Hyperball is a simple optimizer wrapper that sets fixed Frobenius norms for weight matrices and their updates. It improves training speed and learning rate transfer in large models, achieving 20--30% token equivalent speedup over weight decay baselines on up to 1.2B parameter models.
Factorized Neural Operators (FaNO) decompose spectral representations into equivariant dynamic and invariant persistent responses. This factorized structure enables better interpretability, generalization, and consistent predictions across scales, domains, and physical regimes.
CEAP, a new circuit discovery method, substantially reduces resampling variance compared to EAP-IG. The paper shows that rephrasing variance arises from prompt templates activating different circuits, suggesting LLMs are inherently hard to steer across diverse inputs. Sample-wise variance is largely benign, as poor unfaithfulness scores result from selective contribution scaling, not circuit defects.
We propose a new functional gradient descent algorithm that adapts its representation during optimization. The method achieves convergence to a stationary point under smooth losses and to a global minimizer under smoothness and a Polyak-Lojasiewicz condition, despite using finite-dimensional approximations. It outperforms both fixed-approximation FGD and neural network baselines in regression, PDE solving, and computer vision tasks.
This paper proposes a unified causal-origin taxonomy for distributional shifts in reinforcement learning, linking ID/OOD generalization to non-stationary settings. It decomposes the agent-environment interaction using a POMDP framework, identifying internal, agent-driven, and external, environment-driven shifts, with explicit, implicit, and hybrid types defined by the shifted-time boundary. The work introduces an evaluation framework to measure shift impact through performance degradation and recovery metrics, enabling systematic analysis of RL robustness.
A study identifies extrinsic (crucial tokens) and intrinsic (cognitive behaviors) properties that enhance code interpreter reasoning in large language models. Stronger reasoning models show higher prevalence of verification, backtracking, and backward chaining, with these properties improving performance during inference and training, reducing overthinking and boosting token efficiency.
CrossMaps is a real-time, confidence-aware semantic mapping pipeline that uses RGB-D data to create language-queryable maps. It integrates multi-scale CLIP embeddings with a dual-memory architecture—Short-Term and Long-Term Memory—to aggregate visual observations and promote coherent, confident cells as persistent semantic landmarks. The system enables natural language queries to guide rover navigation via semantic heatmaps.
CircuitLasso enables scalable circuit learning in large language models by using sparse linear regression. It recovers circuits with structural accuracy matching state-of-the-art methods at significantly lower computational cost, and demonstrates human-interpretable semantic propagation through model components. The learned circuits achieve comparable performance on a domain-generalization task with reduced cost.
The study introduces PReLU-IPM, a new integral probability metric based on a neural network discriminator with a single node. The resulting PReLU-TST test is nonparametric, consistent, and asymptotically equivalent to standard IPM-based tests, showing higher power or competitive performance on simulated and real datasets.
A model-agnostic auditing framework detects and distinguishes true and phantom disclosures in synthetic data. It uses only synthetic outputs and a held-out control set to perform statistical testing, offering tighter privacy leakage bounds than prior methods without requiring model access or additional training.
A contrastive encoder trained on simulated signals maps DNA barcode signals into an interpretable molecular coordinate system. The method enables molecule identification with a single pass, reducing computational cost by three orders of magnitude and allowing data pooling across devices while remaining invariant to acquisition conditions.
A convolutional variational autoencoder trained on 6,034 Binance Options surfaces for BTC and ETH achieves 0.94-1.56 vol-point RMSE under 10-50% masking. The hybrid predictor reduces error from 7.00 to 0.83 vol points at 50% masking, outperforming parametric re-fit in structured hole patterns and detecting abnormal market events without supervision.
A new activation function enables fixed-size neural networks to approximate any function in Sobolev spaces $W^{s,\infty}((a,b)^d)$ with arbitrary accuracy in the $W^{s-1,\infty}$-norm. The results use elementary activations like EUAF and DUAF$_\infty$, with explicit width and depth bounds, and extend to sigmoidal variants $\widetilde{\mathrm{DUAF}}_n$ preserving accuracy for all $1\leq s\leq n$.
A residual learning approach using directional task-error supervision achieves stable five-ball juggling on real robots, converging from the second attempt. The system outperforms human practice timelines and relies on both directional feedback and an informative prior, with a fixed-Jacobian Newton update proving most reliable.
SPaiK introduces a scalable kernel learning method for pairwise settings using the stochastic generalized vec trick (sGVT). This innovation reduces computational and memory demands, enabling efficient training on large datasets and making pairwise kernel learning feasible for previously intractable data sizes.
A new method decouples ML inference from state persistence in streaming systems using probabilistic thinning. It selectively triggers durable state updates based on event informativeness, reducing persistence path overhead by up to 90% without compromising downstream utility or introducing systemic errors.
Dynestyx is a probabilistic programming library that provides first-class support for state-space models. It enables users to specify arbitrary priors for discrete- or continuous-time dynamical systems, perform inference on mixed-effect data, and obtain state and parameter estimates with principled uncertainty quantification.
We introduce a method to identify agents by their procedural behavior fingerprints, achieving 85.7% accuracy in attributing unseen trajectories to correct agents. Using ProcGrep, we analyze coding agent behavior in SWE-Bench, finding that models from similar release periods or distilled from each other exhibit closer behavioral similarity, with a Jensen-Shannon divergence of 0.25.
A compact spectral representation using Betti numbers, spectral gap, and analytic torsion distills persistent Laplacians into three mathematically grounded invariants. This approach captures essential predictive signals from the full spectrum, outperforms it in some cases, and reduces computational overhead on datasets like MNIST, QM-3D, and SKEMPI WT.
A new multi-center benchmark enables abdominal disease diagnosis and report generation from non-contrast CT by synthesizing contrast-enhanced findings. The dataset includes paired NCCT-CECT studies and reports from two centers, showing NCCT achieves average multi-organ AUCs of 69.1% internally and 63.1% externally. The benchmark and code are publicly released to support research into safer, contrast-free abdominal imaging workflows.