🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Check our new work on cross-modal audio-video generation. Our work produces audio with the best alignment we have seen with respect to actions happening on video. Particularly useful in the era of astounding progress in generative video models.

Video-to-Audio and Audio-to-Video models struggle with temporal alignment. AV-Link solves the problem by conditioning on diffusion model features Great collaboration with Moayed Haji Ali , Aliaksandr Siarohin , Ivan Skorokhodov , Alper Canberk , Kwot Sin Lee, Vicente Ordonez and Sergey Tulyakov

South Main looking like a winter wonderland ❄️ ⛄️

Exploring AI generated content every day has me feeling bored of all content in general, even the real one

ICLR rejections go brrrrr

CVPR reviews are rolling out. My F5 key is holding on for dear life

At this point, I would seriously rather have an LLM reviewing papers instead of human two-liner nonesense #CVPR2025

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.

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?

This year, our research team at Snap is hiring multiple Research Engineer interns to help us build large-scale generative models. You don't need to have papers, but should have solid coding and ML skills. It is a good opportunity for BS/MS and early PhD students. Apply at

In the past 1.5 weeks, there appeared 2 papers by 2 different research groups which develop the exactly same (and embarrassingly simple) trick to improve convergence of image/video diffusion models by 20-100+% (sic!) arxiv.org/abs/2502.14831 arxiv.org/abs/2502.09509

same old, same old third rejection in a row. Lets go 🕺