Synthetic Video Enhances Physical Fidelity in Video Synthesis
Paper
•
2503.20822
•
Published
•
15
Yuhao Dong
THUdyh
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
Synthetic Video Enhances Physical Fidelity in Video Synthesis
upvoted
a
paper
9 days ago
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic
Faithfulness
liked
a dataset
11 days ago
Osilly/Vision-R1-cold
Organizations
THUdyh's activity
upvoted
a
paper
3 days ago
upvoted
a
paper
9 days ago
liked
a
dataset
11 days ago
authored
a
paper
30 days ago
upvoted
a
paper
30 days ago
updated
a
Space
about 1 month ago
The Gradio demo encountered a Runtime Error.
1
#2 opened about 1 month ago
by
danieldeng
Low bit version issues
1
#7 opened about 1 month ago
by
Jilt
upvoted
a
collection
about 1 month ago
Improve Model Card: Correct pipeline tag, add library name and project page link
#1 opened about 1 month ago
by
nielsr
Improve model card
#2 opened about 1 month ago
by
nielsr
Improve Model Card: Correct pipeline tag and add library name
#1 opened about 1 month ago
by
nielsr
liked
2
datasets
about 1 month ago
visual embedding and text embedding projection
2
#1 opened about 1 month ago
by
MonoLeon
Add pipeline tag
#1 opened about 1 month ago
by
nielsr
Add pipeline tag
#1 opened about 1 month ago
by
nielsr
Add model card
#1 opened about 1 month ago
by
nielsr
Add dataset card
#2 opened about 1 month ago
by
nielsr
posted
an
update
about 1 month ago
Post
2126
🔥🔥Introducing Ola! State-of-the-art omni-modal understanding model with advanced progressive modality alignment strategy!
Ola ranks #1 on OpenCompass Leaderboard (<10B)
.
📜Paper: https://arxiv.org/abs/2502.04328
🛠️Code: https://github.com/Ola-Omni/Ola
🛠️We have fully released our video&audio training data, intermediate image&video model at THUdyh/ola-67b8220eb93406ec87aeec37. Try to build your own powerful omni-modal model with our data and models!
Ola ranks #1 on OpenCompass Leaderboard (<10B)
.
📜Paper: https://arxiv.org/abs/2502.04328
🛠️Code: https://github.com/Ola-Omni/Ola
🛠️We have fully released our video&audio training data, intermediate image&video model at THUdyh/ola-67b8220eb93406ec87aeec37. Try to build your own powerful omni-modal model with our data and models!