AI
Children, but not language models, show accelerating returns in word learning
Researchers have found that children's vocabulary growth accelerates over time, contrary to previous...
AI
Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents
Researchers propose a new security principle for Retrieval-Augmented Generation (RAG) systems, which...
AI
Polaris: Learning to Generate Table Descriptions from Retrieval Feedback
Researchers have developed Polaris, a system that generates table descriptions using feedback from r...
AI
AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction
Researchers have developed AISA, a framework that uses large language models to improve highway cons...
AI
Which Source Wins? Task-Dependent Reliance in Vision-Language Models
Researchers studied how vision-language models (VLMs) handle conflicting informa...
AI
The Plot Thins: Uniformity and Linearity in Literary Summaries
Researchers have created a dataset that maps sentences from literary summaries t...
AI
Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal
Researchers have found that temporal leakage in financial news NLP can significa...
AI
Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention
Researchers have proposed Q-Interference, a quantum-inspired attention mechanism...