dataset are available at https://github.com/THU-KEG/MMGeoLM. [7/7 of https://arxiv.org/abs/2505.20152v1]

CLIP), and subsequently train an LMM for geometric problem-solving. Experiments show that our trained model, MMGeoLM, significantly outperforms other open-source models on three geometric reasoning benchmarks. Even with a size of 7B, it can rival [5/7 of https://arxiv.org/abs/2505.20152v1]

MMGeoLM is a 7 billion‑parameter model that improves geometric reasoning; the code and checkpoints are released on GitHub. Read more: https://getnews.me/mmgeolm-hard-negative-contrastive-learning-boosts-geometric-reasoning/ #mmgeolm #hardnegative #geometricreasoning