Guanghao Li
8 papers · 2025–2026 · 4 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
🗺️
Taxonomy Completionist
(20)
⭐
Rising Star
(8)
Top co-authors
Research topics
Computer Vision
(5)
Deep Learning
(4)
Machine Learning
(4)
Application Areas
(4)
Analysis
(3)
Artificial Intelligence
(2)
Architectures
(2)
Core AI
(2)
Models
(2)
Processing
(2)
Domain-Specific
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Keywords
transformer architecture
(1)
vision transformer
(1)
image generation
(1)
object detection
(1)
attention mechanism
(1)
autonomous driving
(1)
video understanding
(1)
frame selection
(1)
latent representation
(1)
hidden state
(1)
adversarial perturbation
(1)
3d gaussian splatting
(1)
representation alignment
(1)
positional encoding
(1)
frequency domain
(1)
forward learning
(1)
temporal attention
(1)
privacy protection
(1)
end-to-end training
(1)
model compression
(1)
Papers
DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
CVPR 2026
GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
CVPR 2026
MacTok: Robust Continuous Tokenization for Image Generation
CVPR 2026
Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
AAAI 2026
ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
CVPR 2025
Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
ICCV 2025
FLOPS: Forward Learning with OPtimal Sampling
ICLR 2025
VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition
ICCV 2025