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

[2603.29953] Structured Intent as a Protocol-Like Communication Layer: Cross-Model Robustness, Framework Comparison, and the Weak-Model Compensation Effect

Abstract page for arXiv paper 2603.29953: Structured Intent as a Protocol-Like Communication Layer: Cross-Model Robustness, Framework Com...

[2603.29928] ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules

Abstract page for arXiv paper 2603.29928: ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules

[2603.29908] C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving

Abstract page for arXiv paper 2603.29908: C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving

[2603.29902] ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation

Abstract page for arXiv paper 2603.29902: ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation

[2603.29895] A Rational Account of Categorization Based on Information Theory

Abstract page for arXiv paper 2603.29895: A Rational Account of Categorization Based on Information Theory

[2603.29871] ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training

Abstract page for arXiv paper 2603.29871: ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training

[2603.29791] Reasoning-Driven Synthetic Data Generation and Evaluation

Abstract page for arXiv paper 2603.29791: Reasoning-Driven Synthetic Data Generation and Evaluation

[2603.29761] Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers

Abstract page for arXiv paper 2603.29761: Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers

[2603.29755] CausalPulse: An Industrial-Grade Neurosymbolic Multi-Agent Copilot for Causal Diagnostics in Smart Manufacturing

Abstract page for arXiv paper 2603.29755: CausalPulse: An Industrial-Grade Neurosymbolic Multi-Agent Copilot for Causal Diagnostics in Sm...

[2603.29735] Spontaneous Functional Differentiation in Large Language Models: A Brain-Like Intelligence Economy

Abstract page for arXiv paper 2603.29735: Spontaneous Functional Differentiation in Large Language Models: A Brain-Like Intelligence Economy

[2603.29681] Beyond the Steeper Curve: AI-Mediated Metacognitive Decoupling and the Limits of the Dunning-Kruger Metaphor

Abstract page for arXiv paper 2603.29681: Beyond the Steeper Curve: AI-Mediated Metacognitive Decoupling and the Limits of the Dunning-Kr...

[2603.29500] Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries

Abstract page for arXiv paper 2603.29500: Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Int...

[2603.29366] AI-Generated Prior Authorization Letters: Strong Clinical Content, Weak Administrative Scaffolding

Abstract page for arXiv paper 2603.29366: AI-Generated Prior Authorization Letters: Strong Clinical Content, Weak Administrative Scaffolding

[2603.29361] Rigorous Explanations for Tree Ensembles

Abstract page for arXiv paper 2603.29361: Rigorous Explanations for Tree Ensembles

[2603.29357] BenchScope: How Many Independent Signals Does Your Benchmark Provide?

Abstract page for arXiv paper 2603.29357: BenchScope: How Many Independent Signals Does Your Benchmark Provide?

[2603.29262] Grokking From Abstraction to Intelligence

Abstract page for arXiv paper 2603.29262: Grokking From Abstraction to Intelligence

[2603.29231] Beyond pass@1: A Reliability Science Framework for Long-Horizon LLM Agents

Abstract page for arXiv paper 2603.29231: Beyond pass@1: A Reliability Science Framework for Long-Horizon LLM Agents

[2603.29211] Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems

Abstract page for arXiv paper 2603.29211: Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecos...

[2603.29206] Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of Routing-Style Meta Prompts on LLM Internal States

Abstract page for arXiv paper 2603.29206: Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of R...

[2603.29199] AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction

Abstract page for arXiv paper 2603.29199: AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Constru...