Samet Oymak
@oymak.bsky.social
EECS Prof @UMich, Research on the Foundations of ML+RL+LLM
https://sota.engin.umich.edu/
https://sota.engin.umich.edu/
Some SAC context for NeurIPS 2025 review scores - out of my batch of 100 papers:
- 1 paper ≥5.0
- 6 papers ≥4.5
- 11 papers ≥4.0
- 25 papers ≥3.75
- 42 papers ≥3.5
Good luck to all with rebuttals!
- 1 paper ≥5.0
- 6 papers ≥4.5
- 11 papers ≥4.0
- 25 papers ≥3.75
- 42 papers ≥3.5
Good luck to all with rebuttals!
July 24, 2025 at 5:02 PM
Some SAC context for NeurIPS 2025 review scores - out of my batch of 100 papers:
- 1 paper ≥5.0
- 6 papers ≥4.5
- 11 papers ≥4.0
- 25 papers ≥3.75
- 42 papers ≥3.5
Good luck to all with rebuttals!
- 1 paper ≥5.0
- 6 papers ≥4.5
- 11 papers ≥4.0
- 25 papers ≥3.75
- 42 papers ≥3.5
Good luck to all with rebuttals!
I like "slay" here. Makes theory research more RPG-like
arxiv.org/abs/2411.17668 Our postdoc zihan slays another COLT open problem! proceedings.mlr.press/v247/kornows...
Anytime Acceleration of Gradient Descent
This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsize schedule that all...
arxiv.org
November 28, 2024 at 2:59 PM
I like "slay" here. Makes theory research more RPG-like
Reposted by Samet Oymak
NeurIPS Test of Time Awards:
Generative Adversarial Nets
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le
Generative Adversarial Nets
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le
November 27, 2024 at 5:32 PM
NeurIPS Test of Time Awards:
Generative Adversarial Nets
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le
Generative Adversarial Nets
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le
Hello world! Unfortunately, my first post happens to be a paper (thre)ad 😊: Our “Selective Attention” is a simple but effective method that dynamically adjusts the sparsity of the attention maps through temperature scaling: arxiv.org/pdf/2411.12892 (#neurips2024)
November 21, 2024 at 10:19 PM
Hello world! Unfortunately, my first post happens to be a paper (thre)ad 😊: Our “Selective Attention” is a simple but effective method that dynamically adjusts the sparsity of the attention maps through temperature scaling: arxiv.org/pdf/2411.12892 (#neurips2024)