Yuan 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

AutoMixQ: Automatic Mixed-precision Quantization for Deploying Bit-Efficient LLMs

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

Orochi: Versatile Biomedical Image Processor

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

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

SparseVLM: Visual Token Sparsification for Efficient Vision Language Models Inference

Frequency-Decoupled Cross-Modal Knowledge Distillation