SenseNova-U1
Collection
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture • 6 items • Updated • 45
Haiwen Diao
Paranioar
AI & ML interests
Vision-and-Language, Parameter-efficient Transfer Learning, Multi-modal Large Language Model
Recent Activity
updated a collection 5 days ago
SenseNova-U1 updated a collection 5 days ago
SenseNova-U1 liked a model 9 days ago
sensenova/SenseNova-U1-8B-MoT-8step-previewOrganizations
updated a
collection 5 days ago
liked a
model 9 days ago
liked 2
models 11 days ago
upvoted a collection 11 days ago
commented on NEO-unify: Building Native Multimodal Unified Models End to End 14 days ago
Hopefully they can involve NEO-Unify in discussions of their paper, haha~
commented on NEO-unify: Building Native Multimodal Unified Models End to End 14 days ago
Model available on HF ? 👀
We just open-sourced it here: https://github.com/OpenSenseNova/SenseNova-U1 .
Give it a try!
upvoted a paper 15 days ago
updated a
collection 20 days ago
upvoted 2
papers about 1 month ago
upvoted 5
papers about 2 months ago
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
Paper • 2603.19227 • Published • 42
MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction
Paper • 2603.19231 • Published • 36
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
Paper • 2603.16669 • Published • 70
Demystifing Video Reasoning
Paper • 2603.16870 • Published • 371
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions
Paper • 2603.15612 • Published • 153
updated a
collection about 2 months ago