Published in NeurIPS 2022 (Spotlight), 2022
Adversarial training with structured priors for stronger out-of-distribution robustness.
Recommended citation: Qixun Wang*, Yifei Wang*, Hong Zhu, Yisen Wang. (2022). "Improving Out-of-distribution Robustness by Adversarial Training with Structured Priors." NeurIPS 2022 (Spotlight).
Download Paper
Published in NeurIPS 2024, 2024
An analysis of why invariant learning methods fail on graph-structured data.
Recommended citation: Qixun Wang, Yifei Wang, Yisen Wang, Xianghua Ying. (2024). "Dissecting the Failure of Invariant Learning on Graphs." NeurIPS 2024.
Download Paper
Published in ICLR 2025, 2025
A systematic analysis of in-context learning under out-of-distribution tasks.
Recommended citation: Qixun Wang, Yifei Wang, Xianghua Ying, Yisen Wang. (2025). "Can In-context Learning Really Generalize to Out-of-distribution Tasks?" ICLR 2025.
Download Paper
Published in CVPR 2026, 2025
Reasoning in latent visual space for unified multimodal understanding and generation.
Recommended citation: Qixun Wang, Yang Shi, Yifei Wang, Yuanxing Zhang, Pengfei Wan, Kun Gai, Xianghua Ying, Yisen Wang. (2025). "Monet: Reasoning in Latent Visual Space Beyond Images and Language." CVPR 2026.
Download Paper
