Add OraRL project video
Browse files
README.md
CHANGED
|
@@ -15,6 +15,10 @@ We build **OraRL**, a reinforcement-learning framework for **unified video multi
|
|
| 15 |
|
| 16 |
Our goal is to make broad video RL both **reliable** and **efficient** by treating task annotations as positive rollouts while retaining policy samples for the on-policy baseline. The resulting **Video-ORA** family handles seven task families without chain-of-thought decoding.
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
## What we release
|
| 19 |
|
| 20 |
- **Video-ORA-9B**: a unified video MLLM for temporal and spatial grounding, segmentation, tracking, video QA, and spatial intelligence.
|
|
|
|
| 15 |
|
| 16 |
Our goal is to make broad video RL both **reliable** and **efficient** by treating task annotations as positive rollouts while retaining policy samples for the on-policy baseline. The resulting **Video-ORA** family handles seven task families without chain-of-thought decoding.
|
| 17 |
|
| 18 |
+
<video controls playsinline preload="metadata" width="100%" src="https://orarl.github.io/assets/orarl-teaser.mp4"></video>
|
| 19 |
+
|
| 20 |
+
<p align="center"><strong>▶ OraRL project overview (1:38)</strong></p>
|
| 21 |
+
|
| 22 |
## What we release
|
| 23 |
|
| 24 |
- **Video-ORA-9B**: a unified video MLLM for temporal and spatial grounding, segmentation, tracking, video QA, and spatial intelligence.
|