Search papers, labs, and topics across Lattice.
4
0
8
Recursive self-improvement in Macaron-V1 leads to continual learning that adapts to real-world experiences, setting a new standard for open agent models.
LongStraw enables RL post-training with over 2 million tokens on a fixed GPU budget, pushing the boundaries of context length in AI applications.
Puppet-based storytelling on robots boosts engagement and comprehension, outperforming traditional gesture-only methods in educational settings.
Personal agents can now dynamically synthesize UIs directly from dialogue context, achieving state-of-the-art results without relying on explicit schemas.
