Ni Ou

gitouni

4 5

·

https://scholar.google.com/citations?user=FW3OeUQAAAAJ&hl=zh-CN

gitouni

AI & ML interests

Generative Models, Transformers, 3D Vision

Recent Activity

upvoted a paper 5 days ago

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts

upvoted a paper about 1 month ago

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation

upvoted a paper about 2 months ago

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

View all activity

Organizations

None yet

upvoted a paper 5 days ago

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts

Paper • 2609.21346 • Published 8 days ago • 99

upvoted a paper about 1 month ago

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation

Paper • 2608.13489 • Published Aug 13 • 101

upvoted a paper about 2 months ago

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published Aug 3 • 188

upvoted a paper 3 months ago

DreamX-World 1.0: A General-Purpose Interactive World Model

Paper • 2606.16993 • Published Jun 15 • 116

liked a Space over 1 year ago

Joy Caption Pre Alpha

Generate descriptive captions for any image

liked a model almost 2 years ago

Xenova/text-embedding-ada-002

Updated Aug 18, 2025 • 79

liked 3 models about 2 years ago

google/owlv2-base-patch16-ensemble

Zero-Shot Object Detection • 0.2B • Updated Oct 31, 2024 • 1.79M • 129

diffusers/stable-diffusion-xl-1.0-inpainting-0.1

Text-to-Image • 3B • Updated Sep 3, 2023 • 105k • 384

microsoft/git-base

Image-to-Text • 0.2B • Updated Apr 24, 2023 • 27.5k • 111