Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

SpatialAxiom

https://d2i-ai.github.io/SpatialAxiom/
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

JosephTongĀ  authored a paper about 12 hours ago
MM-OPD: Towards One More Bottleneck Between Perception and Reasoning
JosephTongĀ  authored a paper about 12 hours ago
SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs
JosephTongĀ  authored a paper about 12 hours ago
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
View all activity

Papers

DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection

CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering

View all Papers

Yujing  Lou's profile picture Guo's profile picture chenpingyi's profile picture Lubin Fan's profile picture Jintao Tong's profile picture ShenCao's profile picture Jiaqi Gu's profile picture hongyuyang's profile picture Yunzhuo Hao's profile picture
Organization Card
Community About org cards

šŸ‘‹ Welcome to SpatialAxiom

This is the organization of SpatialAxiom, built by the D2I Lab, Alibaba Group. In this organization, we continuously release spatial intelligence projects. Feel free to enjoy our latest models!

spaces 2

Running on Zero
MCP

SpatialAxiom-9B

🧠

Spatial reasoning VLM for 3D relations and perspective

Aug 3

models 2

SpatialAxiom/SpatialAxiom-9B

Image-Text-to-Text • 9B • Updated Aug 5 • 134 • 18

SpatialAxiom/SpatialAxiom-35B-A3B

Image-Text-to-Text • 35B • Updated Aug 5 • 41 • 13

datasets 0

None public yet
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs