Papers by Diandian Guo

3 papers
Two Streams, One Sarcasm: Orthogonal Expert Tuning for Holistic Multimodal Sarcasm Understanding (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for multimodal satirical cognition hinder evaluation of multimodal Sarcasm Understanding . lack of a unified benchmark for holistic satire cognition hampers evaluation of MSU .
Approach: They propose a framework to decouple experts into orthogonal shared perception and private execution streams to physically block gradient interference between tasks.
Outcome: The proposed framework achieves superior performance on DocMSU-PLUS.
Multi-View Incongruity Learning for Multimodal Sarcasm Detection (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for multimodal sarcasm detection rely on spurious correlations, demonstrating poor generalizability beyond training environments.
Approach: They propose a method that integrates multimodal incongruities via contrastive learning for multimodal sarcasm detection by using three views to drive multi-view learning.
Outcome: The proposed method outperforms existing methods on benchmark datasets and shows that it is more generalizable than existing methods.
Conformal Event Prediction with Temporal Knowledge Graph (2026.findings-acl)

Copied to clipboard

Challenge: Current event prediction methods lack rigorous uncertainty quantification, which limits their reliability for decision-making.
Approach: They propose a conformal prediction framework that applies conformal predictions to event prediction to address this challenge.
Outcome: The proposed framework guarantees coverage while improving efficiency on three public datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations