AI News

Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy (arxiv.org)

AI Mathematician: Towards Fully Automated Frontier Mathematical Research (arxiv.org)

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (arxiv.org)

Evaluating the Evaluator: Summarization Metrics and LLM-Judges beyond English (arxiv.org)

DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models (arxiv.org)

A Comparative Study of Graph Representations for GNN-Based Power Grid Control in L2RPN (arxiv.org)

TrajMind: Chaining Role-Specialized LoRAs for Fast-and-Slow Collective Trajectory Anomaly Diagnosis (arxiv.org)

A Common Measure of Communication for Speech Brain-Computer Interfaces (arxiv.org)

Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling (arxiv.org)

Source Distribution Estimation by Posterior Averaging (arxiv.org)

A Survey of Transformer-based Language Models with Focus on Efficiency (arxiv.org)

Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models (arxiv.org)

Differentiable Electricity-Market Clearing for Gradient-Based Planning (arxiv.org)

Multi-Agent Retrieval-Augmented Generation for Efficient Cloud Knowledge Base Search in Telecom SNOC Environment (arxiv.org)

Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights (arxiv.org)

H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression (arxiv.org)

LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates (arxiv.org)

Do Tabular Foundation Models Know Physics? Contamination, Units, and the Deterministic Limit (arxiv.org)

Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation (arxiv.org)

ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation (arxiv.org)

Bernini: Latent Semantic Planning for Video Diffusion (arxiv.org)

Multimodal Language Models as Text-to-Image Model Evaluators (arxiv.org)

GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models (arxiv.org)

Deep Reinforcement Learning for Reach-Avoid-Stay Problems (arxiv.org)

Enhancing brain age estimation with structural MRI and synthesized cerebral blood volume maps (arxiv.org)

Sample Complexity of Linear Quadratic Regulator Without Initial Stability (arxiv.org)

Quantum Speedups for Sampling and Non-convex Optimization with Stochastic Oracles (arxiv.org)

Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time Analysis (arxiv.org)

Secure AI-Driven Super-Resolution for Real-Time Mixed Reality Applications (arxiv.org)

On Cost-Aware Designs for Sequential Hypothesis Testing (arxiv.org)

Learning and extrapolating scale-invariant processes (arxiv.org)

Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models (arxiv.org)

PIE-APT: Abductive Planning over Temporal Dynamic Knowledge Graphs via Incremental Reasoning (arxiv.org)

Rating the Raters: Rasch Measurement Theory for LLM Evaluation (arxiv.org)

When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems (arxiv.org)

AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents (arxiv.org)

Dutch central bank moves 86 tonnes of gold from US citing 'geopolitical unrest' (www.theguardian.com)

Global Heating Will Hit At Least 1.8C, UN Warns, and There Are 'No Good Outcomes' (news.slashdot.org)

Wk. 6 of Vibecoding an MMO (eldermyr.com)

Nex (www.producthunt.com)

Write Software in Latin (2025) [video] (www.youtube.com)

Edyt (www.producthunt.com)

Show HN: The cheapest GPU cloud – H100s at $2.04/HR, H200s at $3/HR (compute.cheap)

Marche-Course Octobre Rose Nancy 2026 - Factuel - l'Info de l'Université de Lorraine (factuel.univ-lorraine.fr)

Even Water-Rich Minnesota Is Confronting Water Scarcity - Governing Magazine (www.governing.com)

Meta Pushes Its New AI Agent on Employees—but Eases Off on Tokenmaxxing (www.wired.com)

Effort to ban NDAs with data centers gets 'do-not-pass' recommendation in committee (www.kfyrtv.com)

Go grandmaster Shin defeats AI KataGo with a two-stone handicap (www.kedglobal.com)

One data center property. More than 3 million gallons of water lost. Schools closed ... - Facebook (www.facebook.com)

GPS glitched across the US by as much as 33 feet (www.sciencealert.com)