Fangzhou

Fzz1's activity

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

updated 2 datasets about 4 hours ago

Fzz1/tb-full-data

Viewer • Updated about 4 hours ago • 31.8k • 2.69k

Fzz1/tb-training-mix-agentpick

Viewer • Updated about 4 hours ago • 1.96k • 3.48k

New activity in Fzz1/SWE-Rebench-Tasks-Clean about 1 month ago

Grade a fix the agent committed: locate the repo by base ancestry, reset tests from base

1

#2 opened about 1 month ago by

Chrisyichuan

published a dataset about 1 month ago

Fzz1/tb-full-data

Viewer • Updated about 4 hours ago • 31.8k • 2.69k

published 2 datasets about 2 months ago

Fzz1/tb-training-mix-agentpick

Viewer • Updated about 4 hours ago • 1.96k • 3.48k

Fzz1/tb-training-mix

Viewer • Updated Sep 21 • 400 • 418

updated 2 datasets about 2 months ago

Fzz1/tb-training-mix

Viewer • Updated Sep 21 • 400 • 418

Fzz1/Tmax-Tasks-Clean

Viewer • Updated Sep 14 • 2.58k • 7.67k

New activity in andylizf/TerminalWorld-Seeds-Clean 2 months ago

Apply combined TW curation exclusions to the v3 training selection

#2 opened 2 months ago by

Fzz1

updated a dataset 2 months ago

Fzz1/Tmax-Tasks-Clean

Viewer • Updated Sep 14 • 2.58k • 7.67k

published a dataset 3 months ago

Fzz1/Tmax-Tasks-Clean

Viewer • Updated Sep 14 • 2.58k • 7.67k

upvoted a paper 3 months ago

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

Paper • 2608.21500 • Published Aug 21 • 39

updated 2 datasets 3 months ago

Fzz1/SWE-Rebench-Tasks-Clean

Viewer • Updated Oct 11 • 1.32k • 1.06k • 1

Fzz1/SWE-Smith-Seeds-Clean

Viewer • Updated Aug 23 • 1.55k • 104

published a dataset 3 months ago

Fzz1/SWE-Rebench-Tasks-Clean

Viewer • Updated Oct 11 • 1.32k • 1.06k • 1

upvoted 2 papers 3 months ago

AVA-Encoder: Towards Agent-Native Video Representation Learning

Paper • 2608.12313 • Published Aug 12 • 36

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published Aug 17 • 112

published a dataset 3 months ago

Fzz1/SWE-Smith-Seeds-Clean

Viewer • Updated Aug 23 • 1.55k • 104

upvoted a paper 7 months ago

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Paper • 2604.06916 • Published Apr 8 • 29

upvoted a collection 8 months ago

M2RNN

Collection

Note that the 7B models are MoE with 1.1B active parameters and 400M models are dense models • 14 items • Updated Mar 12 • 7