Picture for Stanley Wei

Stanley Wei

What Makes a Reward Model a Good Teacher? An Optimization Perspective

Add code
Mar 19, 2025
Viaarxiv icon

Provable unlearning in topic modeling and downstream tasks

Add code
Nov 20, 2024
Viaarxiv icon

Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot

Add code
Jun 11, 2024
Figure 1 for Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
Figure 2 for Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
Figure 3 for Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
Figure 4 for Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
Viaarxiv icon