{"slug": "lingbot-video-a-new-open-source-moe-model-for-embodied-video-generation", "title": "LingBot-Video: A New Open-Source MoE Model for Embodied Video Generation", "summary": "Robbyant has released LingBot-Video, an open-source Mixture-of-Experts (MoE) video generation model trained on web videos and over 70,000 hours of embodied data. The model achieves top rank on the RBench Leaderboard with an average score of 0.620, outperforming both open-source and closed-source competitors. It features a multi-reward training system for physical rationality and task completion, and offers 3x faster inference than dense models.", "body_md": "Robbyant has introduced LingBot-Video, an open-source large-scale Mixture-of-Experts (MoE) video generation model. This release marks a significant step towards integrating video synthesis with embodied intelligence, focusing on generating videos that reflect physical world understanding. The project includes the technical report, code, models, and rewriters, all released under an Apache 2.0 License.\n\nLingBot-Video differentiates itself through its MoE architecture, which is designed for efficiency and scalability. It has been trained on a substantial dataset comprising massive web videos combined with over 70,000 hours of embodied data. The model's training incorporates a multi-reward system, optimizing for high aesthetic quality, physical rationality, and task completion within generated videos.\n\nLingBot-Video leverages an efficient MoE architecture, enabling approximately 3x faster inference compared to dense models while maintaining capacity. The model suite includes several components:\n\nThe recommended inference workflow involves a three-stage process: prompt rewriting, automatic negative prompt generation, and unified inference. The prompt rewriter converts plain natural-language prompts into structured JSON captions. An Auto Negative block then prunes the negative prompt based on this caption. Finally, the unified inference runner executes the video generation, supporting both direct `diffusers`\n\nand SGLang Diffusion backends. For multi-GPU inference, the `--enable_fsdp_inference`\n\nflag shards the base DiT and refiner DiT across GPUs, reducing memory pressure, though sufficient system RAM is required for loading large MoE checkpoints.\n\nThe project provides installation instructions and a `requirements.txt`\n\nfile specifying dependencies like `torch`\n\n(recommended `2.12.0.dev20260220+cu130`\n\n), `transformers`\n\n(`5.8.1`\n\n), and `diffusers`\n\n(`0.39.0`\n\n). Optional SGLang dependencies are available for SGLang Diffusion or fused/FP8 MoE runtime. Ready-to-run scripts are provided for single-GPU and multi-GPU inference configurations, covering dense and MoE models for T2I, T2V, and TI2V tasks, with options for refiner integration and FSDP/CP8 optimizations.\n\nAs of July 9th, 2026, LingBot-Video holds the top rank on the RBench Leaderboard. The model achieved an average score of **0.620**. Specific category scores include:\n\nCompared to other open-source models like Cosmos3 Super (Avg. 0.581), LongCat-Video (Avg. 0.437), Wan 2.2 A14B (Avg. 0.507), and HunyuanVideo 1.5 (Avg. 0.460), LingBot-Video demonstrates superior overall performance. Against closed-source models such as Wan 2.6 (Avg. 0.607), Seedance 1.5 pro (Avg. 0.584), and Veo 3 (Avg. 0.563), LingBot-Video maintains a competitive edge, particularly in average score and several specific categories like Manipulation, Long-horizon, and Quadruped tasks.\n\nDevelopers working on embodied AI, robotics, or advanced video generation now have access to an open-source MoE model that prioritizes physical rationality and task completion. The Apache 2.0 License allows for broad use and modification. The provided inference workflow, including prompt rewriting and auto-negative generation, offers a structured approach to leveraging the model effectively. The support for both `diffusers`\n\nand SGLang backends, along with multi-GPU inference scripts, provides flexibility for deployment across different hardware configurations.\n\nThe emphasis on structured JSON captions for inference suggests that developers will need to integrate the prompt rewriter into their pipelines or design their prompt inputs accordingly. The model's ability to generate physically rational videos could be particularly valuable for simulating complex robotic tasks or creating realistic training data for embodied agents. The efficiency gains from the MoE architecture could also reduce computational costs for certain applications.\n\nLingBot-Video represents a notable advancement in open-source video generation, specifically tailored for embodied intelligence. Its MoE architecture, trained on extensive embodied data, delivers efficient inference and strong performance in generating physically coherent and task-oriented videos. The comprehensive release, including code, models, and detailed inference workflows, provides developers with a powerful tool for applications requiring sophisticated video synthesis with a focus on real-world understanding.", "url": "https://wpnews.pro/news/lingbot-video-a-new-open-source-moe-model-for-embodied-video-generation", "canonical_source": "https://dev.to/pneumetron/lingbot-video-a-new-open-source-moe-model-for-embodied-video-generation-2m3a", "published_at": "2026-07-14 02:49:55+00:00", "updated_at": "2026-07-14 03:28:29.109273+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-tools"], "entities": ["Robbyant", "LingBot-Video", "RBench", "Cosmos3 Super", "LongCat-Video", "Wan 2.2 A14B", "HunyuanVideo 1.5", "Veo 3"], "alternates": {"html": "https://wpnews.pro/news/lingbot-video-a-new-open-source-moe-model-for-embodied-video-generation", "markdown": "https://wpnews.pro/news/lingbot-video-a-new-open-source-moe-model-for-embodied-video-generation.md", "text": "https://wpnews.pro/news/lingbot-video-a-new-open-source-moe-model-for-embodied-video-generation.txt", "jsonld": "https://wpnews.pro/news/lingbot-video-a-new-open-source-moe-model-for-embodied-video-generation.jsonld"}}