Publications

(2025). MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?. The Thirteenth International Conference on Learning Representations.
(2025). Imagine while Reasoning in Space: Multimodal Visualization-of-Thought. arXiv preprint arXiv:2501.07542.
(2024). TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting. arXiv preprint arXiv:2412.20810.
(2024). LogoRA: Local-Global Representation Alignment for Robust Time Series Classification (TKDE 2024). IEEE Transactions on Knowledge and Data Engineering.