GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mis2
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mis2
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
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.
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.
bash
hf download mis2/ViSS-8B --local-dir checkpoints/ViSS-8BUse a Transformers version supporting Qwen3-VL; the retained model configuration specifies Transformers 4.57.3.
python
import torchfrom 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.
bash
cd checkpoints/ViSS-8B/codepython -m pip install -e ".[inference,test]"python -m pytest -q testsSee 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.
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.
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}}import torchfrom 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",)cd checkpoints/ViSS-8B/codepython -m pip install -e ".[inference,test]"python -m pytest -q tests@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}}