Scaling Unified Multimodal Models to Long-Horizon Interleaved Generation
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 29 pages, 11 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
- How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation
- UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
- Thinking with Generated Images
- Emu3.5: Native Multimodal Models are World Learners
- ChatUMM: Robust Context Tracking for Conversational Interleaved Generation
- Emerging Properties in Unified Multimodal Pretraining
- Lance: Unified Multimodal Modeling by Multi-Task Synergy
- TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
- DINOv3
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
- Emu3: Next-Token Prediction is All You Need
- Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training
- UniSpace: Unified Visual Representation and Scalable Multimodal Modeling
- IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
- Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
- Qwen-Image-2.0 Technical Report
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