Throughout the week our researchers will be participating in 18 workshops — hope to see you there! A few to look out for Today
– Computer Vision for Mixed Reality
– International Workshop on Large Scale Holistic Understanding Tomorrow
– 3rd Ego4D & 11th Epic Workshop
MULTIMODAL AI
-
Meta Researchers Participate in 18 Workshops This Week
By
–
-
Meta AI Researcher Larry Zitnick Presents Climate Change Computer Vision Keynote
By
–
Meta AI Researcher, Larry Zitnick will be presenting a keynote on Thursday sharing perspectives and insights on approaching climate change through the lens of computer vision research https://
bit.ly/3Xb38vb 2/6 -
Synthesia’s Avatar Technology Powers Fastest Growing Generative AI Business
By
–
@jnstrck and @synthesiaIO
's avatar technology that's powering the fastest growing generative AI business out there -
GAIA-1 World Models for Self-Driving and Embodied AI
By
–
catch @alexgkendall and @Jamie_Shotton who'll present GAIA-1 and world model work for self-driving and embodied AI
-
WellnessGP: AI Chatbot for Health and Nutrition Guidance
By
–
WellnessGP(T) by Nafisa Marei A chatbot trained on health-related YouTube videos that can answer questions about fasting, nutrition, sleep optimization, and more. If it doesn't have the answer, it will return a URL to a YouTube video that does
-
GAIA-1: Generative AI Model for Autonomous Driving Videos
By
–
GAIA-1: A Cutting-Edge Generative AI Model for Autonomy
— AK (@_akhaliq) 18 juin 2023
blog: https://t.co/xcK2YNl4Vu
GAIA-1 is a new generative AI model for autonomy that creates realistic driving videos by leveraging video, text and action inputs. It offers fine-grained control over ego-vehicle behaviour… pic.twitter.com/H8RR0ZxaQJGAIA-1: A Cutting-Edge Generative AI Model for Autonomy blog: https://
wayve.ai/thinking/intro
ducing-gaia1/
… GAIA-1 is a new generative AI model for autonomy that creates realistic driving videos by leveraging video, text and action inputs. It offers fine-grained control over ego-vehicle behaviour -
VideoComposer Todo: 8-Second Video Generation Without Watermark
By
–
under todo: https://
github.com/damo-vilab/vid
eocomposer#todo
… "Release pretrained model that can generate 8s videos without watermark." -
VideoComposer: Controllable Motion Video Synthesis Models Released
By
–
VideoComposer: Compositional Video Synthesis
— AK (@_akhaliq) 17 juin 2023
with Motion Controllability models are out!
paper page: https://t.co/jb0kyDGCVH
github: https://t.co/GARo57U90t
The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in… pic.twitter.com/7RFfNJq3TVComposer: Compositional Synthesis
with Motion Controllability models are out! paper page: https://
huggingface.co/papers/2306.02
018
…
github: https://
github.com/damo-vilab/vid
eocomposer
… The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in -
Linguistic Binding in Diffusion Models for Better Attribute Correspondence
By
–
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment paper page: https://
huggingface.co/papers/2306.08
877
…
demo: https://
huggingface.co/spaces/Royir/S
ynGen
… Text-conditioned image generation models often generate incorrect associations between entities and their -
Comprehensive Survey on Transformer Applications Across Multiple Deep Learning Domains
By
–
A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks A great survey paper that provides a comprehensive analysis of highly influential transformer-based models in top five application domains: NLP, Computer Vision, Multi-Modality, Audio and Speech