Machine Learning

Meta Unveils New A.I. Model, Its First From the Superintelligence Lab

Meta has introduced a new A.I. model, marking the first release from its Superintelligence Lab.

Anthropic’s ‘Claude Mythos’ model sparks fear of AI doomsday if released to public: ‘Weapons we can’t even envision’

Anthropic has triggered alarm bells by touting the terrifying capabilities of “Claude Mythos” – with executives warning the new AI model ...

Meta’s New AI Model Gives Mark Zuckerberg a Seat at the Big Kid’s Table

[2402.08151] Perturbative adaptive importance sampling for Bayesian LOO cross-validation

Abstract page for arXiv paper 2402.08151: Perturbative adaptive importance sampling for Bayesian LOO cross-validation

[2312.00357] A Generalizable Deep Learning System for Cardiac MRI

Abstract page for arXiv paper 2312.00357: A Generalizable Deep Learning System for Cardiac MRI

[2603.13334] Lipschitz-Based Robustness Certification Under Floating-Point Execution

Abstract page for arXiv paper 2603.13334: Lipschitz-Based Robustness Certification Under Floating-Point Execution

[2603.16661] Self-Aware Markov Models for Discrete Reasoning

Abstract page for arXiv paper 2603.16661: Self-Aware Markov Models for Discrete Reasoning

[2603.13909] FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for Non-IID Data

Abstract page for arXiv paper 2603.13909: FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for...

[2511.16148] Enhancing Nuclear Reactor Core Simulation through Data-Based Surrogate Models

Abstract page for arXiv paper 2511.16148: Enhancing Nuclear Reactor Core Simulation through Data-Based Surrogate Models

[2601.16399] A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning

Abstract page for arXiv paper 2601.16399: A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to ...

[2601.00473] Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning

Abstract page for arXiv paper 2601.00473: Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning

[2511.18789] Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictors

Abstract page for arXiv paper 2511.18789: Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Le...

[2511.18000] Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning

Abstract page for arXiv paper 2511.18000: Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Indi...

[2512.03923] Quantum-Classical Physics-Informed Neural Networks for Solving Reservoir Seepage Equations

Abstract page for arXiv paper 2512.03923: Quantum-Classical Physics-Informed Neural Networks for Solving Reservoir Seepage Equations

[2511.18178] Bayesian Calibration of Engine-out NOx Models for Engine-to-Engine Transferability

Abstract page for arXiv paper 2511.18178: Bayesian Calibration of Engine-out NOx Models for Engine-to-Engine Transferability

[2511.11743] Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts

Abstract page for arXiv paper 2511.11743: Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts

[2511.06767] QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations

Abstract page for arXiv paper 2511.06767: QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common P...

[2510.27321] MedM2T: A MultiModal Framework for Time-Aware Modeling with Electronic Health Record and Electrocardiogram Data

Abstract page for arXiv paper 2510.27321: MedM2T: A MultiModal Framework for Time-Aware Modeling with Electronic Health Record and Electr...

[2510.14814] Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift

Abstract page for arXiv paper 2510.14814: Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift

[2510.15495] OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning

Abstract page for arXiv paper 2510.15495: OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning

[2510.14751] Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries

Abstract page for arXiv paper 2510.14751: Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries

[2510.06020] RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics

Abstract page for arXiv paper 2510.06020: RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics

[2510.00430] PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment

Abstract page for arXiv paper 2510.00430: PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment