arxiv arXiv cs.LG · 6d ago

QCPIKAN: Quantum-Classical Physics-Informed KAN for PDEs

QCPIKAN is the first quantum-classical physics-informed Kolmogorov-Arnold network designed to solve partial differential equations. It uses Chebyshev-polynomial KAN layers and parameterized quantum circuits to embed physical constraints into training, achieving exponential error convergence and reduced numerical dispersion. Validated on seepage scenarios in porous media, it outperforms existing quantum-classical neural networks in prediction accuracy, error control, and dynamic tracking.

arxiv arXiv cs.CL · 6d ago

Introducing P-CHR AUC and CRR for Semantic Caching

We introduce Precision-Cache Hit Ratio (P-CHR) AUC and Calibration Retention Rate (CRR) to address the calibration gap in semantic caching. These metrics evaluate precision across cache utilization levels and measure how offline ranking quality persists in deployment. Our analysis shows the gap is driven by training objectives, not data scale, and post-hoc calibration only partially resolves it.

arxiv arXiv cs.CL · 6d ago

Multi-Agent Transactive Memory Framework

Multi-Agent Transactive Memory (MATM) enables population-level storage and retrieval of agent-generated trajectories. It allows producer agents to share procedural knowledge with consumer agents, improving task performance and reducing interaction steps in interactive environments like ALFWorld and WebArena without coordination or joint training.

arxiv arXiv cs.CL · 6d ago

Tool-Intent Stabilization in Streaming RAG

A study measures tool-intent stabilization in Streaming RAG, defining when speculative tool queries converge to correct answers. On the CRAG benchmark, 73.9% of queries allow substantial latency hiding, with early stabilization observed in questions with verbatim retrievable evidence. Question type significantly predicts early versus late stabilization, informing when speculative triggers are effective.

arxiv arXiv cs.CL · 6d ago

PASQA: Pitch-Accent-Focused Speech Quality Model

PASQA is a speech quality assessment model designed to evaluate pitch-accent correctness in synthetic Japanese speech. It uses a dataset with controlled accent errors and incorporates self-supervised learning, mora-conditioned fusion, ranking loss, and accent-error localization to achieve high accuracy in detecting accent errors across speakers, outperforming conventional models in alignment with human judgments.

arxiv arXiv cs.CL · 6d ago

Token-Operations-Oriented Inference Optimization Techniques

This paper introduces a four-layer technical architecture for token-oriented inference optimization, including Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It reviews key technologies and industry status, analyzing their real-world application value in reducing token costs, enhancing service efficiency, and ensuring stable token supply.

arxiv arXiv cs.CL · 6d ago

CATCH-ME if you RAG: Multilingual Counterspeech Dataset for Hate and Misinformation

CATCH-ME introduces the first large-scale, multilingual dataset of contextually annotated, multi-turn counterspeech dialogues targeting hate and misinformation. The dataset covers five languages and focuses on seven marginalized groups, with dialogues grounded in verified fact-checking sources and including document- and chunk-level span annotations for RAG systems.

arxiv arXiv cs.LG · 7d ago

Cross-dataset AUC for Realistic Deepfake Detector Evaluation

A new metric, Cross-dataset AUC (Cross-AUC), addresses limitations of traditional AUC evaluations by averaging per-domain AUCs and incorporating prediction polarization via Wasserstein Distance. It better reflects real-world performance under domain shifts and provides interpretable insights into detector degradation.

arxiv arXiv cs.LG · 7d ago

XGBoost-Forget for Machine Unlearning in Network Intrusion Detection

XGBoost-Forget enables efficient machine unlearning for XGBoost models on tabular network intrusion datasets. It maintains model performance while achieving faster unlearning compared to full retraining, addressing a gap in unlearning research for tabular data in network intrusion detection.

arxiv arXiv cs.LG · 7d ago

Chandra-Gaia Catalog Uses Machine Learning to Resolve X-ray and Optical Source Matches

A machine learning framework resolves ambiguous matches between Chandra X-ray and Gaia optical sources by using magnitude, color, and distance data. It identifies counterparts for 113,000 of 254,000 Chandra sources, finds plausible multiple counterparts for 7,000, and validates its performance on the COUP survey with 95% accuracy without positional data.

arxiv arXiv cs.LG · 7d ago

LOCUS: A Local Ordinance Corpus for the United States

LOCUS provides machine-readable access to U.S. municipal and county ordinances, covering 9,239 cities and counties. It includes a county-harmonized layer for 2,309 of 3,144 U.S. counties, serving the majority of the population. The corpus, built with OCR and metadata, enables research on legal opacity and paternalism using ModernBERT-based models.

arxiv arXiv cs.AI · 7d ago

XGBoost-Forget for Machine Unlearning in Network Intrusion Detection

XGBoost-Forget enables efficient machine unlearning for XGBoost models on tabular network intrusion datasets. It maintains model performance while achieving faster unlearning compared to full retraining, addressing a gap in unlearning research for tabular data in network intrusion detection.

arxiv arXiv cs.AI · 7d ago

Taxonomy Links Caregiver Needs to Mental Health Tech

A new taxonomy connects Alzheimer's and dementia caregiver mental health needs with technology interventions. It identifies gaps in support for issues like relational strain and compassion fatigue, and offers a shared framework for designing person-centered, clinically grounded technologies.

arxiv arXiv cs.CL · 7d ago

Dango: A Strictly L1-Only LLM for SLA Research

Dango is a 1.8B-parameter LLM designed to study Japanese-to-English second language acquisition. It uses a filtering method to minimize English contamination in monolingual pretraining, preserving realistic L1 exposure. Fine-tuned on LLM-generated lessons, Dango produces human-like L2 outputs, outperforming unfiltered and standard multilingual models.

arxiv arXiv cs.CL · 7d ago

LOCUS: A Local Ordinance Corpus for the United States

LOCUS provides machine-readable access to nearly all publicly available U.S. municipal and county ordinance codes, covering 9,239 cities and counties. It includes a county-harmonized access layer for 2,309 of 3,144 U.S. counties, serving the majority of the population. The corpus, built with OCR and metadata for reproducibility, enables large-scale analysis of local law, including dimensions like opacity and paternalism, using ModernBERT-based models.

arxiv arXiv cs.LG · 7d ago

Detecting Structural Biases via Causal Mechanism Shifts

This paper introduces StruBI, an algorithm that identifies hidden confounding and selection biases by analyzing causal mechanism shifts across environments. It formalizes a mutual information-based criterion to detect structural biases and demonstrates superior performance in recovering biased variables on synthetic and real-world data.

arxiv arXiv cs.LG · 7d ago

Scaling AEB with Unlabeled Data via Meta-Feedback SSL

A meta-feedback semi-supervised learning framework enables scaling of automatic emergency braking using massive unlabeled fleet data. The stabilized approach reduces pseudo-label errors and suppresses risk hallucinations, achieving a 100:1 positive-to-false activation ratio and 35% more accident-free driving mileage compared to a rule-only baseline in real-world deployment.

arxiv arXiv cs.LG · 7d ago

Domain-Shift Aware Neural Networks for Unbalance Mass Estimation

A domain-shift aware neural network is proposed for estimating unbalance masses in rotating shafts under varying operating conditions. The model uses maximum mean discrepancy to align feature representations across different operational domains, improving prediction accuracy when system behaviors differ from training conditions. Results show its effectiveness in structural health monitoring applications where domain discrepancies are unknown or unaccounted for.

arxiv arXiv cs.LG · 7d ago

TransitNet Achieves 95.2% Accuracy in Low-SNR Transit Searches

TransitNet, a compact attention-augmented deep learning framework, achieves 95.2% accuracy in low-SNR transit blind searches, outperforming TLS and BLS in ROC-AUC and PR-AP values. It recovers 93.0% of injected Earth- and sub-Earth-size transits, with 97.4% of injected transits fully covered by estimated transit windows, and successfully recovers all 34 confirmed Kepler planets with a mean midpoint error of 1.24 hours.

arxiv arXiv cs.LG · 7d ago

Zero-Shot Active Feature Acquisition via LLM-Elicitation

A new framework enables zero-shot active feature acquisition by leveraging LLMs to elicit only discriminative statistics like unary deviations and pairwise co-variations. Using maximum-entropy closure, it resolves ambiguity in feature selection and outperforms LLMs itself, especially on challenging IBD patient cases where diagnostic uncertainty is high.