An MLLM agent reformulates image editing tasks into executable operation sequences to improve reliability on challenging cases across existing generative backbones.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DPPMG learns discrete modal-specific preferences via a dedicated GNN from multimodal user data, quantizes them into tokens, and feeds them into generators with a consistency reward to produce personalized text and images.
citing papers explorer
-
Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions
An MLLM agent reformulates image editing tasks into executable operation sequences to improve reliability on challenging cases across existing generative backbones.
-
Discrete Preference Learning for Personalized Multimodal Generation
DPPMG learns discrete modal-specific preferences via a dedicated GNN from multimodal user data, quantizes them into tokens, and feeds them into generators with a consistency reward to produce personalized text and images.