Evci, Utku

1. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
   2025/07/07 by Gheorghe Comanici, Eric Bieber, Comanici, Gheorghe +6844 · 8 voices · 1365 citations
   #cs.CL #cs.AI
2. Gemma 3 Technical Report
   2025/03/25 by Aishwarya Kamath, Gemma Team, Johan Ferret +418 · 3 voices · 470 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.AI #cs.CL
3. Scaling Vision Transformers to 22 Billion Parameters
   2023/02/10 by Mostafa Dehghani, Josip Djolonga, Dehghani, Mostafa +81 · 66 citations
   Computer Science · #Multimodal Machine Learning Applications #Domain Adaptation and Few-Shot Learning #Advanced Neural Network Applications
4. Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
   2017/06/14 by Levent Sagun, Sagun, Levent, Utku Evci +7 · 43 citations
   Computer Science · Engineering · Mathematics · #Stochastic Gradient Optimization Techniques #Sparse and Compressive Sensing Techniques #Random Matrices and Applications
5. The Dormant Neuron Phenomenon in Deep Reinforcement Learning
   2023/02/24 by Ghada Sokar, Sokar, Ghada, Rishabh Agarwal +5 · 21 citations
   Neuroscience · Computer Science · #Neural dynamics and brain function #Reinforcement Learning in Robotics #Neural Networks and Applications
6. The State of Sparse Training in Deep Reinforcement Learning
   2022/06/17 by Laura Graesser, Graesser, Laura, Utku Evci +5 · 11 citations
   Computer Science · #Reinforcement Learning in Robotics #Domain Adaptation and Few-Shot Learning #Machine Learning and ELM
7. The Difficulty of Training Sparse Neural Networks
   2019/06/25 by Evci, Utku, Pedregosa, Fabian, Gomez, Aidan +1 · 3 citations
   #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
8. Natural Language Understanding with the Quora Question Pairs Dataset
   2019/07/01 by Sharma, Lakshay, Graesser, Laura, Nangia, Nikita +1 · 3 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
9. Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win
   2020/10/07 by Utku Evci, Evci, Utku, Yani Ioannou +5 · 3 citations
   Computer Science · #68T07 #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Stochastic Gradient Optimization Techniques
10. Dynamic Sparse Training with Structured Sparsity
    2023/05/03 by Lasby, Mike, Golubeva, Anna, Evci, Utku +2 · 4 citations
    #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
11. Scaling Laws for Sparsely-Connected Foundation Models
    2023/09/15 by Elias Frantar, Carlos Riquelme, Frantar, Elias +7 · 3 citations
    Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
12. Towards Optimal Adapter Placement for Efficient Transfer Learning
    2024/10/21 by Aleksandra Nowak, Nowak, Aleksandra I., Otniel-Bogdan Mercea +9 · 3 citations
    Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Speech Recognition and Synthesis
13. A Practical Sparse Approximation for Real Time Recurrent Learning
    2020/06/12 by Menick, Jacob, Elsen, Erich, Evci, Utku +3 · 1 citation
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
14. Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
    2021/04/06 by Vincent Dumoulin, Neil Houlsby, Dumoulin, Vincent +11 · 1 citation
    Computer Science · Medicine · #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Multimodal Machine Learning Applications
15. Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask
    2022/09/15 by Sheng-Chun Kao, Kao, Sheng-Chun, Amir Yazdanbakhsh +9 · 1 citation
    Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG) #Machine Learning and Data Classification #Performance (cs.PF)
16. JaxPruner: A concise library for sparsity research
    2023/04/27 by Lee, Joo Hyung, Park, Wonpyo, Mitchell, Nicole +22 · 1 citation
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Software Engineering (cs.SE)
17. Spark Transformer: Reactivating Sparsity in FFN and Attention
    2025/06/07 by You, Chong, Wu, Kan, Jia, Zhipeng +16 · 3 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
18. Compression Scaling Laws:Unifying Sparsity and Quantization
    2025/02/23 by Frantar, Elias, Evci, Utku, Park, Wonpyo +2 · 2 citations
    #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
19. Learning Parameter Sharing with Tensor Decompositions and Sparsity
    2024/11/14 by Üyük, Cem, Lasby, Mike, Yassin, Mohamed +2 · 1 citation
    #FOS: Computer and information sciences #Machine Learning (cs.LG)