Picture for Victor Rühle

Victor Rühle

Microsoft

Ensuring Fair LLM Serving Amid Diverse Applications

Add code
Nov 24, 2024
Viaarxiv icon

EcoAct: Economic Agent Determines When to Register What Action

Add code
Nov 03, 2024
Viaarxiv icon

Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers

Add code
May 17, 2024
Viaarxiv icon

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Add code
Mar 19, 2024
Figure 1 for LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Figure 2 for LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Figure 3 for LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Figure 4 for LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Viaarxiv icon

Unlocking Spatial Comprehension in Text-to-Image Diffusion Models

Add code
Nov 28, 2023
Figure 1 for Unlocking Spatial Comprehension in Text-to-Image Diffusion Models
Figure 2 for Unlocking Spatial Comprehension in Text-to-Image Diffusion Models
Figure 3 for Unlocking Spatial Comprehension in Text-to-Image Diffusion Models
Figure 4 for Unlocking Spatial Comprehension in Text-to-Image Diffusion Models
Viaarxiv icon

Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective

Add code
Nov 27, 2023
Viaarxiv icon

Bayesian Estimation of Differential Privacy

Add code
Jun 15, 2022
Figure 1 for Bayesian Estimation of Differential Privacy
Figure 2 for Bayesian Estimation of Differential Privacy
Figure 3 for Bayesian Estimation of Differential Privacy
Figure 4 for Bayesian Estimation of Differential Privacy
Viaarxiv icon

Privacy Regularization: Joint Privacy-Utility Optimization in Language Models

Add code
Mar 12, 2021
Figure 1 for Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
Figure 2 for Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
Figure 3 for Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
Figure 4 for Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
Viaarxiv icon

Privacy Analysis in Language Models via Training Data Leakage Report

Add code
Jan 14, 2021
Figure 1 for Privacy Analysis in Language Models via Training Data Leakage Report
Figure 2 for Privacy Analysis in Language Models via Training Data Leakage Report
Figure 3 for Privacy Analysis in Language Models via Training Data Leakage Report
Figure 4 for Privacy Analysis in Language Models via Training Data Leakage Report
Viaarxiv icon