🌴 ARES is an open-source framework for adaptive multimodal reasoning, featuring a two-stage pipeline—Adaptive Cold-Start and Entropy-Shaped Policy Optimization—to balance reasoning depth and effici…

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

PyTorch implementation of the InfoNCE loss for self-supervised learning.