Qinsi Wang
4 papers · 2023–2026 · 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
(10)
Venues
Top co-authors
Research topics
Machine Learning
(4)
Application Areas
(4)
Artificial Intelligence
(3)
Core AI
(3)
Deep Learning
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Processing
(1)
Techniques
(1)
Keywords
token pruning
(2)
vision-language model
(2)
transfer learning
(1)
video understanding
(1)
neural architecture search
(1)
computational efficiency
(1)
singular value decomposition
(1)
divide and conquer
(1)
streaming inference
(1)
memory efficiency
(1)
low-rank model
(1)
hardware acceleration
(1)
performance prediction
(1)
neuron pruning
(1)
flops reduction
(1)
keyframe selection
(1)
mathematical programming
(1)
modular search space
(1)
block performance
(1)
model compression
(1)
Papers
FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
AAAI 2026
CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
ICML 2025
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
ICCV 2025
MathNAS: If Blocks Have a Role in Mathematical Architecture Design
NeurIPS 2023