LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference

Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• LaMoGen introduces LabanLite, a motion representation that encodes each atomic body-part action as a discrete Laban symbol paired with a textual template.method 95%
• Prevailing methods relying on joint text-motion embeddings struggle to synthesize temporally accurate, detailed motions and often lack explainability.limitation 85%
• LaMoGen enables large language models to compose motion sequences through symbolic reasoning, producing motions that are both interpretable and linguistically grounded.method 90%
• The paper introduces a Labanotation-based benchmark with structured description-motion pairs and three metrics that jointly measure text-motion alignment across symbolic, temporal, and harmony dimensions.method 95%
• LaMoGen establishes a new baseline for both interpretability and controllability, outperforming prior methods on the proposed benchmark and two public datasets.result 85%
• LabanLite establishes a symbolic link between high-level language and low-level motion trajectories by decomposing complex motions into interpretable symbol sequences and body-part instructions.technical 90%
• The symbolic reasoning and agent-based design of LaMoGen provides advantages for language-driven motion synthesis.result 80%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card