Xiangyu He
18 papers · 2018–2026 · 7 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (52) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(12)
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Renaissance Researcher
(5)
ποΈ
Keyword Collector
(92)
Top co-authors
Research topics
Machine Learning
(14)
Deep Learning
(13)
Computer Vision
(8)
Application Areas
(8)
Architectures
(6)
Models
(6)
Artificial Intelligence
(4)
Generation
(4)
Learning Types Β· Machine Learning
(4)
Optimization & Theory Β· Machine Learning
(4)
Optimization & Theory Β· Deep Learning
(4)
Processing
(4)
Core AI
(3)
Core Methods
(3)
Learning Types Β· Deep Learning
(3)
Keywords
model compression
(5)
efficient computing
(3)
image editing
(2)
image generation
(2)
zero-shot learning
(2)
neural network quantization
(2)
neural network optimization
(2)
privacy attack
(1)
action recognition
(1)
image classification
(1)
multi-task learning
(1)
vision transformer
(1)
self-attention mechanism
(1)
network architecture
(1)
post-training quantization
(1)
object detection
(1)
style transfer
(1)
hyperparameter optimization
(1)
transfer learning
(1)
semantic segmentation
(1)
Papers
Breaking Multimodal LLM Safety via Video-Driven Prompting
CVPR 2026
FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
ICML 2025
Multi-turn Consistent Image Editing
ICCV 2025
Z-Magic: Zero-shot Multiple Attributes Guided Image Creator
CVPR 2025
Z*: Zero-shot Style Transfer via Attention Reweighting
CVPR 2024
Code-Aware Cross-Program Transfer Hyperparameter Optimization
AAAI 2023
APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers
CVPR 2022
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
NeurIPS 2022
Towards Fully Sparse Training: Information Restoration with Spatial Similarity
AAAI 2022
Dynamic Dual Gating Neural Networks
ICCV 2021
ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices
ECCV 2020
Skeleton-Based Action Recognition With Shift Graph Convolutional Network
CVPR 2020
Soft Threshold Ternary Networks
IJCAI 2020
Sparsity-Inducing Binarized Neural Networks
AAAI 2020
Towards Accurate Post-training Network Quantization via Bit-Split and Stitching
ICML 2020
K-Nearest Neighbors Hashing
CVPR 2019
ODE-Inspired Network Design for Single Image Super-Resolution
CVPR 2019
Learning Compression from Limited Unlabeled Data
ECCV 2018