Search Results for author:
Found 2 papers, 1 papers with code
LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
Based on this, we propose PruMerge, a novel adaptive visual token reduction approach, which largely reduces the number of visual tokens while maintaining comparable model performance.
Causal-DFQ: Causality Guided Data-free Network Quantization
Inspired by the causal understanding, we propose the Causality-guided Data-free Network Quantization method, Causal-DFQ, to eliminate the reliance on data via approaching an equilibrium of causality-driven intervened distributions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
