# WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation

arXiv: https://arxiv.org/abs/2511.11434 · HTML: https://mlsanity.com/paper/2511.11434/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2025.

## Built on by (most cited first, 7 of 7)

- [GENIUS: Generative Fluid Intelligence Evaluation Suite](https://mlsanity.com/paper/2602.11144/) (2026)
- [Feedforward 3D Editing Learns from Semantic-Part Transformation](https://mlsanity.com/paper/2605.27351/) (2026)
- [PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks](https://mlsanity.com/paper/2602.06663/) (2026)
- [Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation](https://mlsanity.com/paper/2606.30054/) (2026)
- [Thinking in Video: Can Video Generators Really Reason About the Real World?](https://mlsanity.com/paper/2607.17523/) (2026)
- [ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation](https://mlsanity.com/paper/2603.29902/) (2026)
- [IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation](https://mlsanity.com/paper/2606.09169/) (2026)

## Abstract (arXiv)

Recent advances in unified multimodal models (UMMs) have enabled impressive progress in visual comprehension and generation. However, existing datasets and benchmarks focus primarily on single-turn interactions, failing to capture the multi-turn, context-dependent nature of real-world image creation and editing. To address this gap, we present WEAVE, the first suite for in-context interleaved cross-modality comprehension and generation. Our suite consists of two complementary parts. WEAVE-100k is a large-scale dataset of 100K interleaved samples spanning over 370K dialogue turns and 500K images, covering comprehension, editing, and generation tasks that require reasoning over historical context. WEAVEBench is a human-annotated benchmark with 100 tasks based on 480 images, featuring a hybrid VLM judger evaluation framework based on both the reference image and the combination of the original image with editing instructions that assesses models' abilities in multi-turn generation, visual memory, and world-knowledge reasoning across diverse domains. Experiments demonstrate that training on WEAVE-100k enables vision comprehension, image editing, and comprehension-generation collaboration capabilities. Furthermore, it facilitates UMMs to develop emergent visual-memory capabilities, while extensive evaluations on WEAVEBench expose the persistent limitations and challenges of current approaches in multi-turn, context-aware image generation and editing. We believe WEAVE provides a view and foundation for studying in-context interleaved comprehension and generation for multi-modal community.