AI News

Algebraic Integer Quantization for Machine Learning Applications (arxiv.org)

Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK (arxiv.org)

Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective (arxiv.org)

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance (arxiv.org)

Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics (arxiv.org)

Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification (arxiv.org)

Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction (arxiv.org)

OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models (arxiv.org)

One-Step Text Generation by Seq-Drifting (arxiv.org)

Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses (arxiv.org)

Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization (arxiv.org)

Towards Defining, Measuring, and Leveraging Creativity in AI Applications (arxiv.org)

Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing (arxiv.org)

Neural networks are more modular than single neurons suggest (arxiv.org)

Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems (arxiv.org)

Representation Alignment from a Few Paired Data via Distilled Optimal Transport (arxiv.org)

Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs (arxiv.org)

VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails (arxiv.org)

AgroGround: Multi-Granularity Grounded Recognition in Agriculture (arxiv.org)

EvoBelief: Falsifiable World Models for Self-Improving LLM Agents (arxiv.org)

MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis (arxiv.org)

CLEAT: Learning Value-Guided Clarification for Interactive Agents (arxiv.org)

A small cognitive core explains human behavior at scale (arxiv.org)

DAG Structure Learning with Node-Varying Heavy-Tailed Disturbances (arxiv.org)

Enriched Holomorphic Neural Networks for 2D and 3D Laplace Problems (arxiv.org)

Efficient Learning of Survival Analysis Models Under Outcome-Dependent Truncation and Censoring (arxiv.org)

Market Impact Estimation via Causal Foundation Models (arxiv.org)

Kairos: Toward a Byte-Level Foundation Model for Every Modality (arxiv.org)

CoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property Prediction (arxiv.org)

Static Gradient Attribution Underperforms a Density-Matched Random Mask on Loss-Based Forgetting Within LoRA B-Matrix (arxiv.org)

Neural expectation-maximization and meta-models (arxiv.org)

Robust Machine Learning for Regulatory Sequence Modeling under Biological and Technical Distribution Shifts (arxiv.org)

Bayesian dynamic scheduling of multipurpose batch processes under incomplete look-ahead information (arxiv.org)

A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring) (arxiv.org)

Optimizable Model Averaging for Ensembling Heterogeneous Model Outputs (arxiv.org)

Linearized Wasserstein dimensionality reduction with approximation guarantees (arxiv.org)

Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data (arxiv.org)

Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions (arxiv.org)

Locally Private Parametric Methods for Change-Point Detection (arxiv.org)

HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos (arxiv.org)

Data-Driven Stochastic Optimal Control in Reproducing Kernel Hilbert Spaces (arxiv.org)

Infinitesimal Operator World Models: Finite-Sample Guarantees for Offline Reinforcement Learning (arxiv.org)

One Thing Leads to Another: The Essentials of Time Series Causal Discovery (arxiv.org)

BLOKS: Scaling Kernel Solvers with Sketched Block Preconditioning (arxiv.org)

Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction (arxiv.org)

A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics (arxiv.org)

Solving VeriContest with a Lean-Backed Rust Verifier (arxiv.org)

GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive (arxiv.org)

Green-Routed Neural Operators: Physics Determines Where the Network Reads (arxiv.org)

Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents (arxiv.org)