2025
DebugAgent: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging.
CoRR, January, 2025

The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities.
CoRR, January, 2025

HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis.
CoRR, 2024

2023
FrAug: Frequency Domain Augmentation for Time Series Forecasting.
CoRR, 2023

HiBug: On Human-Interpretable Model Debug.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Are Transformers Effective for Time Series Forecasting?
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Research on Progress of Blockchain Consensus Algorithm: A Review on Recent Progress of Blockchain Consensus Algorithms.
Future Internet, 2022

An Empirical Study on the Efficacy of Deep Active Learning for Image Classification.
CoRR, 2022

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

HybridRepair: towards annotation-efficient repair for deep learning models.
Proceedings of the ISSTA '22: 31st ACM SIGSOFT International Symposium on Software Testing and Analysis, Virtual Event, South Korea, July 18, 2022