Search papers, labs, and topics across Lattice.
GLANCE is introduced, a multi-agent framework for music-grounded non-linear video editing that uses a bi-loop architecture: an outer loop for long-horizon planning and an inner loop for segment-wise editing. To handle cross-segment conflicts, a global-local coordination mechanism is implemented, including a context controller, conflict region decomposition module, and dynamic negotiation. Evaluated on a new benchmark, MVEBench, GLANCE outperforms existing baselines, improving by 33.2% and 15.6% over the strongest baseline with GPT-4o-mini.
Music-grounded video editing can now produce significantly more coherent timelines thanks to a novel global-local coordination mechanism that resolves cross-segment conflicts.
Music-grounded mashup video creation is a challenging form of video non-linear editing, where a system must compose a coherent timeline from large collections of source videos while aligning with music rhythm, user intent, story completeness, and long-range structural constraints. Existing approaches typically rely on fixed pipelines or simplified retrieval-and-concatenation paradigms, limiting their ability to adapt to diverse prompts and heterogeneous source materials. In this paper, we present GLANCE, a global-local coordination multi-agent framework for music-grounded nonlinear video editing. GLANCE adopts a bi-loop architecture for better editing practice: an outer loop performs long-horizon planning and task-graph construction, and an inner loop adopts the"Observe-Think-Act-Verify"flow for segment-wise editing tasks and their refinements. To address the cross-segment and global conflict emerging after subtimelines composition, we introduce a dedicated global-local coordination mechanism with both preventive and corrective components, which includes a novelly designed context controller, conflict region decomposition module, and a bottom-up dynamic negotiation mechanism. To support rigorous evaluation, we construct MVEBench, a new benchmark that factorizes editing difficulty along task type, prompt specificity, and music length, and propose an agent-as-a-judge evaluation framework for scalable multi-dimensional assessment. Experimental results show that GLANCE consistently outperforms prior research baselines and open-source product baselines under the same backbone models. With GPT-4o-mini as the backbone, GLANCE improves over the strongest baseline by 33.2% and 15.6% on two task settings, respectively. Human evaluation further confirms the quality of the generated videos and validates the effectiveness of the proposed evaluation framework.