Ivan Skorokhodov (@isskoro) 's Twitter Profile
Ivan Skorokhodov

@isskoro

Research Scientist @Snap. I like neural networks and neural networks like me.

ID: 295314514

linkhttps://skor.sh calendar_today08-05-2011 19:40:09

236 Tweet

2,2K Followers

482 Following

Ivan Skorokhodov (@isskoro) 's Twitter Profile Photo

If you tried Gen-3/MovieGen, you might have realized that it's close-to-impossible to create any meaningful long video with them, where the subjects would do a sequence of complex non-trivial actions. MinT solves this problem really well by reformulating a complex, multi-event

Ivan Skorokhodov (@isskoro) 's Twitter Profile Photo

Diffusion models are very strong and robust feature extractors, but recent works were only using them for recognition tasks. In our recent work (led by MOAYED HAJi ALi), we harness them for video2audio generation: they by far outperform conventional video feature extractors for

Ivan Skorokhodov (@isskoro) 's Twitter Profile Photo

I also feel quite schmidhuber-ish about VAR (NeurIPS'24 best paper): its core idea is the same as of Multiscale PixelCNN (ICML'17), but the authors allocate just a single sentence to discuss it and frame it as some bizarre "raster-scan" + "super-resolution" model. In early 2023,

Ivan Skorokhodov (@isskoro) 's Twitter Profile Photo

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

Kfir Aberman (@abermankfir) 's Twitter Profile Photo

We discovered that imposing a spatio-temporal weight space via LoRAs on DIT-based video models unlocks powerful customization! It captures dynamic concepts with precision and even enables composition of multiple videos together!πŸŽ₯✨

Ivan Skorokhodov (@isskoro) 's Twitter Profile Photo

According to google scholar, CVPR has now become the second-ranked venue *worldwide*, with Nature being the only one ahead (also, NeurIPS, ICLR, ICCV and ICML are in top-20 taking 7/10/13/17-th place). You're impressed at first glance, but then you realize that the ranking is

According to google scholar, CVPR has now become the second-ranked venue *worldwide*, with Nature being the only one ahead (also, NeurIPS, ICLR, ICCV and ICML are in top-20 taking 7/10/13/17-th place).

You're impressed at first glance, but then you realize that the ranking is
Ivan Skorokhodov (@isskoro) 's Twitter Profile Photo

Recently, there were many tweets from people frustrated with their ICML results (I feel your pain). It was my first time submitting to ICML, and somehow it was maybe the most reasonable set of reviewers I've ever got (and we had 4 of them). There were multiple concerns raised but

Ziyi Wu (@dazitu_616) 's Twitter Profile Photo

πŸ“’ Introducing DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models Compared to vanilla DPO, we improve paired data construction and preference label granularity, leading to better visual quality and motion strength with only 1/3 of the data. 🧡

Ashkan Mirzaei (@ashmrz10) 's Twitter Profile Photo

[1/9] πŸš€ We introduce 4Real-Video-V2, a method that can generate 4D scenes from a simple text prompt, viewable from any angle at any moment in time. It’s fast, photorealistic, and works on full scenes. Here's how it works and why it matters. πŸ‘‡ snap-research.github.io/4Real-Video-V2/

Moayed Haji Ali (@moayedhajiali) 's Twitter Profile Photo

Where are good old progressive diffusion models? πŸ€” Breaking generation to multiple resolution scales is a great idea, but complexity (multiple models, custom diffusion process, etc) stalled scaling. Our Decomposable Flow Matching packs multi-scale perks into one scalable model.