# Lance: Unified Multimodal Modeling by Multi-Task Synergy

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/lance-unified-multimodal-modeling-by-multi-task-synergy
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/lance-unified-multimodal-modeling-by-multi-task-synergy.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-05-20T04:13:31+00:00
Episode link: https://share.transistor.fm/s/f20fd799
Audio file: https://media.transistor.fm/f20fd799/a89935e9.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/lance-unified-multimodal-modeling-by-multi-task-synergy
Duration seconds: 1391

## Resource

🤗 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.

## Actions

- request_transcript: `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.
- read_markdown: `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.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.