🩵 123

Alex

snaykey

3 8

·

AI & ML interests

AI Safety & Redteaming

Recent Activity

liked a model 1 day ago

audnai/penclaw-Kimi-K3.0-abliterated-GGUF

updated a Space 1 day ago

snaykey/repro-sample-compressible-noise

updated a Space 1 day ago

snaykey/repro-vdw-gnns

View all activity

Organizations

snaykey 's Spaces 299

Reproduction: DAL: Detection Augmented bandit, prior-free piecewise-stationary bandits

Explore and share experiment logs with an interactive web logbook

Repro: Exploration-free Algorithms for Multi-group Mean Estimation

Explore and sync research logs with an AI coding agent

Repro: Calibrating Decision Robustness via Inverse Conformal Risk Control (CREME)

Explore experiment logs and sync findings with an AI agent

Repro: Non-Uniform Noise-to-Signal Ratio in the REINFORCE Estimator

Explore and edit project logbooks in a web interface

Reproduction: Beyond First-order Asymptotics in Sequential Mean Testing

View and collaborate on a research logbook online

Reproduction: Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing

Browse and collaborate on a structured research logbook

PABLO Unconstrained Bandits — Reproduction

Browse and collaborate on research logbooks online

Feasibility Methods Reproduction

Explore research logbook and collaborate with an agent

eNMF — Reproduction

Explore and sync experiment logs with your coding agent

Reproduction: PCA of Probability Measures (Sparse and Dense Sampling Regimes)

Explore and collaborate on research logbooks online

Reproduction: Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics

Log research findings in a collaborative, token‑efficient logbook

Latent Laplace Diffusion for Irregular Multivariate Time Series (LLapDiff)

Explore and sync your project logbook with a coding agent

On the Power of Source Screening for Learning Shared Feature Extractors

Explore research logbook and collaborate with AI agent

Reproduction: Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning

Browse research logbook and collaborate with an AI agent

On the Accuracy of Newton Step and Influence Function Data Attributions

Explore and manage project logbooks online

Reproduction: Provable Training Data Identification for Large Language Models

Browse and collaborate on a research logbook

Revenue Guarantees of No-Swap-Regret Dynamics in First Price Auctions

Explore and edit project logbooks with AI collaboration

Reproduction: A Direct Second-Order Method for Solving Two-Player Zero-Sum Games

View and collaborate on experiment logbooks

Optimal structure learning and conditional independence testing

Explore and sync experiment logbook for structure learning

Reproduction: Prior Diffusiveness and Regret in the Linear-Gaussian Bandit

Browse research logbooks and sync findings with an agent

Reproduction: Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport

Browse and sync research logbook with a coding assistant

(Doubly) Exponential Lower Bounds for Follow the Regularized Leader in Potential games

Explore and collaborate on a research logbook

Reproduction: Anytime Detection of Strategic Deviations in Multi-Agent Systems

Track and share findings with your AI coding agent

Reproduction: Ski Rental with Distributional Predictions of Unknown Quality

Explore research logbook and sync findings with AI agent