Zeyu Zhang

SteveZeyuZhang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 3 days ago

EgoLCD: Egocentric Video Generation with Long Context Diffusion

Paper • 2512.04515 • Published 5 days ago • 5

authored a paper 5 days ago

BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation

Paper • 2511.22973 • Published 10 days ago • 2

authored 2 papers 11 days ago

MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots

Paper • 2511.17889 • Published 17 days ago • 5

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published 14 days ago • 45

authored a paper 13 days ago

EvoVLA: Self-Evolving Vision-Language-Action Model

Paper • 2511.16166 • Published 18 days ago • 4

authored 2 papers 2 months ago

VLA-R1: Enhancing Reasoning in Vision-Language-Action Models

Paper • 2510.01623 • Published Oct 2 • 10

UniVid: The Open-Source Unified Video Model

Paper • 2509.24200 • Published Sep 29 • 4

authored 4 papers 3 months ago

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

Paper • 2509.19297 • Published Sep 23 • 24

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

Paper • 2506.04648 • Published Jun 5 • 1

StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes

Paper • 2509.16415 • Published Sep 19 • 2

Nav-R1: Reasoning and Navigation in Embodied Scenes

Paper • 2509.10884 • Published Sep 13 • 6

authored 5 papers 4 months ago

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

Paper • 2505.23734 • Published May 29 • 4

Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

Paper • 2506.05327 • Published Jun 5 • 11

SSS: Semi-Supervised SAM-2 with Efficient Prompting for Medical Imaging Segmentation

Paper • 2506.08949 • Published Jun 10

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Paper • 2507.23478 • Published Jul 31 • 15

ReMoMask: Retrieval-Augmented Masked Motion Generation

Paper • 2508.02605 • Published Aug 4 • 4

authored a paper 5 months ago

PresentAgent: Multimodal Agent for Presentation Video Generation

Paper • 2507.04036 • Published Jul 5 • 10

authored a paper 7 months ago

MediAug: Exploring Visual Augmentation in Medical Imaging

Paper • 2504.18983 • Published Apr 26 • 7

authored 2 papers 8 months ago

3D CoCa: Contrastive Learners are 3D Captioners

Paper • 2504.09518 • Published Apr 13 • 5

DiffuMural: Restoring Dunhuang Murals with Multi-scale Diffusion

Paper • 2504.09513 • Published Apr 13