Papers by Yongshuo Zhang
DEAR: Distributional Error-Aware Reliability for Robust Multimodal Sentiment Analysis with Missing Modalities (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on feature completion but neglect semantic shifts caused by distribution gaps and decision risks under high uncertainty. |
| Approach: | They propose a distributional error-aware reliability estimation framework for robust MSA . they propose reconstructed features to be explicitly aligned with original distributional manifold . |
| Outcome: | The proposed framework mitigates semantic shifts by aligning reconstructed features with original distributional manifold . Extensive experiments on MOSI, MOSEI, and SIMS validate the framework . |
SMART: Semantic Header Flattening and Pseudo-Code-Style Reasoning for LLM-based Complex Table Question Answering (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to complex table question answering rely on handcrafted table linearization or prompts . Existing methods rely only on hand-crafted table and require hierarchical hierarchies to align conditions, attributes, and values. |
| Approach: | They propose a framework that explicitly decouples table structure understanding from reasoning execution. |
| Outcome: | Experiments show that SMART improves accuracy and robustness of complex table question answering (TQA) . SMart decouples table structure understanding from reasoning execution, enabling state-of-the-art performance. |