2. Help implement state tracking and evaluate consistency modeling for generated videos.

3. Participate in exploring "unified generation-understanding" model architectures.

Assist in evaluating causal consistency control and physical constraints for "action input → video output" pipelines.

4. Contribute to researching hybrid architectures aimed at achieving low-latency feedback for real-time interactive generation.

5. Work with the team to test and refine the end-to-end closed loop of "generation → understanding → control → feedback."

6. Assist in validating interactive capabilities in simulated/game scenarios and help build evaluation metrics.

7. Track the latest industry academic papers and open-source projects related to video understanding and generation.

2. Good understanding of the internal mechanisms of video generation/VLM models and diffusion model principles.

3. Academic or project experience in interactive video generation, controllable generation, or multimodal understanding.

4. Solid coding and engineering skills; able to assist in building and debugging model training pipelines.

5. Proficient in Python/PyTorch; publications in related fields are a strong plus.

6. Familiarity with Game AI, simulation environments, or reinforcement learning frameworks is preferred.