Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Affiliation:
4
0
4
1
Assigning reward credit to specific tokens, rather than uniformly, dramatically improves multi-reward RL for LLMs.
Sparse rewards in multi-objective RL are no longer a bottleneck; a simple density correction unlocks faster, more robust learning.
Nearly 40% of GRPO rollouts yield zero gradient due to uninformative all-or-nothing groups, but an offline anchor pass can slash this cold-start compute waste before the target policy generates a single token.
Forget scaling laws: verifiable RL can teach smaller models to abstain and clarify unanswerable questions as well as much larger models.