A novel computational method for token pruning in vision-language models, demonstrated on 3D reasoning benchmarks with no peer review and no clinical or translational validation reported.
Loading
Researcher
Zhejiang Chinese Medical University
2 developments in the corpus
Following this puts new work involving it at the top of your briefing, with a note saying why it is there. Links are taken from the source record, never inferred.
Latest
Everything in the corpus, newest first.
A novel computational method for token pruning in vision-language models, demonstrated on 3D reasoning benchmarks with no peer review and no clinical or translational validation reported.
SEP 2, 2026 · JOURNAL ARTICLE
Scientific Reports
Observational cohort study with propensity score matching showing no primary association between aspirin and MAFLD, with exploratory subgroup findings that the authors themselves characterize as hypothesis-generating due to multiple comparisons.