AI
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
Researchers have developed a new approach to optimizing the performance of large language models (LL...
AI
A Standardized Framework for Machine Learning in Power System Protection
Researchers have proposed a standardized framework for evaluating the performance of machine learnin...
AI
Multi-Method Causal Evidence Synthesis: Ranking Candidate Drivers by Convergent Cross-Method Evidence from Observational Data
Researchers have developed a framework called Multi-Method Causal Evidence Synthesis (MCES) to analy...
AI
Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
Researchers have developed Daedalus-150M, a hybrid AI model that combines convolutional neural netwo...
AI
From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation
Researchers conducted a study on how autonomous coding agents interact with tech...
AI
Prompt-Conditioned Channel Attention for Hierarchical Feature Modulation toward Anatomy-Agnostic Segmentation
Researchers have developed a new method called Prompt-Conditioned Channel Attent...
AI
Growth Without Us: Machine Consumers, Corporate Circularity, and the Decoupling of GDP from Humanity after AGI
A new economic model has been proposed for a world where artificial general inte...
AI
Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
Researchers have developed a new post-training framework called IAR (Inject, Ali...