Feng Hong

Orcid: 0009-0004-0137-4087

Affiliations:
  • Shanghai Jiao Tong University, Cooperative Medianet Innovation Center, Shanghai, China


According to our database1, Feng Hong authored at least 15 papers between 2023 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling.
CoRR, July, 2025

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs.
CoRR, July, 2025

Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning.
CoRR, July, 2025

Uncover the balanced geometry in long-tailed contrastive language-image pretraining.
Mach. Learn., April, 2025

Learning to Instruct for Visual Instruction Tuning.
CoRR, March, 2025

2024
UniChest: Conquer-and-Divide Pre-Training for Multi-Source Chest X-Ray Classification.
IEEE Trans. Medical Imaging, August, 2024

Balanced Destruction-Reconstruction Dynamics for Memory-Replay Class Incremental Learning.
IEEE Trans. Image Process., 2024

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.
Medical Image Anal., 2024

Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Diversified Batch Selection for Training Acceleration.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

On Harmonizing Implicit Subpopulations.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.
CoRR, 2023

Bag of Tricks for Long-Tailed Multi-Label Classification on Chest X-Rays.
CoRR, 2023

Combating Representation Learning Disparity with Geometric Harmonization.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Long-Tailed Partial Label Learning via Dynamic Rebalancing.
Proceedings of the Eleventh International Conference on Learning Representations, 2023


  Loading...