Jiachang Zhang

Projects

Page 1 - Showing 3 of 3research projects

Research CV
A frame generated by the DIET-pruned video model: an astronaut standing in a lake, surrounded by ducks.

ICLR 2027 submission · arXiv:2609.37829

DIET: DeletIon-response Expert Trimming for Video Diffusion Transformers

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.

MoEVideo diffusionModel compression
Project page
An AI2-THOR indoor environment used for embodied recovery data collection.

AAAI submission in preparation

Embodied Failure-Recovery Data Collection

A data-collection and evaluation workflow for recoverable embodied task failures in AI2-THOR, with replayable traces and branch-level evidence.

Embodied AIAI2-THORData collection
GitHub

Ongoing collaboration

Multi-Agent World-Model Data Collection

Contributing multi-agent interaction data and quality control. Model training is planned for a later stage.

World modelsMulti-agent systemsData quality

Selected project visuals are shown for research context.