MOAYED HAJi ALi

Great news from #CVPR2024 🎉🎉🎉 Happy to share that our paper ElasticDiffusion: Training-free Arbitrary Size Image Generation was accepted @CVPR. Big thanks to my collaborators @bluevincent and Guha Balakrishnan. Checkout more details from here: elasticdiffusion.github.io

@Peldaaaaaaa @Telegraph Bruh idk what kind of arabic you speak, but we do say that. Never heard the phrase "jihad one's self"? which means fighting your inner self? mawdoo3.com/%D9%83%D9%8A%D…

@MoayedHaji @Telegraph What a cope. Bro literally no one says that. 😂

🔴 BBC removed references to ‘Jews’ and ‘jihad’ in Gaza documentary

Happy to announce AlignVLM📏: a novel approach to bridging vision and language latent spaces for multimodal understanding in VLMs! 🌍📄🖼️ 🔗 Read the paper: arxiv.org/abs/2502.01341 🧵👇 Thread

Introducing ⚗️ Video Alchemist Our new video model supporting 👪 Multi-subject open-set personalization 🏞️ Foreground & background personalization 🚀 Without the need of inference-time tuning snap-research.github.io/open-set-video… [Results] 1. Sora girl rides a dinosaur on a savanna 🧵👇

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 @MoayedHaji), we harness them for video2audio generation: they by far outperform conventional video feature extractors for audio/video temporal alignment and allow to achieve SotA results in sound quality as well: snap-research.github.io/AVLink/

Can we use the intermediate representations of pretrained video generation models to generate audio, and vice versa? 🤔🔀 It turns out that this approach can be powerful. Introducing AV-Link, an approach to connect video and audio diffusion models in a self-contained framework

6/6 Check out qualitative examples in the project website (snap-research.github.io/AVLink/index.h…). and our preprint (arxiv.org/abs/2412.15191) for more details about the architecture.

5/6 For the first time, our approach shows audio-synchronized video generation for “in-the-wild” scenarios, surpassing existing methods in both generation quality and semantic and temporal alignment (#A2V_upscaled_w_prompt" target="_blank" rel="nofollow noopener">snap-research.github.io/AVLink/a2v_w_p…).

1/6 Introducing AV-Link, an approach to connect video and audio diffusion models in a self-contained framework to enable video-to-audio and audio-to-video generation with superb audio-video synchronization. Project page: snap-research.github.io/AVLink

@anonperson09 @xwang_lk It is more terrible than what you think

@xwang_lk The fact that 20% of academic discourse on twitter is about review procedures makes me really not want to go into academia. Is it like this irl too?

I remember one time while reviewing for an NLP conference, not only could the AC see the reviewer's identities, but the reviewers could also see each other's identities. It worked like a charm. Transparency and accountability are crucial to improve reviewing quality.

🧵 1/4 Introducing ColFlor: An Efficient, OCR-Free Vision-Language Document Retrieval Model 🌟 Earlier this year, ColPali transformed document retrieval by removing error-prone OCR pipelines, creating embeddings directly from images. However, its 3 billion parameters make it computationally expensive. That’s where ColFlor comes in! ⚡👇 #AI #NLP huggingface.co/blog/ahmed-mas…

@nasdaily طب كسمك

I am excited to announce that I had my first Free Palestine protest come to a Nas Daily meetup. I told them I agreed with them. I also want a Free Palestine from Hamas. Free Palestine from terrorism. Free Palestine from radical religion. They disagreed. They just wanted a Free Palestine from Jews. Oh well.

I am excited to share that two of our research works will be presented at ECCV 2024. #ECCV2024 They focus on augmenting language models with fine-grained visual recognition ability. AutoVER made successful attempts at generative visual recognition. It was accepted to the ECCV 2024 main conference and was invited to the ILR Workshop as an oral presentation. Collaboration w/ @pcascanteb @vislang #Microsoft Extractive Reranker was accepted to the ILR Workshop as a poster. We explored how the long-context sequence modeling ability of language models can benefit image retrieval, a fundamental computer vision problem.

@iraninarabic_ir 😂😂

غادروا مدنكم! فجيش أبابيل قادم للانتقام. #اسماعيل_هنية

@tolga_birdal @UKRI_News @imperialcollege @ICComputing Big congratulations 🎊🍾

I'm honored to become a UKRI Future Leaders Fellow! I will push the frontiers in topological deep learning and 3D vision for the next 4+ years. Several PhD and Postdoc positions available. #UKRIFutureLeaders @UKRI_News #FLF @imperialcollege @ICComputing 🔗ukri.org/news/68-new-fu…

📢Excited to share our recent work ✂️CLIPAway, a plug-and-play solution to simple object removal using latent diffusion models. It works like a charm! 📄Paper: arxiv.org/abs/2406.09368 🔗Project website: yigitekin.github.io/CLIPAway/ 🤗@huggingface Spaces Demo: huggingface.co/spaces/yigitek…

@ftm_guney Honestly it is so crowded that it might be not very safe for kids to be here

I’m not at CVPR but still following the news here. incredibly happy to see friends and mentors getting awards, congrats to Angjoo, Andrea, and Andreas’s team! sad to see kids are not allowed at CVPR, like why? looking forward to reading the papers bookmarked after the holiday.