaluation of the base model says little about its derivatives. We give criteria for assigning a system to a tier along capability, autonomy, domain-consequence, and usage/safety axes, and combine MAIAM with the SAFE AI Operating Point into a two-part framework: a Capability Boundary that fixes the safety limits not to be crossed, and an Accessibility Boundary that fixes who may obtain a capability below that limit. Capability limits alone do not make AI safe; a tiered access regime administered by regulating bodies is also needed. --- ### Forecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models Authors: Mohammad Kian Golkar, Luciano Alves de Oliveira, Mohamad Alipour Published: 2026-10-14 Categories: physics.ao-ph, cs.AI arXiv: https://arxiv.org/abs/2610.20918v1 Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts. We examined how forecast lead time affects the value of outage predictions for crew deployment, using operational forecasts from two AI weather models, GraphCast and FourCastNet, to predict outage occurrence for counties across the contiguous United States 24 to 120 hours ahead. Forecasts were evaluated by the share of outage burden captured by the counties where crews would be staged. Captured burden declined with lead time: the loss between three and five days was significant in all analyses, whereas the loss within three days was significant only for outages that had not yet started. Early deployment with all requested crews outperformed late deployment with fewer, and we report the availability ratio at which the two break even. Antecedent land surface predictors computed at forecast valid time include weather from the forecast period, which inflates their skill by 42 to 53% and reverses their apparent advantage over forecast meteorology at long lead times. Computed correctly, they improved occurrence skill by 17.5% at 24 hours but did not significantly change captured burden, a gap that attribution analysis linked to their static component. Prediction intervals covered only 0.476 of tropical cyclone events against a nominal 0.90. Calibration by hazard class corrected most of this shortfall at an 11% cost in interval width, as a diagnostic only, because hazard class is known only after the event. --- ### Decision-FLIP: Budget-Free Structured Pruning for Gaussian Occupancy Models Authors: Jingxing Li, Anurag Paul, Subhasis Das, Cindy Xu Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.20917v1 Occupancy predictors rely on large persistent banks of Gaussians or learned queries whose size is fixed by hand. Common pruning proxies, such as opacity, activation frequency, or parameter magnitude, do not measure whether removing a row changes the model's voxel decisions. We introduce Decision-FLIP, a budget-free compilation framework whose scoring and structure selection need only unlabeled calibration inputs. Exact Mean-FLIP scores each persistent row by the number of voxel argmax decisions that change when the row is removed from the readout; a guarded Otsu split of the log-score distribution selects the survivor count without a target and abstains when the split is unsupported; and the survivors are physically compiled into a smaller checkpoint, so camera sampling, attention, and aggregation shrink with the bank. For streaming banks, scores are integrated over each row's lifecycle through warp, death, and refill. Across four Gaussian-bank model-dataset settings and one persistent-query transfer, the automatically selected cuts remove 12-79% of eligible rows and cut bank/query-dependent latency by 7-45% across settings with component profiles, with whole-model savings of up to 8.0% on the primary endpoints bounded by fixed-cost image, voxel, and sensor modules and peak-memory savings of up to 16.6%. Under matched one-epoch recovery controls, semantic mIoU changes by at most 0.18 point. Same-$K$ controls show that the ranking, not only the bank size, matters: random removal collapses GaussianFormer-1 and OccFormer, while label-free Mean-FLIP matches or outperforms supervised Taylor ranking on all five settings where that control was run. The method applies when removable primitives keep a stable checkpoint-row identity; it is budget-free in survivor count, not parameter-free. --- ### Recursive Offline Distillation via Entropy Gain Sampling and Answer Mixing Authors: Andrey Goncharov, Daniil Vyazhev, Simon Epanov, Alexey Zaytsev Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.20914v1 Distillation of reasoning chains from Large Language Models (LLMs) into their smaller siblings is a standard training approach. Frequently, researchers do not have full access to a teacher model and its internal representations, which limits the resulting performance. We propose a recursive offline distillation method combining two components: entropy-based sampling for selective distillation and answer mixing. Specifically, for three open models (3-4B), at each epoch, we sample reasoning chains weighted by entropy difference with an auxiliary medium model (70-72B) and, next, supplement thinking traces with single-token ground truth answers. Our approach consistently outperforms naive distillation with comparable data budgets ($57.15 \pm 1.01$ vs 51.61 on average) and offers a much steeper learning curve. Additionally, we present a comparative analysis of methods to generate and normalize distillation traces. --- ### Replicable Dueling Bandits Authors: Rohan Deb, Aadirupa Saha, Udaya Ghai, Karan Singh, Arindam Banerjee Published: 2026-10-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.20908v1 Dueling bandits choose each comparison based on earlier noisy outcomes, so two runs on the same preferences can compare different pairs. We study replicable dueling bandits, where two executions with shared internal randomness and independent comparison outcomes must select the same ordered pair in every round with probability at least $1-ρ$. Building on Beat-the-Mean, whose scores change as arms are eliminated and need not rank the best arm highest, we design the first such algorithms with sublinear regret. Under relaxed stochastic transitivity with parameter $γ\ge 1$ and the stochastic triangle inequality, we design an algorithm that achieves expected regret $\widetilde{O}(γ^8 K^4 H_{\mathrm{p}}/ρ^2)$, where $H_{\mathrm{p}}=\sum_{i=2}^{K}(P_{1i}-1/2)^{-1}$. Under strong stochastic transitivity, we design an algorithm based on simultaneous elimination that improves the dependence on $K$ and achieves $\widetilde{O}(K^2 H_{\mathrm{p}}/ρ^2)$ regret. For linear dueling bandits, we design an algorithm that achieves regret $\widetilde{O}(d^3\sqrt{T}/(c_μρ))$. Experiments on synthetic and language-model preferences show replicability, with sublinear regret. --- ### Task-Centric Multimodal Learning for Cognitive Impairment Detection Authors: Sankalp Vaish, Rishank Singh, Sumukh Veeramalla, Caroline Summerour, John A. Batsis, Xiaohui Liang Published: 2026-10-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.20906v1 Dementia affects millions of older adults worldwide, yet early detection remains difficult outside clinical settings. Traditional models primarily rely on text or voice-based responses, capturing only a limited view of human cognition despite the inherently multimodal nature of human expression. This work proposes a contactless, multimodal screening framework that leverages video, audio, and text signals collected during structured voice-based interactions with Amazon Alexa. By incorporating these modalities, our approach captures a more holistic representation of human behavior encompassing speech patterns, vocal characteristics, facial expressions, and linguistic structure, which may enable more accurate detection of cognitive decline. Different participants completed three conversational tasks designed to probe spontaneous speech, comprehension, and recall. We pursued three objectives: (1) evaluate which of the three Alexa tasks provides the most informative cognitive signals, (2) compare the effectiveness of unimodal models, and (3) assess the benefits of multimodal fusion models. Task-level analysis shows that the video model achieves its best performance on Command-Reading, with an accuracy of 0.65 (AUC 0.69), while the audio model performs best on Question-Answering, reaching an accuracy of 0.67 (AUC 0.73). In contrast, the multimodal model demonstrates consistently stable performance across tasks, achieving an accuracy of 0.76 (AUC 0.75) on Command-Reading and 0.76 (AUC 0.73) on Question-Answering. These findings demonstrate that multimodal behavioral cues captured through naturalistic interactions can reliably distinguish MCI from healthy aging, highlighting the limitations of traditional diagnostic paradigms and supporting the shift toward multimodal, real-world cognitive assessment frameworks. --- ### EgoJEPA: Beyond Retargeting for Dexterous Manipulation from Egocentric Videos Authors: Meng Cao, Can Zhao, Jinjie Wei, Haonan Zhao, Yulong Zhang, Duo Han, Xiaofan Li, Ziwu Song, Rongtao Xu, Ruyi Gan, Hao Wang, Qian Wang et al. Published: 2026-10-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.20904v1 Egocentric human videos offer a scalable alternative to costly robot demonstra- tions, yet transferring their manipulation priors to robot control remains chal- lenging. The commonly adopted retargeting-based approaches convert human wrist and finger poses into embodiment-specific action commands through hand- crafted geometric mappings. However, such mappings require meticulous recal- ibration across different embodiments and risk propagating hand-tracking errors into downstream robot control pipelines. To this end, we propose EgoJEPA, a three-stage framework that learns embodiment-agnostic representations from ego- centric human videos without rule-based human-to-robot retargeting: 1) Human- action pre-training learns effect-aware latent actions through JEPA-style visual prediction conditioned on hand-motion differences; 2) Latent-action-based world modeling jointly predicts future visual dynamics and latent actions, which decou- ples human prior pre-training from robot-specific control parameterizations; 3) Embodiment-specific tuning adapts the pretrained model to diverse robots through lightweight action adapters. Experiments on five real-world manipulation tasks across three robot embodiments demonstrate the effectiveness and efficiency of EgoJEPA. It achieves a 74% average success rate under the out-of-domain evalu- ation, compared with 65% for the retargeting baseline, while reducing cumulative cross-embodiment wall-clock cost by 47.2%, from 743.2 to 392.7 hours. --- ### Sign Betting for Misspecified Regression: Variance Adaptivity and Optimal Approximation Authors: Yinan Li, Han Han, Kwang-Sung Jun Published: 2026-10-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.20903v1 We study bounded regression under model misspecification, evaluating a function $f$ by its $L_1(P_X)$ distance to the conditional mean $η(x)=\mathbb{E}(Y\mid X=x)$, rather than the standard $L_2(P_X)$. This $L_1$ metric is natural for downstream decision problems such as bandits and reinforcement learning. We analyze the min--max estimator of Baraud & Maillard (2025), which we call \emph{sign-betting regression}. Our main results show that sign-betting regression achieves high-probability $L_1$ oracle inequalities under misspecification. Under realizability, our bound adapts to the average conditional variance and recovers the variance-adaptive rate of Li et al. (2026). We further characterize the optimal universal approximation factor for proper learning by showing that sign betting achieves factor 3, while no proper learner can satisfy a distribution-free, high-probability $L_1$ oracle inequality with a universal approximation factor strictly below 3. We extend the upper-bound analysis beyond finite classes and complement the theory with experiments in synthetic and real-world model-selection tasks. --- ### TGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping Authors: Manav Kulshrestha, Apoorva Vashisth, Damon Conover, Aniket Bera Published: 2026-10-14 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.20901v1 Task-Oriented Grasping (TOG) has emerged as an important skill for purposeful robotic manipulation. Given the task of using a knife to "slice bread," a robot must choose to grasp from the handle, whereas for "hand(ing) the knife over," it is preferable for the handle to remain unobstructed for safe handoff. Current approaches for TOG either focus on 2D planar grasping, remain limited by their reliance on task-agnostic grasp generators, or are constrained by reliance on finite, manually-annotated, task-specific grasp datasets that cannot cover all possible grasp-task pairs. To that end, we present TGrasp6D, a vision-language based approach for generating task-oriented 6DoF grasps in a zero-shot manner. Given a task and a single RGB-D image of an associated object, TGrasp6D reasons about the appropriate semantic affordance for the given task and object geometry to produce an initial task- informed prior. This generated prior is further refined via 6DoF pose optimization for collision avoidance while preserving task consistency. Our approach achieves state-of-the-art success rate of 94% on the TaskGrasp dataset, with the best baseline at 74%. We also deploy our approach on a Franka Research 3 robot to demonstrate zero-shot generalization to real world objects --- ### Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL Authors: Dylan P. Wilson, Chengsong Huang, Jiaxin Huang Published: 2026-10-14 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.20898v1 Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with verifiable rewards. This is puzzling from the usual prompt-level view, in which majority vote only returns a model's modal answer and cannot add information about correctness. We argue that the relevant unit is the batch-level update. Because parameters are shared, a prompt's own gradient accounts for less than 1\% of the change in that prompt's output at practical batch sizes, so a wrong label matters only to the extent that label errors share a direction across prompts. We decompose the majority-vote update into shrinkage and misdirection relative to the gold update, and show that misdirection vanishes with batch size whenever errors are incoherent across prompts, however often the labels are wrong. Measuring per-response gradients on five models, we find that majority-vote errors are as incoherent as a random-reward null, that the majority-vote update agrees with the gold update as closely as two independent gold updates agree with each other, and that its noise-corrected cosine with the gold update is 1 within error. Randomly flipping up to 30\% of gold labels leaves the update direction intact, while the same fraction flipped by a shared rule destroys it, and rewards that favor a kind of response on every prompt, such as a learned reward model, fall measurably short. The equivalence holds at every checkpoint we examine but is local: gold-reward training still ends ahead on held-out majority accuracy. Error coherence, not error rate, determines when self-generated labels can stand in for verification. --- ### Stochastic Gradient Descent: A Nonlinear Time Series Perspective Authors: Jiaqi Li, Zhipeng Lou, Stefan Richter, Wei Biao Wu Published: 2026-10-14 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2610.20894v1 This paper investigates the statistical behavior of Stochastic Gradient Descent (SGD) with constant step size under the framework of iterated random functions. Compared to previous studies establishing the convergence of SGD in probability measure, e.g., Wasserstein distance, our approach directly provides the convergence in Euclidean distance by showing the Geometric Moment Contraction (GMC) of SGD. This new convergence can address the non-stationarity of SGD due to fixed initial points and can provide a more refined asymptotic analysis of SGD. Specifically, we prove quenched central limit theorem, invariance principle and $α$-stable convergence for averaged SGD (ASGD) regardless of initialization. Furthermore, we provide a novel perspective to understand the impact of step sizes in SGD by studying its derivative with respect to the step size. The existence of stationary solutions for the derivative processes is shown, enabling the use of interpolation to recover the full-trajectory of SGD. Subsequently, we utilize multiple step sizes and show an enhanced Richardson-Romberg extrapolation with improved bias representation, which brings ASGD estimates closer to the global optimum. Finally, we propose a new online inference method and a bias-reduced variant for the extrapolated ASGD. Empirical confidence intervals are constructed and the coverage probabilities approach the nominal level as $n$ grows. --- ### Flexible Doubly Robust Proximal Causal Inference for Censored Outcomes Authors: Dhanajit Brahma, Ruolin Meng, Lawrence Carin, Ricardo Henao Published: 2026-10-14 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2610.20893v1 Estimating causal effects on right-censored time-to-event outcomes is challenging under unmeasured confounding. Proximal causal inference addresses unmeasured confounding through proxy variables, but existing proximal survival methods rely largely on restrictive parametric bridge models. We introduce Proximal Survival Bridge learning (PSB), a flexible doubly robust proximal framework for censored outcomes. Building on existing proximal identification of treatment-specific survival curves, the framework yields outcome-bridge (OB), treatment-bridge (TB), and doubly robust (DR) estimators, with two flexible bridge learners: PSB-K, a kernel estimator with a low-rank time decomposition, and PSB-N, a neural estimator trained by a projected maximum-moment-restriction loss. Unlike existing flexible proximal learners for scalar outcomes, PSB directly handles censoring and survival-curve targets. On a standard SEM benchmark, a proximal semi-synthetic ACTG study, and the real-world Framingham study, PSB-K performs strongest on SEM and ACTG, whereas PSB-N is the most stable on Framingham. Additional results with modern causal survival baselines, weakened or invalid proxies, and heavier censoring assess robustness across challenging settings. --- ### Learning Warm Starts for the Simplex Method from Measured Solver Cost Authors: Felix Parker, Danielle A. Ripsman, Emmett Springer, Kimia Ghobadi Published: 2026-10-14 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2610.20892v1 Learned warm starts for the simplex method build starting bases using predictions of which variables will be basic at optimality. Prior work has shown that starting bases predicted by graph neural networks can sharply reduce iteration counts, but the time saved may fall well short of the iterations saved. On 25 classes of linear programs (LPs), we find that a strong supervised basis predictor removes two thirds of the dual simplex's iterations but only a third of its time. Two effects explain the gap: the iterations removed by a good start tend to be cheap, and closeness to an optimal basis does not rank starts by cost. We prove that two starts with equal overlap with an optimal basis and equal pivot counts can differ in linear-algebra work by a factor that grows with the square root of the number of rows. Empirically, across the starts of one LP, the pivot count explains 71% of the variance of log solve time, while the CPU instruction count explains 98.5%. We introduce CostStart, which uses supervised prediction for the basis and trains a small policy on measured instruction counts to choose, per LP, how many predicted columns to use, which algorithm and pricing rule to run, and whether to warm-start at all. On unseen LPs of the training classes, including LPs four times the training size, CostStart roughly halves the solve time relative to the solver's default start and is 1.4 to 2.2 times as fast as two published methods retrained on the same data. --- ### Do Emergent Misalignment Models Share a Circuit? Authors: Muhammad Haseeb, Muhammad Tahir Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.20887v1 Fine-tuning language models on narrowly defined harmful tasks can induce emergent misalignment (EM) across unrelated domains. While prior work has identified shared misalignment-associated representations across independently fine-tuned models, it remains unclear whether these models rely on common computational components. We investigate this question using three LoRA fine-tunes of Qwen2.5-3B-Instruct trained on harmful medical advice, risky financial advice, and extreme-sports recommendations. Using direction-based activation tracing, we identify three attention-head locations shared among the five highest-ranked heads of all three organisms. Replacing each organism's five selected head contributions with Base contributions reduces free-generation EM from 38.9% to 22.9% for medical, 50.7% to 12.5% for finance, and 41.7% to 11.1% for sports, outperforming layer-matched random interventions without reducing judged coherence. Cross-organism activation transfer further shows that the shared heads exhibit partially interchangeable effects on fixed-response preference. These findings provide evidence that representational convergence in EM extends to shared, causally relevant attention-head components within a common model architecture. --- ### Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation Authors: Utku Cicek, Mahip Singh, Ziyao Shang, Kimathi Kaai, C Thomas, Pedro Pablo Guerrero Vela, Alexander Wong, Sirisha Rambhatla Published: 2026-10-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.20881v1 While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbones largely operate at the patch or region level, where annotation requirements remain high due to extensive pixel labeling. Extending ViT-based AL to the pixel-level, low-budget regime is uniquely challenging: with as little as one pixel query per image, a method must simultaneously identify the most informative locations and train a reliable decoder head from an extremely sparse signal. We introduce TEAL (Token-space Efficient Active Learning), the first pixel-level AL framework built around ViT representations. TEAL uses a frozen ViT backbone and performs diversity-based selection directly on its native token lattice, avoiding the artifacts introduced by interpolating token embeddings to dense pixel resolutions. Our framework applies a two-level MaxHerding strategy over multi-layer token descriptors to select representative candidates, followed by margin-based uncertainty refinement on a finer decoder grid. Across CamVid, Cityscapes, ADE20K, and Pascal Context, TEAL consistently outperforms previous baselines under extreme label scarcity, improving over the strongest baseline by up to +24.36 mIoU with a single labeled pixel (px) per image, and reaching up to 97% of fully supervised performance with just 10 px. To rigorously establish the source of the gains, we further show that the improvements persist when all baselines are equipped with the same DINOv3 backbone, demonstrating that coupling token-space selection with uncertainty refinement on the decoder grid makes ViT token geometry an effective foundation for extremely low-budget active segmentation. --- ### DefoliationCAM: An Edge-AI System for Real-Time Insect Defoliation Severity Assessment in Grapevines Authors: Fuchen Li, Wei-Zhen Liang, Pin-Chu Lai, Xin Qiao, Jingqiu Chen, Haw Yen, Zonglin Yanga, Chi-En Chiang, Rudolph Avalos, Abbigail L. Rath Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.20879v1 Insect-induced defoliation threatens grapevine health and yield, yet severity assessment relies on subjective manual scouting. We developed DefoliationCAM (D-CAM), a solar-powered edge AI system that estimates canopy defoliation and transmits results via LoRa to a web dashboard. The pipeline uses YOLOX-Nano to localize grapevine cordons in 4K images and a MobileNet-based classifier with lightweight channel attention to classify 320 x 320 pixel patches. The 29,674 field-collected patches were labeled as background or one of four damage levels: no to negligible, mild, moderate, and severe. Merging moderate and severe classes reduced the class imbalance ratio from approximately 40:1 to 8.8:1. Synthetic augmentation increased macro-F1 from 0.768 to 0.838. The classifier outperformed ResNet-50 in macro-F1 with fewer parameters (1.08 M versus 23.52 M). Patch predictions were aggregated into a canopy-level Non-linear Global Defoliation Severity (NGDS) score and validated against an entomologist's ratings of 86 held-out canopy images. Quadratic discriminant analysis identified boundaries of 9% and 29% separating negligible damage, mild damage requiring monitoring, and action-level damage warranting on-site scouting and insecticide treatment consideration. The 29% boundary aligned with the 25%-30% action threshold range for Japanese beetle management in grapevine. Using TensorRT FP16 on an NVIDIA Jetson Orin Nano, the pipeline processed each 4K image in approximately 1.5 s, with a complete operating cycle of 57-60 s. A five-week deployment of two field units demonstrated the feasibility of autonomous solar-powered operation, LoRa communication, and remote defoliation monitoring. D-CAM supports frequent, objective canopy damage assessment for targeted scouting and timely pest-management decisions. --- ### CogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection Authors: Sankalp Vaish, Sumukh Veeramalla, Rishank Singh, Caroline Summerour, John A. Batsis, Xiaohui Liang Published: 2026-10-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.20877v1 Early detection of mild cognitive impairment remains a critical bottleneck in dementia care, demanding scalable tools capable of capturing subtle behavioral decay. To capture the subtle temporal changes of cognitive decline, we introduce a behavioral dataset collected across seven unscripted multimodal interactions over an 18-month horizon. This dataset formalizes continuous, multi-session interactions into a dense 4D tensor (Batch * Session * Time * Feature) that explicitly preserves concurrent local dynamics alongside long-term changes. To effectively process these complex behavioral patterns, we propose CogDrift-4D: a novel, hierarchical 4D Transformer framework. To capture the complex trajectory of cognitive decline, CogDrift-4D implements a dual-level behavioral fatigue and drift modeling architecture. At the intra-session level, the model computes localized least-squares regression slopes to quantify the acute ``fading'' of frame-level facial action units and acoustic energy. At the inter-session level, a recursive cross-attention feedback encoder acts as a cumulative fatigue accumulator, mapping the patient's continuous behavioral drift across successive sessions. To mitigate environmental noise and track failures across sessions, a localized Quality Gate dynamically filters low-integrity features before final fusion, also an early fusion that integrates semantic insights with raw physical dynamics. Evaluated on structured verbal and linguistic interactions, our architecture successfully detects MCI with a classification accuracy of 0.733 +- 0.13 and an F1-score of 0.716 +- 0.14, outperforming advanced baselines. The framework provides a mathematically rigorous, scalable, and robust foundation for home-based, real-time dementia screening. --- ### A Mixture-of-Experts Framework for Multi-Stream Quickest Change Detection Authors: Wuxia Chen, Arman Adibi, Taposh Banerjee, Vahid Tarokh Published: 2026-10-14 Categories: eess.SP, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2610.20876v1 A Mixture-of-Experts (MoE) framework is proposed for quickest change detection (QCD) where there are multiple experts, and each expert produces a sequence of statistics for change detection. A change is declared when a weighted sum of these statistics crosses a threshold. This framework is then applied to the problem of multi-stream QCD to obtain a family of powerful algorithms that outperform the best known algorithms in the literature. In the multi-stream QCD problem, a decision-maker observes multiple streams of observations. At the change point, the distribution of an unknown subset of the streams changes. The optimal algorithm based on a generalized likelihood ratio is computationally expensive. One of the most computationally and performance-efficient algorithms in the literature is the rank-weighted sum (RWS) scheme based on Shiryaev-Roberts statistics. It is shown in the paper that the MoE-based QCD algorithm for multi-stream data outperforms the RWS scheme. This is demonstrated through simulation results on real-valued Gaussian mean shift data and high-dimensional data from Gaussian--Bernoulli Restricted Boltzmann Machines (GB-RBMs). --- ### Machine-learning-based neutrino-event generation constrained by experimental measurements Authors: Jose Luis Bonilla, Krzysztof M. Graczyk, Rwik Dharmapal Banerjee, Beata E. Kowal, Hemant Prasad, Jan T. Sobczyk Published: 2026-10-14 Categories: hep-ph, cs.LG, hep-ex, nucl-ex, nucl-th arXiv: https://arxiv.org/abs/2610.20870v1 We present a generative surrogate for charged-current \(ν_μ\)-nucleus scattering that can be calibrated to measured differential cross sections without event-level experimental samples. Starting from a theoretical interaction model, we fine-tune the surrogate to a MicroBooNE measurement and show that this also improves the description of observables not used in the fit. The calibrated model can also be applied to measurements from different neutrino fluxes without retuning, while retaining event-level predictions of outgoing-muon kinematics. Our results show that experimental cross sections can directly constrain generative event models while preserving their applicability across different observables and beam configurations. --- ### Clinically Interpretable Biological Age Estimation Using CatBoost and SHAP with Continuous and Categorical Features from NHANES Authors: Yanni Sun, Zheng Qu, Kevin Ren, Zhanglin Lin Cui Published: 2026-10-14 Categories: cs.LG, stat.CO arXiv: https://arxiv.org/abs/2610.20868v1 Biological age (BA) captures inter-individual variation in physiological aging beyond chronological age (CA). Although machine-learning models have advanced BA estimation, many rely primarily on continuous laboratory biomarkers, and SHapley Additive exPlanations (SHAP) dependence plots are typically interpreted visually. We developed a clinically interpretable machine-learning framework for BA estimation using heterogeneous clinical data from the National Health and Nutrition Examination Survey (NHANES 2011-March 2020, N = 24,983 adults aged >= 18). A CatBoost regression model incorporated 44 demographic, laboratory, physical examination, and lifestyle predictors to estimate CA, defining model-estimated age as BA. SHAP provided multi-level interpretability. Crucially, building on standard visual inspection, we implemented a prespecified automated procedure directly on SHAP dependence plots to quantify feature-value ranges associated with lowest and highest BA contributions, corresponding adjustment magnitudes, and zero-crossing thresholds. Model-estimated BA strongly correlated with CA in held-out testing data (Pearson r = 0.798, P < 0.001). Population-level SHAP identified blood urea nitrogen, serum glucose, vigorous recreational activity, red cell distribution width, and alanine aminotransferase among the leading predictors, with three categorical variables ranking among the top 25. Automated quantitative SHAP analysis mapped predictor-specific ranges, effect sizes, and inflection points, while waterfall plots enabled individual explanations. By extending qualitative visual interpretation to reproducible quantitative metrics across heterogeneous clinical data, this framework enhances transparency and provides a scalable methodological foundation for biological aging research and precision health. --- ### Anticipatory Commonsense with Moving Objects: An ASP-Based Framework for Predictive Reasoning with Interacting Trajectories Authors: Julius Monsen, Jakob Suchan, Mehul Bhatt Published: 2026-10-14 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2610.20867v1 We present a general declarative framework for anticipatory reasoning about interactive motion in complex dynamic environments. Our focus is on (explainable) anticipatory space-time mental model formation at a semantic level to heuristically guide low-level motion computation. Our method is hybrid, modular and elaboration tolerant integrating: 1) An ASP model characterising the dynamics of interactive motion trajectories; 2) Semantically-guided prediction for deriving `branching trajectory futures'; and 3) An energy-based {optimisation} model to evaluate, rank and filter anticipations. We evaluate with the Argoverse 2 benchmark, where each anticipated trajectory carries an explicit, inspectable event-level hypothesis, unlike end-to-end stochastic prediction. --- ### SHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations Authors: Wei-Jer Chang, Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Masayoshi Tomizuka, Wei Zhan Published: 2026-10-14 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2610.20866v1 Realistic traffic simulation and autonomous planning both depend on modeling interactions among heterogeneous road users whose dynamics, constraints, and behaviors differ fundamentally. Existing approaches predominantly learn realistic interaction behavior from large-scale human driving demonstrations. In this work, we ask whether such behavior can instead emerge purely through self-play. We present SHRED, a framework that jointly trains vehicles, pedestrians, and cyclists through large-scale heterogeneous self-play from random initialization, without demonstrations or logged-trajectory replay. SHRED combines type-specific dynamics and objectives with procedural scenario generation and per-agent randomization, allowing diverse behaviors to emerge through closed-loop interaction. On the Waymo Open Sim Agents Challenge (WOSAC), SHRED jointly controls all three road-user types and outperforms both the closest demonstration-free self-play baseline and prior self-play methods that use demonstration-trained reference policies. Policies trained only on nuPlan map geometry retain comparable realism under zero-shot evaluation on Waymo. For planning, SHRED outperforms all compared planners on the interaction-heavy InterPlan benchmark. Controlled ablations show that heterogeneity in self-play improves both traffic realism and planning performance, with particularly large planning gains in interaction-heavy scenarios. Together, these results establish heterogeneous procedural self-play as a scalable, demonstration-free paradigm for learning realistic and interactive traffic behavior. --- ### Long-Context Drafting Does Not Require Long-Context Drafters Authors: Aref Jafari, Vansh Bhatia, Matt Qin, Subhajit Dutta Chowdhury, Ben Lee, Vikram Appia, Ali Ghodsi, Mehdi Rezagholizadeh Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.20865v1 Speculative decoding pairs a cheap drafter with parallel verification against the target. At ultra-long context it stops paying, because a drafter that attends over the full prefix inherits the target's context-dependent cost, so the speedup it was meant to provide first erodes and then reverses. The standard response is to build a long-context drafter, by training or fine-tuning one, or by using a multi-token-prediction head shipped inside the target checkpoint. We argue this is unnecessary, because the drafters in use are target-conditioned, reading hidden states the target computed over the entire prefix, so distant context already reaches them without their own attention, and verification corrects what they miss. We therefore freeze released short-context drafters and run them far past their training length under two inference-time mechanisms, one bounding the attention cache they see, which fixes their cost, and one re-basing their rotary position indices into the trained range. No weight is touched and the only tunable saturates early, so one vLLM-side configuration spans 4k to two million tokens, costing at most 0.16x of speedup at short length. We prove when a common index shift leaves the drafter's computation exactly unchanged, and decompose acceptance into two measurable gaps with sharp bounds. Whatever speedup a frozen drafter delivers at short context, it retains out to two million tokens, across three target-drafter pairs and five corpora. The claim concerns the flatness rather than the multiple, and removing either mechanism eliminates it. The gain is conditional on the speculative cost per emitted token staying below the matched target-only cost. --- ### SNOAR: Self-training with Noise filtering, Observation adding, and Remixing for Speech Denoising Without Clean References Authors: Samuele Cornell, Matthew Maciejewski Published: 2026-10-14 Categories: eess.AS, cs.LG, cs.SD, eess.SP arXiv: https://arxiv.org/abs/2610.20863v1 Unsupervised speech denoising methods such as MixIT and noisy-target training can be trained directly on noisy recordings, avoiding the sim-to-real gap of synthetic training data, but remain well below supervised performance. Teacher--student self-training, as in RemixIT, narrows this gap by remixing a teacher's estimates into new mixtures that supervise a student; however, since the student is trained only toward the teacher's estimates, teacher errors, in particular over-suppressed speech, are never recovered and propagate as the teacher is updated from the student. We propose SNOAR, a self-training framework that corrects the teacher's estimates before use: the noise leaked into its speech estimate is removed by differential noise filtering (DNF), and part of the noisy observation is added back in to restore suppressed speech and attenuate artifacts. We show that the two corrections depend on each other, as without DNF the loop collapses to the identity mapping. Compared to RemixIT, SNOAR is more stable along training and outperforms it in signal-based, perceptual, and word error rate metrics, reaching 97\% of the SI-SDR improvement of a fully-supervised topline on WHAM!; on real CHiME-3 recordings, it improves every metric of three different teachers, while RemixIT degrades their perceptual quality. --- ### Time-partitioning Gaussian Process Mixture Model Authors: Guilherme Piantino, Hedibert F. Lopes Published: 2026-10-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.20860v1 We propose the Time-partitioning Gaussian Process Mixture Model (TPGPMM), a Bayesian nonparametric framework for identifying persistent regimes and modelling nonstationary dependence in time series. The model combines an adaptive Pitman--Yor prior on contiguous segmentations with regime-specific Gaussian processes, without imposing Markovian within-regime dependence. Learning the Pitman--Yor discount parameter allows adaptation to homogeneous and heterogeneous regime lengths. A split--merge Metropolis-within-Gibbs sampler with exact Gibbs boundary updates jointly learns change points and model hyperparameters, quantifying uncertainty over segmentations and within-regime dynamics. With an RBF kernel and a fixed, conservative observation-noise level, TPGPMM favours sparse segmentations that distinguish persistent shifts from transient shocks. Simulations demonstrate recovery of the regime structure. Applications to the CBOE Volatility Index (VIX) and the 10-year United States Treasury yield identify regimes aligned with major market and monetary-policy events. Variants that estimate observation noise improve predictive accuracy relative to the main specification, but can produce less sparse or less event-aligned segmentations. A variant with regime-specific means fits better than a fitted stationary Gaussian process and forecasts about as accurately. These results highlight a trade-off between interpretable regime identification and predictive accuracy. --- ### Does Morphological Correctness Matter for Tokenization? A Scrambled Control Study in Tagalog Authors: Abdul Rehman Antall, Baidya Nath Saha Published: 2026-10-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.20859v1 Typology-aware tokenizers are motivated by the claim that segmentation which respects morpheme boundaries preserves information that frequency-driven segmentation destroys. Studies routinely establish that it helps while assuming the boundaries must be linguistically correct. We separate them. Tagalog marks voice with infixes (s-um-ulat 'wrote', s-in-ulat 'was written'), so the root is not contiguous and no sequence of BPE merges can recover it. We build MorphAustro-Tok, a tokenizer that emits the root as a contiguous unit followed by a positional infix token, and compare it against a corpus-matched BPE baseline and, at two of three fertility levels, against a scrambled-morpheme control that preserves morph count, invertibility and per-type consistency while randomising the pseudo-infix. Across 33 runs, MorphAustro-Tok improves Tagalog machine translation over matched BPE by 0.84, 1.49 and 3.40 mean sentence-level chrF++ points. Token count does not explain the gain, since it grows as segmentation coarsens, and neither does capacity: at the coarsest level the scrambled arm carries more parameters and scores lower. Scrambling the analysis moves the gain by less than between-seed dispersion at both controlled levels, so we detect no contribution from morphological correctness at this scale. --- ### Probing Negation Understanding in Vision-Language Models With Object Attention Authors: Beth Pearson, Michael Wray, Martha Lewis Published: 2026-10-14 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.20852v1 Negation is a fundamental aspect of language understanding and it is important vision-language models (VLMs) are able to process it effectively. We investigate how VLMs process negation by analysing attention patterns of different models. We draw comparisons between human gaze and attention in models when processing affirmative vs negated statements. We compare object level model attention to human eye-fixations in both binary and multary settings, evaluating with both synthetic and realistic datasets. We find models generally do not follow human-like attention patterns when resolving negation, suggesting they rely on mechanisms outside of attention. While layerwise analysis shows that PaliGemma2-3B shifts object attention to the alternative under negation, our headwise ablations suggest this is a byproduct rather than a negation processing mechanism. Additionally, we find that LLaVA-1.5-7B displays a spatial bias towards left-side objects. Our evaluation of models on downstream tasks shows that all models have a discrepancy between affirmative and negated questions highlighting the need to better understand the underlying processing of negation to close this performance gap. Code available at https://github.com/otmive/negation_attention --- ### Complete or Sparse: A Tale of Two Identifiabilities Authors: Junze Zhou, David Klindt Published: 2026-10-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.20851v1 Understanding when neural networks learn interpretable representations is central to mechanistic interpretability. We study this through identifiability: when can supervised learning recover the true latent variables underlying the data? We introduce two data generating processes distinguished by their causal direction where either labels cause latents (generative) or latents cause labels (discriminative). When the representation has at least as many dimensions as the latent space, we prove that the optimal encoders are linear in the latents. Conversely, when dimensions are insufficient, identifiability generically fails and encoders become nonlinear. We then show that additional constraints yield recovery of individual latent variables, not just linear mixtures. In the generative setting, non-negative activations and energy efficiency force each neuron to encode exactly one latent, providing a precise account of selective grandmother cell-like responses. In the discriminative setting, when latents are sparse and the true measurement matrix satisfies the spark condition, the learned encoder inherits compressed sensing structure, enabling sparse dictionary learning to perfectly recover individual latents. This constitutes, to our knowledge, the first identifiability result for undercomplete nonlinear independent component analysis. Our framework unifies nonlinear ICA, compressed sensing, and neural network interpretability, delineating exactly when representations transition from nonlinear distortions to linear representations and, under additional constraints or steps, to clean, axis-aligned codes. Theoretical predictions are validated on synthetic benchmarks and on activations drawn from vision models, large language models, and macaque inferotemporal cortex. --- ### Denoising Score Matching in Diffusion Models: The Effect of Rank Constraints on Generalization Authors: Anand Jerry George, Nicolas Macris Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.20850v1 Architectural biases restrict the class of functions that a diffusion score network can represent, but their effect on generalization remains poorly understood. We study denoising score matching with score networks having a rank constrained non-linear term and a linear skip connection. Numerical experiments with trainable three-layer networks on data supported on an embedded sphere show that increasing rank lowers training error, but its effect on test error depends on sample size and data dimension. To explain this behavior, we analyze a random-feature score model under rank constraint with Gaussian data supported on a low-dimensional subspace. We characterize the optimal rank-constrained estimator through a truncated singular value decomposition and derive asymptotically precise limiting training and test errors when sample size $(n)$, feature width $(p)$, data dimension $(D)$, and rank $(r)$ scale proportionally with the ambient dimension $(d)$. The resulting spectral characterization distinguishes eigenmodes that improve the empirical fit from those that improve population accuracy. It also identifies the dimension of the orthogonal complement of the data subspace as a natural rank threshold. The theoretical learning curves qualitatively reproduce the observed rank-dependent overfitting, providing a tractable account of how bottlenecks or rank constraints can regularize score estimation and why their effectiveness depends on data dimension and sample size. --- ### Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents Authors: Yujie Feng, Xiaobin Wang, Jinluan Yang, Xiaonan Shi, Pengjun Xie, Philip S. Yu, Xiaoming Wu, Jieping Ye Published: 2026-10-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.20845v1 Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-improving agents. Current evaluations score the co-evolved policy on the final bank it trained with (the delivered bank). After deployment, however, skills may be rewritten, added or removed more frequently than the policy model is retrained, leaving the policy to operate on a drifted skill bank that neither the training objective nor existing evaluation protocols address. In this paper, we first establish, through theoretical and empirical analysis, that the fragility hidden by this blind spot is not incidental. The acceptance rule these methods share (cooperative acceptance) ties a policy's competence to the bank it co-evolved with, leaving it fragile once skills drift, regardless of the implementation; empirically, sensitivity to skill drift grows as co-evolution training proceeds. We therefore introduce the CO-evolution Drift Audit (CODA), a deployment-oriented evaluation protocol that simulates skill drift and, alongside success rate under worst-case drift, introduces two new metrics: a consistency rate under meaning-preserving edits and a resistance rate to corrupted skills. Across four co-evolution methods and five benchmarks (six settings), worst-case success is 5-13 points below the peak measured for each delivered pair, erasing 52-93% of the delivered bank's gain over the no-skill baseline. CODA thus reframes the target of co-evolution, from peak performance on the co-evolved bank to the ability to harness skills however they evolve, and provides a shared standard against which future methods can be audited. --- ### MARS - A foundational map auto-regressor Authors: Qi Zhang, Suvam Bag, Rupanjali Kukal, Lucas Thai, Jacob Kovarskiy, Mike Bianco, Xiaojie Guo, Raphael Tang, Mikael Figueroa, Rishi Madhok, Nikolaos Karianakis, Fuxun Yu Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.20843v1 Map generation tasks feature extensive non-structural vectorized data (e.g., points, polylines, and polygons) and thus pose significant challenges to common pixel-wise generative models. Conventional approaches use multiple stages, first segmenting these features at the pixel level and then performing vectorized post-processing, with errors and complexity compounding at each stage. Motivated by the recent success of auto-regressive language modeling, we propose the first map foundation model, named Map Auto-Regressor (MARS), that is capable of generating both multi-polyline road networks and polygon buildings in a unified manner. For training MARS, we collected to our knowledge the largest multi-class map extraction dataset totaling 3.4M examples, which we call MAP-3M. Across four road and building datasets, MARS outperforms or matches the performance of multistage baselines. Additionally, we develop a "Chat with MARS" capability that enables interactive human-in-the-loop map generation and correction, supported by the auto-regressive nature of our end-to-end approach. We release our MAP-3M dataset and project demo page at (1) https://huggingface.co/datasets/bag-lab/MAP-3M and (2) https://huggingface.co/spaces/bag-lab/MARS, respectively. --- ### Analog RF Computing for Integrated Data and AI Flows Over Wireless Networks Authors: Wentao Yu, Vincent W. S. Wong Published: 2026-10-14 Categories: cs.IT, cs.ET, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2610.20841v1 Many resource-constrained edge devices require artificial intelligence (AI) services but are not powerful enough to store or execute neural networks (NNs). Analog radio frequency (RF) computing addresses this limitation by letting a base station (BS) multicast a waveform encoding NN weights to different clients. Each client then multiplies the received weight-encoded waveform with its locally generated input-encoded waveform through a passive mixer in its RF frontend, thereby realizing the matrix-vector multiplications (MVMs) needed for AI inference with an extremely low power and memory requirement. This can enable telecom operators to provide AI inference services to the edge devices connected to their networks. In practice, however, this multicast AI flow must share the spectrum, power, and spatial resources with other data flows. This paper considers a multi-user multiple-input multiple-output (MU-MIMO) downlink scenario and studies the resulting relative aggregate data rate reduction from integrating the multicast AI flow with the unicast data flows. We formulate a joint beamforming problem for the data and AI flows to maximize the aggregate data rate subject to computing accuracy, client energy, total power, and hardware-related constraints. We develop a weighted minimum mean-square error (WMMSE)-based algorithm to solve the problem. Numerical results based on 3rd Generation Partnership Project (3GPP) channels show that the relative aggregate data rate reduction from integrating an AI flow with data flows is below 5% in representative settings. This indicates that telecom operators can use analog RF computing to provide edge AI services while providing data communication services simultaneously. --- ### A Phenomenology of Neural Geometry in Vision-Language-Action Models Authors: Mozes Jacobs, Aiden Swann, Mathilde Papillon, Siddharth Boppana, Fenil R. Doshi, Usha Bhalla, Thomas Icard, Matt Feiszli, Thomas McGrath, Vasudev Shyam, Demba Ba, Leon Bergen et al. Published: 2026-10-14 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2610.20840v1 Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it? Prior work on vision-language-action (VLA) policies establishes that task-relevant variables are linearly readable from activations, yet readability certifies only that a variable is present and says nothing about the shape its values trace, which may be curved and multi-dimensional. Using controlled sweeps, natural rollouts, linear probes, and activation interventions, we build a taxonomy of seven task-relevant concepts in VLA models. We find that realized geometry is predominantly multi-dimensional and is shaped by the constraints under which the policy acts. Physical joint limits, for example, leave wrist orientation an open arc rather than a circle, and distance to the target, a single scalar, is realized in two orthogonal subspaces, a coarse ruler for the approach and a fine ruler for the grasp. The same geometries reappear in two further VLA models on real-world robot data, indicating that they are neither model-specific nor artifacts of simulation. We demonstrate how the findings are actionable by steering along the geometry a concept realizes. Overall, this work lays out an initial phenomenology of realized geometry in VLA policies and demonstrates that a concept's shape carries as much importance as its readability. --- ### Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning Authors: Weida Liang, Kenji Kawaguchi Published: 2026-10-14 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.20836v1 Evaluator-guided reasoning presents a local control problem at every step: trust the current answer, return a fallback, or spend more inference. We formulate this choice as a compute-aware three-action controller, scoring terminal actions by predicted answer success and expansion by a rollout-based continuation-success surrogate, with compute cost priced explicitly. A local action-gap analysis characterizes when score errors can change a decision, while an expected regret bound accounts for errors along the realized expansion path. Guided by this analysis, we learn and calibrate action-specific confidence estimates, with local uncertainty penalties for ambiguous decisions. On held-out width expansion and revision tasks, the controller improves observed utility over calibration-selected fixed policies while reducing normalized online compute by about 30% and 16%, respectively. Across four Qwen3-8B seeds, compute is lower than fitted Q in both settings, while utility differences are small and mixed. The results frame evaluator-guided reasoning as resource allocation under uncertainty, rather than a uniformly stronger reasoner. --- ### Amortizing Sequential Experimental Design in Reasoning LLMs Authors: Anita Kriz, Antonin Berthon, Nicolás Astorga, Mihaela van der Schaar Published: 2026-10-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.20832v1 Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather information in experimental design tasks. We study how to amortize sequential Bayesian experimental design (BED) into an LLM by explicitly training the reasoning that guides action selection using information-gain rewards. Our approach specifies the experimental generative model independently of the LLM's own beliefs, allowing us to optimize expected information gain under a model of our choosing. We investigate the design choices for amortization, including alternative generative-model constructions, reward estimation, hypothesis-space specification, multi-step objectives, and computational costs relative to training- and inference-time BED baselines. On Twenty Questions, the resulting policies improve information acquisition and task performance, outperform inference- and training-time BED baselines at substantially lower computational cost, and generalize to unseen categories. We further demonstrate positive transfer from Twenty Questions training to Medi-Q, a real-world clinical dialogue benchmark. These results suggest that information gathering can be learned as a generalizable reasoning skill in LLMs. --- ### PEDBench: Can Speech Models Detect Phonetic Errors? Authors: Zhonghao Shi, Zackary Rackauckas, Jasmine Yip, Savannah Halpern, Simon Campos, Lauren Brace, Emma Yang, Tiantian Feng, Xuan Shi, Shrikanth Narayanan, Teresa Satterfield, Ying Xu Published: 2026-10-14 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2610.20830v1 Phonetic error detection (PED) aims to identify phoneme-level substitutions, deletions, and insertions and is essential for educational and clinical speech assessment and intervention. Despite recent advances in speech models for phoneme recognition, their ability to reliably detect fine-grained phonetic errors remains unclear because of a lack of high-quality evaluation data. To address this gap, we introduce PEDBench, the first PED benchmark spanning a continuum from natural to controlled speech. It comprises real-world recordings of spoken errors made by children (N=334), scripted error productions by human actors (N=1,188), and synthetic error productions generated using phone-conditioned text-to-speech (N=1,083). All phonetic annotations were transcribed and verified by two phonetically trained annotators. Our evaluation of 13 state-of-the-art speech models shows that they fail to reliably detect phonetic errors, even under controlled conditions with acted and synthetic speech, where acoustic variability is reduced. The models also exhibit low precision, frequently misclassifying correctly pronounced phonemes as errors. Our speech-language models, fine-tuned on synthetic data, outperform commercial and open-source baselines on word-level PED, although a sim-to-real domain gap remains. We plan to publicly release our code and recipes, along with our acted and synthetic datasets, to support the development of more accurate PED systems. --- ### CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation Authors: Zinan Tang, Zhuoshi Pan, Kairui Chen, Ze Yan, Shaomian Zheng, Yukun Zhang, Gang Wang, Biqing Huang Published: 2026-10-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.20828v1 Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently remains challenging. Forward CoT generation (FCG) followed by rejection sampling (RS) produces verified, question-only responses, yet may require many teacher calls for difficult problems. Reverse CoT generation (RCG) is cheaper because it conditions on the known answer, but access to this answer can lead to post-hoc rationalization and a mismatch with the student's answer-free inference setting. We propose CoTranslator, which learns to translate reverse CoT responses toward the distribution of verified forward responses. Trained on a small set of paired reverse and rejection-sampled forward responses, it supports large-scale generation and verification of student training data. Across six student models evaluated on six mathematics benchmarks, CoTranslator improves average accuracy over semantic suppression by up to $5.82$ percentage points. For two 4B students, it retains $95.0\%$ of rejection sampling's average accuracy while using $35.9\%$ of its estimated compute. Without retraining, the same translator transfers to a new mathematics dataset, a different teacher, and STEM problems, improving average STEM accuracy by $4.88$ and $4.31$ percentage points for 4B and 8B students, respectively. These results show that CoTranslator offers an efficient and transferable approach to reasoning distillation. --- ### Task-Phase-Conditioned Expert Routing Is Not a Reliable Proxy for Quantization Sensitivity in MoE FFN Tensors Authors: Yifan Liu Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.20826v1 We investigate whether per-layer, per-task-phase (prompt/reasoning/response) expert-routing statistics in a Mixture-of-Experts (MoE) language model can guide layer-wise mixed-precision quantization of routed-expert FFN tensors (down/gate and up). To attain layerwise routing statistics, we build a routing-capture and profiling pipeline for Qwen-3.6-35B-A3B in ik_llama.cpp, derive a composite sensitivity score from routing entropy/decisiveness, coefficient of variation (CV), Jaccard/phase-fragility, and top-1 expert strength, and use coordinate descent to tune a layer allocation that respects a fixed average bits-per-weight budget. Notably, the profiling pipeline is applicable to standard top-k MoE architectures. Across independent experimental conditions (about 4.0 bpw flat, about 2.7 bpw steep, and about 2.7 bpw random allocation as a control), reallocation fails to outperform the uniform baseline within each quality tier. In the flat regime, reallocation is statistically neutral (z about 0.9). For the steep tier, the random reallocation performs within 1 SE of the routing-guided reallocation at the same tier, indicating a structural loss at this quality rung caused by mandatory downgrades and Kullback-Leibler Divergence (KLD) tail injection. This aggressive-budget condition shows a decisive loss (z greater than 4 SE) replicated across three independent weight vectors. We argue that the deeper issue is that routing-behavior statistics are an unvalidated proxy for true per-layer quantization cost. --- ### Linear Independence of Polynomial Compositions with Bounded Input Degree Authors: Xiaotian Chang, Yacoub Hendi Published: 2026-10-14 Categories: math.AG, cs.LG arXiv: https://arxiv.org/abs/2610.20825v1 We prove the weak composition-independence conjectures of Kohn, Marchetti, Massarenti and Mella. The proof uses deformations of rational curves and a single kernel of the linearized equation. Riemann-Roch gives a contradiction from tangent fields with controlled poles. By settling these conjectures, we prove that a neural network with a general polynomial activation function of sufficiently large degree is identifiable. --- ### Wolof-Adapted Industry-Ready Open-Weight Language Models Authors: Gwénolé Lecorvé, Delphine Charlet, Pierre Adam, Floriane Behanzin, Lionel Delphin-Poulat, Johannes Heinecke, Géraldine Damnati, Pelin Kaytmaz, Nourredine Khaous, Charbel Kindji, Meriam Maadi, Abdoulaye Mbaye et al. Published: 2026-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.20824v1 Wolof is spoken by 23M people, mostly in Senegal, but remains weakly supported by open-weight language models, while API models raise cost, governance, and sovereignty constraints for local deployments. In this paper, we present 0.6B-14B open-weight models adapted to Wolof through instruction tuning, preference alignment, and model merging. After presenting the pipeline and data, extensive experiments on 63~public and in-house tasks show good performance on Wolof understanding and generation while remaining effective on other languages and cross-lingual skills, with the 8B and 14B models being particularly competitive with substantially larger commercial systems. The models are currently being evaluated in internal customer-care pilots and are publicly available at https://huggingface.co/collections/Orange/wolof-lm . --- ### Feasibility Ceilings Before Learning: Sizing and Timing Bounds for Drone-Mesh Interception Authors: Dmytro Babarytskyi Published: 2026-10-14 Categories: cs.RO, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2610.20823v1 A mesh of interceptors defending a fixed site must spread over the predicted arrival point of an approaching object. This is a recurring task in multi-agent robotics: N agents, each covering a disc of radius r, spread over a probability density so that a point drawn from it falls within some agent's disc. We give closed forms for the quantities that bound performance before any policy is chosen, and validate each by Monte Carlo. The uncertainty of a point predicted by extrapolating a noisy linear track follows from least-squares variance propagation plus a delta-method term for the uncertain arrival time, agreeing with simulation to within 1.8%. The coverage probability of a packed mesh admits a closed form accurate to 0.007 absolute, with a volumetric analogue. A naive area ratio misses a ceiling: while agents stay at least 2r apart, no mesh exceeds 90.69% coverage in the plane or 74.05% in a volume. This ceiling belongs to the separation constraint, not to the problem - permitting overlap substitutes Kershner's thinnest-covering density and removes it, the better regime above a crossover at p=0.80. Hexagonal packing is optimal among five arrangements; the centroidal-Voronoi configuration coverage control supplies reaches only half its coverage at small budgets. The Gaussian assumption is conservative under heavy tails and anisotropy but fragile under bias: a one-sigma aim-point offset costs 14 points of coverage. A repositioning team must also choose a commit time, and the admissible window can be empty. Against the applicable ceiling, analytic placement attains 85% of what the configuration permits while centralised PPO averages 15% over three trainer seeds, with a paired bootstrap against a null policy containing zero at every seed. We argue such ceilings should be computed before any learning experiment and quoted alongside every result. --- ### Temporal Specification Guidance for Text-to-Video Generation Authors: Avishree Khare, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Rajeev Alur Published: 2026-10-14 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.20822v1 Text-to-video models often generate the visual concepts requested in natural language prompts but fail to satisfy their intended ordering, timing, and persistence requirements. We propose representing these requirements as specifications in a formal Temporal Logic, and introduce Temporal Specification Guidance (TSG), a training-free inference-time framework that turns temporal specifications into executable objectives for guiding video generation during sampling. TSG scores traces of visual concept evidence using differentiable quantitative semantics and uses the score's gradients to construct a specification-guided denoising direction. We instantiate this framework with video-text attention traces, efficient differentiable scores for Metric Temporal Logic, and gradient-derived attention biases. This instantiation requires neither an external concept classifier nor backpropagation through the video transformer. Its attention-steered forward pass yields a denoising direction that augments classifier-free guidance (CFG). On a benchmark of 220 prompts spanning 11 categories of temporal constraints, including ordered object entry and state transitions, this instantiation improves specification satisfaction accuracy over CFG by 9.5-20 percentage points across five models, with minimal memory overhead. These results demonstrate the potential of temporal specifications and differentiable satisfaction objectives as a flexible interface for controlling video generation. --- ### Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation Authors: Qian Yu, Zongyang Qiu, Juncheng Yan, Hongliang Li, Qi Qin, Keqi Wang, Siqi Luo, Junkui Ju, Yapeng Mi, Tiantian Lu, Tian Liu, Pengyu Xie et al. Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.20818v1 Unified multimodal generation covers discrete, continuous, and hybrid paradigms. Discrete approaches with single-codebook visual tokenizers align naturally with text modeling but have limited representational capacity. Continuous and hybrid approaches retain richer visual representations, but they model text and images in heterogeneous spaces with different training objectives, potentially introducing optimization conflicts between modalities with misaligned representation spaces. These choices expose a central question: how to efficiently model high-capacity visual representations alongside textual content in a shared optimization space within a single backbone. We present Intern Lumina U2, to our knowledge the first diffusion language model to represent multi-codebook visual tokens in a fully discrete space. Each visual position is represented by a group of codes from complementary codebooks, increasing its representational capacity while preserving compatibility with discrete text modeling. At the input, the embeddings are concatenated at each position; at the output, a lightweight multi-codebook autoregressive head predicts the codes within each position sequentially, while the diffusion backbone processes all positions in parallel. Built on the unified 4D representation of AToken, Intern Lumina U2 supports image, video, and 3D inputs within a single backbone and achieves leading performance among unified models in visual understanding, image generation, and image editing. We further build a full-stack training, inference, and evaluation system on both Ascend and NVIDIA platforms to verify the cross-platform effectiveness of our model. We also improve the inference efficiency through a stability-aware sampling strategy, which combines confidence-plateau-guided unmasking approach with drift-triggered cache refreshing mechanisms, accelerating image generation by 4.45x. --- ### O-RAN-Native Jamming Detection Under Network Heterogeneity Authors: Sneihil Gopal, Fernando J. Cintrón, Richard A. Rouil Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.20816v1 Radio-frequency jamming threatens cellular network operations in contested environments. The Open Radio Access Network (O-RAN) architecture exposes per-User Equipment (UE) telemetry through the E2 interface, enabling Key Performance Indicator (KPI)-based jamming detection without proprietary hardware. However, operational deployment demands detection methods that generalize across heterogeneous networks. We propose a Statistical Ensemble Method (SEM) combining adaptive Median Absolute Deviation (MAD)-based baseline detection, count-based anomaly detection, and abrupt change detection through a weighted voting system. SEM operates in two modes: a cold-start mode requiring no labeled data for immediate deployment, and a supervised mode where parameters are refined offline via grid search as labeled data accumulates. We evaluate SEM against five machine learning (ML) classifiers and five deep learning (DL) sequence models using approximately 25 hours of testbed data comprising logs from eight heterogeneous 5G environments, employing both single-environment and multi-environment leave-one-out (LOO) validation. Our analysis indicates that under conditions not encountered during training (distribution shift), learning-based models tend to lose recall and miss jamming events, whereas SEM, even in cold-start mode, maintains detection capabilities at the cost of false alarms. Furthermore, SEM's parameter optimization can be mapped to O-RAN's Non-RT RIC as an rApp for continuous refinement, allowing operators to transition to learning-based alternatives once corpus coverage is sufficient. --- ### Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards Authors: Xuanchang Zhang, Tong Zhang Published: 2026-10-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.20814v1 Reinforcement learning with verifiable rewards often trains language models on responses generated by a different, possibly stale behavior policy. Correcting this mismatch with learner-to-behavior importance weights can introduce high variance for long responses. We introduce Gibbs-Gap Policy Optimization (GGPO), which minimizes a log-mean-exp contrast of KL-adjusted rewards among responses to the same prompt, without learner-to-behavior importance weights. We derive GGPO from KL-regularized policy optimization: on policy, its population loss is exactly the KL-regularized optimality gap, and under suitable coverage the learner's single-response expected reward is at least the behavior policy's best-of-$K$ reward, minus terms for the raw finite-group loss, regularization, and finite training data. We characterize reference refresh through exact Gibbs-target composition and a finite-data final-policy reward bound under local reference control and tokenwise behavior mismatch. This refresh is empirically important: in an ablation, fixed-reference GGPO scores $32.96$ on the five-benchmark problem-weighted average, versus $46.58$ with the default refresh schedule. Experiments on mathematical reasoning further show that GGPO outperforms GRPO and AGRO under training-inference mismatch and on fixed offline data, while maintaining its performance as controlled policy staleness grows. --- ### RIGen: Beyond Action Following with Reciprocal Interaction in Generative Gameplay Authors: Mengfei Li, Yi Zhang, Xingtong Ge, Lunjie Zhu, Fangyu Lin, Peng Li, Guanglu Song, Yu Liu, Wei Xue, Wenhan Luo, Yike Guo Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.20811v1 Generative gameplay requires more than immediate responses to player actions.Actions should have persistent consequences, while the generated world should act according to its own state and rules, shaping the player's situation and subsequent choices. Video generation captures local dynamics, but limited history, partially observed game state, and the need for contextual behavior decisions make such interactions difficult to sustain through audiovisual prediction alone. We introduce \rig (Reciprocally Interactive Generation), a framework for reciprocal interaction in generative gameplay. \rig combines persistent state and configurable rules, contextual interaction reasoning, and action-conditioned audiovisual generation. Together, these components make interaction consequences and actor behavior jointly determine generated content while maintaining consistency between game state and visible outcomes. We construct a Xonotic gameplay dataset to train an audiovisual generator for learning dynamics and interactions. Further post-training enables \rigarena, an interactive generative first-person shooter (FPS) prototype. Experiments demonstrate more reliable combat outcomes and reciprocal interaction between the player and the generated world. Project page: https://murphylmf.github.io/RIGen/. ---