Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
L2SR: Learning to Sample and Reconstruct for Accelerated MRI via Reinforcement Learning
Published in Inverse Problem, 2024
Recommended citation: Yang, Pu, and Bin Dong. "L2SR: Learning to Sample and Reconstruct for accelerated MRI via reinforcement learning." Inverse Problems (2024). https://iopscience.iop.org/article/10.1088/1361-6420/ad3b34
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Reinforcement
Published in Arxiv, 2024
Under review as a conference paper in NIPS2024.
Recommended citation: Feng, Y., Dohmatob, E., Yang, P., Charton, F., & Kempe, J. (2024). Beyond Model Collapse: Scaling Up with Synthesized Data Requires Reinforcement. arXiv preprint arXiv:2406.07515. https://arxiv.org/abs/2406.07515
A Tale of Tails: Model Collapse as a Change of Scaling Laws
Published in ICML2024, 2024
Recommended citation: Dohmatob, E., Feng, Y., Yang, P., Charton, F., & Kempe, J. (2024). A Tale of Tails: Model Collapse as a Change of Scaling Laws. arXiv preprint arXiv:2402.07043. https://proceedings.mlr.press/v235/dohmatob24b.html
Identifying average causal effect in regression discontinuity design with auxiliary data
Published in arXiv, 2024
Recommended citation: Feng, X., Hu, W., Yang, P., Li, T., & Zhou, X. H. (2024). Identifying average causal effect in regression discontinuity design with auxiliary data. arXiv preprint arXiv:2412.20840. https://arxiv.org/abs/2412.20840
MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning
Published in arXiv, 2025
Recommended citation: Yang, P., & Dong, B. (2025). MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning. arXiv preprint arXiv:2501.01834. https://arxiv.org/abs/2501.01834
Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping
Published in arXiv, 2025
Recommended citation: Yang, P., Feng, Y., Chen, Z., Wu, Y., & Li, Z. (2025). Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping. arXiv preprint arXiv:2501.18962. https://arxiv.org/abs/2501.18962