Yang Sui
14 papers · 2021–2025 · 6 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (32) 🌍 Conference Polyglot · Silver 🗃️ Keyword Collector (79) 🌈 Renaissance Researcher (5)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(12)
Deep Learning
(9)
Application Areas
(9)
Optimization & Theory · Deep Learning
(8)
Artificial Intelligence
(7)
Core AI
(7)
Optimization & Theory · Machine Learning
(6)
Architectures
(4)
Models
(3)
Techniques
(3)
Computer Vision
(2)
Reinforcement Learning
(2)
Generation
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Keywords
model compression
(9)
neural network optimization
(3)
neural network
(3)
efficient computing
(2)
inference efficiency
(2)
diffusion model
(2)
convolutional neural network
(2)
flops reduction
(2)
adversarial learning
(2)
kv cache
(2)
image generation
(1)
adversarial robustness
(1)
distributional reinforcement learning
(1)
low-rank decomposition
(1)
neural network compression
(1)
knowledge distillation
(1)
model pruning
(1)
sequential decision making
(1)
gradient descent
(1)
u-net architecture
(1)
Papers
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
CVPR 2025
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
CVPR 2025
TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
CVPR 2025
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
NeurIPS 2024
Clean & Compact: Efficient Data-Free Backdoor Defense with Model Compactness
ECCV 2024
Combining Experimental and Historical Data for Policy Evaluation
ICML 2024
MoE-I2: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
EMNLP 2024
Adversarial Learning of Distributional Reinforcement Learning
ICML 2023
CSTAR: Towards Compact and Structured Deep Neural Networks with Adversarial Robustness
AAAI 2023
HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks
AAAI 2023
Implicit Regularization in Over-Parameterized Support Vector Machine
NeurIPS 2023
HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks
CVPR 2022
CHIP: CHannel Independence-based Pruning for Compact Neural Networks
NeurIPS 2021
Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework
CVPR 2021