Pedro Sandoval Segura

20 papers A* 2Journal 14Unranked 4

Year	Rank	Type	Title / Venue / Authors
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
2024	J	`jnl`	DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments. CoRR Xijun Wang, Pedro Sandoval Segura, Chengyuan Zhang, Junyun Huang, Tianrui Guan, Ruiqi Xian, Fuxiao Liu, Rohan Chandra, Boqing Gong, Dinesh Manocha
2024	J	`jnl`	Learning from Convolution-based Unlearnable Datastes. CoRR Dohyun Kim, Pedro Sandoval Segura
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`	JPEG Compressed Images Can Bypass Protections Against AI Editing. CoRR Pedro Sandoval Segura, 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
2022	J	`jnl`	Adversarially robust segmentation models learn perceptually-aligned gradients. CoRR Pedro Sandoval Segura
2022	J	`jnl`	AutoProtoNet: Interpretability for Prototypical Networks. CoRR Pedro Sandoval Segura, Wallace Lawson
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	—	`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
2020	—	`conf`	An Information-Theoretic Perspective on Overfitting and Underfitting. Australasian Conference on Artificial Intelligence Daniel Bashir, George D. Montañez, Sonia Sehra, Pedro Sandoval Segura, Julius Lauw
2020	J	`jnl`	An Information-Theoretic Perspective on Overfitting and Underfitting. CoRR Daniel Bashir, George D. Montañez, Sonia Sehra, Pedro Sandoval Segura, Julius Lauw
2020	—	`conf`	The Labeling Distribution Matrix (LDM): A Tool for Estimating Machine Learning Algorithm Capacity. ICAART (2) Pedro Sandoval Segura, Julius Lauw, Daniel Bashir, Kinjal Shah, Sonia Sehra, Dominique Macias, George D. Montañez
2019	—	`conf`	Harvey Mudd College at SemEval-2019 Task 4: The Clint Buchanan Hyperpartisan News Detector. SemEval@NAACL-HLT Mehdi Drissi, Pedro Sandoval Segura, Vivaswat Ojha, Julie Medero
2019	J	`jnl`	Harvey Mudd College at SemEval-2019 Task 4: The Clint Buchanan Hyperpartisan News Detector. CoRR Mehdi Drissi, Pedro Sandoval Segura, Vivaswat Ojha, Julie Medero
2019	J	`jnl`	The Labeling Distribution Matrix (LDM): A Tool for Estimating Machine Learning Algorithm Capacity. CoRR Pedro Sandoval Segura, Julius Lauw, Daniel Bashir, Kinjal Shah, Sonia Sehra, Dominique Macias, George D. Montañez
2018	J	`jnl`	Program Language Translation Using a Grammar-Driven Tree-to-Tree Model. CoRR Mehdi Drissi, Olivia Watkins, Aditya Khant, Vivaswat Ojha, Pedro Sandoval Segura, Rakia Segev, Eric Weiner, Robert Keller