Picture for Salman Avestimehr

Salman Avestimehr

Maverick-Aware Shapley Valuation for Client Selection in Federated Learning

May 21, 2024
Viaarxiv icon

Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers

May 16, 2024
Viaarxiv icon

Federated Learning Privacy: Attacks, Defenses, Applications, and Policy Landscape - A Survey

May 06, 2024
Viaarxiv icon

Ethos: Rectifying Language Models in Orthogonal Parameter Space

Add code
Apr 01, 2024
Figure 1 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Figure 2 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Figure 3 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Figure 4 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Viaarxiv icon

Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation

Mar 26, 2024
Figure 1 for Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation
Figure 2 for Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation
Figure 3 for Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation
Figure 4 for Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation
Viaarxiv icon

Edge Private Graph Neural Networks with Singular Value Perturbation

Mar 16, 2024
Figure 1 for Edge Private Graph Neural Networks with Singular Value Perturbation
Figure 2 for Edge Private Graph Neural Networks with Singular Value Perturbation
Figure 3 for Edge Private Graph Neural Networks with Singular Value Perturbation
Figure 4 for Edge Private Graph Neural Networks with Singular Value Perturbation
Viaarxiv icon

ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys

Mar 01, 2024
Figure 1 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Figure 2 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Figure 3 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Figure 4 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Viaarxiv icon

MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs

Add code
Feb 20, 2024
Viaarxiv icon

All Rivers Run to the Sea: Private Learning with Asymmetric Flows

Dec 05, 2023
Figure 1 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Figure 2 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Figure 3 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Figure 4 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Viaarxiv icon

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks

Add code
Nov 21, 2023
Viaarxiv icon