Pinned Loading

1. InternRobotics/G2VLM InternRobotics/G2VLM Public

   [CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

   Python 311 9

2. mlpc-ucsd/BLIVA mlpc-ucsd/BLIVA Public

   (AAAI 2024) BLIVA: A Simple Multimodal LLM for Better Handling of Text-rich Visual Questions

   Python 260 25

3. uclanlp/OpenVLThinker uclanlp/OpenVLThinker Public

   OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement

   Python 145 7

4. MQT-LLaVA MQT-LLaVA Public

   [NeurIPS 2024] Matryoshka Query Transformer for Large Vision-Language Models

   Python 124 11

5. mragbench/MRAG-Bench mragbench/MRAG-Bench Public

   [ICLR 2025] Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

   Python 61 3