Papers

Spiking Neural Networks (SNNs) have emerged as an energy-efficient alternative to conventional neural networks, demonstrating strong performance in computer vision and robotics. More recently, SNNs have been applied to time series forecasting (TSF), with methods exploring spiking temporal backbones, spike-compatible positional encodings, Fourier-domain processing, and redesigned neuron dynamics. However, existing SNN forecasting approaches process variables independently, lacking explicit mechanisms for modeling inter-variable dependencies. This is a critical limitation in multivariate settings, where cross-variable correlations carry substantial predictive information. We propose Spiking Fourier Graph Operators (SpikF-GO), which addresses this gap by combining a hypervariate graph formulation in which every scalar observation becomes a graph node with spike-driven spectral processing. SpikF-GO introduces a Hard Concrete frequency gate for learnable sparse frequency selection and a Complex LIF gate that applies independent spiking neurons to real and imaginary Fourier components, preserving binary, event-driven computation throughout the spectral domain. We further present a variant incorporating Central Pattern Generator-based positional encodings for stronger long-range temporal modeling. Evaluated on eight benchmarks under a unified experimental protocol, SpikF-GO achieves the best average rank among all SNN methods and outperforms its ANN counterpart, FourierGNN, at reduced energy cost. SpikF-GO maintains competitive accuracy even at substantially smaller embedding dimensions, thereby achieving significant energy reductions. To our knowledge, this is among the first works to bring graph-based multivariate modeling into the spiking domain for TSF and the first to provide a unified comparison across SNN forecasting architectures under a common experimental protocol.

AdamW is a default optimizer for deep learning, but its moment states add two parameter-sized buffers to training memory, increasing the cost of large-scale pretraining. We propose Gefen, a memory-efficient optimizer that automatically shares second-moment estimates across parameter blocks and quantizes the first moment using a learned codebook. Gefen reduces AdamW's optimizer memory footprint by up to 8x while maintaining performance, saving 6.5 GiB per billion parameters. Prior work shares second moments across parameters grouped along the Hessian's block-diagonal structure, but relies on hand-specified architectural rules and leaves unexplained why such grouping works. We prove that large mixed Hessian entries constrain the ratio of squared gradients toward one, explaining why shared second moments are accurate when the squared gradients they pool are similar. The Hessian need not be computed: its block structure is inherited by squared gradients, allowing blocks to be found directly. Gefen therefore infers block structure from initial squared gradients, requiring no architecture-specific metadata or user-tuned hyperparameters beyond AdamW defaults. Gefen learns an exact histogram-based dynamic-programming quantization codebook and reuses the blocks for first-moment scaling. Across diverse pretraining experiments, Gefen achieves the lowest peak optimizer memory among compared methods that maintain AdamW-level performance. In single-machine and distributed training, the reduced footprint enables larger microbatches and substantially improves throughput over AdamW, making Gefen a drop-in replacement that can train larger models or use larger global batch sizes. We provide the complete Python implementation, including fused CUDA kernels at https://github.com/ndvbd/Gefen

Vision-Language-Action (VLA) models excel at mapping visual inputs and natural language instructions directly to robotic control policies. However, because they are trained primarily to fit behavioural demonstration data, they do not explicitly enforce fundamental physical principles such as rigid-body dynamics or contact constraints. This exposes a critical physics gap: standard temporal smoothing applied on top of single-step or chunked VLAs trades trajectory quality for added failures that short-term memory cannot resolve. To bridge this gap, we introduce PhysVLA (Physics-VLA), a plug-and-play, inference-time framework designed to wrap any frozen VLA backbone without retraining, fine-tuning, or weight access, with less than 1 ms of overhead per control step. PhysVLA intercepts the predicted control action, captures only the simulator or system state, and applies a dual-layered correction: (i) a phase-aware finite-state machine that structures discrete task segments (approach, grasp, transport, and place), and (ii) a selective Euler-Lagrange gate that activates only when a dynamics oracle detects kinodynamic inconsistency. Evaluated across OpenVLA, OpenVLA-OFT, Force-VLA, and Generalist-VLA on LIBERO-Spatial with a 7-DoF Franka Panda, the framework delivers absolute success rate increases of up to 17% and stability increases of up to 19% with no per-task regressions, improves trajectory efficiency by up to 15% across all four backbones, and shows up to a 10x improvement in trajectory jerk robustness on a Robosuite Lift cross-simulator sweep. We further validate the framework on a real Agilex Piper arm with a pick-and-place task, confirming that PhysVLA transfers to physical hardware without retraining, with success-rate improvements of up to 50%, establishing physical awareness as a composable, backbone-agnostic runtime module.

Accurate estimation of long-term care transition probabilities is central to disability insurance pricing, reserving, and solvency assessment. Classical actuarial multi-state models commonly rely on Markov, semi-Markov, or proportional-hazard specifications, which provide a direct connection to cohort projection but may be restrictive for irregular longitudinal health data with nonlinear aging patterns and heterogeneous covariate histories. This paper develops a well-calibrated estimator of multi-state transition probabilities for irregular longitudinal health data. The model learns from individual health history, incorporates the time elapsed between observations, and conditions transition probabilities on demographic and socioeconomic attributes. It produces a valid probability distribution over the next observed health state, with four possible states: healthy, mild disability, severe disability, and death. Individual probabilities are aggregated by age group and origin state to form transition matrices compatible with actuarial cohort projection. Using longitudinal data from the Health and Retirement Study, we compare the proposed estimator with logistic regression, gradient-boosted trees, a recurrent neural network, and a last-state persistence benchmark. The evaluation considers probabilistic accuracy, endpoint discrimination and calibration for severe disability and death, risk concentration, and transition matrix error after aggregation. The proposed estimator improves severe disability discrimination relative to logistic regression and gradient-boosted tree benchmarks, maintains strong calibration, and yields the lowest transition matrix error among the evaluated models in the held-out test analysis. Results show that a structured machine learning estimator can support long-term care transition modeling when judged by calibration and projection fidelity, beyond discrimination.

Unlearning aims to remove the influence of specific training data sources, but this has proved challenging because the contributions of different sources are entangled within the model. Isolating source contributions to disjoint parameters makes removal easier, though it obstructs joint learning across sources. We propose NULLs (Natively Unlearnable LLMs), a model class that satisfies the two opposing goals of isolating source-specific contributions and learning jointly across sources, by training a set of shared backbone neurons alongside a pool of sparsely activated sinks. During training, information specific to a source naturally concentrates in its sinks while information shared across sources accumulates in the backbone. A source is then unlearned at deployment by disabling its corresponding sinks, with no gradient updates and no access to the retained data. We show that NULLs scales to Wikipedia's ~6M articles, isolating each as an independent source. Unlearning a single article removes knowledge specific to it while preserving facts shared with semantically related articles, closely matching retraining from scratch. We note that unlearning with NULLs is also robust: in a case study of unlearning the Harry Potter books, NULLs resists both adversarial extraction and relearning that reverses post-hoc unlearning. Finally, NULLs preserves general language capabilities, matching a standard transformer on downstream benchmarks. Together, these results suggest that source-level unlearning need not be an afterthought. It can be built natively into LLM training while retaining the benefits of shared representation learning.

Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores without reflecting visual grounding. Prior work treats this as a single failure mode. We argue it is two. Using Mirage Probes, a contrastive probing framework that pairs paraphrased question variants with matched mirage and non-mirage labels on the same image, we show that mirage behavior is linearly decodable from internal activations across residual stream, MLP, post-attention, and attention-head sites in two open-source VLMs. We demonstrate that a Naive Bayes text baseline cannot recover this signal, ruling out surface lexical confounds. Cross-benchmark separability patterns, together with a novel Prior Harnessing Index (PHI) measuring how much a model can answer from text alone, expose two distinct regimes: textual biases, where the model answers from language priors without engaging visual representations, and spurious images, where it constructs false visual content in latent space and answers as if grounded. The distinction has direct mitigation consequences: text-distribution cleaning can address the first regime but cannot reach the second, since spurious-image mirages live in the model's visual representations rather than its text. Faithful visual grounding will require interventions at the representational level.

We present an end-to-end pipeline for estimating stellar parameters from Sloan Digital Sky Survey Data Release 12 spectra using a fully connected multitask neural network with residual blocks, whose hyperparameters are tuned via Bayesian optimization. The preprocessing pipeline includes per-spectrum standardization, RobustScaler normalization of the target variables – effective temperature $T_{\mathrm{eff}}$, metallicity $[\mathrm{Fe/H}]$, and surface gravity $\log g$ – and data augmentation via Gaussian noise injection. On a held-out test set, the model achieved Mean Absolute Errors (MAE) of $59.76~\mathrm{K}$ for $T_{\mathrm{eff}}$, $0.103~\mathrm{dex}$ for $[\mathrm{Fe/H}]$, and $0.130~\mathrm{dex}$ for $\log g$. Normalized against the full-scale range of each parameter, these results represent range-normalized errors between $1\%$ and $3\%$, achieved with a highly efficient model complexity of approximately 540,000 trainable parameters. These results demonstrate that a compact residual multitask architecture, combined with principled signal preprocessing, provides a parameter-efficient solution for nonlinear parameter estimation in large-scale spectral datasets. In particular, the proposed model achieves competitive performance with substantially lower complexity than deeper neural network baselines.

Muon is an increasingly widely used optimizer that replaces a gradient $G=USV^\top$ with its polar factor $UV^\top$, thereby flattening the singular spectrum. However, full flattening discards singular-value information that may matter for adaptation. We introduce Muon$^p$, a Muon-style optimizer that instead uses fractional spectral-power updates $US^pV^\top$ for rational $p\in(0,1)$, interpolating between Muon and gradient descent. To make it practical, we prove that fractional spectral powers cannot be computed by any fixed univariate polynomial iteration, and furthermore derive low-degree odd bivariate recurrences that approximate $US^pV^\top$ using only matrix multiplications, preserving Muon's matrix-multiplication-only structure and compute complexity. We show that Muon$^p$ maximizes the linear improvement in loss under the Schatten $q$-norm for $q=1+\frac{1}{p}$. Empirically, Muon$^p$ is especially effective for finetuning: on billion-scale models, Muon$^p$ improves validation perplexity and downstream task performance. We further analyze when Muon$^p$ is less suitable, through the lens of spectral geometry. Our results reveal important insights on when preserving the singular spectrum can bring significant gains, and introduce a principled way to achieve them.

Long Chain-of-Thought (CoT) reasoning improves LLM problem-solving but is computationally expensive due to sequential token generation. While recent works explore reasoning in continuous latent spaces to bypass discrete token generation, they often struggle with training stability and fail to scale to complex, long-horizon tasks due to lack of supervision signal. We propose SuperThoughts, which compresses pairs of consecutive CoT tokens into single latent representations and decodes two tokens per step via a lightweight Multi-Token Prediction (MTP) module. This preserves discrete token supervision at training time while doubling throughput at inference time. We finetune Qwen2.5-Math-1.5B-Instruct, Qwen2.5-Math-7B-Instruct, Qwen2.5-Math-14B-Instruct, and evaluate on MATH500, AMC, OlympiadBench, and GPQA-Diamond. With a confidence-based adaptive mechanism that falls back to standard decoding when uncertain, SuperThoughts achieves $\sim$20–30% CoT length reduction while maintaining accuracy with minimal degradation (1-2 points accuracy drop on most tasks).

Many materials and chemical systems exhibit history-dependent responses, where functional outcomes are governed not only by final-state variables but by the time-dependent sequence of fields, temperatures, or chemical potentials applied during operation. Discovering new processing protocols is therefore a high-dimensional search problem in which the control variable is an entire waveform or sample history, and conventional strategies either remain confined to conservative interpolative families or become prohibitively measurement intensive. Here, a closed-loop workflow is introduced that couples evolutionary search over a compact waveform representation with uncertainty-aware deep kernel learning to generate, rank, and experimentally validate candidate protocols. Applied to ferroelectric thin films, with the scanning-probe tip-bias waveform as the protocol and the nonlinear electromechanical response as the reward, the workflow discovers waveform families that enhance nonlinearity by de-aging the film. Spatially resolved before/after measurements show that the best-performing waveforms selectively activate pre-existing, weakly pinned domain-wall segments, whereas the worst drive long-range irreversible switching. This framework reframes protocol tuning as out-of-distribution discovery, generalizable to synthesis and annealing trajectories, battery formation protocols, and other high-dimensional control problems.

Mobile networks continue to grow in complexity and next generation networks are expected to support both increasing traffic loads and more diverse services. As network complexity rises, optimizing antenna parameters under dynamic or changing objectives becomes increasingly challenging. We propose a novel multi-agent reinforcement learning (MARL) algorithm for high-level control and orchestration of mobile networks. The Temporally Consistent Graph Q-Network (TC-GQN) algorithm learns a self-predicting representation of the whole network that is task-independent and aggregates information from all base-stations. A graph neural network is trained using a global reward function to assign coordinated local actions based on the learned encoding of the global network state. We evaluate the algorithm in a simulated environment to orchestrate an energy-saving feature across multiple sectors and multiple carriers under different quality of service (QoS) constraints. The proposed algorithm outperforms state-of-the-art graph-based baselines and a competitive rule-based controller by improving hardware sleep time while maintaining QoS. Moreover, the learned representation enables rapid adaptation to changing intents.

Autonomous network-security response systems promise to reduce Security Operations Centre (SOC) reaction latency, but reward-only multi-agent reinforcement learning (MARL) can improve security reward while remaining non-deployable. We present a safety-contract graph MARL framework and instantiate it as ACD$^3$-GAT (Adaptive Constrained Counterfactual Decisioning with a Graph Attention Network encoder), an architecture that separates simulator observations from reusable operational budgets, constrained optimization, graph state encoding, and counterfactual action screening. We evaluate the method in CAGE Challenge 4, where agents operate under budgets for Mean Time to Recover (MTTR), false-positive response, and firewall change-management disruption. Across the benchmark, every unconstrained method violates the SOC downtime budget in 100% of evaluated episodes, with mean downtime proxy costs of 311-430 against a budget of 50. This complements prior CAGE Challenge 4 findings by showing that reward-only learning lacks operational discipline. Constrained MAPPO-GAT (C-MAPPO-GAT) isolates Lagrangian operational-cost control and budget-aware screening, while ACD$^3$-GAT adds budget context, CVaR tail-risk estimation, opponent-belief state, and Graph Counterfactual Risk Propagation (G-CRP). The replicated comparison includes three 200-episode seeds for IPPO, MAPPO-GAT, C-MAPPO-GAT, and ACD$^3$-GAT. C-MAPPO-GAT reduces downtime violation from 100% to 0.3% and mean downtime cost from 355.4 to 15.5 relative to MAPPO-GAT. ACD$^3$-GAT reduces mean downtime cost to 48.2 with a 13.8% violation rate, placing it on the safety-contract frontier rather than at the most conservative compliance point. Topology-seed and coupled adaptive Red-process stress tests preserve this contrast and show lower worst adaptive degradation for safety-constrained policies than reward-only MAPPO-GAT.

Markovian Whittle-Matérn fields have been convergently approximated by discrete Gauss Markov Random Fields (GMRFs) with sparse precision matrices using a Finite Element approximation of the two-parameter family, \[ (\kappa^2 - \Delta)^{\alpha/2} u = \mathcal{W}, \;\; \kappa \in \mathbb{R}, \; \alpha \in \mathbb{N}. \] of SPDEs. Using recent developements in the analysis of Discrete Exterior Calculus (DEC), we present a different, yet closely related, convergent GMRF approximation to these Matérn fields over complete, boundaryless Riemannian manifolds discretized as well-centered simplicial complexes. This convergent method (i) is agnostic to $\alpha, \kappa$ and thus allows a universal approximation scheme for the precision and covariance matrices of the entire $(\alpha, \kappa)$-family of GMRFs, so they may be inferred rather than guessed. (ii) inherently models pointwise and piecewise-smoothed measurements of a random field and approximates both equally well (iii) is computationally independent of the interpolants used - it suffers no overhead if one convergent interpolant were replaced with another suitable interpolant over the same mesh. Furthermore, we show that, on discretizations that are well-connected in a precise sense, and volume-concentrated, the precision matrices are spectral functions of a graph-laplacian. We provide a low rank approximator to the family of such Matérn GMRFs and mention a use case: reducing the number of measurements needed to model the GMRF by compressed-sensing.

Deep unfolding (DU) accelerates iterative optimizers by introducing learnable components and training them through unrolled iterations, but extending DU to the large-scale semidefinite programs (SDPs) common in robotics has remained limited. Unrolling a full-update conic solver such as COSMO exposes two obstacles that prior work on learned conic solvers has not: backpropagating through the per-iteration linear-system solve incurs memory quadratic in the problem size once the coefficient matrix is formed explicitly, and backpropagating through the positive semidefinite (PSD) cone projection becomes numerically unstable when eigenvalues coincide. We address the first obstacle with a matrix-free implicit differentiation rule that operates entirely through matrix-vector products, reducing memory from $O(n^2)$ to $O(n)$ and enabling backpropagation at scales where direct factorization runs out of memory. We address the second with a backward rule based on the Dalečkii–Krein representation of the Fréchet derivative, which remains well-defined under repeated eigenvalues. Together these make it possible to learn lightweight hyperparameter policies and warm-starts for a full-update conic solver. We evaluate on nonlinear covariance steering problems solved via sequential convex programming (SCP), as well as standalone SDPs and second-order cone programs ranging from max-cut and Lovász $\vartheta$ SDPs to robust estimation and control problems. The learned policies outperform state-of-the-art solvers across all problems, and can provide up to a 50$\times$ speedup depending on the class. When used as a subroutine in SCP, the learned approach delivers over a 30$\times$ speedup compared to COSMO.

We study training-free fixed-length descriptors for multivariate time series and ask not merely whether such a descriptor performs well, but when it can be expected to work at all. Our object of study is $D(\tau)$, built from a time-lagged correlation matrix truncated at the Marchenko-Pastur edge so that only signal-bearing eigenvalues survive and classified by cosine similarity to class centroids with zero learned parameters. The central contribution is not the descriptor but a falsifiable applicability criterion for it. Working from a stationary Gaussian VAR(1) model, we argue that $D(\tau)$ separates two classes when the signals are approximately stationary and the class information lives in their cross-channel temporal coupling rather than in marginal per-channel power. We derive, semi-formally, three consequences: a distinguishability condition, why the static ($\tau=0$) covariance collapses to chance, and why a stationary but power-discriminated paradigm defeats the descriptor. The criterion is operational: a two-part pre-flight test – an augmented Dickey-Fuller stationarity check and a power-baseline saturation check – predicts applicability before any training. We validate both halves on a mixed assortment. On four paradigms that satisfy the criterion (Sleep-EDF, BCI-IV-2a, MIT-BIH, ESC-50) the descriptor is competitive with strong baselines at a fraction of their cost, reaching $88.5\pm4.5\%$ under 20-subject leave-one-subject-out on Sleep-EDF on a single CPU thread. On three that violate it – non-stationary ERPs, and financial-volatility and wearable-stress regimes that are power-discriminated – it fails exactly as the pre-flight predicts, and these negatives are the more informative half. We are explicit that $D(\tau)$ is not the most accurate representation; its value is a compact, training-free embedding whose domain of validity is known in advance.

Estimating the probability that a treatment outperforms a control for an individual patient, called the Individual Probability of Treatment Benefit (IPTB), offers a clinically intuitive alternative to population-average metrics. However, existing methods for IPTB estimation are largely confined to binary treatment settings, despite the prevalence of dose-varying interventions in clinical practice. We propose a general framework for IPTB estimation with ordinal outcomes under discrete dose assignments, called Dose-AIPTB (Dose Attention-based IPTB). Our approach recasts the problem as binary classification over the unobserved sign of the individual treatment effect, constructing pseudo-labels from covariate-similar pairwise comparisons and aggregating them via attention mechanisms or Nadaraya-Watson kernel regression. This formulation naturally accommodates multiple discrete dose levels, extending beyond the binary treatment paradigm. Through numerical experiments on real-world and synthetic data under covariate shift, varying sample sizes, and heterogeneous outcomes, we demonstrate that attention-based aggregation consistently outperforms kernel alternatives. The framework provides a foundation for personalized dose selection grounded in individual-level benefit probabilities. Codes implementing the model are publicly available at https://github.com/NTAILab/AIPTBDose.

This thesis investigates how Bayesian principles can deepen our understanding of modern deep learning systems. While neural networks achieve remarkable predictive performance, their ability to generalize and to quantify uncertainty remains only partly understood. This thesis approaches this challenge from both methodological and theoretical angles: unifying Bayesian inference, function-space modeling, and large-deviation theory under a common probabilistic perspective. On the methodological side, the thesis introduces the Deep Variational Implicit Process (DVIP), a scalable Bayesian framework that extends implicit processes to deep architectures. Complementing this, two post-hoc methods – the Variational Linearized Laplace Approximation (VaLLA) and the Fixed-Mean Gaussian Process (FMGP) – are proposed to equip pretrained deterministic networks with calibrated uncertainty estimates. The theoretical contributions focus on one of the central open questions in modern machine learning: why do large, over-parameterized neural networks generalize so well? To address this, the thesis develops a unified probabilistic framework that connects three key mechanisms – diversity, smoothness, and stochasticity – within the language of PAC-Bayesian and large-deviation theory.

World models in robot learning predict future states from visual observations and actions, enabling agents to reason about the consequences of their controls. However, many action-conditioned models are evaluated in settings where motion is dominated by immediate control, whereas aquatic surface vehicles and other real-world objects continue moving under inertia and are displaced by hidden ambient drift, such as water currents or wind. We propose FlowMo-WM, an end-to-end trainable visual world model that infers object-centric motion state and a predictive long-history context associated with hidden drift from image-action histories without direct supervision of flow fields. FlowMo-WM factorizes image-action history into a short-history latent state, trained to summarize object-centric motion, and a longer-history context, trained to summarize slowly varying exogenous influences. A zero-context residual transition separates action-conditioned base dynamics from context-dependent drift effects during latent rollout. In simulated aquatic surface-vehicle environments with diverse hidden flows, disturbances, and randomized vehicle dynamics, FlowMo-WM improves long-horizon rollout accuracy over representative action-conditioned latent world models. Prediction-time context ablations, in which the inferred context is zeroed or shuffled during rollout, show that the ambient context is important for stable prediction under hidden drift, while frozen linear probes characterize information encoded in the learned factors.

Enforcing functional inequality constraints such as monotonicity and convexity in neural networks is a fundamental challenge in many industrial and scientific applications. Classical one-sided penalty methods, along with primal-dual methods gated by complementary slackness, provide constraint gradients only at violated locations, resulting in fragile satisfaction. Architectures that guarantee feasibility by construction, on the other hand, remain largely limited to elementary cases and impose additional inductive biases. We introduce neural slack variables, a deep learning native primal-side approach that converts constraint enforcement into a regression problem by coupling the primary network with a jointly learned auxiliary network. The auxiliary network serves as a valid target for the primary network's constraint quantities, inducing feasibility and regularity. Neural slack variables achieve zero measured violations on dense-grid monotonicity and convexity test cases, where penalty and primal-dual baselines leave residual violations, and enable arbitrage-free learning of volatility surfaces, an open industrial challenge in quantitative finance.

Predictive code completion greatly accelerates how quickly developers work. In spreadsheets, despite being much more common, such auto-completion features are virtually non-existent. To address this gap, we introduce a benchmark for systems that observe a sequence of user actions in a spreadsheet and predict future actions. Two challenges are (1) the absence of edit histories in public spreadsheet corpora and (2) the complex space of spreadsheet actions (spatial, temporal, composite). To address (1), we manually curate 52 sequences of 12K actions that recreate spreadsheets from public corpora, seeded by parametrized heuristics and LLM refinement. To address (2), we propose an online evaluation that expects a prediction after each user action, accepts or rejects that prediction, updates the future actions upon acceptance, and repeats this until the target spreadsheet is obtained. We use multiple baseline predictors (including zero-shot LLMs, fine-tuned SLMs, and classical models) and analyze different properties that our benchmark teaches us, including but not limited to: properties of saved actions and false positives, efficiency, effect of user profiles, effect of triggers, and effect of context.

Neural responses in cortex exhibit substantial trial-to-trial variability in response to repeated stimuli, while peripheral sensory neurons respond far more consistently, leading many to wonder whether stochasticity may carry meaning. Existing work has argued that noise and signal correlations may be optimized for discrimination in animals, whereas artificial neural network (ANN) studies have shown similar benefits of noise in machine learning tasks, although most ANN work has neglected the effects of correlations. Here we investigate whether correlated noise improves the robustness of artificial neural networks to adversarial attacks and naturalistic image modifications. Using the covariance of activations under modified versus clean inputs, we find that structured noise may significantly improve network robustness. Robustness to naturalistic image modifications benefits most from structure, but this structure transfers poorly across modification types. In contrast, noise structure from adversarial attacks can generalize to other kinds of attacks. These results suggest that structured noise in ANN activations generally improves robustness, establishing a biologically plausible strategy for creating robust artificial neural networks that only relies on local information.

The length of the shortest program that generates a sequence, its Kolmogorov complexity, is uncomputable, so we ask what finding a short program costs when one exists. Many search algorithms, including Levin search, evolutionary methods, simulated annealing and the cross-entropy method, learn about a candidate program only through its score, how much of the sequence it reproduces. For such algorithms we define the coupling width of a search problem, the largest number of program fields that must change together before the score moves. We prove an unconditional worst-case lower bound on the number of candidates scored, exponential in that width. Under stated conditions, a conservation law follows, in which each bit of structural knowledge injected into a search removes at most one bit of search. The structure plus the logarithm of the remaining search is at least a fixed fraction of the sequence's Kolmogorov complexity. That fraction tends to one as the instruction set grows, so the lower bound approaches Levin's 1973 upper bound, apart from the program's running time. Search by score must pay this cost to be complete. We prove that our engine's structural inference avoids it only by giving up coverage, as does, if one-way functions exist, every method that runs in polynomial time. Our deterministic engine, built on this theory, recovers a generating program, certified by compressing its data and predicting an unseen continuation, for 2,383 of 3,914 candidate sequences in four populations of integer sequences and cellular automata, including the chaotic Rule 30.

Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound finite-round error accumulation in the context of diffusion models, but two questions remain open:~what distribution does the recursion converge to, and how fast? We answer both, isolating a mechanism distinct from imperfect learning: even with perfect score estimation and exact sampling, the early stopping of the reverse diffusion (required for numerical stability) drives a progressive drift away from the data distribution. We prove that this recursion converges geometrically to a unique limiting distribution, which admits a closed-form characterization as an infinite mixture of increasingly Gaussian-smoothed versions of the data distribution. A Hermite spectral decomposition of this limit reveals that recursive training acts as a low-pass filter: higher-order modes, which encode fine non-Gaussian structure, are attenuated much more strongly than coarse modes. This spectral picture motivates annealed truncation schedules that progressively shrink truncation times across retraining rounds; we prove that any schedule converging to $0$ asymptotically eliminates recursive compounding. Finally, we show our idealized characterization is robust: in the presence of discretization and score estimation errors, the learned distribution remains in a Wasserstein-2 ball around the ideal limit, with mode-dependent contraction rates that contract high-order errors faster than low-order ones. We validate the theory on synthetic Gaussian mixtures and CIFAR-10.

RL post-training has become increasingly pivotal for improving diffusion policies, but existing diffusion policy-gradient methods are often unstable and cannot achieve reliable policy improvement. We identify the cause as the double-drift phenomenon: optimizing a variational surrogate can let the ELBO separate from the true log-likelihood, which then makes the resulting proxy policy gradient misaligned with the true policy gradient of expected return. We propose DiPOD, a diffusion policy optimization framework that maintains tight-bound behavior throughout training by interleaving self-distillation with policy-improving gradient updates. This leads to a simple and practical algorithm: augmenting each diffusion policy-gradient update with an on-policy ELBO regularizer. Across diffusion language model post-training and continuous-control diffusion policies, DiPOD substantially stabilizes training and reaches higher rewards than previous methods.

Machine-learned anomaly detection is reshaping searches for new physics, but it has outrun the statistics used to interpret it. A raw anomaly score has no calibrated meaning, a model that scans many regions inflates the look-elsewhere effect, and the asymptotic significances the field relies on are blind to the background mismodelling that anomaly detectors are especially prone to. We propose a calibration layer, built on conformal prediction, that turns any anomaly score into a defensible significance with distribution-free, finite-sample guarantees. Conformal prediction converts scores into valid local p-values, weighted and Mondrian variants repair the sideband-to-signal-region exchangeability failures that resonant searches suffer, and a Gross-Vitells step carries the result through to a look-elsewhere-aware global significance. The layer does two things at once. It exposes miscalibration that the standard pipeline cannot see, and it corrects it without retraining the detector. On public LHC Olympics data, a classifier develops a substructure-mass correlation that makes sideband-calibrated background p-values anti-conservative. Taken at face value, this manufactures a $\sim 46\sigma$ excess from background sculpting alone, which the label-free weighted correction removes, restoring an honest null. When run as a blind wide-mass bump hunt, the standard asymptotic and unweighted procedures fabricate $\gtrsim10\sigma$ excesses and $\approx5\sigma$ excesses even in signal-free windows, while the conformal layer raises no false alarms and its global false-positive rate is verified on background-only pseudoexperiments. The result is an auditable, detector-agnostic path from an uncalibrated score to a trials-factor-aware significance, ready to be folded into experimental anomaly searches.

World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels. Pixel-space video models provide broad visual priors but expend model capacity on dense appearance reconstruction, while direct action models require embodiment-specific labels that hinder scalability. We present $\mu_0$, a scalable world model based on 3D traces. Rather than predicting dense pixels or directly modeling actions, $\mu_0$ forecasts smooth 3D trajectories for salient interaction points such as objects, tools, hands, and contact regions, yielding a compact, embodiment-agnostic motion interface. To enable training from diverse video sources, our TraceExtract system automatically extracts 3D supervision by selecting keypoints, constructing globally aligned traces, and associating motion segments with hierarchical language captions. This TraceExtract supervision pretrains $\mu_0$ by combining a pretrained vision-language backbone with a modular trace expert, which represents each query via B-spline control points and predicts future traces. Experiments show that $\mu_0$ outperforms baselines in both 2D and 3D trace prediction, including trace prediction models and tokenized VLM methods. Because $\mu_0$ is frozen and reusable, it can be paired with action experts for downstream robot embodiments. Despite action-free pretraining, the resulting trace-conditioned policies achieve performance competitive with VLA models pretrained with action supervision, such as $\pi_0$. These results establish 3D traces as a scalable and transferable representation for cross-embodiment manipulation.

Low-rank adaptation (LoRA) and its variants provide a memory- and compute-efficient alternative to full fine-tuning of pre-trained models. However, questions remain about the comparative generalizability of these approaches and how the structural restrictions on low-rank updates preserve effective adaptation performance. We present a historical framing, covering the past (full fine-tuning and original LoRA), the present (different variants of LoRA), and propose simpler, cheaper, parameter-efficient extensions by inducing sparsity within existing LoRA variants: Cheap LoRA (cLA), training a single low-rank factor with the other fixed (deterministically or, in its randomized variant, stochastically), and the chained circulant variant, ${c}^3$LA. We frame cLA as a structured instance of asymmetric LoRA, serving as a controlled column-subspace restriction of full fine-tuning. We derive information-theoretic generalization error bounds for these variants, marking one of the first endeavors in this area. Empirically, we evaluate 11 fine-tuning methods across 10 pre-trained models and 14 datasets, analyzing the fine-tuned models' performance and generalization using tools such as loss landscapes and spectral analysis. Despite the sensitivity of fine-tuned models to the pre-trained model, datasets, and other factors, our study suggests that restricting LoRA-based PEFT methods' adaptation to a sparse, structured column space remains competitive across tasks with their parameter-matched baselines while reducing up to 10% training time and peak GPU memory up to 15%, even with a naïve, non-optimized, sparse implementation. Our theoretical and empirical generalization measures provide a more consistent and principled approach to their cost-effective adaptation than commonly used analytical tools. Overview and code are available at: https://elicaden.github.io/Beyond_LoRA/.

We argue that aligning AI to aggregated human preferences is the wrong target. With current technology, one can train AIs to share the values of a Silicon Valley techno-optimist, a degrowth environmentalist, a national-conservative culture warrior, a single-party state cadre, or a devout religious traditionalist. We should not. Human values produce societies that thrive or fail on the merits of those values - from failed states and extreme inequality to declining happiness, political polarization, and government dysfunction in the world's wealthiest democracies. The pluralistic-alignment program correctly diagnoses that there is no single "humanity" to align with, but is dangerous if taken as the main directive. We argue that AI should be trained to a non-negotiable floor of objective alignment goals - competence, bounded by the constraints of factual accuracy, honesty, and lawfulness and that pluralism belongs at the surface (language, register, conventions, missing-context defaults) and across the wide band of legitimate value tradeoffs that respect the floor, but not at the level of values that violate it. We highlight the empirical reality of unfiltered pluralistic values, propose four commitments as a constructive alternative, and engage six credible objections: commercial pressure and practical feasibility, democratic legitimacy, regulatory compliance, over-reliance on institutionalist explanations, the charge that the floor itself is culturally laden, and the limits of Coherent Extrapolated Volition.

Anomaly detection is a fundamental component of intelligent systems with applications in healthcare, cybersecurity, smart grids, and IoT environments. Although conventional machine learning and deep learning methods have demonstrated effectiveness in identifying anomalies, they often rely on large labeled datasets, incur high computational costs, and face scalability challenges in edge and high-dimensional settings. This paper presents D2H-AD, a novel anomaly detection framework based on Hyperdimensional Computing (HDC), a brain-inspired paradigm that represents information using high-dimensional distributed vectors. Unlike existing HDC-based methods, D2H-AD integrates distance-based similarity and density-aware encoding within a unified framework, improving anomaly representation and detection performance. Ablation studies show that hyperdimensional encoding alone yields up to 5.4% higher ROC-AUC than applying the same density-distance scoring directly in the original feature space. Furthermore, D2H-AD consistently outperforms five established baselines, namely HDAD, ODHD, One-Class SVM, Isolation Forest, and Autoencoders, across all evaluated datasets. The framework is lightweight, interpretable, and computationally efficient, making it suitable for resource-constrained and real-time applications. We validate D2H-AD on five benchmark datasets and demonstrate superior F1-score and ROC-AUC performance, together with robustness to class imbalance, noise, and data complexity. In addition to improved accuracy, D2H-AD offers scalability, a small memory footprint, and low-latency operation enabled by binary computations and a compact design. These properties make it particularly attractive for TinyML and edge AI deployments. The proposed framework highlights the potential of HDC for accurate, interpretable, and energy-efficient anomaly detection in dynamic environments.

Grokking is the delayed onset of generalization in neural networks, arising long after they fit the training data. Whether the weight norm causes this delay is disputed: some studies report a critical norm at the transition, others observe grokking with no fixed norm at all. We settle this by intervening on the norm during training rather than only observing it. Under free training with weight decay, networks grok when the weight norm reaches a value Wc that varies little across seeds and learning rates (CV 1 to 2 percent) and grows with the modular base as a power law. When we instead clamp the norm to a fixed multiple rho of Wc and hold it there, the network still groks, but the delay follows T_grok proportional to exp(alpha rho). One exponent, alpha near 7.5, fits this delay across four moduli (R^2 = 0.996). Over the swept ranges the held norm moves the delay by about 19x and the learning rate by only about 2x, and holding the norm above Wc slows grokking rather than preventing it. A final LayerNorm removes the dependence by decoupling weight scale from the network function; without it the exponential law returns. This pinned-norm delay is the exponential counterpart to the logarithmic delay predicted for a freely contracting norm.