Bingzheng Wei

Bingzheng's activity

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

upvoted 2 papers about 3 hours ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 2 days ago • 24

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 7 days ago • 106

upvoted 4 papers 2 days ago

Trust Region Policy Distillation

Paper • 2607.04751 • Published 9 days ago • 24

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published 6 days ago • 63

Scalable Visual Pretraining for Language Intelligence

Paper • 2607.09657 • Published 5 days ago • 49

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published 5 days ago • 58

upvoted 5 papers 5 days ago

AdaJEPA: An Adaptive Latent World Model

Paper • 2606.32026 • Published 15 days ago • 2

Vidu S1: A Real-Time Interactive Video Generation Model

Paper • 2607.03118 • Published 12 days ago • 133

Infinite Worlds with Versatile Interactions

Paper • 2607.07534 • Published 7 days ago • 40

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

Paper • 2607.07608 • Published 7 days ago • 55

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Paper • 2607.07708 • Published 7 days ago • 85

upvoted a paper 6 days ago

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 7 days ago • 62

upvoted 4 papers 7 days ago

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 8 days ago • 92

Vision Pretraining for Dense Spatial Perception

Paper • 2607.05247 • Published 9 days ago • 43

AlayaWorld: Long-Horizon and Playable Video World Generation

Paper • 2607.06291 • Published 8 days ago • 87

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Paper • 2607.04033 • Published 11 days ago • 75

upvoted 4 papers 8 days ago

UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning

Paper • 2607.04425 • Published 10 days ago • 70

GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation

Paper • 2607.02642 • Published 13 days ago • 37

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

Paper • 2607.04438 • Published 10 days ago • 61

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

Paper • 2607.04439 • Published 10 days ago • 54