InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models Paper • 2510.11341 • Published 16 days ago • 33
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency Paper • 2508.18265 • Published Aug 25 • 201
ArchCAD-400K: An Open Large-Scale Architectural CAD Dataset and New Baseline for Panoptic Symbol Spotting Paper • 2503.22346 • Published Mar 28 • 2