请查看 Induction Labs 的完整技术报告：https://www.inductionlabs.com/news/scaling-video-pretraining 以及 X 上的公告帖：https://x.com/induction_labs/status/2080322704973160760。对此研究的所有功劳归属于该项目的研究人员。
Michal Sutter 是一名数据科学专业人员，拥有帕多瓦大学（University of Padova）的数据科学硕士学位。凭借在统计分析、机器学习和数据工程方面的坚实基础，Michal 擅长将复杂的数据集转化为可操作的洞察。
构建一个智能事件场地运营代理 [完整代码]：https://pxllnk.co/twdn5
谢谢！我们的团队将很快与您联系 🙌
Most agents that learn from video need to know what action produced each frame. Induction Labs：https://www.inductionlabs.com/ is arguing that this requirement is the bottleneck. Last week, they released imagination models , a foundation model architecture that pretrains on raw video with no action labels at all.
Their test system is Photon-1 , a sparse 106B-A5B mixture-of-experts (MoE) transformer trained on 18 years of computer demonstration video. On an internal computer use benchmark, Induction Labs reports that Photon-1 beats Gemini 3.1 Flash-Lite：https://www.inductionlabs.com/news/scaling-video-pretraining while using far less pretraining compute and costing roughly 3× less to serve.
An imagination model predicts future frames autoregressively using a next-latent-token-prediction objective. It does not generate pixels during pretraining. Everything is modeled in a learned representation space.
The claim that matters is this: predicting future states teaches the model to complete tasks, even though it never sees an action during pretraining. Induction Labs calls this an implicit policy . The model learns concepts of what a person is doing, rather than a label for each mouse click.
The architecture depends on a vision encoder that uses finite scalar quantization (FSQ) . Each frame is compressed into 960 discrete tokens. Each token is an 8-dimensional vector. Each dimension takes one of five values: −1, −1/2, 0, 1/2, 1. That gives a codebook of 5⁸ possible codes.
The resulting encoding is about 2.2 KB per frame. Induction Labs reports over 100× better compression than existing OCR and multimodal-model representations, while preserving text, layout and state changes.
To hit that rate, Photon-1 uses a differential latent encoder . It encodes video frames as pairs, so the latents describe differences between frames rather than frame contents.
The corpus starts from an internal index of 2 billion publicly available videos . Filtering reduces that to roughly 2 million computer screen recordings . An internal keyframe detection model strips redundant frames.
The final dataset is 575 million frames , sampled at 1 frame per second. That equals 552 billion tokens, or about 18 years of video. Photon-1 was pretrained from scratch for a single epoch .
Training the 106B-A5B MoE at 32K context took approximately 30,000 H200 GPU-hours , or 4.4×10²² training FLOPs. The research team implemented training in PyTorch with custom fused kernels for the vision encoder and MoE layers, sustaining 40% end-to-end MFU . Those three figures are mutually consistent: 30,000 H200-hours at 40% MFU lands almost exactly on 4.3×10²².
Induction Labs finetuned Photon-1 on fewer than 35,000 computer use trajectories to teach the action and instruction format. Special computer use tokens let the model emit actions. At inference, Photon-1 predicts the next frame’s state first, then outputs the action that gets there.
Online reinforcement learning follows. Rollouts run in real time on virtual machines at scale, and outcomes are verified programmatically to produce reward. The Linux VMs run five desktop environments (LXQt, Xfce, MATE, GNOME and Plasma), each with a Google account for login-restricted web apps and an internal ChatGPT clone with no rate limits.
*Weighted at a 10:1 input-to-output token ratio, which Induction Labs says matches its computer use tests.
Two caveats belong next to that table. First, the Gemini figure is Induction Labs’ own conservative estimate , assuming 8B active parameters and 25T pretraining tokens. Taken at face value the ratio is about 27×, not the 30× headline; Induction Labs states “at least 30×” on the basis that the true Gemini number is likely higher and the model was likely distilled. Second, the benchmark is internal and unreleased, so the result is not independently reproducible today.
Photon-1’s own breakeven cost on Induction Labs’ hardware is $0.06 per 1M input tokens and $0.60 per 1M output tokens , with no speculative decoding.
This is the more interesting test, because Photon-1 saw only computer use video. The research team finetuned it on domains absent from pretraining and compared against two baselines: a vision encoder baseline with the same architecture and size but no imagination pretraining, and an LLM baseline (Ling-flash-2.0：https://huggingface.co/inclusionAI/Ling-flash-2.0 from Inclusion AI, pretrained on 20T tokens).
On 20,000 tournament checkers games from the Open Checkers Archive 2.0：https://fierz.ch/download.php/checkers.htm, Photon-1 beat both baselines on world simulation and on move quality. On 10,000 synthetically generated billiard games simulated at 5 fps, it produced a mean absolute error of 0.47 against the ground-truth physics engine, versus 1.15 for the LLM baseline and 1.44 for the vision encoder baseline.
Photon-1 also picked up human priors from the pretraining video. After RL, it learned to use the in-VM ChatGPT clone to draft artifacts and answer knowledge questions, steering the LLM the way a person would.
Check out the full technical writeup from Induction Labs：https://www.inductionlabs.com/news/scaling-video-pretraining and the announcement thread on X：https://x.com/induction_labs/status/2080322704973160760. All credit for this research goes to the researchers of this project.
Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data engineering, Michal excels at transforming complex datasets into actionable insights.
Build an Agentic Event Venue Operator [Full Codes]：https://pxllnk.co/twdn5
扫码直达文章详情