S*, the first hybrid test-time scaling framework that substantially improves the coverage and selection accuracy of LLM generated code. Also for deep reasoning models.
All rights w/ authors:
S*: Test Time Scaling for Code Generation
Dacheng Li, Shiyi Cao, Chengkun Cao, Xiuyu Li,
Shangyin Tan, Kurt Keutzer, Jiarong Xing, Joseph E. Gonzalez, Ion Stoica
University of California, @UCBerkeley
Work done w/ support from https://lambdalabs.com
#airesearch
#codegeneration
#aicoding
#berkeley
コメント