AI
What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations
Researchers from Xiaonan Xu and Wenjing Wu analyzed the migration of commercial large language model...
AI
Learnware for CSI Feedback: Scene-specific Small Models Can Do Big
Researchers have developed a system to improve the performance of channel state information (CSI) fe...
AI
Training with synthetic data for drone detection in thermal imagery
Researchers have developed a method to improve the detection of drones in thermal imagery using synt...
AI
Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses
Researchers investigated whether the ways large language models (LLMs) process information are simil...
AI
MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure
Researchers have created a new AI system called MotoSafety to assess collision r...
AI
The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges
Researchers have developed a method to detect when language models are leaking s...
AI
AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis
Researchers from various institutions have developed AdaLens, an interactive sys...
AI
Encoded but Not Actionable: Auditing the Decode-Generate-Steer Gap in Frozen LLMs for Geometric Constraints
Researchers have been trying to understand what large language models (LLMs) rea...