2 papers
cs.CV2026
From "What" to "How": Constrained Reasoning for Autoregressive Image Generation
Ruxue Yan, Xubo Liu, Wenya Guo +3
Autoregressive image generation has seen recent improvements with the introduction of chain-of-thought and reinforcement learning. However, current methods merely specify "What" de…
cs.MM2025
Multimodal Graph-Based Variational Mixture of Experts Network for Zero-Shot Multimodal Information Extraction
Baohang Zhou, Ying Zhang, Yu Zhao +2
Multimodal information extraction on social media is a series of fundamental tasks to construct the multimodal knowledge graph. The tasks aim to extract the structural information…