Hongwu Peng
6 papers · 2023–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π§
Keyword Pioneer
π
Conference Polyglot
(4)
π
Cross-Pollinator
(9)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(11)
Conferences
NIPS (2)
ACL (1)
ICCV (1)
ICLR (1)
ICML (1)
Top co-authors
Research topics
Keywords
privacy-preserving machine learning
(1)
model compression
(1)
representation learning
(1)
feature learning
(1)
imitation learning
(1)
knowledge distillation
(1)
neural network optimization
(1)
efficient computing
(1)
regularization technique
(1)
student learner
(1)
homomorphic encryption
(1)
graph convolutional network
(1)
student-teacher learning
(1)
polynomial approximation
(1)
encrypted inference
(1)
private inference
(1)
neural network
(1)
robustness against attack
(1)
multiplication depth
(1)
deliberative alignment
(1)
Papers
Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
ACL 2026
RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs
ICLR 2025
Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
NIPS 2024
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
ICML 2024
LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
NIPS 2023
AutoReP: Automatic ReLU Replacement for Fast Private Network Inference
ICCV 2023