Tiansheng Huang
14 papers · 2023–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (15) π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (22) π£ Hot Topic Early Bird π Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(8)
π€
Dynamic Duo
(10)
β‘
Prolific Year
(6)
π
Century Club
(12)
Conferences
ICLR (3)
NIPS (3)
ACL (1)
CVPR (1)
EACL (1)
ECCV (1)
EMNLP (1)
ICCV (1)
ICML (1)
WACV (1)
Top co-authors
Keywords
model compression
(2)
harmful fine-tuning
(2)
fine-tuning attack
(2)
safety alignment
(2)
neural network
(2)
knowledge distillation
(1)
attention mechanism
(1)
adversarial robustness
(1)
model fusion
(1)
efficient computing
(1)
model robustness
(1)
fisher information
(1)
early exit
(1)
adaptive inference
(1)
adversarial perturbation
(1)
model merging
(1)
deep neural network
(1)
mixture of expert
(1)
model collapse
(1)
model pruning
(1)
Papers
H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
EACL 2026
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
ACL 2026
Adversarial Attention Perturbations for Large Object Detection Transformers
ICCV 2025
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
ICLR 2025
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
ICLR 2025
Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
ICML 2025
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
NIPS 2024
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
NIPS 2024
Adaptive Deep Neural Network Inference Optimization With EENet
WACV 2024
Resource-Efficient Transformer Pruning for Finetuning of Large Models
CVPR 2024
Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
ECCV 2024
LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity
EMNLP 2024
FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy
ICLR 2023
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
NIPS 2023