Search papers, labs, and topics across Lattice.
2
0
3
Chain-of-thought context can be halved without sacrificing accuracy by using the geometric trajectory of hidden states to selectively compress exploratory reasoning steps into continuous latent tokens.
Group-Calibrated On-Policy Distillation boosts long-context reasoning performance by reconciling teacher guidance with verifier feedback, achieving up to a 12-point increase in benchmark scores.
