wu

ZiangWu's activity

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

upvoted a paper 3 days ago

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published 4 days ago • 148

liked a model 28 days ago

tencent/Hy4-preview

Text Generation • 780B • Updated 28 days ago • 21.2k • • 496

authored a paper about 2 months ago

Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

Paper • 2608.00574 • Published Aug 1 • 9

submitted a paper to Daily Papers about 2 months ago

Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

Paper • 2608.00574 • Published Aug 1 • 9

upvoted a paper about 2 months ago

Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

Paper • 2608.00574 • Published Aug 1 • 9

upvoted a paper 4 months ago

Self-Improving Language Models with Bidirectional Evolutionary Search

Paper • 2605.28814 • Published May 27 • 63

upvoted a paper 7 months ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published Mar 4 • 175

published 2 models 10 months ago

ZiangWu/qwen2-vl-7b-drivelm

Updated Jul 17, 2025

ZiangWu/qwen2-vl-sft-drivelm-1121-full

Updated Nov 21, 2025

updated a model 10 months ago

ZiangWu/qwen2-vl-7b-sft-drivelm-1121

Updated Nov 21, 2025

published a model 10 months ago

ZiangWu/qwen2-vl-7b-sft-drivelm-1121

Updated Nov 21, 2025

updated a model 10 months ago

ZiangWu/qwen2-vl-sft-drivelm-2b-1121

Updated Nov 21, 2025

published a model 10 months ago

ZiangWu/qwen2-vl-sft-drivelm-2b-1121

Updated Nov 21, 2025

updated a model about 1 year ago

ZiangWu/qwen2-vl-7b-drivelm

Updated Jul 17, 2025

liked a dataset about 1 year ago

Xkev/LLaVA-CoT-100k

Viewer • Updated Dec 20, 2025 • 98.6k • 1.66k • 106

New activity in Niujunbo2002/qwen2_vl-2b-full-sft-cambrian-737k over 1 year ago

Question on training details.

2

#1 opened over 1 year ago by

ZiangWu

authored a paper almost 2 years ago

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

Paper • 2406.18139 • Published Jun 26, 2024 • 2

upvoted a paper almost 2 years ago

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

Paper • 2406.18139 • Published Jun 26, 2024 • 2

liked 2 models almost 2 years ago

facebook/DiT-XL-2-256

Updated Jan 17, 2023 • 10.6k • 34

Chat-UniVi/MoH-DiT-XL-90

Updated Oct 17, 2024 • 3