Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
3
5
15
Omni-modal foundation models achieve self-improvement via RL compute scaled to 1M context, leveraging asynchronous training and agentic grading for enhanced intelligence.
Unlock zero-shot cross-lingual speech understanding and generation with a surprisingly data-efficient training method that aligns speech and text across languages.