🔄 In a Training Loop

SSH PRO

ProCreations

P(doom) <0.01%

·

https://ssh.codes

AI & ML interests

i make stuff

Recent Activity

liked a model 1 day ago

ProCreations/Image-2.1-Turbo-Calibrated-NVFP4

liked a model 1 day ago

ProCreations/Image-2.1-Turbo-Calibrated-FP8

updated a model 2 days ago

ProCreations/Image-2.1-Turbo-Calibrated-NVFP4

View all activity

Organizations

$Refract AI Labs's profile picture$

ProCreations 's Spaces 359

Repro - No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

Track and sync research reproducibility notes with an AI agent

Reproduction - Finding Most Influential Sets

Exact top-k and selection-consistency audit

Reproduction — Approximate Reward Models for Inference-Time Scaling

Explore research logbook and sync findings with an AI agent

Reproduction - Sketch-and-Project Natural Gradient

Subsampled natural-gradient and SPRING audit

Reproduction - Randomized Feasibility Methods

Adaptive randomized-feasibility convergence audit

Reproduction - Exact Categorical Functional ANOVA

Exact dependent categorical ANOVA identity and speed audit

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