Single-stage fine-tuning is pervasive, yet catastrophic forgetting persists when the source pre-training data is inaccessible. Data weighting affords a natural lever to modulate sample influence. Yet existing weighting methods lack a principled mechanism to explicitly arbitrate knowledge retention against new-task adap...
Long-context decoding is increasingly constrained by key--value (KV) cache memory and bandwidth. Existing fixed-budget compression methods typically separate retention from compensation, while a retention ranking specifies neither discarded attention mass nor the direction of induced output error. We start from an exac...
Compared to contemporary or one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total runtime by reducing the number of agents involved.
Wei-Liang Zhang, Xiao-Han Huang, Yi Du et al.· ACM Transactions on Knowledg...· 1 citation
Efficient large language model (LLM) instruction tuning requires selecting response supervision with supporting prompt context. Existing methods typically value both sides separately, risking selection-state mismatch between valuation and retained training subsets. BRIDGE (Budgeted Response-Prompt Interaction via Direc...
Can Wu, Xin-Rui Chen, Ou Wu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.