Search papers, labs, and topics across Lattice.
3
0
7
6
CoFree (Collapse-Free Reasoning Embedding), a two-stage framework that progressively integrates LLM reasoning into query and document embedding optimization while preserving reasoning quality, is proposed.
Process supervision does not require generating explicit text: continuous latent reasoning can halve token generation costs while outperforming standard CoT through soft prototype alignment.
Proactively committing mid-entropy pivot positions can accelerate dLLM decoding by up to 18 times while improving accuracy.
