PROJECT / First-party project
KineJing
Evidence-bound experiments for action and world-model research, including a lightweight motion baseline, a visual feature path, and a small trained three-view action-feature predictor.
01 / Overview
KineJing
Evidence-bound experiments for action and world-model research, including a lightweight motion baseline, a visual feature path, and a small trained three-view action-feature predictor.
02 / Research question
Research question
How can reproducible baselines, representations and action prediction be studied within limited compute?
03 / Approach
Approach
Report baselines, real feature inference and the small predictor separately, with provenance and limitations.
04 / Architecture and scope
Architecture and scope
Consult repository documentation and code for exact architecture and interfaces. This page describes only the public research scope.
05 / Current stage
Research preview
06 / Inspect the evidence
Inspect the evidence
View evidence ↗07 / Limitations
Limitations
This is not a new foundation model; no official TriWorldBench score has been verified.
08 / CODE
Repository
https://github.com/kineworld/KineJing ↗09 / Next steps
Next steps
Follow new inspectable experiments and documentation in the repository.