RepoAlerts

galilai-group/prh-proof

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 17 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

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

What it is

Research code that tests the Platonic Representation Hypothesis with JEPA objectives. It trains separate encoders per modality, measures how far their embeddings align through a single rotation, and provides evaluation scripts, theory checks, and an image and video captioner…

Who it's for

Machine learning researchers studying multimodal representation alignment and JEPA-style self-supervised training

How to use it

Install

pip install -e ".[dev]"

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 galilai-group/prh-proof in my project. Follow its README: https://github.com/galilai-group/prh-proof. Explain each step and check it is safe before running anything.

Star curve

230From 0 to 230 stars between 13 Oct 2026 and 15 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.

[![galilai-group/prh-proof on RepoAlerts](https://repoalerts.com/badge/galilai-group/prh-proof.svg)](https://repoalerts.com/repo/galilai-group/prh-proof?ref=badge)
Share on X

  • zylwithxy/HRDiT

    Research code for HRDiT, a training-free method that adapts off-the-shelf FLUX.1-dev diffusion transformers to generate high-resolution images up to 4K. It combines Spatial Position Alignment (SPA) to

    Models & inferencePython · 317 stars · 103 days old

  • slee-persis/GVS5H

    Research code for ledger-based zero-shot self-orchestration, a training-free method where fresh instances of one model decompose coding problems and coordinate through a shared filesystem holding a pl

    AI agentsPython · 1,207 stars · +4 this week · 83 days old · HN 188 pts

  • AmSach/maple

    Research project that prunes low-activation experts from Mixture-of-Experts LLMs using routing statistics from a calibration corpus, with a reference Gemma 4 26B-A4B model reduced to about 4.75 GB for

    Models & inferencePython · 60 stars · +15 this week · 10 days old · HN 21 pts

  • Robbyant/lingbot-touch

    Inference code for LingBot-Touch, a JEPA-based foundation model that learns latent representations from heterogeneous tactile sensor signals (magnetic, piezoresistive, visuotactile). It provides a fro

    ModelModels & inferencePython · 755 stars · +630 this week · 8 days old

  • prabanta-dev/janas

    A C inference engine for running large mixture-of-experts language models on ordinary computers, with or without a GPU. Weights stay on disk, and the experts each token needs are streamed from an NVMe

    Models & inferenceC · 729 stars · +44 this week · 58 days old · HN 220 pts

  • Clearailhc/clearai-dsh

    A DSH agent preset that organises research into a domain ontology. Each question is framed with its measured quantities and candidate hypotheses, tested against evidence, and accepted as an establishe

    AgentAI agentsJavaScript · 701 stars · +3 this week · 66 days old