Shuming Liu
10 papers · 2016–2026 · 5 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 ↓+3 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (28) 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 👥 Mega-Team · Squad
🗃️
Keyword Collector
(52)
📈
Trend Setter
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Deep Learning
(7)
Computer Vision
(6)
Artificial Intelligence
(5)
Core AI
(5)
Processing
(5)
Machine Learning
(4)
Architectures
(4)
Learning Types · Deep Learning
(4)
Analysis
(3)
Application Areas
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Optimization & Theory · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Natural Language Processing
(1)
Keywords
video understanding
(4)
model compression
(2)
temporal action detection
(2)
reinforcement learning
(1)
transfer learning
(1)
feature extraction
(1)
action recognition
(1)
chain-of-thought reasoning
(1)
data annotation
(1)
memory efficiency
(1)
image editing
(1)
text-to-image generation
(1)
network optimization
(1)
frame selection
(1)
action localization
(1)
text classification
(1)
pre-trained model
(1)
model fine-tuning
(1)
multimodal large language model
(1)
multi-task learning
(1)
Papers
Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
CVPR 2026
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
CVPR 2026
A Simple yet Efficient Prompt Compression Method for Text Classification Data Annotation Using LLM
COLING 2025
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
CVPR 2025
Boundary Denoising for Video Activity Localization
ICLR 2024
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
ECCV 2024
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
CVPR 2024
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
CVPR 2024
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
CVPR 2023
Urban Water Quality Prediction Based on Multi-Task Multi-View Learning
IJCAI 2016