Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

arXiv:2511.20561 · cs.CV, cs.CL · Submitted 2025-11-25 · Read on arXiv

cs.CV, cs.CL

Submitted: 2025-11-25

Updated: 2026-09-25

Code: https://github.com/vllm-project/vllm

Terminology

• Ablation — 9× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Consistency — 5× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 3× in this paper · explained in 4 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• When Chain-of-Thought — 2× in this paper
• Decode — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
• Multimodal Language Models as Text-to-Image Model Evaluators
• BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
• R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation
• Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
• Emerging Properties in Unified Multimodal Pretraining
• PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
• X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
• Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
• CLIPScore: A Reference-free Evaluation Metric for Image Captioning
• UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
• UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
• UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
• WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
• Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
• T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation
• Chameleon: Mixed-Modal Early-Fusion Foundation Models
• MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
• Ovis-U1 Technical Report
• Emu3: Next-Token Prediction is All You Need

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models