Justin Johnson

RyeCatcher

·

https://www.jandsgroupllc.com

AI & ML interests

Im a builder

Recent Activity

updated a Space 2 days ago

RyeCatcher/repro-quantifying-error-propagation-and-model-collapse-in-diffusion-models

published a Space 2 days ago

RyeCatcher/repro-quantifying-error-propagation-and-model-collapse-in-diffusion-models

updated a Space 2 days ago

RyeCatcher/repro-scalora-optimally-scaled-low-rank-adaptation-for-efficient-high-rank-fine-tuning

View all activity

Organizations

RyeCatcher 's Spaces 163

Reproduction: Quantifying Error Propagation and Model Collapse in Diffusion Models

Explore research logs, code, and traces in one view

Reproduction: ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning

Explore code, traces, and workspace in an interactive logbook

Reproduction: A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms

Explore and manage research logs with a web‑based logbook

Reproduction: On Structured State-Space Duality

Explore code logs, traces, and workspace interactively

Reproduction: Modeling Covariate Transition for Efficient Estimation of Longitudinal Treatment Effects in Randomized Experiments

Explore experiment logs, traces, and workspace online

Reproduction: Robust and Consistent Ski Rental with Distributional Advice

Explore experiment logs, code, and traces

Reproduction: Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees

Explore project logs, traces, and workspace in a web dashboard

Reproduction: Perceptrons and Localization of Attention’s Mean-Field Landscape

Explore code logs, traces, and workspace in an interactive logbook

Reproduction: Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation

Explore code, traces, and workspace in an interactive logbook

Reproduction: A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization

Explore project logs, code, and traces in an interactive web logbook

Reproduction: From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning

Explore experiment logs, traces, and workspace online

Reproduction: Curated Synthetic Data Doesn’t Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences

Explore project logs, traces, and workspace in one view

Reproduction: ICML 2026 reproduction zxJXgfCm63

Explore experiment logs and traces in an interactive logbook

Reproduction: ICML 2026 reproduction yE3zbIOW3e

Explore research logbook with code, traces, and workspace

Reproduction: ICML 2026 reproduction xixoixLXCr

Explore research reproduction logs and traces

Reproduction: ICML 2026 reproduction okzQ1x71pS

Explore research logbooks with code, traces, and workspace views

Reproduction: ICML 2026 reproduction ljNZyrAlaa

Explore and manage research logbooks with interactive views

Reproduction: ICML 2026 reproduction l35QweVxgn

Explore reproducibility logs with code, traces, and workspace

Reproduction: ICML 2026 reproduction 1JwSFRvC4E

Explore research reproducibility logbook with code and traces

Reproduction: ICML 2026 reproduction 01caH9oj7C

Explore experiment logs, code, and traces in a web dashboard

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

Explore code logs, traces, and workspace in a web logbook

Reproduction: Allocating Variance to Maximize Expectation

Explore code, traces, and workspace in an interactive logbook

Reproduction: Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks

Browse and organize experiment logs, code, and traces

Reproduction: On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification

Explore code, traces, and workspace in an interactive logbook