Fatih Ilhan
10 papers · 2023–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π£ Hot Topic Early Bird π Conference Polyglot (6) π Renaissance Researcher (5) π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(20)
π§
Keyword Pioneer
π€
Dynamic Duo
(10)
π
Century Club
(10)
Conferences
CVPR (3)
NIPS (2)
EACL (1)
EMNLP (1)
ICCV (1)
ICLR (1)
WACV (1)
Top co-authors
Keywords
model compression
(3)
early exit
(2)
neural network
(2)
object detection
(2)
federated learning
(2)
knowledge distillation
(2)
safety alignment
(1)
fisher information
(1)
adaptive inference
(1)
model pruning
(1)
deep neural network
(1)
adversarial perturbation
(1)
mixture of expert
(1)
neural network robustness
(1)
inference optimization
(1)
fine-tuning attack
(1)
model optimization
(1)
parameter-efficient finetuning
(1)
taylor approximation
(1)
llm alignment
(1)
Papers
H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
EACL 2026
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
ICLR 2025
Adversarial Attention Perturbations for Large Object Detection Transformers
ICCV 2025
LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity
EMNLP 2024
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
NIPS 2024
Resource-Efficient Transformer Pruning for Finetuning of Large Models
CVPR 2024
Adaptive Deep Neural Network Inference Optimization With EENet
WACV 2024
STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
CVPR 2023
ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients
CVPR 2023
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
NIPS 2023