G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
Paper
•
2511.21688
•
Published
•
8
Natural Language Processing, Bias and Fairness in NLP
LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training
DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation