18 citations · 41 across the 9 of their papers we have counts for
9 papers
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
Forgetting Transformer: Softmax Attention with a Forget Gate
Zhixuan Lin, Evgenii Nikishin, Xu Owen He +1
An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturall…
The Curse of Diversity in Ensemble-Based Exploration
Zhixuan Lin, Pierluca D'Oro, Evgenii Nikishin +1
We uncover a surprising phenomenon in deep reinforcement learning: training a diverse ensemble of data-sharing agents -- a well-established exploration strategy -- can significantl…
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons
Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin +3
When training neural networks, dying neurons -- units becoming inactive or saturated -- are traditionally seen as harmful. This paper sheds new light on this phenomenon. By explori…
Deep Reinforcement Learning with Plasticity Injection
Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski +4
A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however,…
Understanding plasticity in neural networks
Clare Lyle, Zeyu Zheng, Evgenii Nikishin +3
Plasticity, the ability of a neural network to quickly change its predictions in response to new information, is essential for the adaptability and robustness of deep reinforcement…
The Primacy Bias in Deep Reinforcement Learning
Evgenii Nikishin, Max Schwarzer, Pierluca D'Oro +2
This work identifies a common flaw of deep reinforcement learning (RL) algorithms: a tendency to rely on early interactions and ignore useful evidence encountered later. Because of…
Quantifying and Understanding Adversarial Examples in Discrete Input Spaces
Volodymyr Kuleshov, Evgenii Nikishin, Shantanu Thakoor +2
Modern classification algorithms are susceptible to adversarial examples--perturbations to inputs that cause the algorithm to produce undesirable behavior. In this work, we seek to…
Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation
Evgenii Nikishin, Romina Abachi, Rishabh Agarwal +1
The shortcomings of maximum likelihood estimation in the context of model-based reinforcement learning have been highlighted by an increasing number of papers. When the model class…