Avi Schwarzschild

56 papers A* 13C 1Misc 1Journal 38Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Antidistillation Sampling. CoRR Yash Savani, Asher Trockman, Zhili Feng, Yixuan Even Xu, Avi Schwarzschild, Alexander Robey, Marc Finzi, J. Zico Kolter
2025	J	`jnl`	Command-V: Pasting LLM Behaviors via Activation Profiles. CoRR Barry Wang, Avi Schwarzschild, Alexander Robey, Ali Payani, Charles Fleming, Mingjie Sun, Daphne Ippolito
2025	J	`jnl`	Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective. Trans. Mach. Learn. Res. Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P. Dickerson, Pin-Yu Chen, Jeff A. Bilmes
2025	J	`jnl`	Existing Large Language Model Unlearning Evaluations Are Inconclusive. CoRR Zhili Feng, Yixuan Even Xu, Alexander Robey, Robert Kirk, Xander Davies, Yarin Gal, Avi Schwarzschild, J. Zico Kolter
2025	J	`jnl`	Extrapolation by Association: Length Generalization Transfer in Transformers. CoRR Ziyang Cai, Nayoung Lee, Avi Schwarzschild, Samet Oymak, Dimitris Papailiopoulos
2025	J	`jnl`	Has My System Prompt Been Used? Large Language Model Prompt Membership Inference. CoRR Roman Levin, Valeriia Cherepanova, Abhimanyu Hans, Avi Schwarzschild, Tom Goldstein
2025	A*	`conf`	Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges. ICML Nayoung Lee, Ziyang Cai, Avi Schwarzschild, Kangwook Lee, Dimitris Papailiopoulos
2025	J	`jnl`	Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges. CoRR Nayoung Lee, Ziyang Cai, Avi Schwarzschild, Kangwook Lee, Dimitris Papailiopoulos
2025	J	`jnl`	Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence. CoRR Sean McLeish, Ang Li, John Kirchenbauer, Dayal Singh Kalra, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Tom Goldstein, Micah Goldblum
2025	J	`jnl`	Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models. CoRR Sarah Ball, Niki Hasrati, Alexander Robey, Avi Schwarzschild, Frauke Kreuter, Zico Kolter, Andrej Risteski
2024	J	`jnl`	Benchmarking ChatGPT on Algorithmic Reasoning. CoRR Sean McLeish, Avi Schwarzschild, Tom Goldstein
2024	A*	`conf`	Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization. NeurIPS Mucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou, Tom Goldstein, John Langford, Animashree Anandkumar, Furong Huang
2024	J	`jnl`	Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization. CoRR Mucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou, Tom Goldstein, John Langford, Anima Anandkumar, Furong Huang
2024	J	`jnl`	Forcing Diffuse Distributions out of Language Models. CoRR Yiming Zhang, Avi Schwarzschild, Nicholas Carlini, Zico Kolter, Daphne Ippolito
2024	A*	`conf`	NEFTune: Noisy Embeddings Improve Instruction Finetuning. ICLR 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
2024	J	`jnl`	Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers. CoRR Joshua Nathaniel Williams, Avi Schwarzschild, J. Zico Kolter
2024	A*	`conf`	Rethinking LLM Memorization through the Lens of Adversarial Compression. NeurIPS Avi Schwarzschild, Zhili Feng, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter
2024	J	`jnl`	Rethinking LLM Memorization through the Lens of Adversarial Compression. CoRR Avi Schwarzschild, Zhili Feng, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter
2024	A*	`conf`	Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. ICML Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2024	J	`jnl`	Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. CoRR Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2024	J	`jnl`	TOFU: A Task of Fictitious Unlearning for LLMs. CoRR Pratyush Maini, Zhili Feng, Avi Schwarzschild, Zachary C. Lipton, J. Zico Kolter
2024	J	`jnl`	The CLRS-Text Algorithmic Reasoning Language Benchmark. CoRR Larisa Markeeva, Sean McLeish, Borja Ibarz, Wilfried Bounsi, Olga Kozlova, Alex Vitvitskyi, Charles Blundell, Tom Goldstein, Avi Schwarzschild, Petar Velickovic
2024	A*	`conf`	Transformers Can Do Arithmetic with the Right Embeddings. NeurIPS Sean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Jonas Geiping, Avi Schwarzschild, Tom Goldstein
2024	J	`jnl`	Transformers Can Do Arithmetic with the Right Embeddings. CoRR Sean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Jonas Geiping, Avi Schwarzschild, Tom Goldstein
2024	A*	`conf`	Universal Guidance for Diffusion Models. ICLR Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	A Cookbook of Self-Supervised Learning. CoRR 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
2023	J	`jnl`	Baseline Defenses for Adversarial Attacks Against Aligned Language Models. CoRR Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-Yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses. IEEE Trans. Pattern Anal. Mach. Intell. Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein
2023	—	`—`	Deep Thinking Systems: Logical Extrapolation with Recurrent Neural Networks. Avi Schwarzschild
2023	J	`jnl`	Effective Backdoor Mitigation Depends on the Pre-training Objective. CoRR Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P. Dickerson, Jeff A. Bilmes
2023	J	`jnl`	NEFTune: Noisy Embeddings Improve Instruction Finetuning. CoRR 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
2023	J	`jnl`	Neural Auctions Compromise Bidder Information. CoRR Alex Stein, Avi Schwarzschild, Michael J. Curry, Tom Goldstein, John P. Dickerson
2023	C	`conf`	Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective. AIES Avi Schwarzschild, Max Cembalest, Karthik Rao, Keegan Hines, John P. Dickerson
2023	J	`jnl`	Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective. CoRR Avi Schwarzschild, Max Cembalest, Karthik Rao, Keegan Hines, John P. Dickerson
2023	A*	`conf`	Transfer Learning with Deep Tabular Models. ICLR Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, Arpit Bansal, C. Bayan Bruss, Tom Goldstein, Andrew Gordon Wilson, Micah Goldblum
2023	—	`conf`	Universal Guidance for Diffusion Models. CVPR Workshops Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	Universal Guidance for Diffusion Models. CoRR Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein
2022	A*	`conf`	End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking. NeurIPS Arpit Bansal, Avi Schwarzschild, Eitan Borgnia, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking. CoRR Arpit Bansal, Avi Schwarzschild, Eitan Borgnia, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein
2022	A*	`conf`	The Uncanny Similarity of Recurrence and Depth. ICLR Avi Schwarzschild, Arjun Gupta, Amin Ghiasi, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	Transfer Learning with Deep Tabular Models. CoRR Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, Arpit Bansal, C. Bayan Bruss, Tom Goldstein, Andrew Gordon Wilson, Micah Goldblum
2021	—	`conf`	Adversarial attacks on machine learning systems for high-frequency trading. ICAIF Micah Goldblum, Avi Schwarzschild, Ankit B. Patel, Tom Goldstein
2021	A*	`conf`	Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks. NeurIPS Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, Tom Goldstein
2021	J	`jnl`	Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks. CoRR Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, Tom Goldstein
2021	J	`jnl`	Datasets for Studying Generalization from Easy to Hard Examples. CoRR Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Arpit Bansal, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein
2021	A*	`conf`	Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks. ICML Avi Schwarzschild, Micah Goldblum, Arjun Gupta, John P. Dickerson, Tom Goldstein
2021	J	`jnl`	MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data. CoRR Arpit Bansal, Micah Goldblum, Valeriia Cherepanova, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein
2021	J	`jnl`	SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training. CoRR Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein
2021	J	`jnl`	Thinking Deeply with Recurrence: Generalizing from Easy to Hard Sequential Reasoning Problems. CoRR Avi Schwarzschild, Arjun Gupta, Micah Goldblum, Tom Goldstein
2020	J	`jnl`	Adversarial Attacks on Machine Learning Systems for High-Frequency Trading. CoRR Micah Goldblum, Avi Schwarzschild, Naftali Cohen, Tucker Balch, Ankit B. Patel, Tom Goldstein
2020	J	`jnl`	Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses. CoRR Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein
2020	Misc	`conf`	Headless Horseman: Adversarial Attacks on Transfer Learning Models. ICASSP Ahmed Abdelkader, Michael J. Curry, Liam Fowl, Tom Goldstein, Avi Schwarzschild, Manli Shu, Christoph Studer, Chen Zhu
2020	J	`jnl`	Headless Horseman: Adversarial Attacks on Transfer Learning Models. CoRR Ahmed Abdelkader, Michael J. Curry, Liam Fowl, Tom Goldstein, Avi Schwarzschild, Manli Shu, Christoph Studer, Chen Zhu
2020	J	`jnl`	Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks. CoRR Avi Schwarzschild, Micah Goldblum, Arjun Gupta, John P. Dickerson, Tom Goldstein
2020	A*	`conf`	Truth or backpropaganda? An empirical investigation of deep learning theory. ICLR Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein
2019	J	`jnl`	Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory. CoRR Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein