Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
Paper
•
2010.14819
•
Published
hankai
hankaixyz
AI & ML interests
None yet
Recent Activity
liked
a model
1 day ago
Lpzhan/openPangu-embedded-gguf
new activity
18 days ago
facebook/MobileLLM-Pro:Seems lagging behind Pangu-1B
new activity
21 days ago
facebook/MobileLLM-Pro:Seems lagging behind Pangu-1B
Organizations
None yet
authored
16
papers
over 1 year ago
GhostNet: More Features from Cheap Operations
Paper
•
1911.11907
•
Published
Transformer in Transformer
Paper
•
2103.00112
•
Published
•
1
GhostNetV2: Enhance Cheap Operation with Long-Range Attention
Paper
•
2211.12905
•
Published
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Paper
•
2303.11579
•
Published
GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception Tasks?
Paper
•
2306.00693
•
Published
Masked Image Modeling with Local Multi-Scale Reconstruction
Paper
•
2303.05251
•
Published
Augmented Shortcuts for Vision Transformers
Paper
•
2106.15941
•
Published
Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings
Paper
•
2308.12894
•
Published
ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks
Paper
•
2306.14525
•
Published
PanGu-$π$: Enhancing Language Model Architectures via Nonlinearity Compensation
Paper
•
2312.17276
•
Published
•
16
LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models
Paper
•
2312.00674
•
Published
Rethinking Optimization and Architecture for Tiny Language Models
Paper
•
2402.02791
•
Published
•
13
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper
•
2402.03749
•
Published
•
14
A Survey on Transformer Compression
Paper
•
2402.05964
•
Published
•
1
DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models
Paper
•
2403.00818
•
Published
•
19