Zengbin Wang

MuMing0102's activity

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

authored a paper about 23 hours ago

Visually-Guided Policy Optimization for Multimodal Reasoning

Paper • 2604.09349 • Published 29 days ago • 2

updated 2 collections 1 day ago

SpatialGenEval

Collection

[ICLR 2026] Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models • 1 item • Updated 1 day ago

VGPO-RL

Collection

[ACL 2026] Visually-Guided Policy Optimization for Multimodal Reasoning • 3 items • Updated 1 day ago

upvoted a paper 12 days ago

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published about 1 month ago • 187

upvoted a paper 14 days ago

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

Paper • 2604.17295 • Published 20 days ago • 84

upvoted a paper 18 days ago

Elucidating the SNR-t Bias of Diffusion Probabilistic Models

Paper • 2604.16044 • Published 22 days ago • 74

upvoted a collection 25 days ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.61k

published a model 25 days ago

MuMing0102/VGPO-RL-7B

Image-Text-to-Text • 8B • Updated 25 days ago • 24

updated a model 25 days ago

MuMing0102/VGPO-RL-32B

Image-Text-to-Text • 33B • Updated 25 days ago • 23

published a model 25 days ago

MuMing0102/VGPO-RL-32B

Image-Text-to-Text • 33B • Updated 25 days ago • 23

updated a model 25 days ago

MuMing0102/VGPO-RL-7B

Image-Text-to-Text • 8B • Updated 25 days ago • 24

upvoted a paper 25 days ago

Visually-Guided Policy Optimization for Multimodal Reasoning

Paper • 2604.09349 • Published 29 days ago • 2

upvoted a paper 28 days ago

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published 30 days ago • 289

upvoted 3 papers about 2 months ago

Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models

Paper • 2603.22212 • Published Mar 23 • 126

Video-CoE: Reinforcing Video Event Prediction via Chain of Events

Paper • 2603.14935 • Published Mar 16 • 91

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

Paper • 2603.03143 • Published Mar 3 • 145

upvoted 2 papers 2 months ago

From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

Paper • 2603.00141 • Published Feb 24 • 137

MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios

Paper • 2602.22638 • Published Feb 26 • 106