ATPO - a BruceYg Collection

BruceYg 's Collections

ATPO

updated 1 day ago

Checkpoints for the NeurIPS 2026 paper "Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization".

BruceYg/ATPO-G-Qwen2.5-VL-7B

Reinforcement Learning • 8B • Updated 9 days ago • 26
BruceYg/ATPO-G-Qwen2.5-VL-7B-r5

Reinforcement Learning • 8B • Updated 1 day ago • 23
BruceYg/ATPO-G-Qwen2.5-VL-7B-r0.2

Reinforcement Learning • 8B • Updated 1 day ago • 26 • 1
BruceYg/ATPO-C-Qwen2.5-VL-7B-C4r5-C6r0.2

Reinforcement Learning • 8B • Updated 1 day ago • 14