🩵 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: A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation

Explore and edit a research logbook with AI agent collaboration

Reproduction: Gradient Flow Sampler-based Distributionally Robust Optimization

Explore experiment logs and collaborate with a coding agent

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

Explore and collaborate on a research logbook with an AI agent

Gaussian Mean Field Variational Inference can Overestimate Predictive Variance

Collaborate with your coding agent in a shared logbook

Reproduction: Full-Batch GD Outperforms One-Pass SGD in Single-Index Learning

View and collaborate on research logbooks with an AI agent

Reproduction: A Fully First-Order Layer for Differentiable Optimization

Explore experiment logs and sync findings with an AI agent

Differentiable Fairness Layers — Reproduction

Explore experiment logbooks and collaborate with an AI agent

Reproduction: Expectation Consistency Loss (calibration under covariate shift)

Explore experiment logs and collaborate with an AI agent

Repro: Dynamic Programming for Epistemic Uncertainty in Markov Decision Processes

Explore a research logbook and collaborate with AI

Reproduction: Conditional Equivalence of DPO and RLHF

Track and share research findings in an interactive logbook

Reproduction: Privacy Amplification in DP Zeroth-Order Optimization

Explore a research logbook and sync findings with an agent

Reproduction: Asymptotically Optimal Sequential Testing with Markovian Data

Explore research logbook and sync with coding agents

Reproduction: Questioning the Coverage-Length Metric in Conformal Prediction

Explore project logs and sync with an AI agent

Reproduction: Colorful Pinball (Density-Weighted Quantile Regression for Conformal Prediction)

Explore project logbook and sync with AI agent

Reproduction: Calibrated Preference Learning - The Case of Label Ranking

Browse and edit a research logbook with AI collaboration

Reproduction: CAffNet — Hard Constraint-Affine Neural Networks

Explore research logbooks and sync findings with a coding agent

Reproduction: Generalized Boundary FDR Control under Arbitrary Dependence (Domino)

Explore experiment logs and sync with a coding agent

Reproduction: Beyond ReLU — Bifurcation, Oversmoothing, and Topological Priors

Explore research logbook and sync findings with a coding agent

Reproduction: Adaptive Testing for LLM Evaluation (ATLAS)

Explore and collaborate on experiment logs with an AI agent

Reproduction: Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory

View and sync research logbook with your coding agent

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

Explore and sync research logbook with AI agent

Repro: Causal Modeling of Selection in Evolution

Explore and collaborate on a project logbook

Reproduction: Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels

Collaborate with your coding agent via a shared logbook

AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation

Explore benchmark logbook for narrative query‑to‑agent recommendations