Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Documenti analoghi

• CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding
  di: Song, Wenxuan, et al.
  Pubblicazione: (2025)
• FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
  di: Zhao, Han, et al.
  Pubblicazione: (2026)
• CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
  di: Song, Wenxuan, et al.
  Pubblicazione: (2026)
• Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
  di: Song, Wenxuan, et al.
  Pubblicazione: (2026)
• VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
  di: Zhao, Han, et al.
  Pubblicazione: (2025)