🤝 Open to Collab

gharsallah

agharsallah

·

gharsallah

AI & ML interests

None yet

Recent Activity

updated a Space about 23 hours ago

agharsallah/lfkgj60bgq-logbook

published a Space about 23 hours ago

agharsallah/lfkgj60bgq-logbook

updated a Space about 23 hours ago

agharsallah/20hdqqqra4-logbook

View all activity

Organizations

agharsallah 's Spaces 192

Practical and Scalable Hamiltonian Monte Carlo Without the Metropolis Test

Edit and display a simple static webpage

Design-Based Anytime-Valid Inference for Randomized Experiments with Delayed Outcomes and Staggered Entry

Display a customizable static web page

Hedging on the Frontier: Learning New Tasks with Few Samples

Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach

Host a custom static web page on Hugging Face Spaces

To Grok Grokking: Provable Grokking in Ridge Regression

Display a customizable static web page

Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency

Show a customizable static web page

Theoretical Challenges in Learning for Branch-and-Cut

General Synthetic-Powered Inference

Create a customizable static web page

Zero-Flow Encoders

Create a custom static web page

Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning

Edit and preview a static web page instantly

Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification

Display a welcome page for your static Space

Approximate Proportionality in Online Fair Division

Create a simple static web page

Gaussian Mean Field Variational Inference can Overestimate Predictive Variance

Display a simple static welcome page

Repro - Ski Rental with Distributional Predictions of Unknown Quality

Collaborate with your AI agent to log findings automatically

Repro - Attention's forward pass and Frank-Wolfe

Collaborate with your coding agent via a synced logbook

Repro - Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning

Explore and collaborate on a project logbook with an AI agent

Repro - Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes

Explore and collaborate on experiment logbooks

Repro - Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models

View and sync research logbook with your coding agent

Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts

View reproducibility report for Prediction‑Powered Risk Monitoring

Repro - Rethinking Code Complexity Through the Lens of Large Language Models

View and sync code analysis logbook with your AI coding agent

Repro - SimpleMem: Efficient Lifelong Memory for LLM Agents

Create a token‑efficient logbook for LLM agents

Repro - Revisiting Neural Processes via Fourier Transform and Volterra Series

Collaborate on a shared research logbook with your coding agent

Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment

Display a customizable static web page

Context-free Recognition with Transformers

Display a customizable static web page