V-Reflection

garlandchou/V-Reflection

V-Reflection is a visual question answering model from garlandchou. Use it for the visual question answering task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

V-Reflection is a Qwen2.5-VL-based multimodal model that turns the MLLM into an active interrogator via a think-then-look visual reflection mechanism: fixed-length latent visual reasoning before answering.

Downloads · 30 days

15% of all-time downloads

All-time downloads

176

Public

Parameters

921K

16.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors16.8 GB · 99%

At a glance

Task: Visual Question Answering
License: apache-2.0
Model type: qwen2_5_vl
Access: Public
Created: Mar 17, 2026
Updated: Apr 7, 2026
SHA: 8c066514

Base models

Qwen/Qwen2.5-VL-7B-Instruct

Model card

From the Hugging Face model README

V-Reflection (7B)

V-Reflection is a Qwen2.5-VL-based multimodal model that turns the MLLM into an active interrogator via a think-then-look visual reflection mechanism: fixed-length latent visual reasoning before answering.

Resource	Link
Paper	arxiv.org/abs/2604.03307
Project page	idea-research.github.io/V-Reflection
Code & scripts	github.com/IDEA-Research/V-Reflection

Model summary

Architecture: Built on Qwen2.5-VL-7B-Instruct with Box-Guided Compression (BCM) and Dynamic Autoregressive Compression (DAC) for latent visual probing.
Stage 1 (BCM): Box-guided compression produces stable pixel-to-latent targets; stochastic decoupled alignment trains the resampler and LLM jointly.
Stage 2 (DAC): Student maps LLM hidden states into dynamic probes over the global visual map, with MSE distillation from a frozen BCM teacher.
Inference: BCM/DAC are inactive at inference; decoding is end-to-end autoregressive in latent space (8-step latent reasoning by default).

Repository contents

This Hub repo includes model weights (sharded Safetensors) and pre-formatted LVR training annotations used in the paper project:

File(s)	Role
`*.safetensors`, `config.json`, tokenizer assets	Fine-tuned V-Reflection checkpoint
`meta_data_lvr_sft_stage1.json`	Meta config for default SROIE + DUDE mix
`viscot_sroie_dude_lvr_formatted.json`	SROIE + DUDE subset
`viscot_363k_lvr_formatted.json`	Full Visual CoT–style 363K split

Download images for Visual CoT / listed datasets from their official sources (see the code repo data section).

Intended use

Research on visual reasoning, high-resolution understanding, and latent multimodal reasoning.
Not a drop-in replacement for stock Qwen2.5-VL in generic chat UIs without the official custom model class and generation path.

How to run

Loading and evaluation rely on the QwenWithLVR implementation and scripts in the GitHub repository (training, packing, and benchmarks are documented there).

Clone IDEA-Research/V-Reflection and follow README.md (environment, data layout).
Download this checkpoint into a local directory (or rely on hf_hub_download from their evaluation scripts).
Point EVAL_CHECKPOINT_PATH (or the training script checkpoint args) to the unpacked folder.

Example evaluation entrypoint (from upstream docs):

bash scripts_release/evaluation/evaluation_7b_stage2.sh

Results (reported in project materials)

Benchmark	V-Reflection	Qwen2.5-VL-7B
MMVP	72.3	66.7
BLINK	56.4	54.5
V*	81.7	78.5
HRBench-4K	72.6	68.0
HRBench-8K	66.3	63.8
MME-RealWorld-Lite	53.9	45.8

Limitations

Requires the official codebase for correct loading and latent reasoning behavior.
Performance and safety have not been audited for unrestricted production deployment; use judgment for real-world products.
Biases may mirror base model and training data distributions.

License

Apache-2.0 (same as the codebase). See the license file in the GitHub repository.

Acknowledgements

Qwen2.5-VL, LVR, Visual-CoT, InternVL.

Task: Visual Question Answering
Type: qwen2_5_vl
License: apache-2.0
Created: Mar 17, 2026
Updated: Apr 7, 2026