3 accepted papers
Gradient-based data influence approximation has been leveraged to select useful data samples in the supervised fine-tuning of large language models. However, the computation of gradients throughout the fine-tuning process requires too many resources to be feasible in practice. In this paper, we prop
Although the overall performance of existing optical flow estimation methods has improved rapidly, motion discontinuities caused by large displacements and occlusions remain significant challenges for accurate optical flow estimation. To address this issue, we propose a novel Inject Context Informat…
Adapting models deployed to test distributions can mitigate the performance degradation caused by distribution shifts. However, privacy concerns may render model parameters inaccessible. One promising approach involves utilizing zeroth-order optimization (ZOO) to train a data adaptor to adapt the te…