eVI-group-SCU/V-Zero

Vero: An Open RL Recipe for General Visual Reasoning

[ECCV 2026] Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"

Vision-OPD is a regional-to-global on-policy self-distillation framework that transfers a model's own privileged crop-conditioned perception to its full-image policy, enabling fine-grained visual understanding in a single forward pass without external teachers, labels, or verifiers.

One Discrete Word for Visual Reasoning Overtakes Agentic and Latent Methods

Witness the aha moment of VLM with less than $3.

Code for the Molmo Vision-Language Model

Benchmark and training code for MindCube: spatial mental modeling in vision-language models from limited views.

The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"