Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence

📄 Paper · 🌐 Project Page

Capek 0.5 is an execution-centric vision-language model. It brings spatial reasoning, temporal understanding, action guidance, and state verification into a single model for embodied reasoning. This repository provides Capek0.5-35B-A3B, built on Qwen3.6-35B-A3B, in Hugging Face Transformers format.

The four capabilities provide complementary evidence throughout the observation–reasoning–action cycle.

Capabilities and Training

Capek 0.5 organizes embodied reasoning around four recurring requirements of task execution:

• Spatial Reasoning: geometry, relative positions, and viewpoint changes.
• Temporal Understanding: event order, scene changes, and temporal localization.
• Action Guidance: target points, affordance regions, and ordered image-space trajectories.
• State Verification: physical predicates and task completion.

Each capability is first learned by a dedicated specialist through reinforcement learning with verifiable rewards, starting from the same backbone. TIES weight merging combines the specialists to initialize a unified student, which is refined through routed multi-teacher on-policy distillation (MOPD). Specialist routing is used during training; inference runs on a single consolidated checkpoint.

Model Details

• Architecture: Qwen3_5MoeForConditionalGeneration (qwen3_5_moe).
• Scale: 35B total parameters, approximately 3B active per token, following the upstream architecture.
• Inputs: text, images, and video through the supplied multimodal processor and chat template.
• Outputs: generated text, including structured predictions when requested by the prompt.

Evaluation Results

Under the paper's matched evaluation protocol, Capek0.5-35B-A3B improves 28 of 34 benchmark rows over its Qwen3.6-35B-A3B initialization. Selected results are shown as Qwen3.6 → Capek 0.5:

• VSI-Bench: 60.83 → 70.69; Video-MME: 71.33 → 74.19.
• PointBench: 76.66 → 81.22; StateBench-P: 65.80 → 76.80.
• EmbodiedBench task success: EB-HAB 46.0% → 63.0%; EB-ALF 50.7% → 55.3%.

License and Attribution

Original Capek 0.5 contributions and the Qwen-derived components are distributed under Apache 2.0, as described in LICENSE.

• LICENSE-Apache-2.0: the Apache License, Version 2.0.
• LICENSE-Qwen3.6: the unchanged upstream license, including Copyright 2026 Alibaba Cloud.

This is a modified, post-trained derivative. Preserve the applicable license texts, attribution, and modification notices when redistributing. The upstream revision linked in LICENSE identifies the verified license text, not the exact training initialization revision.

Citation

@misc{chen2026capek05,
  title={Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence},
  author={Ying Chen and Weizhen Li and Zhe Hu and Zhenjiang Li and Rui Jiang and Zhifeng Gu and Lihuang Fang and Jiangping Liu and Lei Yi and Jie Chen},
  year={2026},
  eprint={2608.06756},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2608.06756}
}