Jiachang Zhang · AI Research
Undergraduate researcher at XJTU and intern at SJTU. I work on embodied AI, world models, and data for learning systems.
Selected work
ICLR 2027 submission · arXiv:2609.37829
Training-free pruning of 50% of the experts in a 30B video diffusion transformer: the checkpoint footprint drops from 57 GB to 30 GB, enabling single-card deployment on a 48 GB GPU, with the official VBench Total rising from 0.7941 to 0.8115 on a fixed 284-case protocol.
Project page
AAAI submission in preparation
A data-collection and evaluation workflow for recoverable embodied task failures in AI2-THOR, with replayable traces and branch-level evidence.
GitHubResearch map
Collecting auditable trajectories that preserve failures, recovery attempts, and counterfactual branches.
Studying how routed video models represent visual changes, dynamics, and physical interactions.
Contributing interaction data and quality control for world-model research in multi-agent settings.