Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Summary
LingBot-Video presents a DiT-based video pretraining framework with Mixture-of-Experts architecture, specialized data augmentation, and multi-dimensional reward system for embodied intelligence applications.
View Cached Full Text
Cached at: 07/09/26, 07:51 AM
Paper page - Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Source: https://huggingface.co/papers/2607.07675 Published on Jul 8
#2 Paper of the day Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
LingBot-Video presents a DiT-based video pretraining framework with Mixture-of-Experts architecture, specialized data augmentation, and multi-dimensional reward system for embodied intelligence applications.
Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inherently prioritizes visual fidelity and creativity over computational efficiency and physical realism. In this work, we present LingBot-Video, aDiT-based video pretrainingparadigm specifically tailored forembodied intelligence. From the architecture perspective, we adopt theMixture-of-Experts(MoE), instead of dense, framework to achieve a better trade-off between modeling capacity and inference efficiency, and manage to scale it up from scratch. From the data perspective, we construct adata profiling enginethat augments standard internet videos with extensiverobot-oriented footage, encompassing manipulation, navigation, and egocentric perspectives, to equip the base model with an intrinsic understanding of actions and world dynamics. From the training perspective, we develop amulti-dimensional reward systemto enforce the alignment regardingphysical rationalityandtask completion, going beyond standard criteria such as aesthetics, prompt-following, and motion consistency. Comprehensive evaluations validate its performance and efficiency as a video foundation model. We contribute LingBot-Video as the inaugural large-scale, open-source MoE video foundation model to the community, in a pioneering effort to bridge digital creativity and physical actuation.
View arXiv pageView PDFProject pageGitHub77Add to collection
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.07675 in a model README.md to link it from this page.
Datasets citing this paper1
#### cy0307/awesome-egocentric-atlas Viewer• Updatedabout 1 hour ago • 816 • 1.21k • 5
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.07675 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
robbyant/lingbot-video-moe-30b-a3b
LingBot-Video is the first open-source large-scale MoE video generation model for embodied intelligence, featuring efficient MoE architecture, massive embodied data training, and multi-reward system for high aesthetics, physical rationality, and task completion.
@heyshrutimishra: New video model just dropped. But this one isn't built for cinematic video. LingBot-Video is designed for embodied inte…
LingBot-Video, a 30B-parameter video model with sparse MoE, designed for embodied intelligence, is open-sourced. It outperforms existing models on RBench, trained on 70K+ hours of embodied data.
LingBot-Video: sparse-MoE video diffusion transformer (13B total, 1.4B active) post-trained as an action-conditioned world model[R]
LingBot-Video is a 13B sparse-MoE video diffusion transformer (1.4B active) post-trained with RL as an action-conditioned world model, open-sourced with weights and code. It includes a physical-plausibility reward graded by a VLM and frames itself as a policy evaluator and action planner, though closed-loop robot results are absent.
@_akhaliq: LingBot-Video is out on Hugging Face MoE-based video foundation model built for embodied intelligence 30B params, only …
LingBot-Video, a 30B parameter MoE-based video foundation model for embodied intelligence, has been released on Hugging Face with only 3B active parameters at inference, augmented with 70K hours of embodied data.
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
This paper presents MoE-ViE, a mixture-of-experts vision encoder that efficiently scales for image and video understanding, outperforming larger dense models with lower inference latency.