Search papers, labs, and topics across Lattice.
2
0
5
Latent reasoning, previously unstable in RL, can now outperform explicit reasoning while using 3-4x shorter chains, thanks to a new method that stabilizes latent space exploration.
Today's best language models can barely make sense of your messy group chats and fragmented digital life, achieving only 19% accuracy on a new benchmark of real-world reasoning.
