Tali Dekel
@talidekel
Followers
2K
Following
125
Media
14
Statuses
111
Associate Professor @ Weizmann Institute Research Scientist @ Google DeepMind
Joined May 2019
Best Paper Award @ SIGGRAPH'25 🥳.
So much is already possible in image generation that it's hard to get excited. TokenVerse has been a refreshing exception!. Disentangling complex visual concepts (pose, lighting, materials, etc.) from a single image — and mixing them across others with plug-and-play ease!.
5
1
94
Insane! They certainly convinced me 🤣.
Prompt Theory (Made with Veo 3). What if AI-generated characters refused to believe they were AI-generated?
0
0
2
So much is already possible in image generation that it's hard to get excited. TokenVerse has been a refreshing exception!. Disentangling complex visual concepts (pose, lighting, materials, etc.) from a single image — and mixing them across others with plug-and-play ease!.
Excited to share that "TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space" got accepted to SIGGRAPH 2025!.It tackles disentangling complex visual concepts from as little as a single image and re-composing concepts across multiple images into a coherent
0
1
28
#CVPR2025 🚀.
Understanding the inner workings of foundation models is key for unlocking their full potential. While the research community has explored this for LLMs, CLIP, and text-to-image models, it's time to turn our focus to VLMs. Let's dive in! 🌟 .
0
2
22
"Giraffe wearing a neck warmer" .2024: entirely generated video by Veo. 2022: text-driven editing using test time optimization and CLIP by Text2LIVE. quite a stride!
1
1
20
RT @pika_labs: Today we launched our Pika 2.0 model. Superior text alignment. Stunning visuals. And ✨Scene Ingredients✨that allow you to up….
0
352
0
Understanding the inner workings of foundation models is key for unlocking their full potential. While the research community has explored this for LLMs, CLIP, and text-to-image models, it's time to turn our focus to VLMs. Let's dive in! 🌟 .
🔍 Unveiling new insights into Vision-Language Models (VLMs)!. In collaboration with @OneViTaDay & @talidekel, we analyzed LLaVA-1.5-7B & InternVL2-76B to uncover how these models process visual data. 🧵.
0
23
153
Working on layered video decomposition for a few years now, I'm super excited to share these results! .Casual videos to *fully visible* RGBA layers, even under significant occlusions!.Kudos @YaoChihLee, @erika_lu_, Sarah Rumbley, @GeyerMichal, @jbhuang0604, and @forrestercole.
Excited to introduce our new paper, Generative Omnimatte: Learning to Decompose Video into Layers, with the amazing team at Google DeepMind!. Our method decomposes a video into complete layers, including objects and their associated effects (e.g., shadows, reflections).
1
17
128
Creating a panoramic video out of a casual panning video requires a strong generative motion prior, which we finally have! Kudos @JingweiMa2 and team!.
We are excited to introduce "VidPanos: Generative Panoramic Videos from Casual Panning Videos". VidPanos converts phone-captured panning videos into (fully playing) video panoramas, instead of the usual (static) image panoramas. Website: Paper:
0
0
9
Unlike images, getting customized video data is challenging. Check out how we can customize a pre-trained text-to-video model *without* any video data!.
Introducing✨Still-Moving✨—our work from @GoogleDeepMind that lets you apply *any* image customization method to video models🎥. Personalization (DreamBooth)🐶stylization (StyleDrop) 🎨 ControlNet🖼️—ALL in one method!. Plus… you can control the amount of generated motion🏃♀️.🧵👇
0
3
26
Self-supervised representation learning (DINO) + test time optimization=DINO-tracker! Achieving SOTA tracking results across long range occlusions. Congrats @tnarek99 @assaf_singer and @OneViTaDay on the great work! 🦖🦖.
Excited to present DINO-Tracker (accepted to #ECCV2024)! A novel self-supervised method for long-range dense tracking in video, which harnesses the powerful visual prior of DINO. Project page: [1/4].@assaf_singer .@OneViTaDay.@talidekel
1
22
138
Thank you @WeizmannScience for featuring our research!.
Weizmann’s Dr. @TaliDekel, among the world’s leading researchers in generative AI, focuses on the hidden capabilities of existing large-scale deep-learning models. Her research with Google led to the development of the recently unveiled Lumiere >>
0
1
44
RT @_k_a_c_h_: Hi friends — I'm delighted to announce a new summer workshop on the emerging interface between cognitive science 🧠 and compu….
0
31
0
Thank you @ldvcapital for the recognition and for supporting women in Tech!.
Since 2012, we have been showcasing brilliant women whose work in #VisualTech and #AI is reshaping business and society. We are thrilled to feature 120+ women driving today's tech innovations 🚀.
1
1
7
Thank you @SagivTech for the opportunity to take part in @IMVC2024, and for keeping our Israeli Vision community live and kicking during these challenging times!
0
0
13
Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer -- accepted to #CVPR2024! Code is available: .w/ @DanahYatim @RafailFridman @omerbartal @yoni_kasten.
Text2video models are getting interesting!📽️. Check out how we leverage their space-time features in a zero-shot manner for transferring motion across objects and scenes!. Led by @DanahYatim @RafailFridman,@yoni_kasten @talidekel.[1/3]
0
2
54
Honored and very excited to speak at EUROGRAPHICS this year next to these legendary researchers! . I'll speak about my research journey in the realm of video generation: going from *single-video* models to *all-video* models.
0
0
39
Looking forward to it!.
AI for Content Creation workshop is back at #CVPR2024. 21st March paper deadline @ Plus stellar speakers:.@AaronHertzmann .@liuziwei7 .@robrombach .@talidekel .@Jimantha .@Diyi_Yang .late breaking speakers and special guest panel.!!!.
0
0
3