3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models Paper • 2609.06535 • Published 26 days ago • 1
Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes Paper • 2604.14914 • Published Apr 16 • 5
Dynamic Reflections: Probing Video Representations with Text Alignment Paper • 2511.02767 • Published Nov 4, 2025 • 4
Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces Paper • 2503.05283 • Published Mar 7, 2025 • 4