March 2024
- Controlled Study Reveals Pretrained Language Model Choice Drives Most Gains in Coreference Resolution· AI
- LLMs excel at comparative emotion ratings, not direct scales· AI
- Robots learn to work with imperfect humans through adaptive teaming· AI
- When robots own their mistakes: Study reveals error acknowledgment builds human trust· Robotics
- New comprehensive guide outlines the foundations of differentiable programming· AI
- New method stabilizes deep learning on graphs using quantum-inspired unitary operations· AI
- CLIP-EBC brings accurate crowd counting to vision-language models via blockwise classification· AI
- New Framework Combines AI and Privacy Tools to Secure Connected Medical Devices· AI
- State-Space Models Outpace Attention for Efficient Long-Form Video Generation· AI
- Federated Learning Method Boosts Privacy and Performance in Few-Shot Language Model Training· AI
- Computer vision model predicts land shifts from carbon storage, cutting simulation costs· AI
- Researchers tackle AI alignment across conflicting stakeholder preferences· Agentic AI
- New Survey Maps the Path to Trustworthy AI-Human Partnerships with Foundation Models· AI
- Biologically-Inspired Framework Helps Robots Navigate When Vision Systems Fail· AI