Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences, University of Chinese Academy of Sciences
2
0
3
Overthinking in RL models can amplify during training, but Dynamic Rollout Editing effectively curtails this behavior, enhancing reasoning efficiency.
Latent reasoning can now outperform explicit reasoning in complex tasks, thanks to a new RL method that stabilizes training by explicitly handling issues like invalid latent states and misaligned token-level updates.
