Cohere、グローバルAIの文化的公平性を論述

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations

arXiv cs.CL (Computation and Language) ・ 2026-06-24

Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect

arXiv cs.CL (Computation and Language) ・ 2026-06-24

Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

Weave of Formal Thought

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

Measurable Majorities Are Not Finitely Axiomatizable

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

Confidence Sequences for Online Statistical Model Checking of Markov Decision Processes

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

Bridging Spherical Black-Box Optimizers

arXiv cs.LG (Machine Learning) ・ 2026-06-24

Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning

arXiv cs.CL (Computation and Language) ・ 2026-06-24

Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution

arXiv cs.CL (Computation and Language) ・ 2026-06-24

Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning

arXiv cs.LG (Machine Learning) ・ 2026-06-24

Power-Budgeted Underwater Vehicle Control via Constrained Reinforcement Learning

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

BitNet Text Embeddings

arXiv cs.CL (Computation and Language) ・ 2026-06-24

Learning Subset-Shared Invariances for Domain Generalization with Mixture-of-Experts

arXiv cs.LG (Machine Learning) ・ 2026-06-24

Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-24

Statistically Valid Hyperparameter Selection: From Tuning to Guarantees

arXiv cs.LG (Machine Learning) ・ 2026-06-24

SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding

arXiv cs.CL (Computation and Language) ・ 2026-06-24

Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems

arXiv cs.CL (Computation and Language) ・ 2026-06-24

Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming

arXiv cs.CL (Computation and Language) ・ 2026-06-24

OpenThoughts-Agent: Data Recipes for Agentic Models

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

SHERLOC: Structured Diagnostic Localization for Code Repair Agents

arXiv cs.CL (Computation and Language) ・ 2026-06-23

OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

BluTrain: A C++/CUDA Framework for AI Systems

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

Are We Ready For An Agent-Native Memory System?

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Posterior Refinement: Fast Language Generation via Any-Order Flow Maps

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Decentralised AI Training and Inference with BlockTrain

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

Model selection with proper scoring rules on data sets of time series

arXiv cs.LG (Machine Learning) ・ 2026-06-23

TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environments

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

LaGO: Latent Action Guidance for Online Reinforcement Learning

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge

arXiv cs.CL (Computation and Language) ・ 2026-06-23

CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

QC-SMOTE: Quality-Controlled SMOTE for Imbalanced Classification

arXiv cs.LG (Machine Learning) ・ 2026-06-23

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

Uncertainty-Aware Longitudinal Forecasting of Alzheimer's Disease Progression Using Deep Learning

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

Qwen-AgentWorld: Language World Models for General Agents

arXiv cs.CL (Computation and Language) ・ 2026-06-23

To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias

arXiv cs.CL (Computation and Language) ・ 2026-06-23

AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

arXiv cs.CL (Computation and Language) ・ 2026-06-23

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-23

An LLM-based Two-Stage Transformer Framework for Cross-Domain Bearing Fault Diagnosis with Limited Data

arXiv cs.CL (Computation and Language) ・ 2026-06-23

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

arXiv cs.LG (Machine Learning) ・ 2026-06-23

AutoSpecNER: A Fine-Grained Named Entity Recognition Dataset for Vehicle Specification Extraction

arXiv cs.CL (Computation and Language) ・ 2026-06-23

MorfFlex: Handling Rich Morphology

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints

arXiv cs.LG (Machine Learning) ・ 2026-06-23

Meet UD_Czech-PDTC: A Large and Genre-Rich Treebank in Universal Dependencies

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Prague Dependency Treebank -- Consolidated 2.0: Enriching a Complex Annotation Scheme

arXiv cs.CL (Computation and Language) ・ 2026-06-23

PROTECT-90: A Fault Dataset for Power System Protection

arXiv cs.LG (Machine Learning) ・ 2026-06-23

AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression

arXiv cs.CL (Computation and Language) ・ 2026-06-23

MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Dialogue to Discovery: Attribute-Aware Preference Elicitation for Conversational Product Search Assistants

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Co-occurring associated retained concepts in Diffusion Unlearning

arXiv cs.CL (Computation and Language) ・ 2026-06-23

Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment

arXiv cs.LG (Machine Learning) ・ 2026-06-23

A Pāninian Foundation for Indic Language Processing

arXiv cs.LG (Machine Learning) ・ 2026-06-23

BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks

arXiv cs.LG (Machine Learning) ・ 2026-06-23

Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning

arXiv cs.LG (Machine Learning) ・ 2026-06-23

Blockwise Policy-Drift Gating for On-Policy Distillation

arXiv cs.LG (Machine Learning) ・ 2026-06-23

Rapid FinFET Modelling Using an Autoencoder

arXiv cs.LG (Machine Learning) ・ 2026-06-23

RoPE-Aware Bit Allocation for KV-Cache Quantization

arXiv cs.LG (Machine Learning) ・ 2026-06-23

Semantic Browsing: Controllable Diversity for Image Generation

arXiv cs.LG (Machine Learning) ・ 2026-06-22

AIR: Adaptive Interleaved Reasoning with Code in MLLMs

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

Can LLMs Reliably Self-Report Adversarial Prefills, and How?

arXiv cs.CL (Computation and Language) ・ 2026-06-22

Discovering Latent Groups for Robust Classification

arXiv cs.LG (Machine Learning) ・ 2026-06-22

Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS

arXiv cs.LG (Machine Learning) ・ 2026-06-22

The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

Decentralized Autonomous Traffic Management through Corridor Networks

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline Regression

arXiv cs.LG (Machine Learning) ・ 2026-06-22

Approximating velocity fields with planted attractors via Neural-ODEs for classification purposes

arXiv cs.LG (Machine Learning) ・ 2026-06-22

Simulation-Free Estimation of Traffic Flows from Sparse Count Data

arXiv cs.LG (Machine Learning) ・ 2026-06-22

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

arXiv cs.LG (Machine Learning) ・ 2026-06-22

CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

TriggerBench: Investigating Prospective Memory for Large Language Models

arXiv cs.CL (Computation and Language) ・ 2026-06-22

Selective Time Series Forecasting via Metalearning

arXiv cs.LG (Machine Learning) ・ 2026-06-22

Rethinking Object-Centric Representations for Video Dynamics Modeling

arXiv cs.LG (Machine Learning) ・ 2026-06-22

Interpretable Kolmogorov-Arnold Network with Feature-Isolated Temporal Attention Mechanism for Electricity Load Forecasting

arXiv cs.LG (Machine Learning) ・ 2026-06-22

GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation

arXiv cs.LG (Machine Learning) ・ 2026-06-22

Leveraging Similarities in Multi-Armed Bandits

arXiv cs.LG (Machine Learning) ・ 2026-06-22

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-22

Uncertainty-based Debiasing and Unlearning for Decontamination

arXiv cs.CL (Computation and Language) ・ 2026-06-22

Judgment-Grounded Expansion for Peer Review Generation

arXiv cs.CL (Computation and Language) ・ 2026-06-22

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?

arXiv cs.CL (Computation and Language) ・ 2026-06-22

PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation

arXiv cs.CL (Computation and Language) ・ 2026-06-22

Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning

arXiv cs.CL (Computation and Language) ・ 2026-06-22

PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models

arXiv cs.CL (Computation and Language) ・ 2026-06-22

Unlimited OCR Works

arXiv cs.CL (Computation and Language) ・ 2026-06-22

Predicate Importance Estimation and Decoupled Rationale-Score Distillation for Entity Alignment

arXiv cs.CL (Computation and Language) ・ 2026-06-22