Qinsi Wang
4 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
ICCV (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
model compression
(1)
network architecture
(1)
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)
vision language model
(1)
low-rank model
(1)
token pruning
(1)
performance prediction
(1)
keyframe selection
(1)
mathematical programming
(1)
modular search space
(1)
block performance
(1)
Papers
FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
AAAI 2026
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
ICCV 2025
CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
ICML 2025
MathNAS: If Blocks Have a Role in Mathematical Architecture Design
NIPS 2023