2 citations · 3 across the 7 of their papers we have counts for
7 papers
The Role of Feedback Alignment in Self-Distillation
Semih Kara, Oğuzhan Ersoy
Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this impr…
Congestion Reduction in EV Charger Placement Using Traffic Equilibrium Models
Semih Kara, Yasin Sonmez, Can Kizilkale +3
Growing EV adoption can worsen traffic conditions if chargers are sited without regard to their impact on congestion. We study how to strategically place EV chargers to reduce cong…
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy +12
Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1…
Aggregate Fictitious Play for Learning in Anonymous Polymatrix Games (Extended Version)
Semih Kara, Tamer Başar
Fictitious play (FP) is a well-studied algorithm that enables agents to learn Nash equilibrium in games with certain reward structures. However, when agents have no prior knowledge…
Differential Equation Approximations for Population Games using Elementary Probability
Semih Kara, Nuno C. Martins
Population games model the evolution of strategic interactions among a large number of uniform agents. Due to the agents' uniformity and quantity, their aggregate strategic choices…
Population Games With Erlang Clocks: Convergence to Nash Equilibria For Pairwise Comparison Dynamics
Semih Kara, Nuno C. Martins, Murat Arcak
The prevailing methodology for analyzing population games and evolutionary dynamics in the large population limit assumes that a Poisson process (or clock) inherent to each agent d…
Pairwise Comparison Evolutionary Dynamics with Strategy-Dependent Revision Rates: Stability and Delta-Passivity (Expanded Version)
Semih Kara, Nuno C. Martins
We report on new stability conditions for evolutionary dynamics in the context of population games. We adhere to the prevailing framework consisting of many agents, grouped into po…