Haiwen Diao

Paranioar's activity

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

upvoted 2 papers 1 day ago

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published 2 days ago • 64

Demystifing Video Reasoning

Paper • 2603.16870 • Published 2 days ago • 121

upvoted a paper 2 days ago

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published 3 days ago • 142

updated a collection 6 days ago

NEO1_5

Collection

From Pixels to Words -- Towards Native One-Vision Foundation Models at Scale • 2 items • Updated 6 days ago • 1

upvoted an article 14 days ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

14 days ago

•

100

published an article 14 days ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

14 days ago

•

100

upvoted a paper 15 days ago

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published 16 days ago • 85

upvoted 2 papers 23 days ago

VLANeXt: Recipes for Building Strong VLA Models

Paper • 2602.18532 • Published 27 days ago • 52

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published 24 days ago • 515

upvoted 2 papers 29 days ago

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Paper • 2602.12279 • Published Feb 12 • 20

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published 30 days ago • 115

upvoted 2 papers about 1 month ago

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published Feb 9 • 52

Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition

Paper • 2602.08439 • Published Feb 9 • 28

upvoted a paper about 2 months ago

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

Paper • 2601.22153 • Published Jan 29 • 74

updated a collection about 2 months ago

NEO1_5

Collection

From Pixels to Words -- Towards Native One-Vision Foundation Models at Scale • 2 items • Updated 6 days ago • 1

updated a dataset 2 months ago

Paranioar/datacomp

Viewer • Updated Jan 16 • 1.7M • 7

liked a model 2 months ago

Paranioar/NEO1_0-9B-SFT

Image-Text-to-Text • 10B • Updated Oct 21, 2025 • 360 • 6