Qizhe Zhang

TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning

ZoomV: Temporal Zoom-in for Efficient Long Video Understanding

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning

HyperAdapter: Generating Adapters for Pre-Trained Model-Based Continual Learning

Discovering Long-Term Effects on Parameter Efficient Fine-tuning