Fatih Ilhan
12 papers · 2023–2026 · 7 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 ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Silver πΊοΈ Taxonomy Completionist (26) π£ Hot Topic Early Bird π€ Dynamic Duo (12)
ποΈ
Keyword Collector
(56)
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(11)
Core AI
(10)
Deep Learning
(5)
Machine Learning
(5)
Computer Vision
(3)
Application Areas
(3)
Architectures
(3)
Optimization & Theory Β· Deep Learning
(3)
Natural Language Processing
(2)
Analysis
(2)
Learning Paradigms
(2)
Learning Types
(2)
Optimization & Theory Β· Machine Learning
(2)
Resources & Methods
(2)
Applications
(1)
Keywords
model compression
(3)
federated learning
(3)
neural network
(2)
early exit
(2)
object detection
(2)
knowledge distillation
(2)
fisher information
(1)
model fusion
(1)
convergence analysis
(1)
ai safety
(1)
backdoor attack
(1)
safety alignment
(1)
efficient computing
(1)
model merging
(1)
model pruning
(1)
adaptive inference
(1)
communication efficiency
(1)
kernel fusion
(1)
video understanding
(1)
attention mechanism
(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
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
Resource-Efficient Transformer Pruning for Finetuning of Large Models
CVPR 2024
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
NeurIPS 2023
ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients
CVPR 2023
STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
CVPR 2023