The Archive

LexFlip benchmark with 373 Quebec French perturbations diagnoses legal meaning preservation in simplified clauses via dissociation method.

Framework for evaluating automatic NLG metrics via behavioral correctness assumptions under controlled response transformations.

GLASS framework aligns graph encoders with text embeddings via hypersphere geometry for cross-domain transferable anomaly detection.

Quantum machine learning framework using RL-optimized circuits for semiconductor device modeling with reduced error versus classical baselines.

FluxDisco applies physics-informed symbolic regression via Monte Carlo graph search for stoichiometric ODE discovery.

SparseBin: tuned GPU self-organizing map algorithm achieving 5.6-10.1x speedup on best-matching-unit search via tile optimization and vectorization.

Proposes new benchmark and evaluation methodology for machine translation addressing saturation of standard benchmarks, metric unreliability, and reproducibility gaps in human evaluation.

Deep learning + FEM approach predicts filament geometry in 3D concrete printing to improve structural stability assessment.

FLY-EVAL++: safety-focused evaluation protocol for LLMs in physics-governed domains; measures constraint violations and physical inconsistency beyond accuracy metrics.

Information-geometric analysis of reinforcement learning via dually flat statistical manifolds and visitation measures under planning-as-inference framework.

llm 0.34 adds usage logging with response duration metrics and performance improvements.

Proposes standardized metrics for speech brain-computer interfaces to enable comparable evaluation across heterogeneous datasets and recording methods.

Learning-based attacks reconstruct encrypted point clouds from unencrypted coordinates, undermining selective coordinate encryption for volumetric video security.

Sparse MoE routing decisions across layers share common geometric structure aligned via control subspaces despite layer-specific coordinate systems.

LLM agent marketplace simulations show guardrail effectiveness claims lack construct validity; economic metrics mask schema/procedure confounds.

Fisher geometry analysis reveals safety alignment fragility in LLMs under benign fine-tuning via selective output-side MLP resharpening.

NeuSOGA framework extracts explicit symbolic mathematical representations from geometric observations using neuro-symbolic learning.

Celeb Twins Test Set (CTTS) benchmark for monozygotic twin face verification with metadata for distinguishing marks and asymmetry.

SVD-MBR applies singular value decomposition to minimum Bayes risk decoding, reducing metric overfitting in text generation via low-rank approximation.

Analysis of Transformer attention heads reveals scaled idempotence pattern in OV operators across 2.8B–235B parameter models via principal-coordinate factorization.

Passive learning framework for Metric Interval Temporal Logic synthesis reduces timed specifications to untimed learning problems.

Perceptual study measures alignment between audio similarity metrics and human judgments for music replication detection across musical attributes.

ASPIRE benchmark evaluates LLM self-evolution from vague natural-language goals without predefined metrics.

Statistical analysis of 13 neural audio codec token sequences across architectures and noise conditions using Zipf/Heaps metrics.

Framework learns latent representations of PDEs by embedding scientific inductive bias into training distributions for hypothesis discovery.

A perception stack is shaped by the vehicle that carries it. Move the same software to a new carline—for example, from an SUV to a sedan or another vehicle... A perception stack is shaped by the vehicle that carries it. Move the same software to a new carline—for example, from…

Knowledge-aligned SFT framework constrains fine-tuning targets to base model's parametric knowledge to reduce hallucinations via Evidence Rewrite and Recall variants.

Geometry of Divergence: framework tracking LLM hidden-state trajectories via temporal curvature and variance to diagnose representation drift in multi-turn reasoning.

Non-collapsible performance metrics in clinical AI can mask fairness disparities across demographic subgroups.

Information geometry framework analyzes how missingness patterns in labels affect efficiency of multiclass classifiers.