arXiv:2610.11373v1 Announce Type: new Abstract: Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities. Existing approaches typically address this challenge by carefully designing how model parameters are updated. In contrast, prompt optimization avoids costly parameter updates while achieving competitive or even superior performance to reinforcement learning methods such as GRPO on individual knowledge-intensive and reasoning tasks. This raises a natural question: \textit{Can prompt optimization, as an efficient adaptation approach, be directly applied to continual learning?} Our analysis shows that, under sequential task adaptation, it suffers from catastrophic forgetting, while optimized prompts accumulate rules that overfit to local task distributions. To address these limitations, we propose \emph{Evolving Functional REpertoires} (EFRE), which replaces a single prompt with a repertoire of functions that evolves as new tasks arrive: compatible updates refine existing functions, while conflicting updates trigger the emergence of new ones. On a three-task continual-learning stream, EFRE achieves a final average performance 7.50 percentage points higher than GRPO. Moreover, after adaptation to the Bio task, its performance on FinQA decreases by only 1.56 percentage points, compared with 25.10 percentage points for the base prompt optimization method. We further instantiate EFRE in a minimal agent system and observe consistent improvements across different backbone models. Overall, these results demonstrate EFRE's strong performance in continual learning for large language models and highlight its substantial potential for continual learning in advanced agent systems.
arXiv:2610.11366v1 Announce Type: new Abstract: Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces. However, this paradigm inherently suffers from prohibitive inference-time overhead and external dependencies. In this paper, we explore whether an MLLM can internalize this agentic capability to operate entirely tool-free. We begin with a simple observation: prompting an MLLM with summarized execution traces of a spatial coding agent naturally unlocks the model's internal spatial Chain-of-Thought (CoT). Motivated by this, we introduce SpatialOPSD, an on-policy self-distillation framework that internalizes spatial reasoning into a standalone MLLM by formulating verified agent traces as privileged information. To mitigate privileged-information leakage during distillation, we introduce Repetition-Aware Distillation, which combines repetition masking with unlikelihood regularization. Experiments across multiple benchmarks demonstrate that self-distilling SpatialOPSD achieves higher average accuracy than SFT and GRPO on both spatial and OOD datasets, exhibiting superior performance and generalization.
arXiv:2610.11362v1 Announce Type: new Abstract: Binary diffusion models typically require a large number of function evaluations (NFEs) to generate high-quality samples, making practical inference computationally expensive. Reducing NFEs while preserving sample quality without distillation or additional training remains a significant challenge. Existing binary diffusion models define a discrete one-step forward path and then derive the reverse posterior. In low-NFE settings requiring cross-step sampling, they approximate the true multi-step likelihood with a single-step likelihood transition, which severely degrades sample quality. To address this fundamental limitation and decouple the generative dynamics from fixed discrete time steps, we propose Bernoulli Flow Models (BFM). Rather than relying on sequential one-step Markov diffusion chains, BFM defines a unified continuous global Bernoulli probability flow path between data distributions and pure noise, from which we derive analytical closed-form posterior transitions over arbitrary time intervals. Consequently, reducing the inference NFE is no longer an approximation based on skipping discrete steps; it only requires re-evaluating the analytical posterior over a new time grid. This eliminates the structural training-inference mismatch inherent to discrete chains and yields self-consistent low-NFE sampling. Experiments show that BFM is highly robust to aggressive NFE reduction. On LSUN Churches 256x256, a BFM trained with 256 steps achieves an FID of 9.22 using only 16 sampling steps, whereas the state-of-the-art discrete baseline degrades to 204.10. BFM also remains competitive with continuous and discrete generative baselines under standard full-step inference. These results establish BFM as a theoretically rigorous, self-consistent, and practically effective framework for fast binary data generation.
arXiv:2610.11315v1 Announce Type: new Abstract: In diffusion transformers, low-rank branches can mitigate 4-bit weight--activation (W4A4) post-training quantization (PTQ) loss by decomposing each weight into a low-bit residual and a high-precision low-rank component. Existing low-rank PTQ approaches, however, either optimize low-rank compensation and residual quantization separately, often requiring higher ranks, or rely on second-order weight updates without explicitly modeling activation quantization error, which becomes particularly pronounced under 4-bit quantization. To address these limitations, we present \method{}, a unified framework modeling low-rank-assisted W4A4 PTQ as a coupled calibration problem and deriving optimization-based solvers from the joint objective. Eliminating the output-side low-rank factor yields a \emph{deflated Hessian} that discounts residual errors already captured by the low-rank component, while an activation-noise surrogate is incorporated to suppress activation quantization error. Across five diffusion backbones, rank-4 \method{} consistently outperforms rank-4 SVDQuant in PSNR and LPIPS. It further surpasses rank-32 SVDQuant on SANA-1.6B, FLUX.1-schnell, and FLUX.1-dev with an $8\times$ smaller rank and up to $6.25\times$ faster quantization. Furthermore, on the Qwen3-8B LLM, rank-4 \method{} improves MMLU accuracy from 61.50\% to 68.17\% over rank-32 SVDQuant. Overall, \method{} achieves better W4A4 performance with substantially lower rank and quantization cost.
arXiv:2610.11313v1 Announce Type: new Abstract: A fundamental question in neural network architecture optimization is whether the minimum hidden-neuron count required to approximate a target function within a prescribed tolerance can be computed efficiently. This paper resolves this question for two-hidden-layer ReLU networks under an $L^p(\mathbb{R}^d,\mathbb{R}^m)$ approximation constraint. For every fixed $d \ge 1$, $m \ge 1$, and $1 \le p < \infty$, we prove that computing the optimum exactly is NP-hard. The result holds even when the target is represented by a rational ReLU network whose realization is nonzero, componentwise nonnegative, compactly supported, globally Lipschitz, and continuous piecewise affine. The polynomial-time reduction from 3-SAT produces an architecture gap in which unsatisfiable formulas yield an optimum of zero, whereas satisfiable formulas yield an optimum of at least $d+2$. The proof constructs compactly supported polyhedral frustum functions realized by two-hidden-layer ReLU networks and establishes the $L^p$-density of finite linear combinations of box-frustum functions. The results offer theoretical justification for employing heuristic approximation methods in the design of ReLU neural networks, illustrating that attaining a minimal configuration within polynomial time is computationally unachievable.
arXiv:2610.11309v1 Announce Type: new Abstract: Different optimizers can fit the same training data while selecting classifiers with substantially different geometries, but whether this difference provably affects population performance remains unclear. We show that row-wise normalization can achieve strictly higher population accuracy than full-batch Adam, a proxy for random-reshuffling Adam, and exact-SVD Muon in high-dimensional multiclass classification. Under an isotropic Gaussian-cloud data model, this advantage arises because row normalization's class-wise Euclidean geometry asymptotically preserves the population decision-boundary directions, whereas Adam's coordinate-wise geometry and Muon's spectral geometry introduce nonvanishing distortions. Beyond isotropy, the advantage persists for full-batch training on class means with independently oriented class-mean and test-noise covariances. It holds for power-law spectra with class-mean exponent below one, even under heavily anisotropic test noise. When both covariances are diagonal and sufficiently close, the advantage over Adam can reverse, while applying the same random rotation to both restores it by changing only their alignment with Adam's coordinate axes. Synthetic and last-layer language-model experiments support the predicted advantage.
arXiv:2610.11288v1 Announce Type: new Abstract: Conditional diffusion models generate diverse, novel, and high-quality samples under prescribed conditions. However, theoretical understanding of their memorization and generalization remains limited, while recent works have characterized these behaviors primarily in unconditional settings. In this work, we analyze a random-feature conditional score model in the high-dimensional proportional limit, deriving asymptotic expressions for training and test losses. By decomposing the test loss, we show that in the overparameterized regime, increasing model width improves prediction of the condition-dependent mean while reducing within-condition prediction variance, a phenomenon we term "malign generalization." Furthermore, analyzing the training loss reveals that more informative conditions lead to memorization of training samples at smaller widths. These theoretical findings are supported by experiments with U-Net architectures on realistic data.
arXiv:2610.11257v1 Announce Type: new Abstract: Learned representations can lose latent degrees of freedom successively, suggesting a cascade of transitions whose underlying stability principle remains unclear. Here we formulate dimension-wise posterior collapse in variational autoencoder (VAE) as a fluctuation theory around partially collapsed states. Interpreting the negative evidence lower bound as an effective free energy, its quadratic expansion defines a Gaussian theory whose Hessian acts as a mass matrix for latent fluctuations. We show that the collapsed directions form an invariant fluctuation sector and derive its exact mass spectrum in terms of a conditional residual operator. A local reactivation direction lowers the free energy when the decoder variance falls below the residual spectral upper edge, with equality marking marginality. The criterion recovers principal component thresholds in the linear Gaussian VAE limit. Viewed in reverse along continuously connected branches, the reactivation boundary provides a local criterion for successive collapse. Numerical continuation experiments show successive loss of latent dimensions near these spectral marginalities. These results support a spectral cascade interpretation governed by residual information left unexplained by the surviving representation.
arXiv:2610.11252v1 Announce Type: new Abstract: This study presents the Neuro-Memory Fuzzy Inference System (NeMeFIS), a hierarchical machine learning architecture that asymmetrically models acceleration and deceleration in car following behavior by integrating five human memory types procedural, working, episodic, semantic, and declarative. By linking external variables to memory functions via metaheuristics and validating them through factor and p-value analyses, NeMeFIS uncovers latent cognitive influences across Arterial, Collector, and Rural Highway corridors for different types of vehicles. Results from 54 different trained models emphasize cognitive thresholds shaped by driver perception limits and cognitive load. The trained NeMeFIS models outperform traditional statistical and conventional machine learning models in replicating realistic driving behavior, including comparisons with Linear Regression, ANFIS, and LSTM architectures. Fuzzy rule analysis reveals that declarative memory demands the highest rule, especially during deceleration, indicating complex braking decisions. Procedural memory drives acceleration, while semantic and declarative memory guide deceleration. Risk perception also emerges as a key factor, particularly on urban roads. Validated on both heterogeneous and homogeneous datasets, NeMeFIS offers a robust framework for modeling driver cognition. The findings support psychotherapeutic applications and the development of adaptive, human-like decision systems in Connected and Autonomous Vehicles (CAVs) to enhance traffic safety.
arXiv:2610.11247v1 Announce Type: new Abstract: On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully understood. Across code generation and mathematical reasoning, OPD with larger-scale teachers exhibits early loss plateaus, with an average final loss reduction of 25.1% after 200 updates, compared with 96.2% for self-RL teachers, obtained by further reinforcement learning (RL) training of the initial student. To understand this difference, we analyze OPD as an idealized continuous-time dynamical system in the small-learning-rate limit. Our training-log diagnostics associate these plateaus with an early decline in a gradient-based learning-signal proxy while substantial loss remains; these measurements do not establish why the underlying gradient weakens. We further prove a local recovery guarantee for teachers sufficiently close to the initial student in a shared parameterization under regularity conditions, offering a conditional explanation for the success of self-RL teachers in our experiments. Across runs with and without loss plateaus, we observe small relative parameter changes (0.025-0.098%) and high similarity between the student's representations before and after OPD (linear CKA $>0.98$ across layers). These observations suggest that limited representation adaptation may contribute to learning-signal collapse, a hypothesis that remains to be tested. Code is available at https://github.com/leizhao7/opd-learning-signals.
arXiv:2610.11245v1 Announce Type: new Abstract: KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places. We study this mismatch using separate budgets for retained bits and bits fetched per query. ReadKV stores each key and value in a progressive code whose prefixes support different reconstruction precisions. For each query, it allocates key-channel prefixes using the query, computes attention from the reconstructed keys, and then allocates value-token prefixes using that attention. Stored entries remain unchanged. Each stage optimizes a calibrated distortion objective under a fixed budget; we prove exact allocation under diminishing refinement gains and relate these objectives to attention-output error. We also exhibit a finite-dimensional attention family where query-dependent access strictly outperforms every query-independent reader at the same read budget, even with unrestricted competing encoders and decoders. Across six base models, reading four bits on average from an eight-bit cache increases C4 perplexity by at most 0.66%, using about one quarter of the logical reads and half the retained capacity of a 16-bit cache. It is consistently more accurate than storing and fully reading four bits at the same payload-read budget. Retaining more bits than each query fetches is aimed at long-context decoding, where the cache bytes moved per step, rather than the weights, dominate cost. Long-context question answering and retrieval on two instruction-tuned models provide additional quality evidence. On the tested 8K-token, batch-one, single-layer workload on an NVIDIA A10G, a restricted eight-bit ReadKV reader with a two-bit mean payload-read budget has 39% lower latency than the tested TurboQuant codec.
arXiv:2610.11236v1 Announce Type: new Abstract: Low-cost sensors enable scalable indoor air quality monitoring but require calibration because of nonlinear distortions, noise, and temporal drift. The conventional strict pairwise calibration setting requires a co-located reference sensor at each deployment location and does not account for spatial and temporal heterogeneity. To address these limitations, we introduce a six-month dataset comprising multivariate indoor air-quality measurements from low-cost and reference sensors with contextual metadata collected at five locations. Using this dataset, we define four evaluation scenarios. The reference-efficient and location-transfer scenarios evaluate spatial generalization, whereas the long-term drift and event-conditioned scenarios assess robustness to gradual and abrupt distribution shifts. Based on these scenarios, we derive design requirements and propose a lightweight temporal model that combines input-window compression with residual temporal and feature fusion. Experiments show strong calibration performance across all four scenarios with low edge-inference cost.
arXiv:2610.11206v1 Announce Type: new Abstract: Flat loss landscapes have long been linked to better generalization in neural networks. However, its role as a causal mechanism for generalization is less established. Grokking provides an unique testbed to understand this distinction: models are prone to fit observed data using non-generalizing structure and remain in that regime for prolonged periods, transitioning to generalization only under particular training conditions. In this work, we study whether flat loss landscapes can act as a driving mechanism in this transition. While recent work has argued for flatness as a necessary geometric condition for this transition, we find that biasing training toward flatter solutions using sharpness-aware minimization (SAM) is insufficient to reliably induce this transition, despite producing flatter solutions. However, when SAM is paired with mechanisms that drive generalization such as weight decay, an interesting property emerges: SAM can accelerate the transition to generalizing solutions by up to 4x at the epoch-level. We theoretically untangle this relationship between SAM and weight decay using a minimal interpolating two-layer ReLU model with both memorizing and generalizing solutions. We show that even in this simple setup, flatness alone cannot distinguish a memorizing solution from a generalizing one, while weight decay favors generalizing solutions. However, under a local stability analysis, there exists a window where a memorizing interpolant is locally stable under gradient descent but unstable under SAM in the low-norm regime, which can explain SAM's ability to accelerate this transition. Overall, our results provide a more interpretable account of the role of flatness in driving generalization, especially in settings where models are vulnerable to minimizing loss through learning non-generalizing structure.
arXiv:2610.11170v1 Announce Type: new Abstract: Long-term time series forecasting (LTSF) models predominantly employ patch-based encoders terminated by a flatten readout head that maps the entire encoded historical memory to all future steps through a single shared projection. This implicit coupling of future positions obscures position-specific historical-to-future alignment and amplifies sensitivity to corrupted inputs and extreme supervision noise. We present SACQ, a plug-in structured prediction head that replaces flatten readout while keeping the encoder unchanged. SACQ adopts a two-stage decoding pipeline: it first establishes a coarse patch-grid forecast scaffold, then refines each future position through cross-attention over historical memory and merges the attention-derived correction with the coarse scaffold via a learned per-patch gate. To stabilize optimization under long horizons and noisy labels, we further propose a batch-adaptive scaled log-cosh loss that automatically calibrates robustness to the current residual scale, suppressing outlier gradients while preserving MSE-like sensitivity for typical errors. SACQ attains top-tier test MSE/MAE across PatchTST, DLinear, and patch-Mamba backbones with only modest incremental overhead in parameters and latency. Under inference-time input corruption and training-set label-noise stress tests, SACQ substantially outperforms flatten readouts, with ablation studies validating each architectural component.
arXiv:2610.11165v1 Announce Type: new Abstract: Multivariate long-horizon forecasting is critical to electricity load scheduling and traffic flow management, and to financial risk control. Existing deterministic backbones output a single trajectory, masking heterogeneous prediction difficulty across horizons and channels and providing no localized reliability signal. We present CARE (Corrective branch with Aligned context and Relative-error Estimation), a lightweight plug-in that enhances any deterministic forecaster without architectural redesign. Operating in parallel with the base model, CARE resamples historical context to match the forecast horizon, learns residual correction patterns from this aligned history, and applies scale-aware bounded updates modulated by per-coordinate sigmoid risk gates. A multi-objective loss jointly optimizes forecast accuracy, residual tracking, risk alignment, and base-model anchoring. Across eight benchmarks with three representative backbones, CARE improves accuracy with marginal parameter and latency overhead. Its risk gates reliably identify high-error regions: on Weather, the highest-gate tertile exhibits nearly four times the error of the lowest-gate tertile, offering planners an interpretable per-step trust signal. Code is available at https://github.com/CG-BNYC/CARE.
arXiv:2610.11133v1 Announce Type: new Abstract: Operating System (OS) Fingerprinting is a technique that can be used to identify a network's operating systems by evaluating network traffic in the form of TCP/IP packets. This research will explore the effectiveness of passively identifying operating systems on the CIC-IDS2017 dataset, a collection of over 47 gigabytes of pcap files with their corresponding operating systems. This research also proposes a new command line interface, OsirisML, which uses nPrint to preprocess the data into tabular data and XGBoost to apply ML to the data to generate, retrain, and test ML models. When packets are split randomly between training and testing, OsirisML models reach an accuracy of 97.66% on a down-sampled subset of the Friday capture and 84.69% on the entire capture. On the entire Monday capture, which contains no attacks, OsirisML reaches an accuracy of 73.83% and an F-1 score of 79.38%.
arXiv:2610.11085v1 Announce Type: new Abstract: Offline multi-task reinforcement learning (Offline MTRL) heavily depends on the quality and distribution of pre-collected data. However, existing methods mainly focus on algorithmic optimization, with less emphasis on data-level improvements to enhance learning ability and generalization performance. This paper, from a data perspective, reveals three key bottlenecks that limit Offline MTRL performance:(i) ineffective utilization of prompts length under diverse task complexities, and (ii) semantic irrelevance of randomly sampled prompt segments, (iii) misleading supervision induced by fragmented and discontinuous trajectories. To address these challenges, we propose DaCe-DT, a robust offline MTRL framework designed to be insensitive to heterogeneous task complexities and data quality, featuring length-gated prompt masking (LGPM), retrieval-augmented prompt construction (RAPC), and value-adaptive return calibration (VARC). Together, these mechanisms enable DaCe-DT to deliver data-centric prompt adaptation and trajectory refinement, resulting in robust multi-task generalization and stable policy learning amid heterogeneous offline data and tasks. Experimental results on Meta-World show that DaCe-DT consistently outperforms state-of-the-art methods, achieving an average improvement of 11.73% on optimal datasets and an improvement of 13.34% on suboptimal datasets, demonstrating its effectiveness in learning stably from imperfect data and improving overall multi-task performance.
arXiv:2610.11074v1 Announce Type: new Abstract: We establish near-optimal regret bounds for budget-constrained online learning against arbitrary classes of budget-pacing experts in the adversarial setting. In particular, given any class of $F$ experts and a candidate budget pacing schedule, we provide a full-information algorithm which obtains regret $O(D \sqrt{\log F}+ \sqrt{T\log F})$ against all experts whose cumulative spending stays within distance $D$ of this schedule, matching lower bounds established by Braverman et al. (2025). We additionally show that our technique extends to various problems in online resource allocation, where the learner gets to see the rewards and costs of the current options available to them, and establish $O(D\sqrt{\log F})$ regret bounds when fractional allocation is allowed. This is the first algorithm we are aware of which can achieve $o(\sqrt{T})$ guarantees for such tasks.
arXiv:2610.10996v1 Announce Type: new Abstract: Latent reasoning models repeatedly update a latent state using the same recurrent block. As the recurrent depth increases, the sequence of latent states may converge to a compact subset of the state space without necessarily converging to a fixed point. Existing models typically predict by applying a prediction head to a single latent state. However, the latent state can continue to change even after many updates, potentially making predictions unstable across recurrent depths. To address this instability, we introduce invariant-measure reasoners (ImR), a framework that uses an invariant measure as a stable representation. This measure describes the long-run distribution of latent states on the compact subset and is invariant under updates by the recurrent block. ImR predicts from the expectation of the prediction head's output under this measure. We use ImR in two ways: fine-tuning only the prediction head of existing models and training models from scratch. Both approaches reduce prediction instability and improve accuracy in many settings on maze and Sudoku tasks. In some settings, models trained with ImR exhibit non-fixed-point behavior more frequently than existing models yet achieve high accuracy even with such behavior, unlike existing models. These results suggest that ImR can leverage otherwise destabilizing dynamics for latent reasoning.
arXiv:2610.10989v1 公告类型：new 摘要：研究人员一直在持续探索有效的一步生成模型，而 Drifting Models（Deng et al., 2026）近期展现出了一步生成的巨大潜力。已有研究揭示了 Diffusion & Flow Style Generative Models（DFSGMs）（Ho et al., 2020；Song et al., 2020a；b；Lipman et al., 2022；Liu et al., 2022）与 Drifting Models（Li & Zhu, 2026；Lai et al., 2026；Turan et al., 2026）之间的联系。然而，据我们所知，尽管二者的优化目标公式几乎完全相同，尚无人在 Drifting Model 与广泛使用的蒸馏方法 Distribution Matching Distillation（DMD/DMD2）（Yin et al., 2024b；a）之间建立精确的对应关系。在本文中，我们证明，通过将预训练 DFSGMs 中的速度场/噪声场转换为 Drifting Models 中的吸引力场，并从生成分布中估计排斥力场，训练 Drifting Model 在本质上等价于 Distribution Matching Distillation。基于这一等价概念，我们从 Drifting Model 的视角出发，提出了一种基于 DMD 的改进方法——Multi-Bandwidth Distribution Matching Distillation（MBDMD）。
arXiv:2610.10972v1 Announce Type: new Abstract: Assessing useful reuse in neural PDE solvers is challenging: final accuracy can reflect source learning and target-time computation. Our reuse contract separates solution accuracy, learning contribution, and numerical utility through paired state comparisons, matched target information and budgets, and cost accounting. A literature audit extracts 18 version-specific protocol records from 12 papers, documenting retained states, target-time resources, and reported controls. For a fixed linear system and residual tolerance, we construct two initial guesses with identical solution-error, energy-error, and residual norms, reaching the same solution with different conjugate-gradient (CG) iteration counts. Across 240 source-training trajectories, two linear PDE families, Fourier neural operators and convolutional networks, a fixed predictor's benefit reverses across correction algorithms. Among pairs with both relative prediction errors less than or equal to 5 percent on 64 in-distribution tasks (63 by 63 interior grids), reductions in all three norms accompany more CG iterations, at mean taskwise rates of 23.5 percent and 23.9 percent in two libraries. Work-based selection saves 2.50-3.33 CG iterations on held-out in-distribution tasks; matched adaptation demonstrates finite-budget pretraining value. Independent batches confirm a 0.73 percent complete online saving for one physics-trained Fourier neural operator against zero-initialized Poisson-preconditioned CG. Reuse requires matched state comparisons and downstream computational evidence.
arXiv:2610.10965v1 Announce Type: new Abstract: The Muon optimizer orthogonalizes each update matrix, setting all of its singular values to one, and has proven highly effective for training large language models. It remains unclear, however, whether this success comes from amplifying small singular directions that gradient descent neglects or from suppressing large, degenerate directions that disrupt training. We introduce Spectrally Targeted Muon, which orthogonalizes only the singular values above or below a threshold $\tau$, so that varying $\tau$ interpolates between normalized SGD and Muon. It isolates the relevant singular subspaces with projections computed by Newton-Schulz iteration on a shifted Gram matrix, so no SVD is needed. We evaluate these variants on the CIFAR-10 and NanoGPT speedruns, tracking the effective rank of gradient, update, and weight matrices and a new metric, the alignment of updates with the tangent space of the weight matrix's isospectral manifold. We find three things. First, the small singular values of the momentum are not noise. Orthogonalizing everything except the few largest singular values of each matrix nearly matches Muon while touching only a small fraction of the momentum, whereas orthogonalizing only the top falls well short even though it holds almost all of it. On language models every momentum singular value is far below one, so targeted orthogonalization can only amplify, and Muon wins by making directions that are too small to train on at their raw scale trainable. Second, shrinking the largest singular values is what keeps the parameter spectrum flat; this is cheap, and it is not what drives the loss. Third, AdamW differs from Muon mainly in how slowly it builds structure, which explains its slower start and why warmup helps AdamW but only hurts Muon.
arXiv:2610.10957v1 Announce Type: new Abstract: Production AI systems deployed in high-stakes domains accumulate a governance liability that existing monitoring frameworks fail to detect: the progressive inability to explain individual decisions when regulators, auditors, or affected individuals demand accountability. We introduce TRACE (Transparency, Risk, Accountability, Compliance, and Explainability), a seven-instrument governance framework for measuring, tracking, and remediating Explainability Debt in production AI systems. The foundational instrument, the Explainability Debt Score (EDS), quantifies the proportion of production decisions falling below a governance-defined explainability confidence threshold at any point in time. Complementary instruments include DART (Debt Accumulation Rate Tracker for breach forecasting), SHIV (Scenario Health and Integrity Validator for daily governance), FDE (Feature Drift Evaluator for causal attribution), HVE (Human Validation Engine), AIDE (Audit Intervention Decision Engine), and ZERO (Zero Explainability Risk Optimiser for remediation). Through a twelve-month longitudinal case study of a production fraud detection system processing 50,000 daily financial transactions, achieving 98.46% accuracy and ROC-AUC of 0.9990, we demonstrate that an EDS of 0.23 on audit day was statistically predictable six months in advance using DART trajectory analysis (beta = 0.008/week, R-squared = 0.94, 95% CI: [0.006, 0.010]), and that 78% of Explainability Debt was concentrated in the highest-regulatory-risk decision category (transactions above $10,000), a risk asymmetry completely invisible to system-level metrics. TRACE provides the first quantitative operational architecture for EU AI Act Article 13 compliance in production AI deployment, establishing a new subdiscipline of explanation governance distinct from explanation generation.
arXiv:2610.10952v1 Announce Type: new Abstract: Brain signal decoding is challenging because neural recordings are noisy and vary across individuals, while labeled data are often limited. Recent attention-based models on the symmetric positive definite (SPD) manifold have nevertheless achieved strong performance using covariance and connectivity representations, yet the contribution of learned token weighting remains unclear. We examine two representative architectures, MAtt (based on log-Euclidean geometry) and GBWAtt (based on generalized Bures--Wasserstein geometry), and find that their learned attention weights remain close to uniform after training. We relate this behavior to bounded similarity parameterizations that, under the original softmax scaling, limit attention-weight contrast. Moreover, replacing learned weights with uniform weights, throughout training and evaluation, has little effect on mean predictive performance while preserving each model's original aggregation geometry. Motivated by these findings, we introduce SPD-MetaFormer, an attention-free architecture built on uniformly weighted Fr\'echet aggregation under log-Euclidean geometry. Its backbone uses a geodesic residual to update a summary token and a shared spectral feedforward map to transform all tokens, followed by a learned weighted readout. Token states remain SPD-valued until tangent-space classification. Across three EEG benchmarks, SPD-MetaFormer achieves competitive results relative to published Euclidean and manifold baselines. Separate matched reproductions test learned versus uniform weighting within MAtt and GBWAtt. These results suggest that, in the short-sequence and limited-data regimes studied, carefully designed SPD architectures can provide a simpler and effective alternative to adaptive manifold attention.
arXiv:2610.10933v1 Announce Type: new Abstract: Spiking language models face a tradeoff between representing continuous semantic features over short temporal windows and retaining costly nonlinear attention operations. We introduce Spora, which jointly designs spike encodings and attention operators. Binary temporal weights let $T$ spikes represent compositional values with up to $T$ bits of capacity, compared with $O(\log_2 T)$ bits for spike-count readout. Unipolar Binary Spiking (UBS) uses thresholds and spike-triggered residual decay to produce non-negative integer codes; Bipolar Binary Spiking (BBS) separates sign and magnitude and learns a scale for signed activations. These representations support accumulation-and-shift dot products and integer-exponent mappings in attention. With four time steps, Spora achieves 76.6 average GLUE score and 44.1 CoLA MCC, improving over SpikeLM by 1.2 and 6.2 points, respectively. Extending BBS to six steps raises these scores to 78.2 and 47.4. Conditional-decay analysis, matched-budget activation-quantization comparisons, event-workload statistics, and fixed-point evaluation further characterize the connection between encoding fidelity and computational cost.
arXiv:2610.10931v1 Announce Type: new Abstract: In memetic symbolic regression, candidate structures are compared after coefficient calibration, so the calibration protocol itself contributes to evolutionary selection. Standard centralized calibration evaluates each structure at its pooled-sample optimum, ignoring how stable this calibration is under covariate shifts, and can thus favor structures whose fit relies on sample-specific coefficients. We propose Dirichlet-Sinkhorn Constant Averaging (DSCA), a calibration strategy that partitions the optimization data into equally sized subsets with different covariate distributions, calibrates each candidate independently on every partition, and evaluates it at the mean of the resulting parameters. We show that the excess loss of DSCA relative to centralized calibration vanishes at the population level for correctly specified, identifiable expressions, whereas under misspecification it persists when partition-specific calibrations do not aggregate to the pooled optimum. On synthetic benchmarks and ten real-world datasets, DSCA improves functional recovery and the accuracy-complexity trade-off over centralized Broyden-Fletcher-Goldfarb-Shanno and Levenberg-Marquardt calibration, under selection by negative log-likelihood and by the Akaike and Bayesian information criteria. Mechanism analyses associate the DSCA excess loss with the generalization gap and show that the effect is not reproduced by repeated centralized fitting. These results indicate that controlled heterogeneous calibration provides a complementary source of selection pressure in symbolic-regression search.