5 papers
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
Zhangyi Hu, Chenhui Liu, Tian Huang +6
Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit…
CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
Songning Lai, Jiayu Yang, Yu Huang +6
Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (…
Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models
Songning Lai, Mingqian Liao, Zhangyi Hu +6
Concept Bottleneck Models (CBMs) enhance the interpretability of AI systems, particularly by bridging visual input with human-understandable concepts, effectively acting as a form…
IMTS is Worth Time Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
Zhangyi Hu, Jiemin Wu, Hua Xu +5
Irregular Multivariate Time Series (IMTS) forecasting is challenging due to the unaligned nature of multi-channel signals and the prevalence of extensive missing data. Existing met…
Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms
Ninghui Feng, Songning Lai, Xin Zhou +9
In real-world time series forecasting, uncertainty and lack of reliable evaluation pose significant challenges. Notably, forecasting errors often arise from underfitting in-distrib…