pinned
Sleeping
LedgerLens Incident Commander
🚨
DataHub incident plans sealed by deterministic policy.
Yim PRO
tomyimkc
AI & ML interests
None yet
Organizations
pinned
Sleeping
Agents
验证边界 Verification Frontier
🛡
Safely Catching Logic Errors in LLM Scientific Reasoning
pinned
Running
Sophia AGI Training Observatory
🔭
Running
MemoryStand
🧾
Memory for AI agents that must prove it worked.
Build error
GOAI Verification Frontier
🔒
Running
Polygraph — Arm64 cloud inference verification
🚀
Verify Arm64 inference path before deployment
Sleeping
Sourcetrace
🔬
Verify factual claims in any paragraph
Sleeping
Agents
1
→ Moved to verification-frontier
➡
Moved to tomyimkc/verification-frontier
Running
Reproduction: Logarithmic Switching Regret for Online Convex Optimization
🎯
Explore code, traces, and workspace in a collaborative logbook
Running
Reproduction: Geometry-Misalignment in Distributional Learning
🎯
Explore and collaborate on project logs and code traces
Running
Reproduction: Inference-time Alignment with Rewards in Besov Spaces: Provable Advantages of Feature Learning and Multi-Step Policy Updates
🎯
Explore and manage project logs, traces, and workspace
Running
Reproduction: A Causal Decomposition Approach for Fair Contextual Multi-Armed Bandits
🎯
Explore project logs, traces, and workspace in a web UI
Running
Reproduction: Robust Learning via Nested Distributionally Robust Optimization
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Reproduction: Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
🎯
Browse code logs, traces, and collaborate with an AI agent
Running
Reproduction: Rethinking the Hardness of PbRL: A Provable General Regret Bound
🎯
Explore project logs and collaborate with an AI agent
Running
7
Reproduction: Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
🎯
Explore and manage research logbooks with interactive views
Running
Reproduction: Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
🎯
Explore and manage project logs, code, and traces
Running
Reproduction: Constrained Meta Reinforcement Learning with Provable Test-Time Safety
🎯
Explore experiment logs, traces, and workspace online
Running
Reproduction: Learning-Augmented Online Covering Problems
🎯
Explore project logs, traces, and workspace online
Running
Reproduction: Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
🎯
Explore code logs, traces, and workspace in a collaborative logbook
Running
Reproduction: Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
🎯
Explore project logs, traces, and workspace in an interactive UI
Running
Reproduction: Is Spurious Correlation Removal Always Learnable?
🎯
Explore project logs, traces and collaborate with a coding agent
Running
Reproduction: Reusing Trajectories in Policy Gradients Enables Fast Convergence
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Reproduction: A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
🎯
Explore code, traces, and workspace in an interactive logbook