3 papers
cs.LG2026
Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training
Guangqi Li, Yongxin Li
Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organization forms during training is u…
cs.LG2026
Selection Plateau and a Sparsity-Dependent Hierarchy of Pruning Features
Guangqi Li, Yongxin Li
We identify a Selection Plateau phenomenon in one-shot neural network pruning: all rank-monotone weight scorers converge to identical accuracy at fixed sparsity, independent of fun…
cs.CV2024
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
You Wu, Yongxin Li, Mengyuan Liu +6
Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. T…