Reproduction: Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher
🎯
Explore and sync research logbook with AI agent
Kiều Sơn Tùng
codemaivanngu
AI & ML interests
None yet
Recent Activity
updated a Space about 19 hours ago
codemaivanngu/repro-adversarial-dual-on-policy-distillation published a bucket about 19 hours ago
codemaivanngu/fa-opd-icml2026-repro-bucket-3 updated a Space about 19 hours ago
codemaivanngu/repro-self-distillation-enables-continual-learningOrganizations
updated a
Space about 19 hours ago
published a
bucket about 19 hours ago
updated a
Space about 19 hours ago
updated a
bucket about 19 hours ago
published a
bucket about 19 hours ago
upvoted a paper 1 day ago
updated a
bucket 1 day ago
updated a
bucket 4 days ago
published 2
buckets 5 days ago
published a
Space 5 days ago
updated a
bucket 5 days ago
published 2
buckets 5 days ago
published a
Space 5 days ago
published 2
buckets 5 days ago
upvoted 3
papers 5 days ago
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
Paper • 2607.21653 • Published • 31
Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering
Paper • 2607.21848 • Published • 8
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
Paper • 2607.20465 • Published • 54