Zhongwei Zhang

zzwustc's activity

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

upvoted a paper 13 days ago

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

Paper • 2609.00188 • Published 15 days ago • 53

upvoted a paper 14 days ago

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

Paper • 2608.29335 • Published 17 days ago • 72

liked a dataset 27 days ago

FireCRT/CoinVE-200K

Preview • Updated 5 days ago • 17.6k • 13

upvoted a paper 27 days ago

CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing

Paper • 2608.17566 • Published 28 days ago • 16

liked a dataset about 1 month ago

zengziyun/VideoArgusBench

Viewer • Updated Aug 7 • 1.03k • 1.32k • 1

upvoted a paper about 1 month ago

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

Paper • 2607.28611 • Published Jul 30 • 23

upvoted 3 papers about 2 months ago

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Paper • 2607.26497 • Published Jul 30 • 53

Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

Paper • 2607.27816 • Published Jul 30 • 35

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

Paper • 2607.27616 • Published Jul 30 • 40

liked a model about 2 months ago

Lightricks/LTX-2.3-22b-IC-LoRA-Clean-Plate

Video-to-Video • Updated 14 days ago • 1.14k • 107

liked a dataset 2 months ago

markov-ai/gaming-500-hours

Viewer • Updated Jun 30 • 776 • 10.4k • 255

upvoted 5 papers 3 months ago

Vera: A Layered Diffusion Model for Content-Preserving Video Editing

Paper • 2606.23610 • Published Jun 22 • 13

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Paper • 2606.03988 • Published Jun 3 • 127

MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation

Paper • 2606.09056 • Published Jun 8 • 8

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Paper • 2605.30263 • Published May 28 • 62

CoVEBench: Can Video Editing Models Handle Complex Instructions?

Paper • 2606.08415 • Published Jun 7 • 53

liked 2 datasets 3 months ago

NJU-LINK/CoVEBench

Viewer • Updated Jun 9 • 626 • 549 • 2

zeqixiao/worldmem_minecraft_dataset

Viewer • Updated Dec 2, 2025 • 12.8k • 2.38k • 2

liked a Space 4 months ago

Running on Zero

Agents

Featured

79

VGGT-Omega Demo

🌀

79

3D reconstruction from images/video with VGGT-Omega

upvoted a paper 4 months ago

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published May 14 • 91