Alert button
Picture for Greg Ver Steeg

Greg Ver Steeg

Alert button

Prompt Perturbation Consistency Learning for Robust Language Models

Feb 24, 2024
Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, Aram Galstyan

Viaarxiv icon

Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding

Feb 14, 2024
Alessandro Achille, Greg Ver Steeg, Tian Yu Liu, Matthew Trager, Carson Klingenberg, Stefano Soatto

Viaarxiv icon

Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks

Dec 22, 2023
Haz Sameen Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong

Viaarxiv icon

Interpretable Diffusion via Information Decomposition

Oct 12, 2023
Xianghao Kong, Ollie Liu, Han Li, Dani Yogatama, Greg Ver Steeg

Figure 1 for Interpretable Diffusion via Information Decomposition
Figure 2 for Interpretable Diffusion via Information Decomposition
Figure 3 for Interpretable Diffusion via Information Decomposition
Figure 4 for Interpretable Diffusion via Information Decomposition
Viaarxiv icon

Tighter Prediction Intervals for Causal Outcomes Under Hidden Confounding

Jun 15, 2023
Myrl G. Marmarelis, Greg Ver Steeg, Aram Galstyan, Fred Morstatter

Figure 1 for Tighter Prediction Intervals for Causal Outcomes Under Hidden Confounding
Figure 2 for Tighter Prediction Intervals for Causal Outcomes Under Hidden Confounding
Figure 3 for Tighter Prediction Intervals for Causal Outcomes Under Hidden Confounding
Figure 4 for Tighter Prediction Intervals for Causal Outcomes Under Hidden Confounding
Viaarxiv icon

Multi-Task Knowledge Enhancement for Zero-Shot and Multi-Domain Recommendation in an AI Assistant Application

Jun 09, 2023
Elan Markowitz, Ziyan Jiang, Fan Yang, Xing Fan, Tony Chen, Greg Ver Steeg, Aram Galstyan

Figure 1 for Multi-Task Knowledge Enhancement for Zero-Shot and Multi-Domain Recommendation in an AI Assistant Application
Figure 2 for Multi-Task Knowledge Enhancement for Zero-Shot and Multi-Domain Recommendation in an AI Assistant Application
Figure 3 for Multi-Task Knowledge Enhancement for Zero-Shot and Multi-Domain Recommendation in an AI Assistant Application
Figure 4 for Multi-Task Knowledge Enhancement for Zero-Shot and Multi-Domain Recommendation in an AI Assistant Application
Viaarxiv icon

Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning

May 30, 2023
Umang Gupta, Aram Galstyan, Greg Ver Steeg

Figure 1 for Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning
Figure 2 for Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning
Figure 3 for Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning
Figure 4 for Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning
Viaarxiv icon

Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models

May 26, 2023
Neal Lawton, Anoop Kumar, Govind Thattai, Aram Galstyan, Greg Ver Steeg

Figure 1 for Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models
Figure 2 for Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models
Figure 3 for Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models
Viaarxiv icon

Measuring and Mitigating Local Instability in Deep Neural Networks

May 19, 2023
Arghya Datta, Subhrangshu Nandi, Jingcheng Xu, Greg Ver Steeg, He Xie, Anoop Kumar, Aram Galstyan

Figure 1 for Measuring and Mitigating Local Instability in Deep Neural Networks
Figure 2 for Measuring and Mitigating Local Instability in Deep Neural Networks
Figure 3 for Measuring and Mitigating Local Instability in Deep Neural Networks
Figure 4 for Measuring and Mitigating Local Instability in Deep Neural Networks
Viaarxiv icon

Improving Mutual Information Estimation with Annealed and Energy-Based Bounds

Mar 13, 2023
Rob Brekelmans, Sicong Huang, Marzyeh Ghassemi, Greg Ver Steeg, Roger Grosse, Alireza Makhzani

Figure 1 for Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
Figure 2 for Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
Figure 3 for Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
Figure 4 for Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
Viaarxiv icon