default search action
Etai Littwin
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [j2]Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind:
The Slingshot Effect: A Late-Stage Optimization Anomaly in Adaptive Gradient Methods. Trans. Mach. Learn. Res. 2024 (2024) - [c16]Enric Boix-Adserà, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua M. Susskind:
When can transformers reason with abstract symbols? ICLR 2024 - [c15]Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin:
Vanishing Gradients in Reinforcement Finetuning of Language Models. ICLR 2024 - [c14]Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin:
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures. ICLR 2024 - [c13]Hattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Joshua M. Susskind, Samy Bengio, Preetum Nakkiran:
What Algorithms can Transformers Learn? A Study in Length Generalization. ICLR 2024 - [i24]Etai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang, Joshua M. Susskind:
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks. CoRR abs/2407.03475 (2024) - [i23]Yicheng Fu, Raviteja Anantha, Prabal Vashisht, Jianpeng Cheng, Etai Littwin:
UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity. CoRR abs/2409.04081 (2024) - [i22]Etai Littwin, Vimal Thilak, Anand Gopalakrishnan:
Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning. CoRR abs/2410.10773 (2024) - 2023
- [j1]Enric Boix-Adserà, Etai Littwin:
Tight conditions for when the NTK approximation is valid. Trans. Mach. Learn. Res. 2023 (2023) - [c12]Etai Littwin, Greg Yang:
Adaptive Optimization in the ∞-Width Limit. ICLR 2023 - [c11]Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Joshua M. Susskind:
Stabilizing Transformer Training by Preventing Attention Entropy Collapse. ICML 2023: 40770-40803 - [c10]Emmanuel Abbe, Samy Bengio, Enric Boix-Adserà, Etai Littwin, Joshua M. Susskind:
Transformers learn through gradual rank increase. NeurIPS 2023 - [i21]Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Joshua M. Susskind:
Stabilizing Transformer Training by Preventing Attention Entropy Collapse. CoRR abs/2303.06296 (2023) - [i20]Enric Boix-Adserà, Etai Littwin:
The NTK approximation is valid for longer than you think. CoRR abs/2305.13141 (2023) - [i19]Enric Boix-Adserà, Etai Littwin, Emmanuel Abbe, Samy Bengio, Joshua M. Susskind:
Transformers learn through gradual rank increase. CoRR abs/2306.07042 (2023) - [i18]Greg Yang, Etai Littwin:
Tensor Programs IVb: Adaptive Optimization in the Infinite-Width Limit. CoRR abs/2308.01814 (2023) - [i17]Samira Abnar, Omid Saremi, Laurent Dinh, Shantel Wilson, Miguel Ángel Bautista, Chen Huang, Vimal Thilak, Etai Littwin, Jiatao Gu, Josh M. Susskind, Samy Bengio:
Adaptivity and Modularity for Efficient Generalization Over Task Complexity. CoRR abs/2310.08866 (2023) - [i16]Enric Boix-Adserà, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua M. Susskind:
When can transformers reason with abstract symbols? CoRR abs/2310.09753 (2023) - [i15]Hattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Josh M. Susskind, Samy Bengio, Preetum Nakkiran:
What Algorithms can Transformers Learn? A Study in Length Generalization. CoRR abs/2310.16028 (2023) - [i14]Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin:
Vanishing Gradients in Reinforcement Finetuning of Language Models. CoRR abs/2310.20703 (2023) - [i13]Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin:
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures. CoRR abs/2312.04000 (2023) - 2022
- [c9]Ruixiang Zhang, Shuangfei Zhai, Etai Littwin, Joshua M. Susskind:
Learning Representation from Neural Fisher Kernel with Low-rank Approximation. ICLR 2022 - [i12]Ruixiang Zhang, Shuangfei Zhai, Etai Littwin, Josh M. Susskind:
Learning Representation from Neural Fisher Kernel with Low-rank Approximation. CoRR abs/2202.01944 (2022) - [i11]Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind:
The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon. CoRR abs/2206.04817 (2022) - 2021
- [c8]Greg Yang, Etai Littwin:
Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics. ICML 2021: 11762-11772 - [c7]Etai Littwin, Tomer Galanti, Lior Wolf:
On random kernels of residual architectures. UAI 2021: 897-907 - [i10]Greg Yang, Etai Littwin:
Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics. CoRR abs/2105.03703 (2021) - [i9]Etai Littwin, Omid Saremi, Shuangfei Zhai, Vimal Thilak, Hanlin Goh, Joshua M. Susskind, Greg Yang:
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks. CoRR abs/2107.00364 (2021) - [i8]Shih-Yu Sun, Vimal Thilak, Etai Littwin, Omid Saremi, Joshua M. Susskind:
Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks. CoRR abs/2107.01301 (2021) - 2020
- [c6]Etai Littwin, Tomer Galanti, Lior Wolf, Greg Yang:
On Infinite-Width Hypernetworks. NeurIPS 2020 - [c5]Etai Littwin, Ben Myara, Sima Sabah, Joshua M. Susskind, Shuangfei Zhai, Oren Golan:
Collegial Ensembles. NeurIPS 2020 - [i7]Etai Littwin, Lior Wolf:
On the Convex Behavior of Deep Neural Networks in Relation to the Layers' Width. CoRR abs/2001.04878 (2020) - [i6]Etai Littwin, Lior Wolf:
Residual Tangent Kernels. CoRR abs/2001.10460 (2020) - [i5]Etai Littwin, Tomer Galanti, Lior Wolf:
On the Optimization Dynamics of Wide Hypernetworks. CoRR abs/2003.12193 (2020) - [i4]Etai Littwin, Ben Myara, Sima Sabah, Joshua M. Susskind, Shuangfei Zhai, Oren Golan:
Collegial Ensembles. CoRR abs/2006.07678 (2020)
2010 – 2019
- 2018
- [c4]Etai Littwin, Lior Wolf:
Regularizing by the Variance of the Activations' Sample-Variances. NeurIPS 2018: 2119-2129 - [i3]Etai Littwin, Lior Wolf:
Regularizing by the Variance of the Activations' Sample-Variances. CoRR abs/1811.08764 (2018) - 2016
- [c3]Etai Littwin, Lior Wolf:
The Multiverse Loss for Robust Transfer Learning. CVPR 2016: 3957-3966 - [c2]Etai Littwin, Lior Wolf:
Complexity of multiverse networks and their multilayer generalization. ICPR 2016: 372-377 - [i2]Etai Littwin, Lior Wolf:
The Loss Surface of Residual Networks: Ensembles and the Role of Batch Normalization. CoRR abs/1611.02525 (2016) - 2015
- [c1]Etai Littwin, Hadar Averbuch-Elor, Daniel Cohen-Or:
Spherical embedding of inlier silhouette dissimilarities. CVPR 2015: 3855-3863 - [i1]Etai Littwin, Lior Wolf:
The Multiverse Loss for Robust Transfer Learning. CoRR abs/1511.09033 (2015)
Coauthor Index
aka: Josh M. Susskind
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-25 22:44 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: