AI News

Type-safe HTML templating in Zig (lalinsky.com)

Veille quotidienne — 12/10/2026

Yandex bot traffic down 99% after data center attack (radar.cloudflare.com)

Will Linux phones become a viable alternative to the Android/iOS duopoly? (amosbbatto.wordpress.com)

Building an @ai Comment Assistant in Google Docs with ADK and the New Docs API v1 Comment… (medium.com)

Spatial Context or Memory? Sizing the Inputs of Neural Surrogates for Partially Observed Fields (arxiv.org)

Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing (arxiv.org)

EliteTable: Self-Improving Program Search for Executable Control Policies (arxiv.org)

Beyond Discrepancy: Oracle Drift in Nonstationary Weighted Risk Minimization (arxiv.org)

Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure (arxiv.org)

Gaussian BROJA Partial Information Decomposition in Closed Form (arxiv.org)

How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference? (arxiv.org)

Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models (arxiv.org)

Markov Chain Convergence in Kernel-Induced Geometry (arxiv.org)

SLICE: Sequential Likelihood-Free Inference via Conformal E-Values (arxiv.org)

SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire (arxiv.org)

Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM (arxiv.org)

SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data (arxiv.org)

Model-agnostic Knowledge Augmented Machine Learning for Weakly Annotated Bioimaging Data (arxiv.org)

SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle (arxiv.org)

COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering (arxiv.org)

LeWAM: End-to-End World and Action Modeling with JEPAs (arxiv.org)

Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search (arxiv.org)

REDaCT: Collapse-Free Unlearning in Large Reasoning Models (arxiv.org)

Meta-Reflective Evolution Effectively Improves Production AI Systems (arxiv.org)

Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries (arxiv.org)

Trajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data (arxiv.org)

KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting (arxiv.org)

Spatial Prediction with Guided Diffusion (arxiv.org)

Minimax Rates for Estimating Powered Sliced Wasserstein Functionals (arxiv.org)

Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability (arxiv.org)

A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models (arxiv.org)

Amortised Inference through One-Step Implicit Sampling (arxiv.org)

Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure (arxiv.org)

Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents (arxiv.org)

Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance (arxiv.org)

Hitting-Time Bounds for Asynchronous Q-Learning (arxiv.org)

Finite-Sample Guarantees for Fully Discrete Conditional Diffusion Models (arxiv.org)

Constrained Probabilistic Numerics: Gaussian Process Solvers for Linear PDEs under Linear Inequality Constraints (arxiv.org)

From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds (arxiv.org)

Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels (arxiv.org)

Scalable Sparse Autoregressive Variational Inference for Non-Gaussian Spatial Fields (arxiv.org)

A Critical Look at Power Sampling when Test Time Sharpening LLMs (arxiv.org)

Some remarks on the connection between generative diffusion and optimal transport (arxiv.org)

CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation Elliptope (arxiv.org)

Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning (arxiv.org)

Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate (arxiv.org)

Model-free Bayesian Clustering and Multimodal Posterior Summarisation (arxiv.org)

Fast Gradient-Based Approximation of Continuous Dynamic Time Warping (arxiv.org)

Why Heavy-Tailed Weight Spectra Predict Model Quality (arxiv.org)