Context-aware Fairness Evaluation and Mitigation in LLMs
"动态剪枝" 相关文章
Context-aware Fairness Evaluation and Mitigation in LLMs
DeepPrune: Parallel Scaling without Inter-trace Redundancy
GLASS: Test-Time Acceleration for LLMs via Global-Local Neural Importance Aggregation
GLASS: Test-Time Acceleration for LLMs via Global-Local Neural Importance Aggregation
南开提出GlimpsePrune动态剪枝，砍掉92%视觉Token性能反超10%！
Apple Researchers Introduce Instruction-Following Pruning (IFPruning): A Dynamic AI Approach to Efficient and Scalable LLM Optimization
