Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
Targeting credit assignment in multi-turn RL can be counterproductive, as uniform reward distribution consistently outperforms sparse rewards in low-information density scenarios.
Untrusted AI agents can now operate at unprecedented speeds while maintaining rigorous safety guarantees, achieving a 2.96x speedup with only 2.1% regret.
MAST achieves targeted forgetting in RLVR-induced reasoning with minimal impact on performance, preserving critical task accuracy while effectively unlearning unwanted knowledge.