Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
A novel Bayesian approach to process reward modeling effectively mitigates overestimation and improves LLM test-time scaling by explicitly accounting for both PRM and policy uncertainties.
A 7B model trained on a new dataset of Chinese porcelain outperforms GPT-4 by 12% on expert connoisseurship tasks, demonstrating the power of domain-specific training and tool integration.