Research Roadmap
A living plan for the next stages of my PhD research program.
Current Focus
- Strict continual learning methods for large language models.
- Reliable evaluation metrics for 3D reasoning systems.
Next 6-12 Months
- 3D hair strand reconstruction.
- Efficient 3D primitive representations.
- Probabilistic and semi-supervised semantic 3D part segmentation.
- Part-based VLA models.
- LLM/VLM model merging and transfer.
Long-Term Direction
- General theory of deep learning and scaling behavior.
- Synthetic internal 3D worlds for part-level causal and physics reasoning.
- Explore super-Turing perspectives (theoretical).