Manifold curvature and intrinsic dimension predict layerwise SAE width exponents and asymptotic floors across Gemma models, with cross-model transfer of the geometric regression, establishing a transferable geometric law instead of a universal scaling law.
Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (58%).
62
Pith papers citing it
Background
58% of classified citations
citation-role summary
background 9
method 3
citation-polarity summary
representative citing papers
Steered LLM activations are non-surjective: under practical assumptions, they lie outside the set of states reachable from any discrete prompt.
Proposes a scale-calibrated median-of-means estimator for robust aggregation of distributed PCA estimates on the product of Euclidean space and Grassmann manifold.
Derives the asymptotic distribution of the spatial Cramér-von Mises independence statistic under β-mixing on R² and implements it in Python with eigenvalue-based critical values.
A 10-qubit convolutional quantum graph neural network fed by autoencoder-compressed jet data achieves performance comparable to classical graph networks in distinguishing boosted Z jets from gluon jets.
The test error of random-feature ridge regression with arbitrary data augmentation admits a closed-form asymptotic characterization in the proportional regime that depends only on population covariances and augmentation statistics.
Time-reversed Young interferometry acts as a source-space information processor where mutual information is the reciprocal invariant and source-label entropy can decrease near destructive interference while Fisher information rises.
Three new provably KL-optimal frequency normalization algorithms are presented, one running in linear time in the number of symbols.
The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.
Jensen-Shannon regularized analogues of KL-based direct-correlation measures are introduced, taking values in [0,1] and accompanied by alphabet-size-dependent upper bounds under the observed marginal p(x,z).
Exponentially-shifted Gaussian smoothing yields zeroth-order gradient estimators with linear dimension dependence, enabling improved complexity bounds for stochastic optimization including decision-dependent regimes.
VGF solves behavior-regularized RL by transporting particles from a reference distribution to the value-induced optimal policy via discrete value-guided gradient flow.
The normalized sum of negative log-likelihoods under sublinear parsings converges almost surely and in L1 to the entropy rate h_P for any shift-invariant measure on a finite shift space.
Statistical Linkage Learning enables a new mask construction algorithm for Partition Crossover that maintains effectiveness on noisy problems with hidden dependencies and matches noise-free performance when decomposition quality is high.
ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
A meta-learning method identifies the conditional mean of task-specific causal demand parameters by conditioning on all prices while masking two demand outcomes, assuming at least two locally exogenous prices per task.
Inflating the min-norm interpolator by a factor >1 reduces generalization error in linear regression with anisotropic covariances when d/n diverges to infinity.
Conditional normalizing flows approximate intractable likelihoods arising from cell division history to conclude that glc3 is mostly inactive under nutrient stress in yeast, with brief transient expression.
Proves cutoff at entropic time log n/h for reversible mixtures of permuted Markov chains under mild assumptions on the base chains.
Hyper-V2X uses a Bayesian hypernetwork with partial weight generation and V2X context embedding to produce calibrated epistemic and aleatoric uncertainty estimates for multi-agent BEV segmentation on the OPV2V benchmark.
SMA-DP-SGD augments DP-SGD with a spectral memory-aware fractional branch from prior privatized updates to improve accuracy on CIFAR and MNIST while preserving conditional differential privacy.
The paper introduces discipline stability, a trace-based evaluation paradigm for checking if RL agents maintain behavioral discipline like rule-based competitors in hidden-state competitive settings such as hotel pricing and bidding.
Derives time-dependent voltage protocols that eliminate an arbitrary number of relaxation modes to accelerate charging and discharging of planar EDLCs in finite time shorter than intrinsic relaxation timescales.
The Adam-SGD gap in large-batch LLM pre-training arises mainly from SGD's restricted effective learning rates caused by small gradients and output-layer spikes; clipping lets SGD recover nearly all of Adam's performance.
citing papers explorer
-
The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
Manifold curvature and intrinsic dimension predict layerwise SAE width exponents and asymptotic floors across Gemma models, with cross-model transfer of the geometric regression, establishing a transferable geometric law instead of a universal scaling law.
-
Steered LLM Activations are Non-Surjective
Steered LLM activations are non-surjective: under practical assumptions, they lie outside the set of states reachable from any discrete prompt.
-
Scale-Calibrated Median-of-Means for Robust Distributed Principal Component Analysis
Proposes a scale-calibrated median-of-means estimator for robust aggregation of distributed PCA estimates on the product of Euclidean space and Grassmann manifold.
-
The Spatial Cram'{e}r--von Mises Test of Independence under $\beta$-Mixing: Asymptotic Theory and Python Implementation
Derives the asymptotic distribution of the spatial Cramér-von Mises independence statistic under β-mixing on R² and implements it in Python with eigenvalue-based critical values.
-
Quantum enhanced identification of boosted jets with quantum graph neural networks
A 10-qubit convolutional quantum graph neural network fed by autoencoder-compressed jet data achieves performance comparable to classical graph networks in distinguishing boosted Z jets from gluon jets.
-
Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
The test error of random-feature ridge regression with arbitrary data augmentation admits a closed-form asymptotic characterization in the proportional regime that depends only on population covariances and augmentation statistics.
-
Entropic Reciprocity in Time-Reversed Young Interferometry
Time-reversed Young interferometry acts as a source-space information processor where mutual information is the reciprocal invariant and source-label entropy can decrease near destructive interference while Fisher information rises.
-
Fast and Exact: Asymptotically Linear KL-Optimal Frequency Normalization
Three new provably KL-optimal frequency normalization algorithms are presented, one running in linear time in the number of symbols.
-
Profile Likelihood Inference for Anisotropic Hyperbolic Wrapped Normal Models on Hyperbolic Space
The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.
-
How to quantify direct correlations between variables
Jensen-Shannon regularized analogues of KL-based direct-correlation measures are introduced, taking values in [0,1] and accompanied by alphabet-size-dependent upper bounds under the observed marginal p(x,z).
-
Complexity Guarantees for Zeroth-order Methods via Exponentially-shifted Gaussian Smoothing: Mitigating Dimension-dependence and Incorporating Decision-dependence
Exponentially-shifted Gaussian smoothing yields zeroth-order gradient estimators with linear dimension dependence, enabling improved complexity bounds for stochastic optimization including decision-dependent regimes.
-
Reinforcement Learning via Value Gradient Flow
VGF solves behavior-regularized RL by transporting particles from a reference distribution to the value-induced optimal policy via discrete value-guided gradient flow.
-
Stability of the Shannon--McMillan--Breiman Theorem under Sublinear Parsings
The normalized sum of negative log-likelihoods under sublinear parsings converges almost surely and in L1 to the entropy rate h_P for any shift-invariant measure on a finite shift space.
-
Obtaining Partition Crossover masks using Statistical Linkage Learning for solving noised optimization problems with hidden variable dependency structure
Statistical Linkage Learning enables a new mask construction algorithm for Partition Crossover that maintains effectiveness on noisy problems with hidden dependencies and matches noise-free performance when decomposition quality is high.
-
Many-Tier Instruction Hierarchy in LLM Agents
ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
-
Causal Multi-Task Demand Learning
A meta-learning method identifies the conditional mean of task-specific causal demand parameters by conditioning on all prices while masking two demand outcomes, assuming at least two locally exogenous prices per task.
-
Shrinkage to Infinity: Reducing Test Error by Inflating the Minimum Norm Interpolator in Linear Models
Inflating the min-norm interpolator by a factor >1 reduces generalization error in linear regression with anisotropic covariances when d/n diverges to infinity.
-
Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell's division history
Conditional normalizing flows approximate intractable likelihoods arising from cell division history to conclude that glc3 is mostly inactive under nutrient stress in yeast, with brief transient expression.
-
Cutoff for mixtures of permuted Markov chains: reversible case
Proves cutoff at entropic time log n/h for reversible mixtures of permuted Markov chains under mild assumptions on the base chains.
-
Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation
Hyper-V2X uses a Bayesian hypernetwork with partial weight generation and V2X context embedding to produce calibrated epistemic and aleatoric uncertainty estimates for multi-agent BEV segmentation on the OPV2V benchmark.
-
SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
SMA-DP-SGD augments DP-SGD with a spectral memory-aware fractional branch from prior privatized updates to improve accuracy on CIFAR and MNIST while preserving conditional differential privacy.
-
When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State
The paper introduces discipline stability, a trace-based evaluation paradigm for checking if RL agents maintain behavioral discipline like rule-based competitors in hidden-state competitive settings such as hotel pricing and bidding.
-
Accelerating charging dynamics of electric double-layer capacitors
Derives time-dependent voltage protocols that eliminate an arbitrary number of relaxation modes to accelerate charging and discharging of planar EDLCs in finite time shorter than intrinsic relaxation timescales.
-
Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning Rates
The Adam-SGD gap in large-batch LLM pre-training arises mainly from SGD's restricted effective learning rates caused by small gradients and output-layer spikes; clipping lets SGD recover nearly all of Adam's performance.
-
Analogical Trajectory Transfer
A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.
-
Scale selection for geometric medians on product manifolds
Joint location-scale minimization for geometric medians on product manifolds degenerates to marginal medians, and three new scale-selection methods restore identifiability with asymptotic guarantees.
-
The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting
Non-affine approval functions create unavoidable miscalibration in proper scoring rules for strategic agents, but step-function thresholds enable first-best screening without it, uniquely for the Brier score.
-
Information-Preserving Domain Transfer with Unlabeled Data in Misspecified Simulation-Based Inference
SPIN performs bidirectional domain transfer in SBI to retain parameter mutual information from unlabeled real observations, improving real-world posterior inference under increasing misspecification.
-
Emergence of Tsallis Statistics from a Self-Referential Nonlinear Operator: A Variational Framework
Tsallis q-exponential distributions arise by minimizing a free energy built from a self-consistency entropy defined via a nonlinear operator Omega, with q = alpha + beta obtained directly from the operator's fixed-point structure.
-
Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems
A new scale-aware diagnostic framework shows that unconstrained diffusion generative models exhibit structural freezing and instability instead of smooth physical responses under multiscale perturbations.
-
Particle transformers for identifying Lorentz-boosted Higgs bosons decaying to a pair of W bosons
PaRT achieves >50% tagging efficiency for boosted H->WW jets at 1% background efficiency, decorrelated from jet mass, with data-to-simulation scale factors of 0.9-1.0 on 138 fb^{-1} of 13 TeV collisions.
-
Sensor Placement for Tsunami Early Warning via Large-Scale Bayesian Optimal Experimental Design
A reformulation of Bayesian OED as dense matrix subset selection plus a pipelined Schur-complement greedy algorithm on hundreds of GPUs enables optimization of 175-sensor networks for billion-degree-of-freedom tsunami models with near-perfect scaling.
-
Niching Importance Sampling for Multi-modal Rare-event Simulation
Niching importance sampling yields a robust probability-of-failure estimator that avoids degeneracy on multi-modal performance functions by integrating evolutionary niching with importance sampling.
-
QuantumXCT: Learning Interaction-Induced State Transformation in Cell-Cell Communication via Quantum Entanglement and Generative Modeling
QuantumXCT learns parameterized quantum circuits to model interaction-induced unitary transformations between non-interacting and interacting cellular state distributions from transcriptomic profiles.
-
Measuring Primitive Accumulation: An Information-Theoretic Approach to Capitalist Enclosure in PIK2, Indonesia
Satellite data projected onto a Marxian simplex shows a 0.405 rad/yr transformation pulse, 38-46 year absorption times into built land, and percolation below random thresholds indicating planned rather than stochastic urban growth in PIK2.
-
Weighted Chernoff information and optimal loss exponent in context-sensitive hypothesis testing
The optimal weighted total loss decays as exp(-n times weighted Chernoff information) when the context weight factors across observations.
-
Testing Dark Matter with Generative Models for Extragalactic Stellar Streams
X-Stream generates thousands of stream realizations in trial potentials and applies nested sampling to constrain the full radial density profile of dark matter halos from imaging data.
-
Conditional Independence of 1D Gibbs States with Applications to Efficient Learning
1D translation-invariant Gibbs states at positive temperature exhibit superexponential decay of Belavkin-Staszewski conditional mutual information, enabling efficient learning from local measurements and tensor network approximations.
-
A Scalable Parametric Item Calibration Engine (SPICE) for Explanatory IRT with Sparse Data
SPICE is a scalable Bayesian MCMC engine for explanatory IRT calibration on sparsely linked persons and items in large assessment banks.
-
Software Between Quantum and Machine Learning -- And Down to Pulses
A JAX-based framework extending quantum machine learning to pulse-level control with composable ansatzes, end-to-end optimization, and Fourier diagnostics.
-
PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.
-
Irreversibility from Self-Reference: Gradient Flow and an H-Theorem for a Self-Referential Statistical Operator Framework
Proves an H-theorem for monotonic decrease of a convex functional under iteration and gradient flow of a self-referential operator Omega within the local kernel approximation, with perturbative stability of the Tsallis index and numerical confirmation of a re-entrant disordered phase at kappa > 0.5.
-
Quantum $f$-divergences via Nussbaum-Szko{\l}a Distributions in Semifinite von Neumann Algebras
Quantum f-divergence equals classical f-divergence of Nussbaum-Szkoła distributions for normal states on semifinite von Neumann algebras.
-
Resonance Statistics -Informed Fitting Applied to Automated Cross Section Evaluation
Resonance statistics-informed methods in automated fitting reduce spin group bias, enhance Wigner statistics consistency, and stabilize resonance density with minimal impact on cross section fit quality.
-
InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Models
LLMs generate 5P causal graphs from 46 psychotherapy intake transcripts that match human expert graphs in structure and meaning, with moderate clinical usefulness ratings.
-
Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models
LLMs classify Gaza War headlines as strongly negative while fine-tuned Arabic BERT models favor neutral labels, producing measurable non-random divergences in sentiment distributions.
-
Stochastic simulation of partial discharge inception
Monte Carlo method simulates electron avalanches with feedback to estimate discharge inception probability and time lag per initial electron position across 2D and 3D electrode geometries.
-
Cosmic dipole tensions: confronting the cosmic microwave background with infrared and radio populations of cosmological sources
Bayesian tension analysis shows Planck CMB dipole in >5σ disagreement with CatWISE infrared sources and moderate-to-strong disagreement with radio surveys NVSS and RACS, with evidence for shared astrophysical signals in some catalogs.
-
An analysis of nuclear parton distribution function based on relative entropy
A relative-entropy method with a minimum-relative-entropy hypothesis reproduces quark nPDF shapes from global fits and indicates that EPPS21 gluon central values align more closely with the hypothesis than nNNPDF3.0.
-
Context-Aware Unit Testing for Quantum Subroutines
Proposes a context-aware unit testing framework for quantum subroutines modeled as parametrized quantum channels, using probabilistic assertions and demonstrated on GHZ preparation and Shor's algorithm subroutines.