GitHub · Python
just-a-go/SOVA
Official implementation of SOVA: Strict Outcome-Conditioned Virtual Advantages for Video Reasoning. Correctness-oriented calibration for TW-GRPO without extra rollouts.
- Stars
- 24
- Forks
- 1
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: grpo, multimodal-learning, qwen2-5-vl, reinforcement-learning, sova, video-reasoning
Latest data point: Nov 22, 2026 · 24 stars · 1 forks