Sihao Hu
12 papers · 2020–2026 · 9 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 ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (34) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze
π€
Dynamic Duo
(11)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(73)
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(9)
Deep Learning
(5)
Machine Learning
(5)
Computer Vision
(3)
Natural Language Processing
(3)
Architectures
(3)
Learning Types
(3)
Resources & Methods
(3)
Application Areas
(2)
Optimization & Theory Β· Deep Learning
(2)
Optimization & Theory Β· Machine Learning
(2)
Data Science & Analytics
(1)
Analysis
(1)
Applications
(1)
Keywords
neural network
(2)
harmful fine-tuning
(2)
model compression
(2)
neural network pruning
(1)
anomaly detection
(1)
ensemble learning
(1)
adversarial robustness
(1)
collaborative filtering
(1)
model robustness
(1)
attention mechanism
(1)
knowledge distillation
(1)
convergence analysis
(1)
video understanding
(1)
real-time interaction
(1)
efficient computing
(1)
model merging
(1)
ai safety
(1)
model fusion
(1)
safety alignment
(1)
object detection
(1)
Papers
A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning
CVPR 2026
H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
EACL 2026
Adversarial Attention Perturbations for Large Object Detection Transformers
ICCV 2025
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
ICLR 2025
Adaptive Deep Neural Network Inference Optimization With EENet
WACV 2024
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
NeurIPS 2024
LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity
EMNLP 2024
Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
ECCV 2024
Resource-Efficient Transformer Pruning for Finetuning of Large Models
CVPR 2024
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
NeurIPS 2024
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
NeurIPS 2023
Interactive Rare-Category-of-Interest Mining from Large Datasets
AAAI 2020