Search papers, labs, and topics across Lattice.
Shanghai AI Laboratory, Dalian University of Technology
2
0
5
0
Fine-tuning smaller reasoning models on data from larger models can backfire spectacularly unless you carefully match the stylistic nuances of the student.
Multilingual reasoning in LLMs isn't just about translation鈥攊t's a powerful knob for improving RL training by expanding the exploration space and boosting exploitation.
