An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, Baobao Chang
Topics & Concepts
Computer scienceInferenceLayer (electronics)AccelerationImage (mathematics)Artificial intelligenceNatural language processingComputer visionPhysicsChemistryClassical mechanicsOrganic chemistryMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningHuman Pose and Action Recognition