Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
Trains a vision-language model on answers and reasoning steps from executed visual programs. Separate answer and rationale objectives let the model answer image questions without generating the intermediate program or rationale at inference.
First public: · Added to this list: October 26, 2026
Cite this paper
Published version
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
Yushi Hu, Otilia Stretcu, Chun-Ta Lu, Krishnamurthy Viswanathan, Kenji Hata, Enming Luo, Ranjay Krishna, Ariel Fuxman
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 9590-9601.
Explore this approach
Internalized reasoning — Learn from worked solutions so that some or all of the reasoning can later happen without writing those steps. Training may use a separate teacher model or progressively remove written steps from the model being trained.