@MeeraHahn

Research Scientist @GoogleAI PhD in Computer Science @GeorgiaTech Undergrad @EmoryUniversity

 Atlanta, GA
meerahahn.net
Joined November 2019
  • Tweets36
  • Following157
  • Followers292
2Media
Meera Hahn retweeted
Zi Wang, Ph.D.@ziwphdMay 15
Check out Proactive Co-Creator on @GoogleAIStudio , a human-AI belief alignment demo I vibe coded: aistudio.google.com/apps/bun… 🧠 See & edit the AI's uncertainty via belief graph. It asks clarifying questions before creating! 📷 Try Image ➔ Story ➔ Video. You can even remix it!
2
4
13
914
A great example of how creatives and artists can use ai to bring to life previously impossible ideas!
Google DeepMind
@GoogleDeepMindJan 26
Our short film Dear Upstairs Neighbors is previewing at @sundancefest. 🎬 It’s a story about noisy neighbors, but behind the scenes, it’s about solving a huge challenge in generative AI: control. Developed by Pixar alumni, an Academy Award winner, researchers, and engineers, here’s how it came together. 🎨
3
222
Exciting new work from @sihyun_yu and our team at Google Deep Mind! Memory-Augmented Latent Transformers (MALT) Diffusion, a new diffusion model specialized for long video generation! arxiv.org/abs/2502.12632

MALT Diffusion: Memory-Augmented Latent Transformers for...

Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still...

arxiv.org
3
17
107
8,870
Check out our tech report on proactive T2I agents that ask clarification questions to reduce uncertainty! With this agent, we obtain 2 times higher VQAScore in just 5 turns!🤯 We've open-sourced our agent code powered by #Gemini @GoogleDeepMind! 🚀 Code:github.com/google-deepmind/p…
Zi Wang, Ph.D.@ziwphd12 Dec 2024
Tired of endless prompt tweaking? We've released a tech report on proactive text-to-image agents powered by #Gemini @GoogleDeepMind! Our agents ask clarifying questions and use belief graphs to understand what you really want. arxiv.org/abs/2412.06771 youtu.be/HQgjLWp4Lo8
2
20
2
65
22,193
legit treflip by Veo 2 with just one error (wheel inversion in the middle). legs move realistically for a treflip 🤯. skateboarding videos are notoriously hard to generate
Justine Moore
@venturetwins17 Dec 2024
I cannot believe this is AI video - we've come insanely far in the last year (Veo 2)
4
5
69
5,556
Many thanks to @MeeraHahn , Wenjun Zeng, Nithish Kannen, Rich Galt, Kartikeya Badola, @_beenkim for making this happen! Stay tuned for code release!
1
5
417
Tired of endless prompt tweaking? We've released a tech report on proactive text-to-image agents powered by #Gemini @GoogleDeepMind! Our agents ask clarifying questions and use belief graphs to understand what you really want. arxiv.org/abs/2412.06771 youtu.be/HQgjLWp4Lo8
1
6
3
18
19,648
6/ Finally, our model can be used to generate videos with consistent 3D camera motion.
3
16
87
11,744
2/ website: walt-video-diffusion.github.… Our approach has two key design decisions. First, we use a causal encoder to compress images and videos in a shared latent space.
2
15
68
11,116
We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇
48
245
70
1,227
431,393
Meera Hahn retweeted
Philipp Tsipman
@ptsi26 Mar 2023
If you’re having trouble keeping up with Video AI😅, there have been 5 state-of-the-art generative video models released *in last 7 days*: 🤯😎🧵
60
638
95
6,430
5,331,602
Have you ever wondered about emergent intelligence in robotic agents? This work shows interesting emergent intelligence and behaviors in blind navigation agents! Blind agents learn maps as they navigate. This allows them to navigate as successfully as an agent with vision
erikwijmans@erikwijmans1 Feb 2023
How do 'map-less' agents navigate? They learn to build implicit maps of their environment in their hidden state! We study 'blind' AI navigation agents and find the following 🧵
1
15
2,075
Meera Hahn retweeted
Max Xu@maxxu0529 Nov 2022
How can we fill in missing pulsative sensor data? Prior state-of-the-art fails in our novel setting, despite its well-defined temporal structure. Checkout our #NeurIPS2022 paper, PulseImpute, @ 4 pm CST! arxiv: openreview.net/pdf?id=x_kBZY… github: github.com/rehg-lab/pulseimp…
11
17
i trained an ai chatbot on my childhood journal entries - so that i could engage in real-time dialogue with my "inner child" some reflections below:
553
6,191
2,441
44,892
Dense self-supervised learning from multiple 3D viewpoints → dense feature representations that generalize both to novel object instances and to novel categories of instances. Checkout our #NeurIPS2022 paper! arxiv: arxiv.org/abs/2211.15059 github: github.com/rehg-lab/dope_sel…
2
20
1
67
✨Transformer-based Localization from Embodied Dialog with Large-scale Pre-training✨ has been accepted as an oral at @aaclmeeting! arxiv.org/abs/2210.04864 w/ @RehgJim
1
5
19
We model indoor environments using FPV panoramic navigation graphs and introduce a visiolinguistic transformer model, LED-Bert, which scores the alignment between navigation graph nodes and dialogs and achieves SOTA performance on the LED task!
1
Today, along with my collaborators at @GoogleAI, we announce DreamBooth! It allows a user to generate a subject of choice (pet, object, etc.) in myriad contexts and with text-guided semantic variations! The options are endless. (Thread 👇) webpage: dreambooth.github.io/ 1/N
42
392
95
1,854
A new year, a new shameless twitter plug: Check out our Toys4K 3D object dataset 4K instances, 105 categories, 15+ instances per category github.com/rehg-lab/lowshot-…
12
1
62
Meera Hahn retweeted
AK
@_akhaliq19 Oct 2021
No RL, No Simulation: Learning to Navigate without Navigating abs: arxiv.org/abs/2110.09470
12
75
Load more