Chunjiang Liu

MTS @ Bake AI Inc

Agentic Workflow 3DV

I received my M.S. in ECE from Carnegie Mellon University, where I worked with Prof. László A. Jeni and Yizhou Zhao, Ph.D.

My research background is in Computer Vision(3DV).

Publications

MOSIV
ICLR 2026

MOSIV: Multi-Object System Identification from Videos

Chunjiang Liu, Xiaoyuan Wang, Qingran Lin, Albert Xiao, Haoyu Chen, Shizheng Wen, Hao Zhang, Lu Qi, Ming-Hsuan Yang, Laszlo A. Jeni, Min Xu, Yizhou Zhao

Paper
MASIV
ICCV 2025

Toward Material-Agnostic System Identification from Videos

Yizhou Zhao, Haoyu Chen, Chunjiang Liu, Zhenyang Li, Charles Herrmann, Junhwa Hur, Yinxiao Li, Ming-Hsuan Yang, Bhiksha Raj, Min Xu

Paper Code
Total-Editing
ICCV 2025 Workshop

Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting

Yizhou Zhao, Chunjiang Liu, Haoyu Chen, Bhiksha Raj, Min Xu, Tadas Baltrusaitis, Mitch Rundle, HsiangTao Wu, Kamran Ghasedi

Paper

Working Experience

Full-time 2026 —
Member of Technical Staff
Bake AI Inc.
– 1Bench: Living benchmark platform tracking frontier AI on expert-verified, unsolvable problems across multiple domains
– ArtArena: Visual aesthetic benchmark evaluating AI models on artist-curated artworks against expert judgments
Full-time 2024 — 2025
Research Associate
Carnegie Mellon University, ECE
– Multi-object dynamic reconstruction and physics estimation from video via differentiable simulation
– Material-agnostic dynamic reconstruction with learnable neural constitutive models
– Unified head avatar editing framework with joint control of appearance, motion, and lighting

Education

CMU
M.S. Electrical and Computer Engineering
Carnegie Mellon University, 2023 — 2024
GPA 3.83 / 4.00
Advanced Computer Vision, Visual Learning, Multi-modal ML, Deep Generative Modeling
UESTC
B.E. Communication Engineering
University of Electronic Science and Technology of China, 2018 — 2022
GPA 3.84 / 4.00
Calculus, Linear Algebra, Probability and Statistics, Signal and System

Academic Projects

Course Project Fall 2024
Stage-Aware Vision-and-Language Navigation
Advisor: Daniel Fried
– Weighted angular distance loss for navigation decisions
– LLM-based instruction paraphrasing for data augmentation
– 53.2% SR on unseen environments (R2R)
Course Project Spring 2024
Zero-Shot Text-to-Video Generation
Advisor: Giulia Fanti
– LLM-based prompt elaboration + few-shot frame consistency
– CLIP: 30.4 (ours) vs 29.6 (baseline)
Course Project Spring 2024
Light-weight Transformer for Next Word Prediction
Advisor: Yuejie Chi
– Knowledge distillation on Daily Dialog (21,976 tokens)
– Perplexity: 35, comparable to GPT-2