🔄 In a Training Loop

Abdullah Mujeeb Khawaja

amkkk

11 3 46

https://navigatingnoise.substack.com/

AI & ML interests

Tough question as I love all areas of DL, but from all of it, embeddings are my favourite topic. Currently obsessed with what can we do around LLMs. MLE @ DPD, prev DS in Recs Systems @ Alibaba Group

Recent Activity

liked a model 4 days ago

fulcrumresearch/echo

liked a dataset 6 days ago

CoderBak/anagram-corpus

liked a model 17 days ago

google/embeddinggemma-2

View all activity

Organizations

amkkk 's Spaces 283

Reproduction: Exploration-free Algorithms for Multi-group Mean Estimation

🎯

Explore code, traces, and workspace of research experiments

Reproduction: Coupled Training with Privileged Information and Unlabeled Data

🎯

Explore code logs, traces, and workspace in a collaborative UI

Reproduction: Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints

🎯

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

Reproduction: A Fully First-Order Layer for Differentiable Optimization

⚙

Explore code, traces, and workspace in an interactive logbook

Reproduction: Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment

🎯

Explore and manage experiment logs and traces online

Reproduction: Understanding Generalization and Forgetting in In-Context Continual Learning

🎯

Explore experiment logs and collaborate with an AI agent

Reproduction: Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces

🎯

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

Reproduction: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

🎯

Explore code, traces, and workspace in an interactive logbook

Reproduction: Multivariate Distributional Reinforcement Learning Using Sliced Divergences

🎯

Explore experiment logs, traces, and workspace online

Reproduction: Understanding Behavior Cloning with Action Quantization

🎯

Explore code, traces, and workspace in an interactive logbook

Reproduction: Relative Entropy Estimation in Function Space

📉

Explore and manage experiment logs with AI collaboration

Reproduction: The Geometry of Projection Heads: Conditioning, Invariance, and Collapse

🧭

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

Reproduction: Perceptrons and Localization of Attention's Mean-Field Landscape

🧪

Explore experiment logs and collaborate with an AI agent

Reproduction: Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization

🧪

Reproduction: Rethinking Contrastive Learning for Graph Collaborative Filtering

🧪

Reproduction: Trajectory-Level Data Augmentation for Offline Reinforcement Learning

🧪

Reproduction: TimeRCD Zero-Shot Time Series Anomaly Detection

🧪

Explore and reproduce zero-shot time series anomaly detection

Reproduction: MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification

🧪

Explore experiment logs and traces in an interactive workspace

Reproduction: Testing For Distribution Shifts with Conditional Conformal Test Martingales

🎯

Explore experiment logs and code in an interactive web view

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

🧪

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

Reproduction: MIRA — A Score for Conditional Distribution Accuracy and Model Comparison

🎯

Explore experiment logs and collaborate with an AI agent

Reproduction: Time series saliency maps: Explaining models across multiple domains

📈

Explore and manage experiment logs with an interactive workspace

Reproduction: Gromov-Wasserstein at Scale, Beyond Squared Norms

📐

Explore and collaborate on project logs, code, and traces

Reproduction: A Geometric Analysis of Small-sized Language Model Hallucinations

📊

Explore research logbooks with code, traces, and workspace views

Abdullah Mujeeb Khawaja

AI & ML interests

Recent Activity

Organizations

amkkk 's Spaces 283 Sort: Recently updated

Reproduction: Exploration-free Algorithms for Multi-group Mean Estimation

Reproduction: Coupled Training with Privileged Information and Unlabeled Data

Reproduction: Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints

Reproduction: A Fully First-Order Layer for Differentiable Optimization

Reproduction: Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment

Reproduction: Understanding Generalization and Forgetting in In-Context Continual Learning

Reproduction: Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces

Reproduction: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Reproduction: Multivariate Distributional Reinforcement Learning Using Sliced Divergences

Reproduction: Understanding Behavior Cloning with Action Quantization

Reproduction: Relative Entropy Estimation in Function Space

Reproduction: The Geometry of Projection Heads: Conditioning, Invariance, and Collapse

Reproduction: Perceptrons and Localization of Attention's Mean-Field Landscape

Reproduction: Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization

Reproduction: Rethinking Contrastive Learning for Graph Collaborative Filtering

Reproduction: Trajectory-Level Data Augmentation for Offline Reinforcement Learning

Reproduction: TimeRCD Zero-Shot Time Series Anomaly Detection

Reproduction: MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification

Reproduction: Testing For Distribution Shifts with Conditional Conformal Test Martingales

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

Reproduction: MIRA — A Score for Conditional Distribution Accuracy and Model Comparison

Reproduction: Time series saliency maps: Explaining models across multiple domains

Reproduction: Gromov-Wasserstein at Scale, Beyond Squared Norms

Reproduction: A Geometric Analysis of Small-sized Language Model Hallucinations

amkkk 's Spaces 283