UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 273
Marcus Ikeda
Marcus-ikeda
·
AI & ML interests
Exploring deep learning, computer vision and LLMs.
Recent Activity
updated a dataset about 23 hours ago
Marcus-ikeda/hw1-ecommerce published a dataset about 23 hours ago
Marcus-ikeda/hw1-ecommerce upvoted a paper about 23 hours ago
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvementOrganizations
None yet