DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
Paper
•
2503.02175
•
Published
•
3
Inference Optimization
-
-
CASP: Compression of Large Multimodal Models Based on Attention Sparsity
Paper • 2503.05936 • Published • 2 -
EBJR: Energy-Based Joint Reasoning for Adaptive Inference
Paper • 2110.10343 • Published • 1 -
E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models
Paper • 2203.00748 • Published • 1 -
GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation
Paper • 2403.19754 • Published -
Efficiently Serving Large Multimodal Models Using EPD Disaggregation
Paper • 2501.05460 • Published • 1 -
ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts Models
Paper • 2510.02613 • Published • 1 -
ExpertWeave: Efficiently Serving Expert-Specialized Fine-Tuned Adapters at Scale
Paper • 2508.17624 • Published