Congratulations to DAIS Lab PhD student Liang Cao and co-authors for winning the Best Paper Award at the International Workshop on Trustworthy Multimodal Learning for Social Media Analysis (TML 2026), held at The Web Conference 2026 in Dubai, UAE.
Paper: Sparse Causal Latent Features for Robust Multimodal Learning under Distribution Shifts
Authors: Liang Cao, Weide Liu, Yan Qin, Zhenghua Chen, Zhuo Chen, Bhushan Gopaluni
This work addresses the challenging problem of maintaining robust performance in multimodal learning systems when facing distribution shifts — a critical issue for deploying AI systems in real-world applications.