Micah Goldblum

184 papers A* 60C 1Misc 4Journal 111Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding. CoRR Rahul Krishna Thomas, Teo Kitanovski, Micah Goldblum, Arka Pal
2026	J	`jnl`	Multi-Token Prediction via Self-Distillation. CoRR John Kirchenbauer, Abhimanyu Hans, Brian R. Bartoldson, Micah Goldblum, Ashwinee Panda, Tom Goldstein
2026	J	`jnl`	Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs. CoRR Arka Pal, Louai Zahran, William Gvozdjak, Akilesh Potti, Micah Goldblum
2025	A*	`conf`	Adaptive Retention & Correction: Test-Time Training for Continual Learning. ICLR Haoran Chen, Micah Goldblum, Zuxuan Wu, Yu-Gang Jiang
2025	J	`jnl`	An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs. CoRR Rahul Krishna Thomas, Louai Zahran, Erica Choi, Akilesh Potti, Micah Goldblum, Arka Pal
2025	J	`jnl`	Cascade: Token-Sharded Private LLM Inference. CoRR Rahul Krishna Thomas, Louai Zahran, Erica Choi, Akilesh Potti, Micah Goldblum, Arka Pal
2025	J	`jnl`	Closing the Train-Test Gap in World Models for Gradient-Based Planning. CoRR Arjun Parthasarathy, Nimit Kalra, Rohun Agrawal, Yann LeCun, Oumayma Bounou, Pavel Izmailov, Micah Goldblum
2025	J	`jnl`	Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks. CoRR Ang Li, Yin Zhou, Vethavikashini Chithrra Raghuram, Tom Goldstein, Micah Goldblum
2025	J	`jnl`	Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement. CoRR Linyang He, Tianjun Zhong, Richard J. Antonello, Gavin Mischler, Micah Goldblum, Nima Mesgarani
2025	J	`jnl`	FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges. CoRR Kevin David Hayes, Micah Goldblum, Vikash Sehwag, Gowthami Somepalli, Ashwinee Panda, Tom Goldstein
2025	J	`jnl`	Gemstones: A Model Suite for Multi-Faceted Scaling Laws. CoRR Sean McLeish, John Kirchenbauer, David Yu Miller, Siddharth Singh, Abhinav Bhatele, Micah Goldblum, Ashwinee Panda, Tom Goldstein
2025	A*	`conf`	Hidden No More: Attacking and Defending Private Third-Party LLM Inference. ICML Rahul Krishna Thomas, Louai Zahran, Erica Choi, Akilesh Potti, Micah Goldblum, Arka Pal
2025	J	`jnl`	Incoherent Beliefs & Inconsistent Actions in Large Language Models. CoRR Arka Pal, Teo Kitanovski, Arthur Liang, Akilesh Potti, Micah Goldblum
2025	—	`conf`	LLM-Generated Passphrases That Are Secure and Easy to Remember. NAACL (Findings) Jie S. Li, Jonas Geiping, Micah Goldblum, Aniruddha Saha, Tom Goldstein
2025	A*	`conf`	LiveBench: A Challenging, Contamination-Limited LLM Benchmark. ICLR Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Benjamin Feuer, Siddhartha Jain, Ravid Shwartz-Ziv, Neel Jain, Khalid Saifullah, Sreemanti Dey, Shubh-Agrawal, Sandeep Singh Sandha, Siddartha V. Naidu, Chinmay Hegde, Yann LeCun, Tom Goldstein, Willie Neiswanger, Micah Goldblum
2025	J	`jnl`	Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning. CoRR Haoran Chen, Houze Xu, Micah Goldblum, Daoguo Dong, Zuxuan Wu
2025	J	`jnl`	Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful. CoRR Martin Marek, Sanae Lotfi, Aditya Somasundaram, Andrew Gordon Wilson, Micah Goldblum
2025	A*	`conf`	Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking. ICLR Benjamin Feuer, Micah Goldblum, Teresa Datta, Sanjana Nambiar, Raz Besaleli, Samuel Dooley, Max Cembalest, John P. Dickerson
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`	The Role of ViT Design and Training in Robustness to Common Corruptions. IEEE Trans. Multim. Rui Tian, Zuxuan Wu, Qi Dai, Micah Goldblum, Han Hu, Yu-Gang Jiang
2025	J	`jnl`	Transformers Boost the Performance of Decision Trees on Tabular Data across Sample Sizes. CoRR Mayuka Jayawardhana, Renbo Tu, Samuel Dooley, Valeriia Cherepanova, Andrew Gordon Wilson, Frank Hutter, Colin White, Tom Goldstein, Micah Goldblum
2025	J	`jnl`	Using Attention Sinks to Identify and Evaluate Dormant Heads in Pretrained LLMs. CoRR Pedro Sandoval Segura, Xijun Wang, Ashwinee Panda, Micah Goldblum, Ronen Basri, Tom Goldstein, David Jacobs
2025	J	`jnl`	Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning. CoRR Ang Li, Charles Wang, Kaiyu Yue, Zikui Cai, Ollie Liu, Deqing Fu, Peng Guo, Wang Bill Zhu, Vatsal Sharan, Robin Jia, Willie Neiswanger, Furong Huang, Tom Goldstein, Micah Goldblum
2024	J	`jnl`	A Simple Baseline for Predicting Events with Auto-Regressive Tabular Transformers. CoRR Alex Stein, Samuel Sharpe, Doron Bergman, Senthil Kumar, C. Bayan Bruss, John Dickerson, Tom Goldstein, Micah Goldblum
2024	J	`jnl`	Adaptive Rentention & Correction for Continual Learning. CoRR Haoran Chen, Micah Goldblum, Zuxuan Wu, Yu-Gang Jiang
2024	A*	`conf`	Compute Better Spent: Replacing Dense Layers with Structured Matrices. ICML Shikai Qiu, Andres Potapczynski, Marc Anton Finzi, Micah Goldblum, Andrew Gordon Wilson
2024	J	`jnl`	Compute Better Spent: Replacing Dense Layers with Structured Matrices. CoRR Shikai Qiu, Andres Potapczynski, Marc Finzi, Micah Goldblum, Andrew Gordon Wilson
2024	J	`jnl`	Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion. CoRR Hossein Souri, Arpit Bansal, Hamid Kazemi, Liam Fowl, Aniruddha Saha, Jonas Geiping, Andrew Gordon Wilson, Rama Chellappa, Tom Goldstein, Micah Goldblum
2024	Misc	`conf`	Identifying Attack-Specific Signatures in Adversarial Examples. ICASSP Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau, Micah Goldblum, Rama Chellappa
2024	—	`conf`	Investigating Style Similarity in Diffusion Models. ECCV (66) Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, Tom Goldstein
2024	J	`jnl`	Just How Flexible are Neural Networks in Practice? CoRR Ravid Shwartz-Ziv, Micah Goldblum, Arpit Bansal, C. Bayan Bruss, Yann LeCun, Andrew Gordon Wilson
2024	A*	`conf`	Large Language Models Must Be Taught to Know What They Don't Know. NeurIPS Sanyam Kapoor, Nate Gruver, Manley Roberts, Katie Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, Andrew Gordon Wilson
2024	J	`jnl`	Large Language Models Must Be Taught to Know What They Don't Know. CoRR Sanyam Kapoor, Nate Gruver, Manley Roberts, Katherine M. Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, Andrew Gordon Wilson
2024	J	`jnl`	LiveBench: A Challenging, Contamination-Free LLM Benchmark. CoRR Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Benjamin Feuer, Siddhartha Jain, Ravid Shwartz-Ziv, Neel Jain, Khalid Saifullah, Siddartha Naidu, Chinmay Hegde, Yann LeCun, Tom Goldstein, Willie Neiswanger, Micah Goldblum
2024	J	`jnl`	Measuring Style Similarity in Diffusion Models. CoRR Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, Tom Goldstein
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	A*	`conf`	Non-Vacuous Generalization Bounds for Large Language Models. ICML Sanae Lotfi, Marc Anton Finzi, Yilun Kuang, Tim G. J. Rudner, Micah Goldblum, Andrew Gordon Wilson
2024	A*	`conf`	On the Reliability of Watermarks for Large Language Models. ICLR John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein
2024	A*	`conf`	Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning. ICML Micah Goldblum, Marc Anton Finzi, Keefer Rowan, Andrew Gordon Wilson
2024	J	`jnl`	Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models. CoRR Neel Jain, Aditya Shrivastava, Chen Zhu, Daben Liu, Alfy Samuel, Ashwinee Panda, Anoop Kumar, Micah Goldblum, Tom Goldstein
2024	A*	`conf`	Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices. NeurIPS Andres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Charlie Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson
2024	J	`jnl`	Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices. CoRR Andres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Zixi Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson
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`	Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking. CoRR Benjamin Feuer, Micah Goldblum, Teresa Datta, Sanjana Nambiar, Raz Besaleli, Samuel Dooley, Max Cembalest, John P. Dickerson
2024	A*	`conf`	TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks. NeurIPS Benjamin Feuer, Robin Schirrmeister, Valeriia Cherepanova, Chinmay Hegde, Frank Hutter, Micah Goldblum, Niv Cohen, Colin White
2024	J	`jnl`	TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks. CoRR Benjamin Feuer, Robin Tibor Schirrmeister, Valeriia Cherepanova, Chinmay Hegde, Frank Hutter, Micah Goldblum, Niv Cohen, Colin White
2024	A*	`conf`	Universal Guidance for Diffusion Models. ICLR Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein
2024	A*	`conf`	Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models. NeurIPS Sanae Lotfi, Yilun Kuang, Marc Finzi, Brandon Amos, Micah Goldblum, Andrew Gordon Wilson
2024	J	`jnl`	Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models. CoRR Sanae Lotfi, Yilun Kuang, Brandon Amos, Micah Goldblum, Marc Finzi, Andrew Gordon Wilson
2024	J	`jnl`	vTune: Verifiable Fine-Tuning for LLMs Through Backdooring. CoRR Eva Zhang, Arka Pal, Akilesh Potti, Micah Goldblum
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	C	`conf`	A Deep Dive into Dataset Imbalance and Bias in Face Identification. AIES Valeriia Cherepanova, Steven Reich, Samuel Dooley, Hossein Souri, John P. Dickerson, Micah Goldblum, Tom Goldstein
2023	A*	`conf`	A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning. NeurIPS Valeriia Cherepanova, Roman Levin, Gowthami Somepalli, Jonas Geiping, C. Bayan Bruss, Andrew Gordon Wilson, Tom Goldstein, Micah Goldblum
2023	J	`jnl`	A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning. CoRR Valeriia Cherepanova, Roman Levin, Gowthami Somepalli, Jonas Geiping, C. Bayan Bruss, Andrew Gordon Wilson, Tom Goldstein, Micah Goldblum
2023	J	`jnl`	A Simple and Efficient Baseline for Data Attribution on Images. CoRR Vasu Singla, Pedro Sandoval Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein
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	A*	`conf`	Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks. NeurIPS Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithvijit Chattopadhyay, Mark Ibrahim, Adrien Bardes, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein
2023	J	`jnl`	Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks. CoRR Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithvijit Chattopadhyay, Mark Ibrahim, Adrien Bardes, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein
2023	J	`jnl`	Bring Your Own Data! Self-Supervised Evaluation for Large Language Models. CoRR Neel Jain, Khalid Saifullah, Yuxin Wen, John Kirchenbauer, Manli Shu, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	A*	`conf`	Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries. ICLR Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	A*	`conf`	Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise. NeurIPS Arpit Bansal, Eitan Borgnia, Hong-Min Chu, Jie Li, Hamid Kazemi, Furong Huang, Micah Goldblum, 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	A*	`conf`	Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models. ICLR Liam H. Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojciech Czaja, Micah Goldblum, Tom Goldstein
2023	A*	`conf`	Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models. CVPR Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	A*	`conf`	Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness. ICLR Yuancheng Xu, Yanchao Sun, Micah Goldblum, Tom Goldstein, Furong Huang
2023	J	`jnl`	Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness. CoRR Yuancheng Xu, Yanchao Sun, Micah Goldblum, Tom Goldstein, Furong Huang
2023	A*	`conf`	Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery. NeurIPS Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery. CoRR Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	A*	`conf`	How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization. ICLR Jonas Geiping, Micah Goldblum, Gowthami Somepalli, Ravid Shwartz-Ziv, Tom Goldstein, Andrew Gordon Wilson
2023	A*	`conf`	Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent. ICLR Ping-Yeh Chiang, Renkun Ni, David Yu Miller, Arpit Bansal, Jonas Geiping, Micah Goldblum, Tom Goldstein
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`	Non-Vacuous Generalization Bounds for Large Language Models. CoRR Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner, Micah Goldblum, Andrew Gordon Wilson
2023	J	`jnl`	On the Reliability of Watermarks for Large Language Models. CoRR John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein
2023	A*	`conf`	Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation. ICLR Hong-Min Chu, Jonas Geiping, Liam H. Fowl, Micah Goldblum, Tom Goldstein
2023	J	`jnl`	Perspectives on the State and Future of Deep Learning - 2023. CoRR Micah Goldblum, Anima Anandkumar, Richard G. Baraniuk, Tom Goldstein, Kyunghyun Cho, Zachary C. Lipton, Melanie Mitchell, Preetum Nakkiran, Max Welling, Andrew Gordon Wilson
2023	A*	`conf`	Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition. NeurIPS Samuel Dooley, Rhea Sanjay Sukthanker, John P. Dickerson, Colin White, Frank Hutter, Micah Goldblum
2023	Misc	`conf`	STYX: Adaptive Poisoning Attacks Against Byzantine-Robust Defenses in Federated Learning. ICASSP Yuxin Wen, Jonas Geiping, Micah Goldblum, Tom Goldstein
2023	—	`conf`	Seeing in Words: Learning to Classify through Language Bottlenecks. Tiny Papers @ ICLR Khalid Saifullah, Yuxin Wen, Jonas Geiping, Micah Goldblum, Tom Goldstein
2023	J	`jnl`	Seeing in Words: Learning to Classify through Language Bottlenecks. CoRR Khalid Saifullah, Yuxin Wen, Jonas Geiping, Micah Goldblum, Tom Goldstein
2023	A*	`conf`	Simplifying Neural Network Training Under Class Imbalance. NeurIPS Ravid Shwartz-Ziv, Micah Goldblum, Yucen Lily Li, C. Bayan Bruss, Andrew Gordon Wilson
2023	J	`jnl`	Simplifying Neural Network Training Under Class Imbalance. CoRR Ravid Shwartz-Ziv, Micah Goldblum, Yucen Lily Li, C. Bayan Bruss, Andrew Gordon Wilson
2023	A*	`conf`	The Lie Derivative for Measuring Learned Equivariance. ICLR Nate Gruver, Marc Anton Finzi, Micah Goldblum, Andrew Gordon Wilson
2023	J	`jnl`	The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning. CoRR Micah Goldblum, Marc Finzi, Keefer Rowan, Andrew Gordon Wilson
2023	J	`jnl`	Towards Transferable Adversarial Attacks on Image and Video Transformers. IEEE Trans. Image Process. Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu, Tom Goldstein, Yu-Gang Jiang, Larry S. Davis
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	A*	`conf`	Understanding and Mitigating Copying in Diffusion Models. NeurIPS Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	Understanding and Mitigating Copying in Diffusion Models. CoRR Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein
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
2023	A*	`conf`	What Can We Learn from Unlearnable Datasets? NeurIPS Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein
2023	J	`jnl`	What Can We Learn from Unlearnable Datasets? CoRR Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein
2023	A*	`conf`	When Do Neural Nets Outperform Boosted Trees on Tabular Data? NeurIPS Duncan C. McElfresh, Sujay Khandagale, Jonathan Valverde, Vishak Prasad C., Ganesh Ramakrishnan, Micah Goldblum, Colin White
2023	J	`jnl`	When Do Neural Nets Outperform Boosted Trees on Tabular Data? CoRR Duncan C. McElfresh, Sujay Khandagale, Jonathan Valverde, Vishak Prasad C., Ganesh Ramakrishnan, Micah Goldblum, Colin White
2022	J	`jnl`	A Deep Dive into Dataset Imbalance and Bias in Face Identification. CoRR Valeriia Cherepanova, Steven Reich, Samuel Dooley, Hossein Souri, Micah Goldblum, Tom Goldstein
2022	A*	`conf`	Autoregressive Perturbations for Data Poisoning. NeurIPS Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein, David Jacobs
2022	J	`jnl`	Autoregressive Perturbations for Data Poisoning. CoRR Pedro Sandoval Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein, David W. Jacobs
2022	A*	`conf`	Bayesian Model Selection, the Marginal Likelihood, and Generalization. ICML Sanae Lotfi, Pavel Izmailov, Gregory W. Benton, Micah Goldblum, Andrew Gordon Wilson
2022	J	`jnl`	Bayesian Model Selection, the Marginal Likelihood, and Generalization. CoRR Sanae Lotfi, Pavel Izmailov, Gregory W. Benton, Micah Goldblum, Andrew Gordon Wilson
2022	A*	`conf`	Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective. CVPR Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping-Yeh Chiang, Yehuda Dar, Richard G. Baraniuk, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective. CoRR Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping-Yeh Chiang, Yehuda Dar, Richard G. Baraniuk, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries. CoRR Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, Tom Goldstein
2022	A*	`conf`	Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers. NeurIPS Wanqian Yang, Polina Kirichenko, Micah Goldblum, Andrew Gordon Wilson
2022	J	`jnl`	Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers. CoRR Wanqian Yang, Polina Kirichenko, Micah Goldblum, Andrew Gordon Wilson
2022	J	`jnl`	Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise. CoRR Arpit Bansal, Eitan Borgnia, Hong-Min Chu, Jie S. Li, Hamid Kazemi, Furong Huang, Micah Goldblum, Jonas Geiping, Tom Goldstein
2022	J	`jnl`	Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models. CoRR Liam Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojtek Czaja, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models. CoRR Gowthami Somepalli, Vasu Singla, 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`	Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification. ICML Yuxin Wen, Jonas Geiping, Liam Fowl, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification. CoRR Yuxin Wen, Jonas Geiping, Liam Fowl, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization. CoRR Jonas Geiping, Micah Goldblum, Gowthami Somepalli, Ravid Shwartz-Ziv, Tom Goldstein, Andrew Gordon Wilson
2022	J	`jnl`	K-SAM: Sharpness-Aware Minimization at the Speed of SGD. CoRR Renkun Ni, Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein
2022	J	`jnl`	On the Importance of Architectures and Hyperparameters for Fairness in Face Recognition. CoRR Rhea Sanjay Sukthanker, Samuel Dooley, John P. Dickerson, Colin White, Frank Hutter, Micah Goldblum
2022	A*	`conf`	PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization. NeurIPS Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson
2022	J	`jnl`	PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization. CoRR Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson
2022	A*	`conf`	Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations. ICML Amin Ghiasi, Hamid Kazemi, Steven Reich, Chen Zhu, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations. CoRR Amin Ghiasi, Hamid Kazemi, Steven Reich, Chen Zhu, Micah Goldblum, Tom Goldstein
2022	—	`conf`	Poisons that are learned faster are more effective. CVPR Workshops Pedro Sandoval Segura, Vasu Singla, Liam Fowl, Jonas Geiping, Micah Goldblum, David Jacobs, Tom Goldstein
2022	J	`jnl`	Poisons that are learned faster are more effective. CoRR Pedro Sandoval Segura, Vasu Singla, Liam Fowl, Jonas Geiping, Micah Goldblum, David Jacobs, Tom Goldstein
2022	A*	`conf`	Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors. NeurIPS Ravid Shwartz-Ziv, Micah Goldblum, Hossein Souri, Sanyam Kapoor, Chen Zhu, Yann LeCun, Andrew Gordon Wilson
2022	J	`jnl`	Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors. CoRR Ravid Shwartz-Ziv, Micah Goldblum, Hossein Souri, Sanyam Kapoor, Chen Zhu, Yann LeCun, Andrew Gordon Wilson
2022	A*	`conf`	Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models. ICLR Liam H. Fowl, Jonas Geiping, Wojciech Czaja, Micah Goldblum, Tom Goldstein
2022	A*	`conf`	Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch. NeurIPS Hossein Souri, Liam Fowl, Rama Chellappa, Micah Goldblum, Tom Goldstein
2022	A*	`conf`	Stochastic Training is Not Necessary for Generalization. ICLR Jonas Geiping, Micah Goldblum, Phillip Pope, Michael Moeller, Tom Goldstein
2022	A*	`conf`	The Close Relationship Between Contrastive Learning and Meta-Learning. ICLR Renkun Ni, Manli Shu, Hossein Souri, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	The Lie Derivative for Measuring Learned Equivariance. CoRR Nate Gruver, Marc Finzi, Micah Goldblum, Andrew Gordon Wilson
2022	A*	`conf`	The Uncanny Similarity of Recurrence and Depth. ICLR Avi Schwarzschild, Arjun Gupta, Amin Ghiasi, Micah Goldblum, Tom Goldstein
2022	J	`jnl`	Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning. CoRR Yuxin Wen, Jonas Geiping, Liam Fowl, Hossein Souri, Rama Chellappa, Micah Goldblum, Tom Goldstein
2022	A*	`conf`	Towards Transferable Adversarial Attacks on Vision Transformers. AAAI Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu, Tom Goldstein, Yu-Gang Jiang
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
2022	J	`jnl`	What do Vision Transformers Learn? A Visual Exploration. CoRR Amin Ghiasi, Hamid Kazemi, Eitan Borgnia, Steven Reich, Manli Shu, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein
2022	A*	`conf`	Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability. NeurIPS Roman Levin, Manli Shu, Eitan Borgnia, Furong Huang, Micah Goldblum, Tom Goldstein
2021	J	`jnl`	Active Learning at the ImageNet Scale. CoRR Zeyad Ali Sami Emam, Hong-Min Chu, Ping-Yeh Chiang, Wojciech Czaja, Richard Leapman, Micah Goldblum, Tom Goldstein
2021	A*	`conf`	Adversarial Examples Make Strong Poisons. NeurIPS Liam Fowl, Micah Goldblum, Ping-Yeh Chiang, Jonas Geiping, Wojciech Czaja, Tom Goldstein
2021	J	`jnl`	Adversarial Examples Make Strong Poisons. CoRR Liam Fowl, Micah Goldblum, Ping-Yeh Chiang, Jonas Geiping, Wojtek Czaja, Tom Goldstein
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`	Comparing Human and Machine Bias in Face Recognition. CoRR Samuel Dooley, Ryan Downing, George Z. Wei, Nathan Shankar, Bradon Thymes, Gudrun Thorkelsdottir, Tiye Kurtz-Miott, Rachel Mattson, Olufemi Obiwumi, Valeriia Cherepanova, Micah Goldblum, John P. Dickerson, Tom Goldstein
2021	J	`jnl`	DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations. CoRR Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, Tom Goldstein
2021	A*	`conf`	Data Augmentation for Meta-Learning. ICML Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, 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`	Encoding Robustness to Image Style via Adversarial Feature Perturbations. NeurIPS Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein
2021	J	`jnl`	Identification of Attack-Specific Signatures in Adversarial Examples. CoRR Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau, Micah Goldblum, Rama Chellappa
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	A*	`conf`	LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition. ICLR Valeriia Cherepanova, Micah Goldblum, Harrison Foley, Shiyuan Duan, John P. Dickerson, Gavin Taylor, Tom Goldstein
2021	J	`jnl`	LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition. CoRR Valeriia Cherepanova, Micah Goldblum, Harrison Foley, Shiyuan Duan, John P. Dickerson, Gavin Taylor, 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`	Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release. CoRR Liam Fowl, Ping-Yeh Chiang, Micah Goldblum, Jonas Geiping, Arpit Bansal, Wojtek Czaja, Tom Goldstein
2021	J	`jnl`	Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models. CoRR Liam Fowl, Jonas Geiping, Wojtek Czaja, Micah Goldblum, 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`	Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch. CoRR Hossein Souri, Micah Goldblum, Liam Fowl, Rama Chellappa, Tom Goldstein
2021	J	`jnl`	Stochastic Training is Not Necessary for Generalization. CoRR Jonas Geiping, Micah Goldblum, Phillip E. Pope, Michael Moeller, Tom Goldstein
2021	Misc	`conf`	Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff. ICASSP Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Arjun Gupta
2021	J	`jnl`	Technical Challenges for Training Fair Neural Networks. CoRR Valeriia Cherepanova, Vedant Nanda, Micah Goldblum, John P. Dickerson, Tom Goldstein
2021	A*	`conf`	The Intrinsic Dimension of Images and Its Impact on Learning. ICLR Phillip Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein
2021	J	`jnl`	The Intrinsic Dimension of Images and Its Impact on Learning. CoRR Phillip Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, 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
2021	J	`jnl`	Towards Transferable Adversarial Attacks on Vision Transformers. CoRR Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu, Tom Goldstein, Yu-Gang Jiang
2021	J	`jnl`	What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors. CoRR Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, Tom Goldstein
2021	J	`jnl`	Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability. CoRR Roman Levin, Manli Shu, Eitan Borgnia, Furong Huang, 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	—	`—`	Adversarial Robustness and Robust Meta-Learning for Neural Networks. Micah Goldblum
2020	A*	`conf`	Adversarially Robust Distillation. AAAI Micah Goldblum, Liam Fowl, Soheil Feizi, Tom Goldstein
2020	A*	`conf`	Adversarially Robust Few-Shot Learning: A Meta-Learning Approach. NeurIPS Micah Goldblum, Liam Fowl, Tom Goldstein
2020	J	`jnl`	An Open Review of OpenReview: A Critical Analysis of the Machine Learning Conference Review Process. CoRR David Tran, Alex Valtchanov, Keshav Ganapathy, Raymond Feng, Eric Slud, Micah Goldblum, Tom Goldstein
2020	J	`jnl`	Analyzing the Machine Learning Conference Review Process. CoRR David Tran, Alex Valtchanov, Keshav Ganapathy, Raymond Feng, Eric Slud, Micah Goldblum, Tom Goldstein
2020	J	`jnl`	Data Augmentation for Meta-Learning. CoRR Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, 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	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	J	`jnl`	Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization. CoRR Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein
2020	J	`jnl`	Random Network Distillation as a Diversity Metric for Both Image and Text Generation. CoRR Liam Fowl, Micah Goldblum, Arjun Gupta, Amr Sharaf, Tom Goldstein
2020	J	`jnl`	Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff. CoRR Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Arjun Gupta
2020	A*	`conf`	Truth or backpropaganda? An empirical investigation of deep learning theory. ICLR Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein
2020	—	`conf`	Understanding Generalization Through Visualizations. ICBINB@NeurIPS W. Ronny Huang, Zeyad Emam, Micah Goldblum, Liam Fowl, J. K. Terry, Furong Huang, Tom Goldstein
2020	A*	`conf`	Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks. ICML Micah Goldblum, Steven Reich, Liam Fowl, Renkun Ni, Valeriia Cherepanova, Tom Goldstein
2020	J	`jnl`	Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks. CoRR Micah Goldblum, Steven Reich, Liam Fowl, Renkun Ni, Valeriia Cherepanova, Tom Goldstein
2020	Misc	`conf`	Witchcraft: Efficient PGD Attacks with Random Step Size. ICASSP Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum, Tom Goldstein, Renkun Ni, Steven Reich, Ali Shafahi
2019	J	`jnl`	Adversarially Robust Distillation. CoRR Micah Goldblum, Liam Fowl, Soheil Feizi, Tom Goldstein
2019	J	`jnl`	Robust Few-Shot Learning with Adversarially Queried Meta-Learners. CoRR Micah Goldblum, Liam Fowl, 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
2019	J	`jnl`	Understanding Generalization through Visualizations. CoRR W. Ronny Huang, Zeyad Emam, Micah Goldblum, Liam Fowl, J. K. Terry, Furong Huang, Tom Goldstein
2019	J	`jnl`	WITCHcraft: Efficient PGD attacks with random step size. CoRR Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum, Tom Goldstein, Renkun Ni, Steven Reich, Ali Shafahi