AI
EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings
Researchers have developed a new AI model called EG-ARSA to help improve road safety in low-income c...
AI
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
Researchers have created a benchmark called SWE Refactor Bench to test the ability of coding agents ...
AI
How to Train a Critic Stably and Efficiently
Researchers from the University of Singapore have developed a new method for training critics in rei...
AI
A Survey on Human-AI Collaboration with Large Foundation Models
A recent survey on human-AI collaboration with large foundation models highlights the importance of ...
AI
Memory-Enhanced Neural Solvers for Routing Problems
Researchers have developed a new approach called MEMENTO to improve the performa...
AI
Evaluating Large Language Models for automatic analysis of teacher simulations
Researchers evaluated two large language models (LLMs) to analyze responses from...
AI
Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective
The paper surveys neural-symbolic reasoning over knowledge graphs from a query p...
AI
Practical Principles for AI Cost and Compute Accounting
Policymakers are using development cost and compute as indicators of AI capabili...