ββββββ βββ βββββββ βββββββ ββββββββ βββ ββββββββ ββββββββ ββββββββ βββ βββ ββββ βββ ββββββββ βββ βββ βββ βββ βββ βββ βββ βββββββββ ββββββββ βββ βββ βββ βββββββ βββββββ
I am open to research collaborations on video generation for top-tier conference publications.
π± Born 1998-11-03
π Hebei, China
π Ph.D. Candidate @ Nankai University
I am a Ph.D. candidate in PCA Lab, VCIP, College of Computer Science, Nankai University.
Iβm grateful to live in an open-source world.
-
WaDi: Weight Direction-aware Distillation for One-step Image Synthesis
Paper Β· Project Β· Code -
Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability
Paper -
One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Model
Paper -
Hierarchical Spatio-Temporal Representation Learning for Gait Recognition
Paper
"Few recognize a tree destined for the clouds in its youth; only when it towers above the sky do they praise its height."