⬇️ Open and extendable Markdown syntax and toolchain.
-
Updated
Sep 13, 2026 - TypeScript
⬇️ Open and extendable Markdown syntax and toolchain.
LiDAR Registration with Visual Foundation Models
ICLR 2026: Agent-X Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
The official implementation of ICCV2025 paper "ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads"
Experimental real-time typesetting previewer for Vivliostyle Flavored Markdown.
Pipeline for generating semantic 3D scene graphs from egocentric RGB-D sequences, enriched with structural priors from BIM/IFC building models. Combines off-the-shelf 2D detection (Grounding DINO + SAM 2), depth back-projection, and IfcOpenShell-based room/door extraction into a unified hierarchical graph.
To associate your repository with the vfm topic, visit your repo's landing page and select "manage topics."