Alert button
Picture for Peter J. Ramadge

Peter J. Ramadge

Alert button

Generative Marginalization Models

Oct 19, 2023
Sulin Liu, Peter J. Ramadge, Ryan P. Adams

Viaarxiv icon

Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming

Jul 01, 2023
Athindran Ramesh Kumar, Kai-Chieh Hsu, Peter J. Ramadge, Jaime F. Fisac

Figure 1 for Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming
Figure 2 for Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming
Figure 3 for Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming
Viaarxiv icon

Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings

May 23, 2023
Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen, Alexander I. Rudnicky, Peter J. Ramadge

Figure 1 for Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
Figure 2 for Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
Figure 3 for Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
Figure 4 for Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
Viaarxiv icon

Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation

May 05, 2023
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky, Peter J. Ramadge

Figure 1 for Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation
Figure 2 for Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation
Figure 3 for Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation
Figure 4 for Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation
Viaarxiv icon

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator

Jun 15, 2022
Ting-Han Fan, Ta-Chung Chi, Alexander I. Rudnicky, Peter J. Ramadge

Figure 1 for Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Figure 2 for Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Figure 3 for Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Figure 4 for Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Viaarxiv icon

KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation

May 20, 2022
Ta-Chung Chi, Ting-Han Fan, Peter J. Ramadge, Alexander I. Rudnicky

Figure 1 for KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
Figure 2 for KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
Figure 3 for KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
Figure 4 for KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
Viaarxiv icon

ProBF: Learning Probabilistic Safety Certificates with Barrier Functions

Dec 24, 2021
Athindran Ramesh Kumar, Sulin Liu, Jaime F. Fisac, Ryan P. Adams, Peter J. Ramadge

Figure 1 for ProBF: Learning Probabilistic Safety Certificates with Barrier Functions
Figure 2 for ProBF: Learning Probabilistic Safety Certificates with Barrier Functions
Figure 3 for ProBF: Learning Probabilistic Safety Certificates with Barrier Functions
Figure 4 for ProBF: Learning Probabilistic Safety Certificates with Barrier Functions
Viaarxiv icon

Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective

Oct 06, 2021
Ting-Han Fan, Peter J. Ramadge

Figure 1 for Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective
Figure 2 for Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective
Figure 3 for Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective
Figure 4 for Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective
Viaarxiv icon

DiffLoop: Tuning PID controllers by differentiating through the feedback loop

Jun 19, 2021
Athindran Ramesh Kumar, Peter J. Ramadge

Figure 1 for DiffLoop: Tuning PID controllers by differentiating through the feedback loop
Figure 2 for DiffLoop: Tuning PID controllers by differentiating through the feedback loop
Figure 3 for DiffLoop: Tuning PID controllers by differentiating through the feedback loop
Figure 4 for DiffLoop: Tuning PID controllers by differentiating through the feedback loop
Viaarxiv icon

Safe Reinforcement Learning with Natural Language Constraints

Oct 11, 2020
Tsung-Yen Yang, Michael Hu, Yinlam Chow, Peter J. Ramadge, Karthik Narasimhan

Figure 1 for Safe Reinforcement Learning with Natural Language Constraints
Figure 2 for Safe Reinforcement Learning with Natural Language Constraints
Figure 3 for Safe Reinforcement Learning with Natural Language Constraints
Figure 4 for Safe Reinforcement Learning with Natural Language Constraints
Viaarxiv icon