DenseReward / README.md
yuffish's picture
Dataset release
92064b5 verified
|
Raw
History Blame Contribute Delete
3.31 kB
metadata
license: apache-2.0
task_categories:
  - robotics
  - image-to-text
  - reinforcement-learning
tags:
  - robot-manipulation
  - reward-model
  - vision-language
  - vlm
  - dense-reward
pretty_name: DenseReward
size_categories:
  - 500K<n<1M

DenseReward Dataset

🌐 Project page · 📄 Paper (arXiv:2607.13033)

This is the dataset for DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation. It pairs single robot-manipulation frames (and short chronological frame windows) with a scalar task-progress reward in [0.000, 1.000], used to finetune a vision-language reward model.

Models trained on this data:

Dataset structure

data/
  droid.zip
  isaac.zip
  robosuite.zip
  libero.zip
splits/
  1frame/{train,val,test}.json          # 1 image per sample -> reward
  3frame-thinking/{train,val,test}.json # 3 chronological images per sample -> <think>reason</think> + reward
  manifest.json                          # trajectory-level train/val/test assignment

Each source's images ship as a zip in data/. Unzip each one in place so it expands to data/droid/*.jpg, matching the paths referenced in splits/*/*.json.

Data format

Each split file is a JSON list of samples in a simple SFT conversation format:

splits/1frame/*.json: one image, plain reward target

{
  "conversation": [
    {"from": "human", "value": "<image>put the alcohol on the plate"},
    {"from": "assistant", "value": "0.327"}
  ],
  "images": ["data/isaac/isaac_alcohol_0_collision_000_frame_000300.jpg"]
}

splits/3frame-thinking/*.json : 3 chronological images (oldest → current; early frames in a trajectory repeat the first frame to pad the window), a reasoning word, then the reward for the last frame. Here the reward drops (0.341 → 0.327) as the robot collides with the object, and the reasoning word reflects it:

{
  "conversation": [
    {"from": "human", "value": "<image><image><image>put the alcohol on the plate"},
    {"from": "assistant", "value": "<think>\ncollision\n</think>\n\n0.327"}
  ],
  "images": [
    "data/isaac/isaac_alcohol_0_collision_000_frame_000240.jpg",
    "data/isaac/isaac_alcohol_0_collision_000_frame_000270.jpg",
    "data/isaac/isaac_alcohol_0_collision_000_frame_000300.jpg"
  ]
}

The <think> vocabulary is correct | miss | collision | fall | not smooth | failure.

License

Released under Apache License 2.0 for this repository.

Citation

@article{fang2026densereward,
    title={DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation},
    author={Fang, Yu and Dong, Wanxi and Liu, Jiaqi and Yang, Yue and Huo, Mingxiao and Mu, Yao and Yao, Huaxiu and Li, Li Erran and Szafir, Daniel and Ding, Mingyu},
    journal={arXiv preprint arXiv:2607.13033},
    year={2026}
}