🩵 123

Alex

snaykey

3 7

·

AI & ML interests

AI Safety & Redteaming

Recent Activity

updated a Space about 3 hours ago

snaykey/repro-vi-bures-wasserstein

published a Space about 3 hours ago

snaykey/repro-vi-bures-wasserstein

updated a Space about 3 hours ago

snaykey/repro-approx-reward-inference

View all activity

Organizations

snaykey 's Spaces 245

Reproduction: Variational inference via Gaussian interacting particles in the Bures-Wasserstein geometry

Explore and collaborate on research logbooks

Reproduction: On the Power of (Approximate) Reward Models for Inference-Time Scaling

Explore and sync research logbook with your AI agent

Reproduction: Anytime Safe PAC Efficient Reasoning

Collaborate with an AI agent to view and edit a logbook

Reproduction: Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

Explore experiment logs and collaborate with your agent

Reproduction: Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality

Create and share a structured research logbook

Reproduction: Language Generation with Replay: A Learning-Theoretic View of Model Collapse

Collaborate with an AI agent on a shared logbook

Reproduction: Context-free Recognition with Transformers

Explore and collaborate on experiment logs with a web logbook

Reproduction: On the Expressive Power of Permutation-Equivariant Weight-Space Networks

Explore and collaborate on research logbooks online

Reproduction: Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models

Explore research logbook and sync AI‑generated findings

Reproduction: Efficient Stochastic Optimisation via Sequential Monte Carlo

Explore and sync research logbook with an AI agent

Reproduction: Universal Representation of Generalized Convex Functions and their Gradients

Browse a research logbook and collaborate with an AI agent

Reproduction: Planar Symmetric Pattern Generation

Explore and sync a coding logbook with your AI agent

Reproduction: Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions

Collaborate with an AI agent to explore your logbook

Reproduction: Positive Distribution Shift as a Framework for Understanding Tractable Learning

Collaborate on research notes with an AI coding agent

Reproduction: Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach

Explore research logbooks and collaborate with an AI agent

Reproduction: Momentum Further Constrains Sharpness at the Edge of Stochastic Stability

Explore and collaborate on research logbooks online

Reproduction: On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks

Reproduction: Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization

Explore and manage your experiment logbook online

Reproduction: Personalized Policy Learning through Discrete Experimentation (DLPT)

Explore and share experiment logs with an AI collaborator

Reproduction: Online Robust Reinforcement Learning with General Function Approximation

Explore and collaborate on a research reproducibility logbook

Repro: Deep Networks Learn to Parse Context-Free Languages from Local Statistics

Collaborate on a coding logbook with your AI agent

Reproduction: Efficiently Solving Discounted MDPs with Predictions on Transition Matrices

Explore research logbook and sync with AI agent

Reproduction: Minimizing Upper Confidence Bounds - A Data-Driven Framework for Stochastic Programming

Browse experiment logs and sync findings with a coding agent

Reproduction: Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy

Explore research logbooks and collaborate with an AI agent