Introduces a Solo-to-Social planner-executor framework where LLMs decompose HHI into phases and roles, then a LoRA-adapted solo motion model grounds them into partner-aware 3D motion.
Motion generation: A survey of gen- erative approaches and benchmarks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CDAMD is a new autoregressive text-to-motion framework operating on continuous motion coordinates with dual constraints and diffusion-inspired components, establishing new benchmarks and claiming SOTA fidelity plus semantic consistency.
Proposes LoRA-based mixture-of-experts with autoencoder routing for continual bidirectional motion-language learning, reporting near-zero forgetting on a 5-task HumanML3D benchmark derived via semantic clustering.
citing papers explorer
-
Social Structure Matters in 3D Human-Human Interaction Generation
Introduces a Solo-to-Social planner-executor framework where LLMs decompose HHI into phases and roles, then a LoRA-adapted solo motion model grounds them into partner-aware 3D motion.
-
Coordinate-Based Dual-Constrained Autoregressive Motion Generation
CDAMD is a new autoregressive text-to-motion framework operating on continuous motion coordinates with dual constraints and diffusion-inspired components, establishing new benchmarks and claiming SOTA fidelity plus semantic consistency.
-
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
Proposes LoRA-based mixture-of-experts with autoencoder routing for continual bidirectional motion-language learning, reporting near-zero forgetting on a 5-task HumanML3D benchmark derived via semantic clustering.