SAVRN
Search Contact SAVRN

Independent publisher

Youhe Feng

ce-amtic

Models in Library1
Datasets in Library0
Models on Hugging Face2
Followers3

Models

Model · Image and text to text

ProcVLM-2B

Youhe Feng

ProcVLM-2B is a procedure-grounded vision-language model for estimating progress rewards from robot manipulation observations. Given a task description and a recent window of video frames, the model reasons about the remaining atomic actions and predicts the current task completion percentage. ProcVLM-2B is designed for research on robot learning, progress reward modeling, embodied evaluation, and procedure-aware video understanding. Typical use cases include: - estimating task completion progress from robot videos; - producing dense progress rewards from sparse demonstrations; - adapting progress prediction to a new environment with one-shot LoRA fine-tuning. This model is not intended to…

Open weights cc-by-4.0 2.4B parameters 262,144 tokens transformers