Add pipeline tag and paper/code links

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +23 -10
README.md CHANGED
@@ -1,13 +1,14 @@
1
  ---
2
- license: apache-2.0
3
- library_name: pytorch
4
  base_model: facebook/pe-av-large
 
 
 
5
  tags:
6
- - audio-video
7
- - audio-visual
8
- - synchronization
9
- - reward-model
10
- - video-generation
11
  ---
12
 
13
  # SyncReward
@@ -16,7 +17,9 @@ SyncReward scores the **audio-visual synchronization** of a generated video with
16
  reward in **[0, 2]** (0 = not synchronized, 2 = well synchronized) and is trained to match human sync
17
  judgments on clips from text-to-audio-video generators.
18
 
19
- Paper, code repository and citation: coming soon.
 
 
20
 
21
  ## Models
22
 
@@ -56,7 +59,7 @@ hf download Guan123/SyncReward --include 'syncreward-stage2/*' --local-dir check
56
  (cd checkpoints/syncreward-stage2 && sha256sum -c SHA256SUMS)
57
  ```
58
 
59
- Loading uses the SyncReward code (repository link coming soon):
60
 
61
  ```python
62
  from syncreward.model import build_reward_model
@@ -106,4 +109,14 @@ Apache-2.0 (see [LICENSE](LICENSE)). The PE-AV backbone `facebook/pe-av-large` i
106
 
107
  ## Citation
108
 
109
- Coming soon.
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
 
2
  base_model: facebook/pe-av-large
3
+ library_name: pytorch
4
+ license: apache-2.0
5
+ pipeline_tag: other
6
  tags:
7
+ - audio-video
8
+ - audio-visual
9
+ - synchronization
10
+ - reward-model
11
+ - video-generation
12
  ---
13
 
14
  # SyncReward
 
17
  reward in **[0, 2]** (0 = not synchronized, 2 = well synchronized) and is trained to match human sync
18
  judgments on clips from text-to-audio-video generators.
19
 
20
+ Paper: [SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation](https://huggingface.co/papers/2610.16338)
21
+
22
+ Code: [https://github.com/WeChatCV/SyncReward](https://github.com/WeChatCV/SyncReward)
23
 
24
  ## Models
25
 
 
59
  (cd checkpoints/syncreward-stage2 && sha256sum -c SHA256SUMS)
60
  ```
61
 
62
+ Loading uses the SyncReward code (repository link above):
63
 
64
  ```python
65
  from syncreward.model import build_reward_model
 
109
 
110
  ## Citation
111
 
112
+ ```bibtex
113
+ @misc{guan2026syncrewardhumanalignedsynchronizationreward,
114
+ title={SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation},
115
+ author={Kaisi Guan and Ying Ba and Wenjing Wang and Xihua Wang and Chen Li and Jing Lyu and Ruihau Song},
116
+ year={2026},
117
+ eprint={2610.16338},
118
+ archivePrefix={arXiv},
119
+ primaryClass={cs.CV},
120
+ url={https://arxiv.org/abs/2610.16338},
121
+ }
122
+ ```