Bencheng Liao
9 papers · 2021–2025 · 7 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
(20)
🐣
Hot Topic Early Bird
🏆
Grand Slam
Top co-authors
Research topics
Deep Learning
(7)
Computer Vision
(6)
Architectures
(6)
Machine Learning
(5)
Artificial Intelligence
(4)
Core AI · Artificial Intelligence
(4)
Analysis
(3)
Application Areas
(3)
Domain-Specific
(3)
Core AI · Computer Vision
(2)
Models
(2)
Optimization & Theory · Deep Learning
(2)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Keywords
autonomous driving
(3)
vision transformer
(3)
gated linear attention
(2)
attention mechanism
(2)
transformer architecture
(2)
diffusion model
(2)
image generation
(1)
knowledge distillation
(1)
motion planning
(1)
object detection
(1)
scene understanding
(1)
image classification
(1)
model distillation
(1)
multimodal learning
(1)
efficient computing
(1)
computer vision
(1)
bipartite matching
(1)
computational efficiency
(1)
sequence learning
(1)
transfer learning
(1)
Papers
DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
CVPR 2025
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
CVPR 2025
MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling
ICCV 2025
ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention
AAAI 2025
Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
ECCV 2024
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
ICML 2024
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
ICLR 2023
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
ICCV 2023
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
NeurIPS 2021