Jingpu Cheng

Orcid: 0000-0003-4164-9474

According to our database1, Jingpu Cheng authored at least 10 papers between 2024 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Closed-Form Concept Erasure via Double Projections.
CoRR, April, 2026

Machine Unlearning under Retain-Forget Entanglement.
CoRR, March, 2026

Deep learning and the rate of approximation by flows.
CoRR, March, 2026

2025
Allocation of Parameters in Transformers.
CoRR, October, 2025

A unified framework on the universal approximation of transformer-type architectures.
CoRR, June, 2025

Interpolation, Approximation, and Controllability of Deep Neural Networks.
SIAM J. Control. Optim., 2025

A unified framework for establishing the universal approximation of transformer-type architectures.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024
Parameter-Efficient Fine-Tuning with Controls.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

An Optimal Control View of LoRA and Binary Controller Design for Vision Transformers.
Proceedings of the Computer Vision - ECCV 2024, 2024


  Loading...