The Archive

Euclidean Fourier Neural Operators address domain-transfer failure in standard FNOs by making spectral weights grid and domain-independent.

PLVR learns verifiable symbolic programs for LLM reasoning instead of embedding capability in weights, enabling interpretability and transfer.

LongPIBench benchmark exposes prompt injection vulnerabilities in long-context settings across document review, screening, and code tasks.

SymboLLM-FE combines LLM guidance with symbolic regression for interpretable automated feature engineering on tabular data with reduced iteration cost.

HiFTS framework generates hierarchical chain-of-thought feedback aligned to essay rubrics before scoring, improving multi-trait consistency.

Post-training method for video VLMs to detect human mistakes in instruction-following tasks using open-set generalization rather than closed-set classification.

CultureConverse: multilingual benchmark for evaluating LLM cultural competence across 10 East/Southeast Asian regions via multi-turn dialogue simulation.

VERA-8B: 8B-param audit reasoning model for SEC filing analysis that grounds audit risk predictions in evidence to prevent plausible but false outputs.

RetailAgent: experimental study of whether LLM trading agents develop predictable directional biases when reacting to intraday equity price movements.

BEACON: knowledge graph construction from cyber threat intelligence reports using MITRE ATT&CK behavior anchors to resolve cross-source naming ambiguity.

Survival model approach for e-commerce repurchase prediction that predicts time-to-repurchase directly instead of separate binary models per time horizon.

CamoDocs: poisoning attack on RAG systems using camouflaged adversarial documents that evade query-inclusion detection and steering defenses.

MAP: multimodal benchmark for evaluating AI accessibility planning across real-world places using claim verification and visual evidence retrieval tasks.

Study showing Vision Transformer attention heads in multimodal LLMs specialize into object/background roles; SHS-Index metric correlates specialization with downstream performance.

Study across 30 LLMs showing linguistic confidence diverges from internal confidence (logits/semantic entropy) on classification and generation tasks.

Quantum federated learning framework using Bures metric geometry for mixed-state noisy quantum devices.

PersonaForge generates realistic multi-turn agent interactions; analysis shows 75.9% of real sessions are multi-turn vs. single-turn training data.

Statistical framework for localizing global distributional discrepancies via marginal contributions and anomaly detection.

SCAN framework for AI task allocation in medical training addresses over-reliance via real-time metacognitive task classification.

Subject-conditioned causal neural surrogate for pediatric cerebral palsy rehabilitation using OpenSim-derived parameters.

Shallow Recurrent Decoder for state estimation in tokamak liquid metal blankets via reduced-order modeling.

EvoUndo framework ensures LLM agent self-modifications are reversible across counterfactual states; identifies 197 safe mutations from 600 tasks.

Optimal testing strategy to recover honest results from adversarial test takers including AI-aided cheating.

GRACE gradient-guided coreset selection constructs forget/retain sets for LLM unlearning without pre-specification.

Framework propagates clinical guideline KG construction-time quality signals into medical QA evidence selection.

AGENT-O ontology framework standardizes semantic representation and governance reporting for healthcare AI agents across 279 scientific publications.

Cross-spectral dense correspondence method enables multimodal medical imaging fusion across disparate wavelength ranges.

Fractional Power Encoding extends hyperdimensional computing with Hadamard product binding for shift-equivariant sequence representations.

BanglaMed-QA introduces medical question-answering system for low-resource Bangla language with 4,493 QA pairs across 506 diseases.

Study measures failure correlation between stacked LLM defenses using Adversary Access-Tier Model, finding defense layers often fail on same inputs.