Moayed Haji Ali
@moayedhajiali
Followers
42
Following
77
Statuses
19
CS PhD @RiceCompSci @vislang | Research Intern @Snap | GenAI & Video & Audio & Computer Vision
Joined January 2025
Can pretrained diffusion models connect for cross-modal generation? 📢 Introducing AV-Link ♾ Bridging unimodal diffusion models in one framework to enable: 📽️ ➡️ 🔊 Video-to-Audio 🔊 ➡️ 📽️ Audio-to-Video 🌐: 📄: ⤵️ Results
2
12
20
RT @isskoro: This year, our research team at Snap is hiring multiple Research Engineer interns to help us build large-scale generative mode…
0
24
0
I've been exploring what factors boost X reach. Surprisingly, number of likes and hashtags don’t seem to help at all. Have you noticed any patterns in your tweets?
0
0
1
This was my first research paper in ICCV 2023. Came at an unfortunate time when GANs were dying and got no attention. But I really like this paper.
VidStyleODE Disentangled Video Editing via StyleGAN and NeuralODEs
0
0
7
At this point, I would seriously rather have an LLM reviewing papers instead of human two-liner nonesense #CVPR2025
0
0
8
CVPR reviews are rolling out. My F5 key is holding on for dear life
0
0
3
Exploring AI generated content every day has me feeling bored of all content in general, even the real one
0
0
2
RT @vislang: Check our new work on cross-modal audio-video generation. Our work produces audio with the best alignment we have seen with re…
0
1
0
RT @WilliMenapace: Video-to-Audio and Audio-to-Video models struggle with temporal alignment. AV-Link solves the problem by conditioning on…
0
3
0
A great collaboration with Snap creative vision team @WilliMenapace, A. Siarohin, @isskoro, @alpercanbe, @kwotsin, @bluevincent, and @SergeyTulyakov Please repost to support our work and check out our Arxiv preprint: Webpage:
0
0
3
Besides Video to Audio (📽️ ➡️🔊), we also support Audio to Video (🔊➡️📽️) generation under the same unified framework.
1
0
4
Compared to Meta Movie Gen Video to Audio, we achieve significantly better temporal synchronization with a 90% smaller scale model.
1
0
4
Precise temporal synchronization remains a significant challenge for current video-to-audio models. AV-Link addresses this by leveraging diffusion features to accurately capture both local and global temporal events, such as hand slides on a guitar and fretboard pitch changes.
1
0
4