Search papers, labs, and topics across Lattice.
The paper introduces EmboAlign, a data-free framework that aligns video generation models (VGMs) with compositional constraints derived from vision-language models (VLMs) to improve zero-shot robotic manipulation. EmboAlign leverages VLMs to extract task-specific compositional constraints from language instructions, which are then used for constraint-guided rollout selection and constraint-based trajectory optimization. Experiments on six real-robot manipulation tasks demonstrate a 43.3% improvement in success rate compared to the strongest baseline, highlighting the effectiveness of aligning VGMs with VLM-derived constraints.
By combining video generation and vision-language models, EmboAlign achieves a 43% boost in real-world robot manipulation success without any task-specific training.
Video generative models (VGMs) pretrained on large-scale internet data can produce temporally coherent rollout videos that capture rich object dynamics, offering a compelling foundation for zero-shot robotic manipulation. However, VGMs often produce physically implausible rollouts, and converting their pixel-space motion into robot actions through geometric retargeting further introduces cumulative errors from imperfect depth estimation and keypoint tracking. To address these challenges, we present \method{}, a data-free framework that aligns VGM outputs with compositional constraints generated by vision-language models (VLMs) at inference time. The key insight is that VLMs offer a capability complementary to VGMs: structured spatial reasoning that can identify the physical constraints critical to the success and safety of manipulation execution. Given a language instruction, \method{} uses a VLM to automatically extract a set of compositional constraints capturing task-specific requirements, which are then applied at two stages: (1) constraint-guided rollout selection, which scores and filters a batch of VGM rollouts to retain the most physically plausible candidate, and (2) constraint-based trajectory optimization, which uses the selected rollout as initialization and refines the robot trajectory under the same constraint set to correct retargeting errors. We evaluate \method{} on six real-robot manipulation tasks requiring precise, constraint-sensitive execution, improving the overall success rate by 43.3\% points over the strongest baseline without any task-specific training data.
