Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
Qizhe Zhang, Mengzhen Liu, Lichen Li, Ming Lu, Yuan Zhang, Junwen Pan, Qi She, Shanghang Zhang
Who it is from
Intelaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Bias and Fairness in Large Language Models: A SurveyIntel · 2,184 citations
- Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal EstimationIntel · 666 citations
- To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy to Generate Unsafe Images ... For NowIntel · 270 citations
- Brain-inspired learning in artificial neural networks: A reviewIntel · 216 citations
- WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion ModelsIntel · 106 citations
- GIM: Learning Generalizable Image Matcher From Internet VideosIntel · 106 citations