Peiyan Dong
9 papers · 2022–2025 · 6 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(15)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Deep Learning
(5)
Machine Learning
(5)
Computer Vision
(4)
Application Areas
(4)
Architectures
(4)
Artificial Intelligence
(3)
Analysis
(3)
Core AI · Artificial Intelligence
(3)
Optimization & Theory · Machine Learning
(3)
Core AI · Computer Vision
(2)
Domain-Specific
(2)
Optimization & Theory · Deep Learning
(2)
Techniques
(1)
Keywords
vision transformer
(4)
model compression
(3)
object detection
(2)
autonomous driving
(2)
sparse training
(2)
bird's eye view
(2)
multi-view perception
(1)
weight quantization
(1)
training acceleration
(1)
edge inference
(1)
quantization-aware training
(1)
patch selection
(1)
temporal fusion
(1)
activation quantization
(1)
token sparsity
(1)
multi-sensor fusion
(1)
neural network
(1)
mobile acceleration
(1)
data redundancy
(1)
hierarchical reduction
(1)
Papers
Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation
WACV 2025
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
AAAI 2024
Data Level Lottery Ticket Hypothesis for Vision Transformers
IJCAI 2023
HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception
NeurIPS 2023
PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile
NeurIPS 2023
Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
AAAI 2023
SpeedDETR: Speed-aware Transformers for End-to-end Object Detection
ICML 2023
SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning
ECCV 2022
You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding
ECCV 2022