Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Paper
•
2104.13840
•
Published
Bo Zhang
boydcheung
AI & ML interests
None yet
Recent Activity
liked
a dataset
about 2 hours ago
LejuRobotics/let_dataset
liked
a dataset
about 23 hours ago
jxu124/OpenX-Embodiment
updated
a collection
1 day ago
Embodied Intelligence
Organizations
authored
8
papers
almost 2 years ago
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
Paper
•
2209.02976
•
Published
YOLOv6 v3.0: A Full-Scale Reloading
Paper
•
2301.05586
•
Published
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation
Paper
•
2011.11233
•
Published
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
Paper
•
2309.02784
•
Published
•
2
MobileVLM : A Fast, Reproducible and Strong Vision Language Assistant for Mobile Devices
Paper
•
2312.16886
•
Published
•
22
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Paper
•
2402.03766
•
Published
•
15
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
Paper
•
2403.00522
•
Published
•
46
authored
4
papers
about 2 years ago
FPTQ: Fine-grained Post-Training Quantization for Large Language Models
Paper
•
2308.15987
•
Published
•
2
Lenna: Language Enhanced Reasoning Detection Assistant
Paper
•
2312.02433
•
Published
•
2
A Speed Odyssey for Deployable Quantization of LLMs
Paper
•
2311.09550
•
Published
•
3
MixPath: A Unified Approach for One-shot Neural Architecture Search
Paper
•
2001.05887
•
Published
•
1