Skip to main content
Search

Youzhi Liu

1 related articles

Subscribe to updates
  1. arXiv

    PMOPD projects parameter updates away from protected task subspaces to ease the multi-teacher distillation capability seesaw, lifting the three-task average by 2.54 points on Qwen2.5-7B and 2.09 on Llama-3.1-8B

    The work proposes PMOPD, which builds per-matrix low-dimensional subspace memories from the cumulative parameter displacements of completed task blocks and projects both gradients and Adafactor optimizer updates of later tasks to remove components conflicting with protected task directions, while a lightweight conflict probe sets task order and a subspace-consistency criterion sets the cycle count; across Code, Reason, and Math, PMOPD improves every evaluated capability over MOPD, raising the three-task average by 2.54 points on Qwen2.5-7B and 2.09 points on Llama-3.1-8B.

You’re all caught up