Picture for Jiwen Lu

Jiwen Lu

PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views

Add code
Oct 24, 2024
Viaarxiv icon

V2M: Visual 2-Dimensional Mamba for Image Representation Learning

Add code
Oct 14, 2024
Viaarxiv icon

GlobalMamba: Global Image Serialization for Vision Mamba

Add code
Oct 14, 2024
Viaarxiv icon

Q-VLM: Post-training Quantization for Large Vision-Language Models

Add code
Oct 10, 2024
Viaarxiv icon

SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation

Add code
Oct 10, 2024
Figure 1 for SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Figure 2 for SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Figure 3 for SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Figure 4 for SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Viaarxiv icon

OPONeRF: One-Point-One NeRF for Robust Neural Rendering

Add code
Sep 30, 2024
Figure 1 for OPONeRF: One-Point-One NeRF for Robust Neural Rendering
Figure 2 for OPONeRF: One-Point-One NeRF for Robust Neural Rendering
Figure 3 for OPONeRF: One-Point-One NeRF for Robust Neural Rendering
Figure 4 for OPONeRF: One-Point-One NeRF for Robust Neural Rendering
Viaarxiv icon

FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner

Add code
Sep 26, 2024
Viaarxiv icon

DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation

Add code
Sep 05, 2024
Figure 1 for DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation
Figure 2 for DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation
Figure 3 for DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation
Figure 4 for DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation
Viaarxiv icon

EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Add code
Aug 21, 2024
Figure 1 for EmbodiedSAM: Online Segment Any 3D Thing in Real Time
Figure 2 for EmbodiedSAM: Online Segment Any 3D Thing in Real Time
Figure 3 for EmbodiedSAM: Online Segment Any 3D Thing in Real Time
Figure 4 for EmbodiedSAM: Online Segment Any 3D Thing in Real Time
Viaarxiv icon

Temporal Feature Matters: A Framework for Diffusion Model Quantization

Add code
Jul 28, 2024
Viaarxiv icon