AI
InjecMEM: Memory Injection Attack on LLM Agent Memory Systems
Researchers have proposed InjecMEM, a novel attack on large language model (LLM) memory systems. Thi...
AI
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
Researchers propose MetaCaster, a framework for training lightweight time series forecasters using f...
AI
What's the Catch? Evaluating Temporal Consistency in Vision-Language Models
Researchers have developed a new evaluation method called TimeCatch to assess the ability of vision-...
AI
Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models
Researchers propose Intention Distillation (INDI), a method to improve Vision-Language-Action models...
AI
When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World
Researchers have created a benchmark called MHER to help computers accurately id...
AI
The Measurement Revolution? Credible Measurement and Inference in the Age of AI
A new review argues that artificial intelligence (AI) has transformed measuremen...
AI
Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition
Researchers have developed a method for detecting malicious packets that can ada...
AI
The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
Researchers have identified a phenomenon called the 'interaction tax' where mult...