VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Overview

Native visual reasoning, i.e., reasoning through visual generation, has recently emerged as a promising direction for studying visual intelligence beyond language. Yet progress remains bottlenecked by the lack of scalable training tasks, reliable feedback, and controlled comparisons across generative substrates. In this work, we introduce VBVR-Pro, a closed-loop testbed that makes native visual reasoning through generation trainable, verifiable, optimizable, and experimentally controllable. 1) Task scaling. VBVR-Pro turns visual reasoning into a controlled task space of 300 procedurally generated tasks. Models trained on VBVR-Pro show strong transfer beyond the proposed suite across six held-out visual reasoning benchmarks such as RISE-Video, MME-CoF-Pro, and BabyVision. Further analysis validates that these gains reflect visual reasoning rather than instruction-pattern fitting. 2) Verifiable rewards. VBVR-Pro provides verifiable reward scorers for task-grounded evaluation. Through a systematic study of leading MLLMs as judges, we identify recurring failure modes of the prevalent VLM-as-a-judge paradigm. In contrast, the proposed scorers are grounded on verifiable task-specific rules, achieve fine-grained alignment with human judgments. Importantly, they serve as reliable reward signals for large-scale multi-task reinforcement learning and demonstrate stronger post-RL performance across visual reasoning tasks. 3) Mechanism study. VBVR-Pro enables controlled modality studies across more than 30 image, video, and interleaved generators. Our analysis shows that video generation remains strongest for tasks requiring persistent spatiotemporal state tracking, while interleaved generation provides a compute-efficient alternative by externalizing intermediate visual states. Critically, ablations and probing confirm the presence of vision-native trajectories, that are a more crucial substrate than explicit linguistic chains of thought for visual reasoning. We release all data, models, scorers, and code to facilitate future research.

The models are presented in the paper VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning.

Models Zoo

Release Information

VBVR-Pro finetuned FLUX.2-dev for instruction-based image editing, trained on the VBVR-Dataset.

This is the merged model — the LoRA (rank 32) has already been fused into the transformer weights. Load it directly with Diffusers; no extra adapters or DiffSynth-Studio needed.

In this release, we present all models presented in paper VBVR-Pro-Trained-Models, VBVR-Pro-Dataset-Video, VBVR-Pro-Dataset-Image, VBVR-Pro-Bench, VBVR-Pro-Code and VBVR-Bench-Leaderboard.

VBVR-Pro Benchmark Results

Quick Start

Method 1: Standalone Diffusers inference

1. Install Diffusers

pip install torch torchvision
pip install git+https://github.com/huggingface/diffusers

2. Run example.py

The included example.py loads the merged checkpoint directly with Diffusers and enables model CPU offloading.

python example.py \
  --model_path Video-Reason/VBVR-Pro-FLUX2-dev \
  --image input.png \
  --prompt "Move the red block to the left of the blue block." \
  --output output.png

Method 2: Unified VBVR-Pro inference

Clone Video-Reason/VBVR-Pro and create its unified inference environment:

git clone https://github.com/Video-Reason/VBVR-Pro.git
cd VBVR-Pro/
uv sync --extra cu124 # or one of [cu118|cu121|cu124|cu126|cu128|cu129]
source .venv/bin/activate

Then run the unified inference script:

python example.py \
  --model_path Video-Reason/VBVR-Pro-FLUX2-dev \
  --image_paths input.png \
  --prompt "Move the red block to the left of the blue block." \
  --output output.png

Citation

@article{vbvr2025,
  title={VBVR: A Very Big Video Reasoning Suite},
  year={2025},
}