Guanyu Feng
3 papers · 2022–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
transformer architecture
(1)
generative model
(1)
diffusion model
(1)
variational autoencoder
(1)
text-to-video generation
(1)
inference efficiency
(1)
sampling acceleration
(1)
sampling trajectory
(1)
diffusion transformer
(1)
model efficiency
(1)
cache management
(1)
virtual memory
(1)
block cache
(1)
out-of-core processing
(1)
memory management
(1)
spatial locality
(1)
address translation
(1)
cache reuse
(1)
cache optimization
(1)
i/o optimization
(1)
Papers
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
ICLR 2025
OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
ICCV 2025
TriCache: A User-Transparent Block Cache Enabling High-Performance Out-of-Core Processing with In-Memory Programs
OSDI 2022