A sequential low-rank adaptation protocol for cross-scale transfer that attains the best point-estimate MAE, RMSE, and macro-$F_1$ on both 0.6B and 1.7B backbones, outperforming target-only training and non-LLM baselines.
AdaPCLA framework is proposed, which enables generative models to adaptively fit and generate EHR data through a data distribution-aware training strategy; this is achieved by internalizing data knowledge parameters by simulated annealing training.
Shuai Cui, Wenxuan Chen, Wenjie Du et al.· arXiv.org· 0 citations
A video-oriented evaluation framework for T2V unlearning that separately measures target forgetting, non-target preservation, video quality, jailbreak robustness, and efficiency, using video-level failure criteria, frame-level residue statistics, paired preservation analysis, VBench-based quality diagnostics, and deplo...
Wenxuan Chen, Wenjie Feng· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.