Tiansheng Huang
16 papers · 2023–2026 · 10 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 ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Gold π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (34) π Keyword Champion (3)
π€
Dynamic Duo
(13)
ποΈ
Keyword Collector
(75)
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
Top co-authors
Research topics
Artificial Intelligence
(14)
Core AI
(13)
Deep Learning
(6)
Machine Learning
(5)
Computer Vision
(3)
Natural Language Processing
(3)
Application Areas
(3)
Architectures
(3)
Optimization & Theory Β· Deep Learning
(3)
Optimization & Theory Β· Machine Learning
(3)
Resources & Methods
(3)
Learning Types
(2)
Analysis
(1)
Applications
(1)
Generation
(1)
Keywords
harmful fine-tuning
(3)
fine-tuning attack
(3)
safety alignment
(3)
large language model
(3)
model compression
(2)
convergence analysis
(2)
ai safety
(2)
federated learning
(2)
neural network
(2)
backdoor attack
(2)
transfer learning
(1)
knowledge distillation
(1)
video understanding
(1)
model merging
(1)
adversarial robustness
(1)
attention mechanism
(1)
model robustness
(1)
adversarial learning
(1)
model fusion
(1)
object detection
(1)
Papers
A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning
CVPR 2026
Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
CVPR 2026
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
ACL 2026
H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
EACL 2026
Adversarial Attention Perturbations for Large Object Detection Transformers
ICCV 2025
Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
ICML 2025
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
ICLR 2025
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
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
FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy
ICLR 2023
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
NeurIPS 2023