NVIDIA、AIファクトリー可観測性の指針公開

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Machine Learning-Based Cyber Defense for Cloud Infrastructure: An Adaptive Deep Q-Network Architecture for Intelligent Intrusion Detection and Automated Threat Mitigation

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

ADEPT: A Unified Framework for Deep Learning Test Adequacy

arXiv cs.LG (Machine Learning) ・ 2026-08-12

A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

arXiv cs.CL (Computation and Language) ・ 2026-08-12

QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Confidence Calibration of Deep Learning Systems

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP

arXiv cs.LG (Machine Learning) ・ 2026-08-12

Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

Clustered Randomized Smoothing for Stochastic Prediction Functions

arXiv cs.LG (Machine Learning) ・ 2026-08-12

From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-12

A Remote Approach to Cashew Orchard Detection: Leveraging Active Learning with Satellite Imagery in Guinea-Bissau

arXiv cs.LG (Machine Learning) ・ 2026-08-12

LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation

arXiv cs.LG (Machine Learning) ・ 2026-08-12

LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training

arXiv cs.CL (Computation and Language) ・ 2026-08-12

Hybrid Gated Attention

arXiv cs.CL (Computation and Language) ・ 2026-08-12

TELLME: Test-Enhanced Learning for Language Model Enrichment

arXiv cs.CL (Computation and Language) ・ 2026-08-12

GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation

arXiv cs.CL (Computation and Language) ・ 2026-08-12

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction

arXiv cs.CL (Computation and Language) ・ 2026-08-12

MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques

arXiv cs.CL (Computation and Language) ・ 2026-08-12

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance

arXiv cs.CL (Computation and Language) ・ 2026-08-12

Surgical WAM: A World-Action Model for Data-Efficient Surgical Robot Learning

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

Hierarchical Empirical-Bayes Naive Bayes: Minimax Smoothing and Calibration with AODE Extension

arXiv cs.LG (Machine Learning) ・ 2026-08-11

A Recommendation System Approach for Interference-Robust Sensor Subset Selection

arXiv cs.LG (Machine Learning) ・ 2026-08-11

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

Efficient Hypergradient Descent for Inverse Reinforcement Learning

arXiv cs.LG (Machine Learning) ・ 2026-08-11

SCOUT: Symmetric Consensus Outlier Detection for Failure Localization in LLM Pre-Training

arXiv cs.LG (Machine Learning) ・ 2026-08-11

Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching

arXiv cs.CL (Computation and Language) ・ 2026-08-11

R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

ConRub-Med: Reinforcement Learning with Consensus Rubrics for Open-Ended Medical Question Answering

arXiv cs.CL (Computation and Language) ・ 2026-08-11

Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

MUSE: A Full-Text Cross-Domain Knowledge Base of Scientific Problems, Solutions, and Rationales

arXiv cs.CL (Computation and Language) ・ 2026-08-11

Threshold Structure of Optimal Policies in Restart POMDPs

arXiv cs.LG (Machine Learning) ・ 2026-08-11

FedCGR: Federated Cross-Domain Generative Recommendation

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

ReOrder-OPD:Reliability-Aware Prompt Ordering for On-Policy Distillation

arXiv cs.LG (Machine Learning) ・ 2026-08-11

Self-Normalized Inference for Constant-Stepsize Temporal-Difference Learning under Markovian Sampling

arXiv cs.LG (Machine Learning) ・ 2026-08-11

Certify or Refuse: A Cross-Model Map for Selective Risk Control with Coverage Floors under Covariate Shift

arXiv cs.CL (Computation and Language) ・ 2026-08-11

MIRA: Medical Image Reflection for Agentic Diagnosis

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

Surfacing the Unsaid: CUE-Bench for Affective Stance in Chinese Discourse

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

BPG: Balancing Plasticity and Generalization for Domain Incremental Learning

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

EvoMem: Memory-Augmented Evolution for Code Optimization

arXiv cs.AI (Artificial Intelligence) ・ 2026-08-11

Most biomedical publications show signs of LLM-assisted writing

arXiv cs.CL (Computation and Language) ・ 2026-08-11

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

arXiv cs.CL (Computation and Language) ・ 2026-08-11

Leveraging Human Reading Behavior for Keyphrase Extraction: A Webcam-based Eye-tracking Corpus

arXiv cs.CL (Computation and Language) ・ 2026-08-11

Seeds Before Objectives: Rethinking Evaluation for Low-Resource Garhwali ASR

arXiv cs.CL (Computation and Language) ・ 2026-08-11

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

arXiv cs.CL (Computation and Language) ・ 2026-08-11