Chengyi Cai

Orcid: 0009-0004-7597-7761

According to our database1, Chengyi Cai authored at least 13 papers between 2022 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
Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models.
CoRR, April, 2026

Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation.
CoRR, April, 2026

Per-parameter Task Arithmetic for Unlearning in Large Language Models.
CoRR, January, 2026

Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning.
CoRR, January, 2026

Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models.
Trans. Mach. Learn. Res., 2026

2025
Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction.
CoRR, June, 2025

Attribute-based Visual Reprogramming for Image Classification with CLIP.
CoRR, January, 2025

Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Attribute-based Visual Reprogramming for Vision-Language Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Bayesian-guided Label Mapping for Visual Reprogramming.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Sample-specific Masks for Visual Reprogramming-based Prompting.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Hybrid Intelligent Classification System for Geriatric Frailty Syndrome Prevention and Control.
Proceedings of the 2024 4th International Conference on Bioinformatics and Intelligent Computing, 2024

2022
CLUE: Consolidating Learned and Undergoing Experience in Domain-Incremental Classification.
Proceedings of the Computer Vision - ACCV 2022, 2022


  Loading...