ChatUMM: Robust Context Tracking for Conversational Interleaved Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914622550835200 |
|---|---|
| author | Dai, Wenxun Zhao, Zhiyuan Zhong, Yule Cheng, Yiji Zhang, Jianwei Wang, Linqing Zhang, Shiyi Lin, Yunlong He, Runze Song, Fellix Zhuang, Wayne Liu, Yong Zhang, Haoji Tang, Yansong Wang, Chunyu |
| author_facet | Dai, Wenxun Zhao, Zhiyuan Zhong, Yule Cheng, Yiji Zhang, Jianwei Wang, Linqing Zhang, Shiyi Lin, Yunlong He, Runze Song, Fellix Zhuang, Wayne Liu, Yong Zhang, Haoji Tang, Yansong Wang, Chunyu |
| contents | Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent requests rather than assistants in continuous dialogue. To bridge this gap, we present ChatUMM. As a conversational unified model, it excels at robust context tracking to sustain interleaved multimodal generation. ChatUMM derives its capabilities from two key innovations: an interleaved multi-turn training strategy that models serialized text-image streams as a continuous conversational flow, and a systematic conversational data synthesis pipeline. This pipeline transforms a diverse set of standard single-turn datasets into fluid dialogues through three progressive stages: constructing basic stateful dialogues, enforcing long-range dependency resolution via ``distractor'' turns with history-dependent query rewriting, and synthesizing naturally interleaved multimodal responses. Extensive evaluations demonstrate that ChatUMM achieves state-of-the-art performance among open-source unified models on visual understanding and instruction-guided editing benchmarks, while maintaining competitive fidelity in text-to-image generation. Notably, ChatUMM exhibits superior robustness in complex multi-turn scenarios, ensuring fluid, context-aware dialogues. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06442 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ChatUMM: Robust Context Tracking for Conversational Interleaved Generation Dai, Wenxun Zhao, Zhiyuan Zhong, Yule Cheng, Yiji Zhang, Jianwei Wang, Linqing Zhang, Shiyi Lin, Yunlong He, Runze Song, Fellix Zhuang, Wayne Liu, Yong Zhang, Haoji Tang, Yansong Wang, Chunyu Computer Vision and Pattern Recognition Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent requests rather than assistants in continuous dialogue. To bridge this gap, we present ChatUMM. As a conversational unified model, it excels at robust context tracking to sustain interleaved multimodal generation. ChatUMM derives its capabilities from two key innovations: an interleaved multi-turn training strategy that models serialized text-image streams as a continuous conversational flow, and a systematic conversational data synthesis pipeline. This pipeline transforms a diverse set of standard single-turn datasets into fluid dialogues through three progressive stages: constructing basic stateful dialogues, enforcing long-range dependency resolution via ``distractor'' turns with history-dependent query rewriting, and synthesizing naturally interleaved multimodal responses. Extensive evaluations demonstrate that ChatUMM achieves state-of-the-art performance among open-source unified models on visual understanding and instruction-guided editing benchmarks, while maintaining competitive fidelity in text-to-image generation. Notably, ChatUMM exhibits superior robustness in complex multi-turn scenarios, ensuring fluid, context-aware dialogues. |
| title | ChatUMM: Robust Context Tracking for Conversational Interleaved Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.06442 |