zhenzhang

namezz's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset about 1 hour ago

namezz/m2rl-issue18-agent32-transfer-public-20261030

Updated 36 minutes ago

published a dataset about 1 hour ago

namezz/m2rl-issue18-agent32-transfer-public-20261030

Updated 36 minutes ago

updated a dataset about 12 hours ago

namezz/m2rl-issue18-code-transfer-public-20261030

Updated about 12 hours ago

published a dataset about 12 hours ago

namezz/m2rl-issue18-code-transfer-public-20261030

Updated about 12 hours ago

updated a dataset 2 days ago

namezz/gptoss-full-sp-rl-stopped-20261028

Preview • Updated 2 days ago • 289

published a dataset 2 days ago

namezz/gptoss-full-sp-rl-stopped-20261028

Preview • Updated 2 days ago • 289

published a model 2 days ago

namezz/gptoss-swallow-full-grpo-best400-20261028

Reinforcement Learning • 21B • Updated 2 days ago • 37

updated a model 2 days ago

namezz/gptoss-swallow-full-grpo-best400-20261028

Reinforcement Learning • 21B • Updated 2 days ago • 37

published a dataset 5 days ago

namezz/seer-agent-traces

Updated 5 days ago • 195

updated a dataset 5 days ago

namezz/seer-agent-traces

Updated 5 days ago • 195

published a dataset 11 days ago

namezz/agent-training-backup-20261019

Viewer • Updated 11 days ago • 600 • 240

updated a dataset 11 days ago

namezz/agent-training-backup-20261019

Viewer • Updated 11 days ago • 600 • 240

updated a model 17 days ago

namezz/soft-prompt-interpretability-six-pairs

Updated 16 days ago

published a model 30 days ago

namezz/soft-prompt-interpretability-six-pairs

Updated 16 days ago

upvoted a paper about 1 month ago

Bellman Policy Optimization

Paper • 2609.15987 • Published Sep 14 • 49

published a dataset about 1 month ago

namezz/soft-prompt-experiments-archive-20260918

Viewer • Updated Sep 18 • 169 • 568

updated a dataset about 1 month ago

namezz/soft-prompt-experiments-archive-20260918

Viewer • Updated Sep 18 • 169 • 568

updated a collection about 2 months ago

Continual Learning with Soft Prompt

Collection

Private reproducibility artifacts for distilling a mathematical reasoning RL checkpoint into a 16-token soft prompt. • 3 items • Updated 30 days ago

updated a dataset 3 months ago

namezz/deepscaler-1p5b-teacher-rollouts-broad

Updated Aug 1 • 474

published a dataset 3 months ago

namezz/deepscaler-1p5b-teacher-rollouts-broad

Updated Aug 1 • 474