Search papers, labs, and topics across Lattice.
5
0
8
0
SciLENS outperforms existing models in scientific literature synthesis by leveraging structural visualization to enhance reasoning and context retention.
Gradient-Aligned Reward transforms how we leverage expert knowledge in reinforcement learning, enabling LLMs to achieve superior reasoning performance with minimal overhead.
SKILLFORGE achieves rapid formal verification of Dafny programs by intelligently orchestrating a library of specialized skills, outperforming existing methods in both speed and accuracy.
Visual-Seeker outperforms proprietary models by actively engaging with visual details, redefining multimodal search capabilities.
Current multimodal browsing agents are surprisingly bad at using visual information on webpages, with even top models scoring below 50% accuracy on a new visual-native search benchmark.
