Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
School of Computer Science and Engineering , Northeastern University , Shenyang , China, Affiliation:
2
0
5
Distilling explicit, reward-guided skills into VLMs without the student model ever seeing the skills themselves unlocks superior multimodal performance.
Refresh timing, not just frequency, dictates Kronecker-preconditioned LLM training performance, with optimal placement flipping based on learning rate.