Search papers, labs, and topics across Lattice.
Kuaishou Technology
4
1
7
4
CRPO effectively mitigates exposure bias in self-distillation, leading to superior performance in complex reasoning tasks.
Process evaluations reveal hidden failures in LLM reasoning, showing that lucky successes can mask critical deficiencies in agent performance.
Bridging the Understanding-Action Gap leads to a 4.5% revenue increase by refining recommendation policies through direct user feedback rather than linguistic reasoning alone.
AlphaOracle not only deciphers ancient scripts but also accelerates scholarly analysis, cutting down research time by over half while aligning with expert insights.
