EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

We introduce ENERVERSE, a generative robotics foundation model that constructs and interprets embodied spaces. ENERVERSE employs a chunk-wise autoregressive video diffusion framework to predict future embodied spaces from instructions, enhanced by a sparse context memory for long-term reasoning. To model the 3D robotics world, we adopt a multi-view video representation, providing rich perspectives to address challenges like motion ambiguity and 3D grounding. Additionally, ENERVERSE-D, a data engine pipeline combining generative modeling with 4D Gaussian Splatting, forms a self-reinforcing data loop to reduce the sim-to-real gap. Leveraging these innovations, ENERVERSE translates 4D world representations into physical actions via a policy head (ENERVERSE-A), achieving state-of-the-art performance in both simulation and real-world tasks. For efficiency, ENERVERSE-A reuses features from the first denoising step and predicts action chunks, achieving about 280 ms per 8-step action chunk on a single RTX 4090. Further video demos, dataset samples could be found in our project page. * † indicates project leader. ‡ indicates corresponding author. 39th Conference on Neural Information Processing Systems (NeurIPS 2025).

as a 'chunk', and the model repeatedly predicts the next chunk to incrementally expand the space. Additionally, to prevent model collapse and enhance the action planning capabilities, we design a sparse context memory mechanism during training. Instead of relying on consecutive memory, this mechanism preserves essential prior content throughout the generation process in a non-redundant manner, theoretically allowing infinite-length sequence generation. While this design achieves stable 2D embodied video generation, it remains insufficient for 3D understanding.

Reonstruction with Obs.