Ziheng Qin

Orcid: 0009-0001-8571-1228

According to our database1, Ziheng Qin authored at least 17 papers between 2023 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection.
CoRR, February, 2026

2025
Scaling Up AI-Generated Image Detection via Generator-Aware Prototypes.
CoRR, December, 2025

Towards Cross-View Point Correspondence in Vision-Language Models.
CoRR, December, 2025

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows.
CoRR, October, 2025

On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation.
CoRR, October, 2025

DD-Ranking: Rethinking the Evaluation of Dataset Distillation.
CoRR, May, 2025

Unlocking the Potential of Lightweight Quantized Models for Deepfake Detection.
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025

Info-Coevolution: An Efficient Framework for Data Model Coevolution.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024
Boosting LLM via Learning from Data Iteratively and Selectively.
CoRR, 2024

Visual Perception in Text Strings.
CoRR, 2024

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024


2023
A robust adversarial attack against speech recognition with UAP.
High Confid. Comput., 2023

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning.
CoRR, 2023

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

CowClip: Reducing CTR Prediction Model Training Time from 12 Hours to 10 Minutes on 1 GPU.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023


  Loading...