AI
TSQueryBench: LLM-as-a-Judge for Time Series Explanations
A new benchmark called TSQueryBench has been developed to evaluate the performance of large language models (LLMs) in generating explanations for time...
AI
AI
Chronos: The AI Co-Historian
Researchers have developed Chronos, an AI tool designed to support historians in their work. It allows users to create customized workflows through na...
AI
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
Researchers have analyzed how large language models (LLMs) handle conflicts of interest when generating revenue through ads. They found that many curr...
AI
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
Researchers have developed a method to use benign natural images as 'jailbreak anchors' to attack Vision-Language Models (VLMs). They created MemJack,...
AI
LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
Researchers have proposed a new approach to vision-language-action models called LoopVLA. This architecture learns to refine multimodal representation...
AI
ScreenSearch: Uncertainty-Aware OS Exploration
Researchers have developed a system called ScreenSearch to help desktop GUI agents navigate complex screens with uncertainty. The system combines stru...
AI
Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference
Researchers have proposed a new measure called the Pander Score to quantify how much AI models pander or agree with user claims. The score assesses ho...
AI
A Multimodal Agentic Pathology Co-pilot via Evidence Grounded Reasoning
Researchers have developed a tool called PathPocket that uses artificial intelligence to help pathologists make more accurate diagnoses. The system is...
AI
ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing
Researchers have developed ChatPlanner, a framework for personalized public transit routing using large language models. The system uses fine-tuned mo...
AI
Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism
Researchers have proposed a new framework for zero-shot composed image retrieval. The current approach to this task involves generating a single query...
AI
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
A self-evolving agent retires its bad skills by watching them fail. However, if the judge cannot see the failures due to bias, skill retirement is dis...
AI
FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation
Researchers have developed a neural-symbolic framework called FormalAnalyticGeo to generate multimodal analytic geometry problems. The framework uses ...