Picture for Huanrui Yang

Huanrui Yang

Personalized Multimodal Large Language Models: A Survey

Add code
Dec 03, 2024
Viaarxiv icon

A Survey of Small Language Models

Add code
Oct 25, 2024
Figure 1 for A Survey of Small Language Models
Figure 2 for A Survey of Small Language Models
Figure 3 for A Survey of Small Language Models
Viaarxiv icon

PAT: Pruning-Aware Tuning for Large Language Models

Add code
Aug 27, 2024
Figure 1 for PAT: Pruning-Aware Tuning for Large Language Models
Figure 2 for PAT: Pruning-Aware Tuning for Large Language Models
Figure 3 for PAT: Pruning-Aware Tuning for Large Language Models
Figure 4 for PAT: Pruning-Aware Tuning for Large Language Models
Viaarxiv icon

Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency

Add code
Aug 19, 2024
Viaarxiv icon

FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models

Add code
Aug 15, 2024
Figure 1 for FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models
Figure 2 for FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models
Figure 3 for FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models
Figure 4 for FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models
Viaarxiv icon

Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance

Add code
Jul 17, 2024
Viaarxiv icon

Fisher-aware Quantization for DETR Detectors with Critical-category Objectives

Add code
Jul 03, 2024
Figure 1 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Figure 2 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Figure 3 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Figure 4 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Viaarxiv icon

Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation

Add code
May 26, 2024
Figure 1 for Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
Figure 2 for Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
Figure 3 for Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
Figure 4 for Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
Viaarxiv icon

Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning

Add code
Apr 13, 2024
Viaarxiv icon

Magic-Me: Identity-Specific Video Customized Diffusion

Add code
Feb 14, 2024
Viaarxiv icon