active
First evidence archive
AI Animation
Evidence archives spanning motion generation, in-betweening, retrieval, constraints, and Unreal Engine runtime integration.
Questions before claims
Research
Active builds, open questions, future directions, and completed evidence stay visibly separate.
06 records
In active implementation
Research builds
Research questions that have moved into implementation, while their systems, evaluations, and findings remain unfinished.
- building
Coordinated Autonomy for a Jazz Jam Companion
In a fixed-form live Jazz jam, can AI piano, bass, and drums make bounded local decisions from shared musical state and respond to a human saxophonist more naturally than static or centrally scripted accompaniment, without reducing ensemble coherence or human control?
In active investigation
Current questions
- active
Hardware Agent Harness
How can natural-language tasks become constrained, testable, and auditable robot skills that move from simulation through safety gates to real hardware?
- active
KIMODO Martial-Arts Adapter
Which data, training, and evaluation loops can extend a motion foundation model toward martial arts while exposing failure as clearly as success?
- active
Agent-native / Zero-people Company
If autonomous agents become economic participants, how might labor, ownership, productivity, and the distribution of wealth change?
Directions worth testing
Future questions
- future
Controllable 3D Motion Generation
Can video-style generation be reframed as generating editable 3D skeleton motion first, then rendering in Blender or Maya for clearer spatial and temporal control?
- future
KIMODO + VLA
Could a motion foundation model provide a semantic coarse-motion prior while a vision-language-action model handles precise grasping and local control?
Completed and bounded records