Machine Learning

Continuous Knowledge Transfer Between Claude and Codex

For the last 8 months I've developed strictly using Claude Code, setting up context layers, hooks, skills, etc. But relying on one model ...

Anthropic's latest AI model identifies 'thousands of zero-day vulnerabilities' in 'every major operating system and every major web browser' — Claude Mythos Preview sparks race to fix critical bugs, some unpatched for decades

Anthropic says its latest AI model is too powerful for public release and that it broke containment during testing

[2603.24475] Conformalized Transfer Learning for Li-ion Battery State of Health Forecasting under Manufacturing and Usage Variability

Abstract page for arXiv paper 2603.24475: Conformalized Transfer Learning for Li-ion Battery State of Health Forecasting under Manufactur...

[2603.24431] Learning Response-Statistic Shifts and Parametric Roll Episodes from Wave--Vessel Time Series via LSTM Functional Models

Abstract page for arXiv paper 2603.24431: Learning Response-Statistic Shifts and Parametric Roll Episodes from Wave--Vessel Time Series v...

[2603.24428] Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching

Abstract page for arXiv paper 2603.24428: Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Ma...

[2603.24384] On the Use of Bagging for Local Intrinsic Dimensionality Estimation

Abstract page for arXiv paper 2603.24384: On the Use of Bagging for Local Intrinsic Dimensionality Estimation

[2603.24382] MolEvolve: LLM-Guided Evolutionary Search for Interpretable Molecular Optimization

Abstract page for arXiv paper 2603.24382: MolEvolve: LLM-Guided Evolutionary Search for Interpretable Molecular Optimization

[2603.24324] Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning

Abstract page for arXiv paper 2603.24324: Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforce...

[2603.24275] Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centers

Abstract page for arXiv paper 2603.24275: Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Sem...

[2603.24254] Embracing Heteroscedasticity for Probabilistic Time Series Forecasting

Abstract page for arXiv paper 2603.24254: Embracing Heteroscedasticity for Probabilistic Time Series Forecasting

[2603.24265] DeepDTF: Dual-Branch Transformer Fusion for Multi-Omics Anticancer Drug Response Prediction

Abstract page for arXiv paper 2603.24265: DeepDTF: Dual-Branch Transformer Fusion for Multi-Omics Anticancer Drug Response Prediction

[2603.24262] Forecasting with Guidance: Representation-Level Supervision for Time Series Forecasting

Abstract page for arXiv paper 2603.24262: Forecasting with Guidance: Representation-Level Supervision for Time Series Forecasting

[2603.24232] Attack Assessment and Augmented Identity Recognition for Human Skeleton Data

Abstract page for arXiv paper 2603.24232: Attack Assessment and Augmented Identity Recognition for Human Skeleton Data

[2603.24213] Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage

Abstract page for arXiv paper 2603.24213: Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link...

[2603.24207] IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting

Abstract page for arXiv paper 2603.24207: IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting

[2603.24202] A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula

Abstract page for arXiv paper 2603.24202: A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula

[2603.24186] TsetlinWiSARD: On-Chip Training of Weightless Neural Networks using Tsetlin Automata on FPGAs

Abstract page for arXiv paper 2603.24186: TsetlinWiSARD: On-Chip Training of Weightless Neural Networks using Tsetlin Automata on FPGAs

[2603.24143] Linear-Nonlinear Fusion Neural Operator for Partial Differential Equations

Abstract page for arXiv paper 2603.24143: Linear-Nonlinear Fusion Neural Operator for Partial Differential Equations

[2603.24138] Efficient Controller Learning from Human Preferences and Numerical Data Via Multi-Modal Surrogate Models

Abstract page for arXiv paper 2603.24138: Efficient Controller Learning from Human Preferences and Numerical Data Via Multi-Modal Surroga...

[2603.24131] Reservoir-Based Graph Convolutional Networks

Abstract page for arXiv paper 2603.24131: Reservoir-Based Graph Convolutional Networks

[2603.24128] On Gossip Algorithms for Machine Learning with Pairwise Objectives

Abstract page for arXiv paper 2603.24128: On Gossip Algorithms for Machine Learning with Pairwise Objectives

[2603.24126] Likelihood hacking in probabilistic program synthesis

Abstract page for arXiv paper 2603.24126: Likelihood hacking in probabilistic program synthesis