Yudong Liu

5

Papers

13

Total Citations

Papers (5)

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Practical Offloading for Fine-Tuning LLM on Commodity GPU via Learned Sparse Projectors

Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing

GridFormer: Point-Grid Transformer for Surface Reconstruction

FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models