AI News

DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies (arxiv.org)

Repair Lot Skyline: A Weighted Constraint Satisfaction Approach to Pavement Repair Optimization from Geospatial Hazard Density (arxiv.org)

An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing (arxiv.org)

A Trust Layer for Agent Evaluation (arxiv.org)

Cascadia: Resident 975B MoE Inference on Eleven AI PCs (arxiv.org)

Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion (arxiv.org)

Sim-to-Real Transfer of Vision-Language Navigation in Continuous Environments Using an Ackermann-Steered Mobile Robot (arxiv.org)

Is this machine playing? (arxiv.org)

AMBER: Training Long-Horizon Web Agents through Append-Only Memory (arxiv.org)

A Data-Driven Framework for Unsupervised Monitoring of Transmission Systems Using End-of-Line Testing Data: A Case Study at Ford Motor Company (arxiv.org)

Uncertainty in Representation Learning on Knowledge Graphs (arxiv.org)

EVFormer: An Egocentric Vision-EMG Bidirectional Attention Model for Bimanual Hand Pose Estimation (arxiv.org)

Do Neural PDE Solvers Learn the Right Dynamics? (arxiv.org)

Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering (arxiv.org)

When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory (arxiv.org)

Verified, not generated: expert-verified AI study materials and the distribution of learning gains in a university course (arxiv.org)

Small Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid Approach (arxiv.org)

Smart Content Ingestion for Generative AI Workloads (arxiv.org)

CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration (arxiv.org)

QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting (arxiv.org)

Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and Benchmarking (arxiv.org)

Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment (arxiv.org)

When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models (arxiv.org)

Inference-Time Projection for Physically Valid Biomolecular Diffusion Models (arxiv.org)

JIVEAdapter: A Multi-Task Additive Low-Rank Adapter via Joint and Individual Variation Explained (JIVE) (arxiv.org)

AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD (arxiv.org)

Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning (arxiv.org)

Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience (arxiv.org)

Should We Skip Diffusion? (arxiv.org)

Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents (arxiv.org)

Joint upper-bound coverage and route-choice utility: an empirical evaluation on two urban proxy tasks (arxiv.org)

When better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value (arxiv.org)

EPOCH: Reliable Discovery through Evidence-Governed Search (arxiv.org)

LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems (arxiv.org)

Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers (arxiv.org)

Comparative review of hybrid forecasting models for short-term prediction of building thermal load (arxiv.org)

Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks (arxiv.org)

When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO (arxiv.org)

TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning (arxiv.org)

From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models (arxiv.org)

Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction (arxiv.org)

Metonymic Circuits for Abstract Concept Grounding in Vision Transformers (arxiv.org)

RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway (arxiv.org)

FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving (arxiv.org)

Memory-Efficient Expert Routing for Distributed MoE Training (arxiv.org)

From Sandbox to Enforcement: Confidence-Qualified Threat Intelligence for Critical Infrastructure (arxiv.org)

Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation (arxiv.org)

Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale (arxiv.org)

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models (arxiv.org)

Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence (arxiv.org)