AI News

Multi-Label Proportion Learning for Sea-Ice Type Prediction (arxiv.org)

World Models for Embodied Intelligence: From Plausible to Controllable to Actionable (arxiv.org)

Channel-Informed Neural Network for Physical Layer Key Generation (arxiv.org)

Generative models for simulation based filtering: Formulations and Empirical Comparisons (arxiv.org)

A Weighted Kernel Method for Approximation that Adapts to Learned Multivariable Structure (arxiv.org)

Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstruction (arxiv.org)

Seeing What Matters: Visual Cue Guided Video Planning for Generalizable Robot Navigation (arxiv.org)

Available but Unclaimed: An Empirical Study of Human-AI Synergy (arxiv.org)

Finding Common Mistakes In Modelling With Mathematical Formalisms Using LLMs (arxiv.org)

AI for Science with GPT-6 Astra: Thermal Design and Electrothermal Analysis of 2D CFET (arxiv.org)

Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations (arxiv.org)

Differentially Private Semantic Plans for Aggregate Insight Generation (arxiv.org)

Scaling Laws for Physics-Aware ACOPF Surrogate Learning (arxiv.org)

Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation (arxiv.org)

Optimal Pruning for Neural Architectures using Fisher Information Distances (arxiv.org)

Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation (arxiv.org)

CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine (arxiv.org)

GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events (arxiv.org)

Position: AI Is Not Ready for Strategic Conflicts (arxiv.org)

R3: Robust Rubric-Agnostic Reward Models (arxiv.org)

Calibrate, Then Route: A Measured Study of Learned Request Routing for Disaggregated LLM Serving (arxiv.org)

Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance (arxiv.org)

Where Should the KV Cache Live? Placement Policies Across GPU, CPU, and SSD for Long-Lived Sessions (arxiv.org)

Toward Governance-Aware Autonomous GIS: A Narrative Review of Ethical and Privacy Risks in LLM-Enabled GeoAI (arxiv.org)

Metacognitive Steering: Learning the Structure of Scientific Judgment (arxiv.org)

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It (arxiv.org)

Time-warping estimation via stationarity-based learning of the de-warped signal (arxiv.org)

On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithm (arxiv.org)

Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data (arxiv.org)

CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design (arxiv.org)

The AI-Enabled Scientific Frontier (arxiv.org)

BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents (arxiv.org)

Cross-Anatomy Transfer Versus Sparse Interpolation in Digital-Twin-Oriented Aortic Fluid-Structure Interaction Surrogates (arxiv.org)

Breaking the 1.58-bit Barrier for Ternary LLMs (arxiv.org)

Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs (arxiv.org)

Skill-based Agentic Evaluation for Real-time Data Science Tasks (arxiv.org)

AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research (arxiv.org)

QueryFormer: Winning Solution for KDD Cup 2026 Tencent UniRec Challenge (arxiv.org)

Query-Aware Source-Risk Triage for Retrieval-Augmented Generation (arxiv.org)

Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models (arxiv.org)

A Framework for Generating Valid Context-Specific Benchmarks through Expert Guidance (arxiv.org)

Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent (arxiv.org)

Mini-batch Sampling Strategies for Long-Tailed Image Classification: An Empirical Study on CIFAR-100-LT (arxiv.org)

Learned Look-Ahead Splitting Rule for CART (arxiv.org)

EVINCE: Optimizing Multi-LLM Dialogues Using Conditional Statistics and Information Theory (arxiv.org)

EchoPath: Execution-Level Replayable Memory for GUI Agents (arxiv.org)

ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training (arxiv.org)

ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds (arxiv.org)

Certified Inference and Training for Deep Equilibrium Networks: A Continuation Framework with Polynomial Complexity Guarantees (arxiv.org)

AI for Games in the Foundation Model Era (arxiv.org)