RepoAlerts

primotion-ai/Yuheng-Inference

Model

Can I trust it?

Be careful with this one.

  • Warnings Check

    Very new: it was created 11 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 5 days ago.

  • Licence Careful

    No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

Inference code for Yuheng, a model that estimates how much of a robot task is complete in an image. Users label keyframes from one successful demonstration with progress values, then score new images or attempts on that scale. Provides 4B and 27B model sizes.

Who it's for

Robotics and machine learning researchers evaluating task progress of robot or human demonstrations with Python and NVIDIA GPUs

How to use it

Install

python -m pip install .

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up primotion-ai/Yuheng-Inference in my project. Follow its README: https://github.com/primotion-ai/Yuheng-Inference. Explain each step and check it is safe before running anything.

Star curve

39From 0 to 39 stars between 6 Nov 2026 and 16 Nov 2026.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![primotion-ai/Yuheng-Inference on RepoAlerts](https://repoalerts.com/badge/primotion-ai/Yuheng-Inference.svg)](https://repoalerts.com/repo/primotion-ai/Yuheng-Inference?ref=badge)
Share on X

  • kaichen-z/SteerAct

    Research code for steering frozen robot action models (pi0.5 and Fast-WAM) on RoboTwin 2.0 tasks. Uses a pretrained sparse autoencoder to rank features from successful and failed rollouts, monitor exe

    ResourceModels & inferencePython · 287 stars · 33 days old

  • apple-aiml-research/ml-rsi-inference-bench

    A long-horizon benchmark for coding agents that improve the inference stack of large language models in vLLM or SGLang. Tasks cover supporting a model on day 0, optimizing it after launch, and repairi

    AI agentsPython · 167 stars · +24 this week · 32 days old

  • ZhuoyangLiu2005/agentic-wam

    A research codebase for AW-0, a world action model for robot manipulation that jointly denoises a code plan, future video and robot actions in one mixture-of-transformers. It includes pretraining, pos

    ModelModels & inferencePython · 176 stars · +9 this week · 44 days old

  • cair-vinuni/roboworm

    Benchmark and code for evaluating embodied robot video world models. It provides KIVA and RIGIS physics metrics that check rollouts against robot kinematics and camera geometry, plus scripts to benchm

    ResourceModels & inferencePython · 20 stars · 19 days old

  • jushengzhang/robot-weight-debugging

    Research code and experiment logs for an approach where an LLM agent inspects a pretrained robot policy's weights and edits 65 token-embedding rows to repair instruction failures, using simulator feed

    ResourceModels & inferencePython · 164 stars · +162 this week · 8 days old

  • THUSI-Lab/GameScaling

    Inference client and system-prompt template for GameScaling, a set of Qwen3.5 vision-language models with continued pre-training on keyboard-and-mouse gameplay. Given the current frame and recent hist

    AgentAI agentsPython · 520 stars · +6 this week · 38 days old