Picture for Kunyu Wang

Kunyu Wang

EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction

Add code
Mar 27, 2025
Viaarxiv icon

Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks

Add code
Dec 09, 2024
Viaarxiv icon

MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with its Application for Colonic Polyp Image Segmentation

Add code
Mar 31, 2024
Viaarxiv icon

NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

Add code
Mar 01, 2024
Figure 1 for NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Figure 2 for NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Figure 3 for NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Figure 4 for NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Viaarxiv icon

Generating Visually Realistic Adversarial Patch

Add code
Dec 05, 2023
Viaarxiv icon

LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations

Add code
Nov 01, 2023
Viaarxiv icon

Boosting Adversarial Transferability by Block Shuffle and Rotation

Add code
Aug 22, 2023
Viaarxiv icon