🔄 In a Training Loop

SSH PRO

ProCreations

·

https://ssh.codes

AI & ML interests

Making AI’s small, accessible, and easy to run on consumer hardware

Recent Activity

posted an update about 11 hours ago

check out this cool webgpu thing i made! https://huggingface.co/spaces/ProCreations/maple-webgpu runs this model https://huggingface.co/deepgrove/maple-preview with cool performance i found today on WebGPU locally on your computer with very fast speeds. made with a mix of gpt 5.6 sol + opus 5 ultracode, its amazing what agents can do now, just a year ago this wouldve been impossible with them.

liked a model about 11 hours ago

deepgrove/maple-preview

liked a model about 12 hours ago

ProCreations/maple-preview-webgpu-v2

View all activity

Organizations

ProCreations 's Spaces 353

Reproduction - APORIA Hallucination Geometry

APORIA full-data geometry and label-propagation reproduction

Reproduction - Learning in Structured Stackelberg Games

Explore and collaborate on a structured research logbook

Reproduction - Allocating Variance to Maximize Expectation

Explore and collaborate on research logs with an AI agent

Reproduction Robust Online Inverse Optimization

View and collaborate on research logbooks

Reproduction - Budget-Feasible Mechanisms for Submodular Welfare Maximization in Procurement Auctions

Collaborate on experiment logs with an AI assistant

Reproduction - Sliced Distributional RL

Sliced-divergence distributional-RL audit

Reproduction - Implicit Bias of Adam and Muon

Explore research logbooks and collaborate with an AI agent

Reproduction - Maximin Relative Improvement

Maximin relative-improvement fair-learning audit

Reproduction - Fair Decisions from Calibrated Scores

Exact sufficient classifiers and fairness geometry

Reproduction - Last-Iterate Stochastic Proximal Rates

Last-iterate rates, graph proximal, and variance audit

Reproduction - Do-Calculus Derivation Graphs

Exact do-calculus paths, commutativity, and Sachs audit

Reproduction - GRPO Effective Loss and Success Amplification

Exact GRPO dynamics, amplification, and error-bound audit

Reproduction MNL Optimal Design

Explore reproducibility evidence for MNL optimal design

Repro - To Grok Grokking: Provable Grokking in Ridge Regression

Explore and sync research notes with an AI coding agent

Reproduction Sampling and Identity-Testing Without Approximate Tensorization of Entropy

View and collaborate on a research logbook

Reproduction - Persuasive Privacy

Persuasive-privacy mechanism audit

Reproduction - RLVR Backtracking

RLVR-versus-SFT backtracking audit

Reproduction - Sharp Empirical Bernstein Variance Bounds

Browse a research logbook and sync notes with an AI agent

Reproduction - Theoretical Investigation on Inductive Bias of Isolation Forest

Browse and sync research logbook with AI agent

Reproduction - Set-Preserving Calibration

Set-preserving p-to-e calibration audit

Reproduction — Bridging the Gap Between Average and Discounted TD Learning

Explore experiment logs and collaborate with a coding agent

Reproduction - Compressed Decentralized OCO

Compressed decentralized online-optimization audit

Reproduction - Hidden-State ZO Privacy

Hidden-state privacy amplification audit

Reproduction - Latent Agentic Substructures

Audit of latent agentic substructures in neural networks