Picture for Wangbo Zhao

Wangbo Zhao

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

Add code
Dec 17, 2024
Figure 1 for Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
Figure 2 for Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
Figure 3 for Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
Figure 4 for Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
Viaarxiv icon

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs

Add code
Dec 05, 2024
Figure 1 for A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
Figure 2 for A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
Figure 3 for A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
Figure 4 for A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
Viaarxiv icon

Dynamic Diffusion Transformer

Add code
Oct 04, 2024
Viaarxiv icon

Prioritize Alignment in Dataset Distillation

Add code
Aug 06, 2024
Figure 1 for Prioritize Alignment in Dataset Distillation
Figure 2 for Prioritize Alignment in Dataset Distillation
Figure 3 for Prioritize Alignment in Dataset Distillation
Figure 4 for Prioritize Alignment in Dataset Distillation
Viaarxiv icon

Conditional LoRA Parameter Generation

Add code
Aug 02, 2024
Figure 1 for Conditional LoRA Parameter Generation
Figure 2 for Conditional LoRA Parameter Generation
Figure 3 for Conditional LoRA Parameter Generation
Figure 4 for Conditional LoRA Parameter Generation
Viaarxiv icon

Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond

Add code
May 06, 2024
Viaarxiv icon

Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

Add code
Mar 18, 2024
Figure 1 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Figure 2 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Figure 3 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Figure 4 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Viaarxiv icon

VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning

Add code
Nov 25, 2023
Viaarxiv icon

Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation

Add code
Sep 20, 2023
Viaarxiv icon

Learning Referring Video Object Segmentation from Weak Annotation

Add code
Aug 04, 2023
Viaarxiv icon