Kudos to Yuran!
The proposed method dynamically updates the teacher’s guidance context according to the student’s evolving training state and employs a specialized mathematical formulation to improve the stability and effectiveness of OPD.
🚀 Introducing Flux-OPD, an OPD paradigm that uses evolving contexts as in-training supervision to capture task preferences in open-ended domains.
🧩 It improves video prompt optimization and medical question answering.
📄 arxiv.org/abs/2607.28022
🤗 huggingface.co/papers/2607.28…
