Jieyu Zhang

4

Papers

16

Total Citations

Papers (4)

Iterated Learning Improves Compositionality in Large Vision-Language Models

One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory

SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models

Offline Training of Language Model Agents with Functions as Learnable Weights