Xiaoheng Deng
4 papers · 2024–2026 · 2 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)
Top co-authors
Research topics
Artificial Intelligence
(2)
Machine Learning
(2)
Security & Privacy
(2)
Application Areas
(2)
Privacy
(2)
Deep Learning
(1)
Robotics
(1)
Applications
(1)
Capabilities
(1)
Core AI
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Keywords
model compression
(1)
federated learning
(1)
robotic manipulation
(1)
orthogonal projection
(1)
gradient estimation
(1)
adversarial attack
(1)
convergence guarantee
(1)
differentiable rendering
(1)
mixture of expert
(1)
privacy protection
(1)
inference acceleration
(1)
spatial reasoning
(1)
expert activation
(1)
vision-language-action model
(1)
model stealing
(1)
model extraction
(1)
gradient leakage attack
(1)
parameter offloading
(1)
sample gradient
(1)
patch-wise perturbation
(1)
Papers
CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices
AAAI 2026
FedMOP: Achieving Enhanced Privacy and Performance in Federated Learning via Momentum Orthogonal Projection
CVPR 2026
Localizing, Structuring, and Rendering: Bridging 3D and 2D Vision-Language-Action Models for Robotic Manipulation
CVPR 2026
Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing
CVPR 2024