Kangning Cui
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
BudgetDraft introduces an acceptance-aware multi-view training method that trains a sparse-KV speculative decoder to maintain high acceptance rates across varying context lengths and sparsity levels, achieving significant speedups in memory-constrained, long-context inference.
BudgetDraft introduces an acceptance-aware multi-view training method that trains a sparse-KV speculative decoder to maintain high acceptance rates across varying context lengths and sparsity levels, achieving significant speedups in memory-constrained, long-context inference.
AwakeForest is an interactive platform for large-scale forest imagery analysis that integrates model-assisted inference, automatic annotation, and human-in-the-loop refinement.
Papers
AwakeForest: An Interactive Geospatial Platform for Large-Scale Forest Imagery
Suraj Prasai, Kangning Cui, Rongkun Zhu, Sarra Alqahtani +4 more
AwakeForest is an interactive platform for large-scale forest imagery analysis that integrates model-assisted inference, automatic annotation, and human-in-the-loop refinement.