Vision-Language Models

Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving
PDF
Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving
Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
PDF
Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View
Compositional reasoning capabilities are usually considered as fundamental skills to characterize human perception. Recent studies show …
PDF Cite Code Project
Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View