Picture for Xiaolong Ma

Xiaolong Ma

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

Add code
Nov 26, 2024
Figure 1 for Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Figure 2 for Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Figure 3 for Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Figure 4 for Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Viaarxiv icon

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design

Add code
Jul 03, 2024
Viaarxiv icon

FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning

Add code
Apr 09, 2024
Figure 1 for FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning
Figure 2 for FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning
Figure 3 for FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning
Figure 4 for FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning
Viaarxiv icon

Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective

Add code
Dec 15, 2023
Viaarxiv icon

Dynamic Sparsity Is Channel-Level Sparsity Learner

Add code
May 30, 2023
Viaarxiv icon

Rethinking Graph Lottery Tickets: Graph Sparsity Matters

Add code
May 03, 2023
Viaarxiv icon

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

Add code
Mar 15, 2023
Viaarxiv icon

Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training

Add code
Nov 19, 2022
Figure 1 for Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Figure 2 for Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Figure 3 for Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Figure 4 for Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Viaarxiv icon

The Lottery Ticket Hypothesis for Vision Transformers

Add code
Nov 02, 2022
Viaarxiv icon

CHEX: CHannel EXploration for CNN Model Compression

Add code
Mar 29, 2022
Figure 1 for CHEX: CHannel EXploration for CNN Model Compression
Figure 2 for CHEX: CHannel EXploration for CNN Model Compression
Figure 3 for CHEX: CHannel EXploration for CNN Model Compression
Figure 4 for CHEX: CHannel EXploration for CNN Model Compression
Viaarxiv icon