collaborators

5 papers

cs.CV2026

PhyWorld: Physics-Faithful World Model for Video Generation

Pu Zhao, Juyi Lin, Timothy Rupprecht +10

World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising…

eess.IV2026

Robust Wildfire Forecasting under Partial Observability: From Reconstruction to Prediction

Chen Yang, Mehdi Zafari, Ziheng Duan +1

Satellite-derived fire observations are the primary input for learning-based wildfire spread prediction, yet they are inherently incomplete due to cloud cover, smoke obscuration, a…

cs.CV2026

Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models

Ci Zhang, Zhaojun Ding, Chence Yang +7

Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficienc…

cs.LG2025

Rethinking the Potential of Layer Freezing for Efficient DNN Training

Chence Yang, Ci Zhang, Lei Lu +11

With the growing size of deep neural networks and datasets, the computational costs of training have significantly increased. The layer-freezing technique has recently attracted gr…

cs.LG2025

Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training

Qitao Tan, Sung-En Chang, Rui Xia +10

Zeroth-order (ZO) optimization is an emerging deep neural network (DNN) training paradigm that offers computational simplicity and memory savings. However, this seemingly promising…