Picture for Mahmoud Salem

Mahmoud Salem

Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment

May 06, 2024
Viaarxiv icon

MediSwift: Efficient Sparse Pre-trained Biomedical Language Models

Add code
Mar 01, 2024
Figure 1 for MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
Figure 2 for MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
Figure 3 for MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
Figure 4 for MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
Viaarxiv icon

Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations

Add code
Sep 12, 2023
Figure 1 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Figure 2 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Figure 3 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Figure 4 for Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
Viaarxiv icon

Gumbel-Softmax Selective Networks

Nov 19, 2022
Figure 1 for Gumbel-Softmax Selective Networks
Figure 2 for Gumbel-Softmax Selective Networks
Figure 3 for Gumbel-Softmax Selective Networks
Viaarxiv icon

Bounding generalization error with input compression: An empirical study with infinite-width networks

Jul 19, 2022
Figure 1 for Bounding generalization error with input compression: An empirical study with infinite-width networks
Figure 2 for Bounding generalization error with input compression: An empirical study with infinite-width networks
Figure 3 for Bounding generalization error with input compression: An empirical study with infinite-width networks
Figure 4 for Bounding generalization error with input compression: An empirical study with infinite-width networks
Viaarxiv icon