Search papers, labs, and topics across Lattice.
3
0
7
7
Social intelligence may require more than just reasoning power: a 7B model trained with SAVOIR beats GPT-4o and Claude-3.5-Sonnet on social interaction tasks.
LLMs can now build playable games from scratch, thanks to a new framework that teaches them to scaffold stable architectures and systematically debug integration errors, not just patch syntax.
Image generation takes a leap towards real-world knowledge by training an agent that actively searches for and integrates external information, substantially boosting performance on knowledge-intensive tasks.
