Sotabase

Career

· Research Scientist, Google2024–
· Student Researcher, Google2023–2024
· Visiting Researcher, Vector Institute2023–2023
· Applied Scientist Intern, Amazon2022–2023
· Student Researcher, Google2022–2024
· Research Intern, Google2021–2021
· Graduate Researcher, Stanford Artificial Intelligence Laboratory (SAIL)2019–2024
· Research Intern, Stanford University School of Engineering2018–2018
· Research, Google DeepMind

Publications (43)

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
rTop-k: A Statistical Estimation Approach to Distributed SGD
IEEE Journal on Selected Areas in Information Theory · 2020
71
cited
Sparse Random Networks for Communication-Efficient Federated Learning
International Conference on Learning Representations · 2022
64
cited
Scaling Laws for Downstream Task Performance of Large Language Models
arXiv.org · 2024
49
cited
An Information-Theoretic Justification for Model Pruning
International Conference on Artificial Intelligence and Statistics · 2021
39
cited
LVAC: Learned volumetric attribute compression for point clouds using coordinate based networks
Frontiers in Signal Processing · 2021
34
cited
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
arXiv.org · 2024
29
cited
Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation
Neural Information Processing Systems · 2023
21
cited
Adaptive Compression in Federated Learning via Side Information
International Conference on Artificial Intelligence and Statistics · 2023
20
cited
Scaling Laws for Downstream Task Performance in Machine Translation
International Conference on Learning Representations · 2025
18
cited
GPT-Zip: Deep Compression of Finetuned Large Language Models
2023
13
cited
Neural Network Compression for Noisy Storage Devices
ACM Transactions on Embedded Computing Systems · 2021
13
cited
Neural 3D Scene Compression via Model Compression
arXiv.org · 2021
10
cited
Successive Pruning for Model Compression via Rate Distortion Theory
arXiv.org · 2021
10
cited
Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations
arXiv.org · 2024
10
cited
Communication-Efficient Federated Learning through Importance Sampling
arXiv.org · 2023
9
cited
Sandwiched Video Compression: Efficiently Extending the Reach of Standard Codecs with Neural Wrappers
International Conference on Information Photonics · 2023
9
cited
On Fairness of Low-Rank Adaptation of Large Models
arXiv.org · 2024
7
cited
Learning under Storage and Privacy Constraints
International Symposium on Information Theory · 2022
6
cited
Rate-Distortion Theoretic Model Compression: Successive Refinement for Pruning
2021
5
cited
Sotabase
Berivan Isik | Researcher Profile | Sotabase | Sotabase