AI News

MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models (arxiv.org)

Myopia Prevention and Control 3.0: Artificial Intelligence--Driven Risk Stratification, Proactive Monitoring, and Personalized Intervention (arxiv.org)

TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation (arxiv.org)

DSTFView: Multi-View Cloud-Edge Workload Forecasting with Dual-Input Spatio-Temporal-Frequency Modeling (arxiv.org)

AIR-BENCH Live: An Evolving Safety Benchmark for Foundation Models (arxiv.org)

DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing (arxiv.org)

Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs (arxiv.org)

ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (arxiv.org)

SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent (arxiv.org)

Multimodal Domain Generalization for Depression Detection: An Attention-Based BiLSTM Network with Domain-Adversarial Training (arxiv.org)

ARdena: Scenario-driven control of real-time LLM agents (arxiv.org)

Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects (arxiv.org)

Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis (arxiv.org)

Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents (arxiv.org)

LanteRn: Latent Visual Structured Reasoning (arxiv.org)

BoneAgeTW2: Automated Skeletal Maturation Assessment via the Tanner-Whitehouse 2 Method, Deep Learning, and Clinical Report Generation with Distribution Curves (arxiv.org)

Learned Interventions in Lean 4 grind (arxiv.org)

HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization (arxiv.org)

Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach (arxiv.org)

LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports (arxiv.org)

Beyond Scale and Generation: Understanding Language Model-based Entity Matching (arxiv.org)

Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents (arxiv.org)

SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents (arxiv.org)

TopoFE: topology-aware LLM-guided Automated Feature Engineering (arxiv.org)

Bit-Accurate FPGA Evaluation of Learned Feature Gating in a Fixed-Point Fourier-Feature Automatic Modulation Classifier (arxiv.org)

Falsifiable Commitment Planning for Self-Correcting Web Agents (arxiv.org)

Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy (arxiv.org)

SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving (arxiv.org)

Codifying the Judge: Scalable Evaluation via Program Distillation (arxiv.org)

DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense (arxiv.org)

Rendering on Real Silicon: GPU Render-Timing as a Passive, AI-Resistant CAPTCHA Signal (arxiv.org)

Beyond Directed Acyclic Graphs: Causal Zeros and Causal Differential Equations (arxiv.org)

TriSP: Tri-Signal Structured Pruning for Large Language Models (arxiv.org)

The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation (arxiv.org)

An empirical investigation into the properties of standard word embeddings (arxiv.org)

Risk reversal for least squares estimators under nested convex constraints (arxiv.org)

From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledge Synthesis (arxiv.org)

An Unofficial FastLAS Tutorial: A Programmer's Guide (arxiv.org)

Operator learning for models of tear film breakup (arxiv.org)

Regulating for AI Legitimacy (arxiv.org)

Embodied GPT-5.1: Evidence of a World Model? (arxiv.org)

Stacking the Deck: Tunable Trainability in Stacked LCUs (arxiv.org)

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy (arxiv.org)

TRE: Training-Free Hallucination Detection for Diffusion Language Models (arxiv.org)

Epistemic Norms for AI Safety and Alignment Research (arxiv.org)

Decentralized Causal Discovery using Judo Calculus (arxiv.org)

Statistically Supported LLM Ingredient and Recipe Data Collection in Computational Nutrition (arxiv.org)

The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting (arxiv.org)

Extending Desbordante with Probabilistic Functional Dependency Discovery Support (arxiv.org)

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis (arxiv.org)