Kiều Sơn Tùng

codemaivanngu

1 33 16

AI & ML interests

None yet

Recent Activity

updated a Space about 6 hours ago

codemaivanngu/repro-decomposing-query-key-feature-interactions-using-contrastive-covariances

updated a bucket about 6 hours ago

codemaivanngu/repro-decomposing-query-key-feature-interactions-using-contrastive-covariances-artifacts

published a bucket about 6 hours ago

codemaivanngu/repro-decomposing-query-key-feature-interactions-using-contrastive-covariances-artifacts

View all activity

Organizations

codemaivanngu 's Spaces 12

Reproduction: Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher

🎯

Browse experiment logs, code, and traces in an interactive web UI

Reproduction: Contrastive QK Covariances

🔬

Explore code, traces, and workspace in an interactive logbook

Reproduction: PolicyGuard

🛡

Explore code logs, traces, and workspace in one web view

Reproduction: Autoregressive Direct Preference Optimization

📐

Explore project logs, traces, and workspace in a web UI

Reproduction: Probability of Matching for Batch Multi-Objective Bayesian Optimization

📐

Explore code logs, traces, and workspace

Reproduction: Hippocampal Place Field Gradient

🧠

Explore project logs, code, and traces in a web dashboard

Reproduction: Self-Distillation Enables Continual Learning

🎯

Explore experiment logs, code, and traces in a web UI

Reproduction: FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU

🎯

Explore experiment logs, code, and traces in a web interface

Reproduction: FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU

🎯

Explore project logs, code, and traces in an interactive UI

Icml2026 Faopd Metrics

🎯

View and analyze your tracking data in a dashboard

Icml2026 Sdft Metrics

🎯

View and monitor your data in an interactive dashboard

ML

🏃

Kiều Sơn Tùng

AI & ML interests

Recent Activity

Organizations

codemaivanngu 's Spaces 12 Sort: Recently updated

Reproduction: Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher

Reproduction: Contrastive QK Covariances

Reproduction: PolicyGuard

Reproduction: Autoregressive Direct Preference Optimization

Reproduction: Probability of Matching for Batch Multi-Objective Bayesian Optimization

Reproduction: Hippocampal Place Field Gradient

Reproduction: Self-Distillation Enables Continual Learning

Reproduction: FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU

Reproduction: FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU

Icml2026 Faopd Metrics

Icml2026 Sdft Metrics

ML

codemaivanngu 's Spaces 12