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 sensitive information...
AI
AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis
Researchers from various institutions have developed AdaLens, an interactive system for monitoring a...
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) really know and how the...
AI
BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models
BEAR-Bench is a new benchmark for multimodal models that evaluates their ability to reason about tex...
AI
Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognition
Researchers have conducted a comparative study of out-of-the-box technology for ...
AI
Analysis of Types of Inquiries in Student-AI Interaction: A case study of two CS2 tasks
Researchers analyzed how students interact with AI systems while working on prog...
AI
A Theoretical Framework for Parallel Lifelong MAPF Using Group Decentralized Planning
Researchers have proposed a new framework for solving the Lifelong Multi-Agent P...
AI
Collective Counterfactual Planning: Coordination, Consent, and Verification under Representational Constraints
Researchers have proposed a formal model called Collective Counterfactual Planni...