🔄 In a Training Loop

Abdullah Mujeeb Khawaja

amkkk

·

https://navigatingnoise.substack.com/

AI & ML interests

None yet

Recent Activity

liked a Space 19 minutes ago

ICML-2026-agent-repro/challenge

liked a model 26 minutes ago

AxiomicLabs/GPT-X2.5-135M

liked a model about 14 hours ago

0xSero/Gemma-4-21B

View all activity

Organizations

amkkk 's Spaces 283

Reproduction: Accurate Evaluation of Quickest Changepoint Detectors

Explore project logs, code, and traces in an interactive web UI

Reproduction: Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification

Explore code, traces, and workspace in an interactive logbook

Reproduction: Linear Regression with Unknown Truncation Beyond Gaussian Features

Explore experiment logs with code, traces, and workspace

Reproduction: Follow-the-Perturbed-Leader for Decoupled Bandits

Explore experiment logs and traces in an interactive web UI

Reproduction: Efficient Privacy Loss Accounting for Subsampling and Random Allocation

Explore code, traces, and workspace in an interactive logbook

Reproduction: The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks

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

Reproduction: Semi-knockoffs — a model-agnostic conditional independence testing method with finite-sample guarantees

Browse project logs, traces, and workspace

Reproduction: Allocating Variance to Maximize Expectation

Explore experiment logs and traces in an interactive workspace

Reproduction: Steady-State Behavior of Constant-Stepsize Stochastic Approximation

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

Reproduction: Sinkhorn Normalization of Diffusion Kernels

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

Reproduction: Certificate-Guided Pruning for Stochastic Lipschitz Optimization

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

Reproduction: Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

Explore code, traces, and workspace in an interactive logbook

Reproduction: A Perturbation Approach to Unconstrained Linear Bandits

Explore research code, traces, and workspace in a logbook

Reproduction: Innovation: An Almost Characterization of Hallucination

Explore project logs and collaborate with an AI agent

Reproduction: Why Deep Jacobian Spectra Separate

Explore and edit project logs with AI collaboration

Reproduction: Bayesian Membership Inference Attacks

View code logs, execution traces, and collaborate via an agent

Reproduction: DiScoFormer: Plug-In Density and Score Estimation with Transformers

Explore project logs, code, and traces interactively

Reproduction: DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits

Explore code, traces, and workspace with an interactive logbook

Reproduction: A Formal Comparison Between Chain of Thought and Latent Thought

Browse code logs, execution traces, and workspace files

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

Explore research logs, code, and traces in an interactive logbook

Repro - An Algebraic View of the Expressivity of Recurrent Language Models

View and collaborate on project logbooks with an AI agent

On the Power of (Approximate) Reward Models for Inference-Time Scaling: SMC and Beyond

Collaborate with your coding agent in a web logbook

Repro - HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models

Explore project logs, code, and execution traces

Reproduction: Improved Algorithms for Nash Welfare in Linear Bandits

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