Yiran Chen

8

Papers

13

Total Citations

Papers (8)

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

LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation

SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers

Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training

Efficient Dataset Distillation via Minimax Diffusion

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

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

LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits