default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAvi Schwarzschild
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[j2]Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P. Dickerson, Pin-Yu Chen, Jeff Bilmes:
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective. Trans. Mach. Learn. Res. 2025 (2025)- [i34]Nayoung Lee, Ziyang Cai, Avi Schwarzschild, Kangwook Lee, Dimitris Papailiopoulos:
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges. CoRR abs/2502.01612 (2025) - [i33]Roman Levin, Valeriia Cherepanova, Abhimanyu Hans, Avi Schwarzschild, Tom Goldstein:
Has My System Prompt Been Used? Large Language Model Prompt Membership Inference. CoRR abs/2502.09974 (2025) - [i32]Yash Savani, Asher Trockman, Zhili Feng, Avi Schwarzschild, Alexander Robey, Marc Finzi, J. Zico Kolter:
Antidistillation Sampling. CoRR abs/2504.13146 (2025) - [i31]Zhili Feng, Yixuan Even Xu, Alexander Robey, Robert Kirk, Xander Davies, Yarin Gal, Avi Schwarzschild, J. Zico Kolter:
Existing Large Language Model Unlearning Evaluations Are Inconclusive. CoRR abs/2506.00688 (2025) - [i30]Ziyang Cai, Nayoung Lee, Avi Schwarzschild, Samet Oymak, Dimitris Papailiopoulos:
Extrapolation by Association: Length Generalization Transfer in Transformers. CoRR abs/2506.09251 (2025) - [i29]Barry Wang, Avi Schwarzschild, Alexander Robey, Ali Payani, Charles Fleming, Mingjie Sun, Daphne Ippolito:
Command-V: Pasting LLM Behaviors via Activation Profiles. CoRR abs/2506.19140 (2025) - 2024
- [c16]Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Universal Guidance for Diffusion Models. ICLR 2024 - [c15]Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
NEFTune: Noisy Embeddings Improve Instruction Finetuning. ICLR 2024 - [c14]Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. ICML 2024 - [c13]Mucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou, Tom Goldstein, John Langford, Animashree Anandkumar, Furong Huang:
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization. NeurIPS 2024 - [c12]Sean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Jonas Geiping, Avi Schwarzschild, Tom Goldstein:
Transformers Can Do Arithmetic with the Right Embeddings. NeurIPS 2024 - [c11]Avi Schwarzschild, Zhili Feng, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter:
Rethinking LLM Memorization through the Lens of Adversarial Compression. NeurIPS 2024 - [i28]Pratyush Maini, Zhili Feng, Avi Schwarzschild, Zachary C. Lipton, J. Zico Kolter:
TOFU: A Task of Fictitious Unlearning for LLMs. CoRR abs/2401.06121 (2024) - [i27]Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. CoRR abs/2401.12070 (2024) - [i26]Sean McLeish, Avi Schwarzschild, Tom Goldstein:
Benchmarking ChatGPT on Algorithmic Reasoning. CoRR abs/2404.03441 (2024) - [i25]Yiming Zhang, Avi Schwarzschild, Nicholas Carlini, Zico Kolter, Daphne Ippolito:
Forcing Diffuse Distributions out of Language Models. CoRR abs/2404.10859 (2024) - [i24]Avi Schwarzschild, Zhili Feng, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter:
Rethinking LLM Memorization through the Lens of Adversarial Compression. CoRR abs/2404.15146 (2024) - [i23]Sean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura
, Abhinav Bhatele, Jonas Geiping, Avi Schwarzschild, Tom Goldstein:
Transformers Can Do Arithmetic with the Right Embeddings. CoRR abs/2405.17399 (2024) - [i22]Larisa Markeeva, Sean McLeish, Borja Ibarz, Wilfried Bounsi, Olga Kozlova, Alex Vitvitskyi, Charles Blundell, Tom Goldstein, Avi Schwarzschild, Petar Velickovic:
The CLRS-Text Algorithmic Reasoning Language Benchmark. CoRR abs/2406.04229 (2024) - [i21]Joshua Nathaniel Williams, Avi Schwarzschild, J. Zico Kolter:
Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers. CoRR abs/2408.06502 (2024) - [i20]Mucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou, Tom Goldstein, John Langford, Anima Anandkumar, Furong Huang:
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization. CoRR abs/2409.18433 (2024) - 2023
- [b1]Avi Schwarzschild:
Deep Thinking Systems: Logical Extrapolation with Recurrent Neural Networks. University of Maryland, College Park, MD, USA, 2023 - [j1]Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein:
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses. IEEE Trans. Pattern Anal. Mach. Intell. 45(2): 1563-1580 (2023) - [c10]Avi Schwarzschild, Max Cembalest, Karthik Rao, Keegan Hines, John P. Dickerson:
Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective. AIES 2023: 662-678 - [c9]Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Universal Guidance for Diffusion Models. CVPR Workshops 2023: 843-852 - [c8]Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, Arpit Bansal, C. Bayan Bruss, Tom Goldstein, Andrew Gordon Wilson, Micah Goldblum:
Transfer Learning with Deep Tabular Models. ICLR 2023 - [i19]Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein:
Universal Guidance for Diffusion Models. CoRR abs/2302.07121 (2023) - [i18]Alex Stein, Avi Schwarzschild, Michael J. Curry, Tom Goldstein, John P. Dickerson:
Neural Auctions Compromise Bidder Information. CoRR abs/2303.00116 (2023) - [i17]Avi Schwarzschild, Max Cembalest, Karthik Rao, Keegan Hines, John P. Dickerson:
Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective. CoRR abs/2303.13299 (2023) - [i16]Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Grégoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum:
A Cookbook of Self-Supervised Learning. CoRR abs/2304.12210 (2023) - [i15]Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein:
Baseline Defenses for Adversarial Attacks Against Aligned Language Models. CoRR abs/2309.00614 (2023) - [i14]Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein:
NEFTune: Noisy Embeddings Improve Instruction Finetuning. CoRR abs/2310.05914 (2023) - [i13]Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P. Dickerson, Jeff A. Bilmes:
Effective Backdoor Mitigation Depends on the Pre-training Objective. CoRR abs/2311.14948 (2023) - 2022
- [c7]Avi Schwarzschild, Arjun Gupta, Amin Ghiasi, Micah Goldblum, Tom Goldstein:
The Uncanny Similarity of Recurrence and Depth. ICLR 2022 - [c6]Arpit Bansal, Avi Schwarzschild, Eitan Borgnia, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein:
End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking. NeurIPS 2022 - [i12]Arpit Bansal, Avi Schwarzschild, Eitan Borgnia, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein:
End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking. CoRR abs/2202.05826 (2022) - [i11]Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, Arpit Bansal, C. Bayan Bruss, Tom Goldstein, Andrew Gordon Wilson, Micah Goldblum:
Transfer Learning with Deep Tabular Models. CoRR abs/2206.15306 (2022) - 2021
- [c5]Micah Goldblum, Avi Schwarzschild, Ankit B. Patel, Tom Goldstein:
Adversarial attacks on machine learning systems for high-frequency trading. ICAIF 2021: 2:1-2:9 - [c4]Avi Schwarzschild, Micah Goldblum, Arjun Gupta, John P. Dickerson, Tom Goldstein:
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks. ICML 2021: 9389-9398 - [c3]Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, Tom Goldstein:
Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks. NeurIPS 2021: 6695-6706 - [i10]Avi Schwarzschild, Arjun Gupta, Micah Goldblum, Tom Goldstein:
Thinking Deeply with Recurrence: Generalizing from Easy to Hard Sequential Reasoning Problems. CoRR abs/2102.11011 (2021) - [i9]Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein:
SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training. CoRR abs/2106.01342 (2021) - [i8]Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, Tom Goldstein:
Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks. CoRR abs/2106.04537 (2021) - [i7]Arpit Bansal, Micah Goldblum, Valeriia Cherepanova, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein:
MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data. CoRR abs/2106.09643 (2021) - [i6]Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Arpit Bansal, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein:
Datasets for Studying Generalization from Easy to Hard Examples. CoRR abs/2108.06011 (2021) - 2020
- [c2]Ahmed Abdelkader, Michael J. Curry, Liam Fowl, Tom Goldstein, Avi Schwarzschild, Manli Shu, Christoph Studer, Chen Zhu:
Headless Horseman: Adversarial Attacks on Transfer Learning Models. ICASSP 2020: 3087-3091 - [c1]Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein:
Truth or backpropaganda? An empirical investigation of deep learning theory. ICLR 2020 - [i5]Micah Goldblum, Avi Schwarzschild, Naftali Cohen, Tucker Balch, Ankit B. Patel, Tom Goldstein:
Adversarial Attacks on Machine Learning Systems for High-Frequency Trading. CoRR abs/2002.09565 (2020) - [i4]Ahmed Abdelkader, Michael J. Curry, Liam Fowl, Tom Goldstein, Avi Schwarzschild, Manli Shu, Christoph Studer, Chen Zhu:
Headless Horseman: Adversarial Attacks on Transfer Learning Models. CoRR abs/2004.09007 (2020) - [i3]Avi Schwarzschild, Micah Goldblum, Arjun Gupta, John P. Dickerson, Tom Goldstein:
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks. CoRR abs/2006.12557 (2020) - [i2]Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein:
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses. CoRR abs/2012.10544 (2020)
2010 – 2019
- 2019
- [i1]Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein:
Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory. CoRR abs/1910.00359 (2019)
Coauthor Index
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 2025-10-22 03:34 CEST 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:
