Picture for Heshan Liu

Heshan Liu

Backdoor Removal for Generative Large Language Models

May 13, 2024
Viaarxiv icon

Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers

May 08, 2024
Figure 1 for Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
Figure 2 for Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
Figure 3 for Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
Viaarxiv icon

Pose-Guided High-Resolution Appearance Transfer via Progressive Training

Aug 27, 2020
Figure 1 for Pose-Guided High-Resolution Appearance Transfer via Progressive Training
Figure 2 for Pose-Guided High-Resolution Appearance Transfer via Progressive Training
Figure 3 for Pose-Guided High-Resolution Appearance Transfer via Progressive Training
Figure 4 for Pose-Guided High-Resolution Appearance Transfer via Progressive Training
Viaarxiv icon