Machine Learning

Can Claude Opus 4.7 and Ensemble AI Models Finally Make Code Review Reliable?

Ensemble AI models like Claude Opus 4.7 transform code review reliability. Discover how multi-model approaches catch subtle bugs human re...

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

Improving AI models’ ability to explain their predictions

[2603.28921] Beta-Scheduling: Momentum from Critical Damping as a Diagnostic and Correction Tool for Neural Network Training

Abstract page for arXiv paper 2603.28921: Beta-Scheduling: Momentum from Critical Damping as a Diagnostic and Correction Tool for Neural ...

[2603.28887] OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models

Abstract page for arXiv paper 2603.28887: OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models

[2603.28858] OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training

Abstract page for arXiv paper 2603.28858: OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training

[2603.28845] OneComp: One-Line Revolution for Generative AI Model Compression

Abstract page for arXiv paper 2603.28845: OneComp: One-Line Revolution for Generative AI Model Compression

[2603.28838] GMA-SAWGAN-GP: A Novel Data Generative Framework to Enhance IDS Detection Performance

Abstract page for arXiv paper 2603.28838: GMA-SAWGAN-GP: A Novel Data Generative Framework to Enhance IDS Detection Performance

[2603.28824] SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

Abstract page for arXiv paper 2603.28824: SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

[2603.28823] Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs

Abstract page for arXiv paper 2603.28823: Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs

[2603.28817] GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models

Abstract page for arXiv paper 2603.28817: GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models

[2603.28813] The impact of multi-agent debate protocols on debate quality: a controlled case study

Abstract page for arXiv paper 2603.28813: The impact of multi-agent debate protocols on debate quality: a controlled case study

[2603.28798] Design and Development of an ML/DL Attack Resistance of RC-Based PUF for IoT Security

Abstract page for arXiv paper 2603.28798: Design and Development of an ML/DL Attack Resistance of RC-Based PUF for IoT Security

[2603.28795] StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving

Abstract page for arXiv paper 2603.28795: StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving

[2603.28809] WAter: A Workload-Adaptive Knob Tuning System based on Workload Compression

Abstract page for arXiv paper 2603.28809: WAter: A Workload-Adaptive Knob Tuning System based on Workload Compression

[2603.28803] CREST: Constraint-Release Execution for Multi-Robot Warehouse Shelf Rearrangement

Abstract page for arXiv paper 2603.28803: CREST: Constraint-Release Execution for Multi-Robot Warehouse Shelf Rearrangement

[2603.28787] Smartphone-Based Identification of Unknown Liquids via Active Vibration Sensing

Abstract page for arXiv paper 2603.28787: Smartphone-Based Identification of Unknown Liquids via Active Vibration Sensing

[2603.28780] Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding

Abstract page for arXiv paper 2603.28780: Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradi...

[2603.28776] DF-ACBlurGAN: Structure-Aware Conditional Generation of Internally Repeated Patterns for Biomaterial Microtopography Design

Abstract page for arXiv paper 2603.28776: DF-ACBlurGAN: Structure-Aware Conditional Generation of Internally Repeated Patterns for Biomat...

[2603.28774] Focus360: Guiding User Attention in Immersive Videos for VR

Abstract page for arXiv paper 2603.28774: Focus360: Guiding User Attention in Immersive Videos for VR

[2603.27006] The Last Fingerprint: How Markdown Training Shapes LLM Prose

Abstract page for arXiv paper 2603.27006: The Last Fingerprint: How Markdown Training Shapes LLM Prose

[2603.30031] The Triadic Cognitive Architecture: Bounding Autonomous Action via Spatio-Temporal and Epistemic Friction

Abstract page for arXiv paper 2603.30031: The Triadic Cognitive Architecture: Bounding Autonomous Action via Spatio-Temporal and Epistemi...

[2603.29993] Extending MONA in Camera Dropbox: Reproduction, Learned Approval, and Design Implications for Reward-Hacking Mitigation

Abstract page for arXiv paper 2603.29993: Extending MONA in Camera Dropbox: Reproduction, Learned Approval, and Design Implications for R...