AI News

Bridging the Gap: Converting Read Text to Conversational Dialogue (arxiv.org)

One Is Not Enough: How People Use Multiple AI Models in Everyday Life (arxiv.org)

Active Learning of Fractional-Order Viscoelastic Model Parameters for Realistic Haptic Rendering (arxiv.org)

KULTURE Bench: A Benchmark for Assessing Language Model in Korean Cultural Context (arxiv.org)

FDE-Gym: The Last Mile of AI Delivery (arxiv.org)

OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents (arxiv.org)

Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery (arxiv.org)

Scene Reconstruction Using Ubiquitous Wireless Signals via Diffusion Posterior Inference Over physics-Grounded Representations (arxiv.org)

TIPS: A Tiny Inference-time Policy for Scaling in Diffusion Language Models (arxiv.org)

Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones (arxiv.org)

Generalization Guarantees of Randomized Block Coordinate Descent for Nonconvex Learning (arxiv.org)

MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering (arxiv.org)

Evaluation Awareness Beyond English: Do LLMs Act Differently When Tested in Indic Languages? (arxiv.org)

KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents (arxiv.org)

Designing Transformers for Continuous Diffusion Language Models (arxiv.org)

ABNAT: Attention-Based Noise-Aware Training for Robust Transformers on Analog Compute-in-Memory Systems (arxiv.org)

Decoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal Alignment (arxiv.org)

Effectiveness of Hidden-State Probes for Localizing Reasoning Failures (arxiv.org)

Momentum, Commentary Tone, and Earnings Surprise in LLM Financial Forecasts (arxiv.org)

Selection Is Not Learning: Choosing Model Futures (arxiv.org)

A team of Gemini 4 Argon agents beats Minecraft (arxiv.org)

Private Retrieval Augmented Generation via Random Projection (arxiv.org)

EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search (arxiv.org)

Improving Environment-Agnostic Coding Agents: The Role of Scaffolding (arxiv.org)

Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process Posteriors (arxiv.org)

Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing (arxiv.org)

Not All Unlabeled Data Are Equal: Unlabeled Data Selection for Semi-Supervised QSAR Modeling with Large Chemical Repositories (arxiv.org)

LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents (arxiv.org)

X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning (arxiv.org)

Disagreement-Guided Weak-to-Strong Routing (arxiv.org)

Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake Detection (arxiv.org)

Learning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs (arxiv.org)

Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods (arxiv.org)

Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference (arxiv.org)

Local Epochs as Optimal Stopping: Theory and Evidence in Federated Learning (arxiv.org)

GNN-Guided Local Refinement for Efficient Layout Decomposition with DSA-MP (arxiv.org)

HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration (arxiv.org)

AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning (arxiv.org)

Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine (arxiv.org)

Measuring the local shape of learning-rate transfer curves (arxiv.org)

Multi-sourced AI Tutor for Non-Native English Speaker Students (arxiv.org)

Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems? (arxiv.org)

RAG-RST: Retrieved Exemplars as In-Context Discourse Schema for RST Parsing (arxiv.org)

Are You Sure Your LLM Is Sure? Repairing and Auditing Confidence (arxiv.org)

Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions (arxiv.org)

Ontology Refinement with Embeddings and LLMs: A Case Study on CASTON (arxiv.org)

Harmful Partial Interventions and Benign Leakage in Concept-based Models (arxiv.org)

Pairwise AUC Optimization Needs Corrective Power: A Unified View (arxiv.org)

Diffusion Language Models as Open Quantum Systems (arxiv.org)

Approaching Backpropagation Accuracy with Weight Perturbation on MNIST (arxiv.org)