🩵 123

Alex

snaykey

3 7

·

AI & ML interests

AI Safety & Redteaming

Recent Activity

updated a Space 6 minutes ago

snaykey/repro-treatment-rep-iv

published a Space 6 minutes ago

snaykey/repro-treatment-rep-iv

updated a Space 6 minutes ago

snaykey/repro-safety-efficacy-poisoning

View all activity

Organizations

updated a Space 6 minutes ago

Repro: Learning Treatment Representations for Downstream Instrumental Variable Regression

published a Space 6 minutes ago

Repro: Learning Treatment Representations for Downstream Instrumental Variable Regression

updated a Space 6 minutes ago

Repro: Safety-Efficacy Trade Off: Robustness against Data-Poisoning

published a Space 6 minutes ago

Repro: Safety-Efficacy Trade Off: Robustness against Data-Poisoning

updated a Space 7 minutes ago

Repro: Robust Sequential Experimental Design for A/B Testing

published a Space 7 minutes ago

Repro: Robust Sequential Experimental Design for A/B Testing

updated a Space 12 minutes ago

Repro: Variational Entropic Optimal Transport (VarEOT)

Explore and manage experiment logs in an interactive webbook

updated 3 Spaces about 6 hours ago

Repro: Swift-SVD — Low-Rank LLM Compression

Explore and share Swift‑SVD experiment logs

Reproduction: Optimal Regret for Policy Optimization in Contextual Bandits

Explore a research logbook and sync findings with an AI agent

Reproduction: Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises

Explore research logbook and sync with coding agent

updated 3 Spaces about 7 hours ago

Reproduction: Robust Learnability of Sample-Compressible Distributions

Explore and share a logbook with an AI coding agent

Repro: Key Collision Attack on LLM Semantic Caching

Explore and sync a research logbook with your coding agent

Repro: Multi-Distribution Robust Conformal Prediction

Track and share experiment logs with AI collaboration

published a Space about 7 hours ago

Repro: Multi-Distribution Robust Conformal Prediction

Track and share experiment logs with AI collaboration

updated a Space about 7 hours ago

Repro: Coupled Training with Privileged Information and Unlabeled Data

Explore and sync research logbook with an AI agent

published a Space about 7 hours ago

Repro: Coupled Training with Privileged Information and Unlabeled Data

Explore and sync research logbook with an AI agent

updated a Space about 7 hours ago

Repro: Riemannian Dueling Optimization

Track and organize research experiments in a collaborative logbook

published a Space about 7 hours ago

Repro: Riemannian Dueling Optimization

Track and organize research experiments in a collaborative logbook

updated a Space about 7 hours ago

Repro: Nonparametric LLM Evaluation from Preference Data

published a Space about 7 hours ago

Repro: Nonparametric LLM Evaluation from Preference Data