Episode
Lance: Unified Multimodal Modeling by Multi-Task Synergy
- Podcast
- Daily Paper Cast
- Published
- May 20, 2026
- Duration seconds
- 1391
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/f20fd799
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/lance-unified-multimodal-modeling-by-multi-task-synergy/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/lance-unified-multimodal-modeling-by-multi-task-synergy.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 62 | cs.CV, cs.AI Authors: Fengyi Fu, Mengqi Huang, Shaojin Wu, Yunsheng Jiang, Yufei Huo, Hao Li, Yinghang Song, Fei Ding, Jianzhu Guo, Qian He, Zheren Fu, Zhendong Mao, Yongdong Zhang Title: Lance: Unified Multimodal Modeling by Multi-Task Synergy Arxiv: http://arxiv.org/abs/2605.18678v1 Abstract: We present Lance, a lightweight native unified model supporting multimodal understanding, generation, and editing for both images and videos. Rather than relying on model capacity scaling or text-image-dominant designs, Lance explores a practical paradigm for unified multimodal modeling via collaborative multi-task training. It is grounded in two core principles: unified context modeling and decoupled capability pathways. Specifically, Lance is trained from scratch and employs a dual-stream mixture-of-experts architecture on shared interleaved multimodal sequences, enabling joint context learning while decoupling the pathways for understanding and generation. We further introduce modality-aware rotary positional encoding to mitigate interference among heterogeneous visual tokens and boost cross-task alignment. During training, Lance adopts a staged multi-task training paradigm with capability-oriented objectives and adaptive data scheduling to strengthen both semantic comprehension and visual generation performance. Experimental results demonstrate that Lance substantially outperforms existing open-source unified models in image and video generation, while retaining strong multimodal understanding capabilities. The homepage is available at https://lance-project.github.io.