12 citations · 35 across the 23 of their papers we have counts for
9 papers · 1 filter
Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
Mohammadreza Armandpour, Fatih Ilhan, David Harrison +6
On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under whi…
FedHFT: Efficient Federated Finetuning with Heterogeneous Edge Clients
Fatih Ilhan, Selim Furkan Tekin, Tiansheng Huang +6
Fine-tuning pre-trained large language models (LLMs) has become a common practice for personalized natural language understanding (NLU) applications on downstream tasks and domain-…
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
Tiansheng Huang, Sihao Hu, Fatih Ilhan +2
Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we…
Adaptive Deep Neural Network Inference Optimization with EENet
Fatih Ilhan, Ka-Ho Chow, Sihao Hu +9
Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test exampl…
Markovian RNN: An Adaptive Time Series Prediction Network with HMM-based Switching for Nonstationary Environments
Fatih Ilhan, Oguzhan Karaahmetoglu, Ismail Balaban +1
We investigate nonlinear regression for nonstationary sequential data. In most real-life applications such as business domains including finance, retail, energy and economy, timese…
Achieving Online Regression Performance of LSTMs with Simple RNNs
N. Mert Vural, Fatih Ilhan, Selim F. Yilmaz +2
Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, Long-Short-Term-Memory N…
Modeling of Spatio-Temporal Hawkes Processes with Randomized Kernels
Fatih Ilhan, Suleyman Serdar Kozat
We investigate spatio-temporal event analysis using point processes. Inferring the dynamics of event sequences spatiotemporally has many practical applications including crime pred…
RNN-based Online Learning: An Efficient First-Order Optimization Algorithm with a Convergence Guarantee
N. Mert Vural, Selim F. Yilmaz, Fatih Ilhan +1
We investigate online nonlinear regression with continually running recurrent neural network networks (RNNs), i.e., RNN-based online learning. For RNN-based online learning, we int…
Stability of the Decoupled Extended Kalman Filter Learning Algorithm in LSTM-Based Online Learning
Nuri Mert Vural, Fatih Ilhan, Suleyman S. Kozat
We investigate the convergence and stability properties of the decoupled extended Kalman filter learning algorithm (DEKF) within the long-short term memory network (LSTM) based onl…