AI Agents That Understand Your Privacy Boundaries
New research explores how to build personal AI assistants that respect individual preferences by reasoning about privacy implications.
Science
The Cost of Convenience: Why AI Hints Might Hinder Deep Learning
New research reveals a surprising tension between student satisfaction and long-term learning when using AI-powered programming assistance.
From Roots to Art: Visualizing Polynomials in a New Light
A novel framework, Polynomiogram, bridges the gap between complex mathematical analysis and striking visual aesthetics.
Decoding Molecules with AI: A New Era for Drug Design
Researchers have developed a powerful artificial intelligence model capable of both understanding and generating molecular structures, accelerating possibilities in chemical informatics and drug discovery.
Beyond Pixels: SAM3-I Understands What You Want to Segment
A new model extends the Segment Anything capabilities by directly interpreting natural language instructions, bridging the gap between vision and language for precise image segmentation.
Better Medicines Through Teamwork: How AI Collaboration Improves Drug Recommendations
A new study demonstrates that combining the strengths of multiple artificial intelligence models can significantly enhance the accuracy and reliability of medication recommendations derived from patient clinical notes.
Turning AI Principles into Practice
New research demonstrates a method for automatically converting abstract AI governance policies into concrete, verifiable rules for implementation.
Does That Movement Feel Real? Evaluating AI-Generated Human Action
As AI-synthesized videos become increasingly realistic, accurately assessing the naturalness of human movement within them remains a significant challenge.
The Rise of Adaptive Systems: Can AI Agents Build Self-Improving Software?
A new framework, POLARIS, explores how multi-agent AI can move beyond reactive self-adaptation to systems that proactively reason about and optimize their responses to changing conditions.
Sharper Steps: Optimizing Agent Performance with Critical Action Learning
A new reinforcement learning approach focuses on identifying and refining the most impactful actions in multi-step problem-solving agents, leading to significant gains in efficiency and success.