Jonas

imadreamerboy

AI & ML interests

AI safety and security: training data and models for safety classification, guardrails, jailbreak detection, and security-focused agents.

Recent Activity

updated a collection 7 days ago

AI Safety Evaluation Datasets

updated a collection 7 days ago

AI Safety Evaluation Datasets

updated a collection 7 days ago

AI Safety Evaluation Datasets

View all activity

Organizations

imadreamerboy 's Spaces 43

Reproduction: SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs

🎯

Explore simulation logs, traces, and workspace files

Reproduction: CauchyNet: Compact and Data-Efficient Learning Using Holomorphic Activation Functions

🎯

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

Reproduction: A hitchhiker's guide to Poisson gradient estimation

🎯

Browse code, traces, and workspace in an interactive logbook

Reproduction: High-accuracy sampling for diffusion models and log-concave distributions

🎯

Browse and manage project logs, traces, and workspace

Reproduction: The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?

🎯

Explore code, traces, and workspace in an interactive logbook

Reproduction: τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

🎯

Explore conversational agent logs and traces

Reproduction: MORE: A Multilingual Document Parsing Benchmark and Evaluation

📄

View C2 disclosure details and review status

Controlled LLM Training on Spectral Sphere — reproduction logbook

📐

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

Reproduction: Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers

🎯

Explore and share your project logbook with an AI agent

Reproduction: Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

🎯

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

Reproduction: The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

🎯

Explore project logs and collaborate with an AI agent

Mountain Car analytic-controller toy

🎯

View a static logbook of Mountain Car controller runs

Reproduction: SAQNN: Spectral Adaptive Quantum Neural Network as a Universal Approximator

🎯

Explore code, traces, and workspace for a research logbook

Reproduction: Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator

🎯

Explore and share research logbook with an AI agent

Reproduction: Semi-Supervised Hypothesis Testing by Betting on Predictions

🧪

Explore research logbook and collaborate with an AI agent

Reproduction: An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale

🎯

Explore and manage experiment logs and traces

Reproduction: A Solver-Free Training Method for Predict-then-Optimize

🎯

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

Reproduction: Flat Minima and Generalization: Insights from Stochastic Convex Optimization

🎯

Explore logs and sync findings with a coding agent

Reproduction: Romberg-Extrapolated Zeroth-Order Gradient Estimator: Higher-Order Bias Reduction with Preserved Leading Directional Variance

🎯

Browse research logs and collaborate with an AI agent

CHB Digits Quickstart Evidence

🔎

Explore quickstart run evidence for sklearn digits data

ReViT bounded CPU equivariance check

🧭

Verify CPU equivariance of ReViT models

Continual Learning Theory Evidence

🔎

KLENT bounded source and proof audit

📐

Browse KLENT source and proof audit summary

Low Kruskal-Rank Adaptation: source-audit candidate

📐

View source audit details for Low Kruskal‑Rank Adaptation

Jonas

AI & ML interests

Recent Activity

Organizations

imadreamerboy 's Spaces 43 Sort: Recently updated

Reproduction: SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs

Reproduction: CauchyNet: Compact and Data-Efficient Learning Using Holomorphic Activation Functions

Reproduction: A hitchhiker's guide to Poisson gradient estimation

Reproduction: High-accuracy sampling for diffusion models and log-concave distributions

Reproduction: The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?

Reproduction: τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reproduction: MORE: A Multilingual Document Parsing Benchmark and Evaluation

Controlled LLM Training on Spectral Sphere — reproduction logbook

Reproduction: Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers

Reproduction: Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reproduction: The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

Mountain Car analytic-controller toy

Reproduction: SAQNN: Spectral Adaptive Quantum Neural Network as a Universal Approximator

Reproduction: Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator

Reproduction: Semi-Supervised Hypothesis Testing by Betting on Predictions

Reproduction: An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale

Reproduction: A Solver-Free Training Method for Predict-then-Optimize

Reproduction: Flat Minima and Generalization: Insights from Stochastic Convex Optimization

Reproduction: Romberg-Extrapolated Zeroth-Order Gradient Estimator: Higher-Order Bias Reduction with Preserved Leading Directional Variance

CHB Digits Quickstart Evidence

ReViT bounded CPU equivariance check

Continual Learning Theory Evidence

KLENT bounded source and proof audit

Low Kruskal-Rank Adaptation: source-audit candidate

imadreamerboy 's Spaces 43