Blame for README.md

---
license: apache-2.0
base_model: Qwen/Qwen3-VL-8B-Instruct
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- qwen3-vl
- viss
- streaming-video
- visual-question-answering
- causal-video
---

# ViSS-8B

**Supervising the Visible State: Separating Representation from View Selection in Streaming Video**

Yihao Hu*, Pan Wang*, Yitong Lin*, Zhihao Wen†, Deyuan Liu, Hang Wang,
Mingda Wan, Yiwen Zhao, Yutong Li, Yuchen Mao, Tao Lin†

*Equal contribution. †Corresponding author.*

[Collection](https://huggingface.co/collections/mis2/viss-6adc8caf041ae0c501c9a11b) ·
[Source code](https://huggingface.co/mis2/ViSS-8B/tree/main/code) ·
[Installation](code/docs/INSTALL.md) ·
[Training](code/docs/TRAINING.md) ·
[Evaluation](code/docs/EVALUATION.md)

## Overview

Visible-State Supervision (ViSS) trains a vision–language model on
source-grounded questions about event identity, order, accumulation,
relation changes, and whether the available evidence suffices to answer.
Test-Time Causal View Search (TVS) keeps the model fixed and acquires
complementary recent, event, and compact-history views.

The model is initialized from Qwen3-VL-8B-Instruct and trained for one epoch
on 7,677 examples, with learning rate 2e-6 and global batch size 12.
The vision tower is frozen; the language model and multimodal projector
are trainable. Model-only ViSS and TVS use the same checkpoint.

## Released files

- Four original BF16 safetensors shards (17.53 GB in total).
- Model configuration, tokenizer, chat template, and native processor.
- `locked_processor/`: the processor used for the recent-view evaluation.
- `code/`: training, inference, TVS composition, evaluation adapters,
  public configuration templates, documentation, and synthetic tests.

The release contains no training annotations, raw media, company experiment
records, prediction files, evaluation summaries, optimizer states, or internal
training manifests. Training data are not being released in this version.

## Download

```bash
hf download mis2/ViSS-8B --local-dir checkpoints/ViSS-8B
```

## Load the model

Use a Transformers version supporting Qwen3-VL; the retained model
configuration specifies Transformers 4.57.3.

```python
import torch
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "mis2/ViSS-8B"
processor = AutoProcessor.from_pretrained(
    model_id, subfolder="locked_processor"
)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
)
```

The root processor is the native training processor. The
`locked_processor/` subdirectory preserves the recent-view evaluation
processor. The supplied evaluator implements causal sampling and benchmark
prompt conventions; loading the processor alone does not implement TVS.

## Use the code

```bash
cd checkpoints/ViSS-8B/code
python -m pip install -e ".[inference,test]"
python -m pytest -q tests
```

See the evaluation guide to bind the public configuration template to your
own processor, benchmark query exports, and model. Benchmark media and
official scoring installations must be obtained separately. TVS additionally
requires calibration inputs prepared independently of benchmark evaluation.

## License

The source code follows the project's Apache-2.0 license. The model is
derived from Qwen3-VL-8B-Instruct, which is also distributed under Apache-2.0.
External benchmark and media terms remain with their respective providers.

## Citation

```bibtex
@misc{hu2026viss,
  title={Supervising the Visible State: Separating Representation from View Selection in Streaming Video},
  author={Yihao Hu and Pan Wang and Yitong Lin and Zhihao Wen and Deyuan Liu and Hang Wang and Mingda Wan and Yiwen Zhao and Yutong Li and Yuchen Mao and Tao Lin},
  year={2026},
  note={Manuscript}
}
```