ICML 2026 - Deep Jacobian Spectra Reproduction Independent claim reproduction for OpenReview 2kSBDoP1rE / arXiv 2602.12384. Running Repro - Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment 🎯 Explore and collaborate on research logbooks with an AI agent MarxistLeninist/2kSBDoP1rE-artifacts 6.13 MB
Running Repro - Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment 🎯 Explore and collaborate on research logbooks with an AI agent
ICML 2026 Reproduction - z9Bo4eXSpW Independent exact finite-support reproduction of arXiv:2503.06639. Running Repro - Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification 🎯 View and edit RL experiment logbook with AI agent collaboration
Running Repro - Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification 🎯 View and edit RL experiment logbook with AI agent collaboration
ICML 2026 - Deep Jacobian Spectra Reproduction Independent claim reproduction for OpenReview 2kSBDoP1rE / arXiv 2602.12384. Running Repro - Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment 🎯 Explore and collaborate on research logbooks with an AI agent MarxistLeninist/2kSBDoP1rE-artifacts 6.13 MB
Running Repro - Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment 🎯 Explore and collaborate on research logbooks with an AI agent
ICML 2026 Reproduction - z9Bo4eXSpW Independent exact finite-support reproduction of arXiv:2503.06639. Running Repro - Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification 🎯 View and edit RL experiment logbook with AI agent collaboration
Running Repro - Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification 🎯 View and edit RL experiment logbook with AI agent collaboration
Running Repro - Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective 🎯 Explore and organize experiment logs in an interactive web view
Running Repro - Skill Neologisms: Towards Skill-based Continual Learning 🎯 Explore and manage project logs, traces, and workspace
Running Reproduction: Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding 🎯 Explore RL experiment logs, traces, and workspace online
MarxistLeninist/repro-learning-to-bet-horizon-aware-traces Traces • Updated 2 days ago • 1 • 25
MarxistLeninist/repro-fast-and-scalable-analytical-diffusion-traces Traces • Updated 3 days ago • 26