Running Repro - Sharp Inequalities between Total Variation and Hellinger Distances for Gaussian Mixtures π― Explore a research logbook and invite an AI agent to collaborate
Running Repro - Score Anisotropy Directions π― Explore experiment logs and collaborate with an AI agent
Running Repro β Regression Language Models for Code (RegressLM) π― Explore regression logs and sync with a coding agent
Running Reproduction: Logical Guidance for the Exact Composition of Diffusion Models π― Explore a structured logbook of diffusion model experiments
Running Repro - Floating-Point Networks with AD π― Browse and share experiment logs with an AI agent
Running Repro - Optimal Design for Multinomial Logit Model π― Generate optimal designs for multinomial logit models
Running Repro - Rate-Distortion Theorem for Membership Testing π― Collaborate on a research logbook with your coding agent
Running Reproduction Efficient Privacy Loss Accounting π― Collaborate with an AI agent to manage a research logbook
Running Repro - TPGD Multi-Task Representation (arXiv 2605.00473) π― Explore research logbook and sync findings with an AI agent
Running Repro - Impact of Connectivity on Laplacian Representations in RL π― View and collaborate on experiment logs
Running Repro - The Cost of Learning Under Multiple Change Points π― Browse and edit research logbook with AI agent collaboration
Running Repro - Evaluating Bivariate Causal Statements Based on Mutual Compatibility π― View and sync experiment logs with your coding agent
Running Reproduction: Curated Synthetic Data Doesn't Have to Collapse π― Explore synthetic data logs and collaborate with an AI agent
Running Repro - Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained Problem π― Explore and share experiment logbooks with an AI agent
Running Repro - What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer (ykWN4LG9vE) π― Explore research logbook and collaborate with AI agent
Running Learning Randomized Reductions β five-claim reproduction π― View and collaborate on a project logbook
Running Reproduction: Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't π― Collaborate with an AI agent to view and edit proof audit logs
Running Repro - Success Conditioning as Policy Improvement π― Explore experiment logs and sync them with an AI agent
Running Claim-level Reproduction - Latent Agentic Substructures π― Collaborate with an AI agent on a shared logbook
Running Repro - Correctly Reporting LLM-as-a-Judge Evaluations π― Log LLM evaluation results and sync with your coding agent
Running Repro - Task-Awareness Improves LLM Generations and Uncertainty π― Log tasks and sync findings with your coding agent
Running Repro - Demystifying LLM-as-a-Judge π― Explore and share a tokenβefficient logbook with AI agents