Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

As #GenerativeAI booms in content generation for human, how can we empower #AutonomousVehicles? We introduce GINA, to appear #CVPR2026. GINA builds a bridge from 𝐫𝐚𝐰 𝐝𝐫𝐢𝐯𝐢𝐧𝐠 𝐝𝐚𝐭𝐚 ➡️ 𝟑𝐃 𝐚𝐬𝐬𝐞𝐭𝐬, which enables a flywheel of 𝐢𝐧-𝐝𝐨𝐦𝐚𝐢𝐧 data generation:

William Shen

2,265 subscribers

40,425 views • 3 years ago •via X (Twitter)

#GenerativeAI #AutonomousVehicles

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🤷What if we want to learn from human data... without human data? In our work NIL (No-data Imitation Learning) #CVPR2026, we explore a simple but ambitious question: Can robots learn directly from AI-generated videos without any curated demonstration data? 🔗

🤷What if we want to learn from human data... without human data? In our work NIL (No-data Imitation Learning) #CVPR2026, we explore a simple but ambitious question: Can robots learn directly from AI-generated videos without any curated demonstration data? 🔗

Chenhao Li

22,062 views • 1 month ago

Google presents VLOGGER Multimodal Diffusion for Embodied Avatar Synthesis We propose VLOGGER, a method for audio-driven human video generation from a single input image of a person, which builds on the success of recent generative diffusion models. Our method consists of

AK

66,375 views • 2 years ago

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10

Xindi Wu

140,046 views • 6 months ago

We're working on a next-generation data center design which includes higher-density racks, liquid cooling to chips and much more. More on how we're transforming our infrastructure for the next generation of AI ➡️

We're working on a next-generation data center design which includes higher-density racks, liquid cooling to chips and much more. More on how we're transforming our infrastructure for the next generation of AI ➡️

AI at Meta

42,488 views • 3 years ago

Gina Gotthilf (Gina Gotthilf) led early growth at Duolingo, scaling the app from 3m to 200m users, led paid growth for the Mike Bloomberg presidential campaign, led international expansion for tumblr, and is now co-founder and COO of @LatitudLatAm, a startup platform supporting the next generation of iconic tech startups in Latin America. In our conversation, we discuss: 🔹 Behind the scenes of Duolingo’s early growth tactics 🔹 How to use PR and brand love as a growth lever 🔹 How to balance the “A" and "B" sides of life 🔹 Wild stories from Mike Bloomberg’s presidential campaign 🔹 Why Gina is passionate about investing in Latin America 🔹 Much more

Lenny Rachitsky

162,380 views • 2 years ago

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:

Xiaolong Wang

354,887 views • 1 year ago

Tencent presents GameGen-O Open-world Video Game Generation We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.

Tencent presents GameGen-O Open-world Video Game Generation We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.

AK

367,108 views • 1 year ago

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Zhiyang (Frank) Dou

14,610 views • 1 year ago

In the era of 10T-parameter foundation models 😈, can we still build next-generation world representations using 🦥 a single RTX 3090 GPU? We introduce WorldString (a name inspired by string theory), a tiny neural network representation for reconstructing dynamic world instances, ranging from articulated motion and skeletal skinning to soft-body deformation. 🔥 We view object representation as the core primitive of world modeling: the basic executable unit from which perception, interaction, simulation, and generation can be built. With a compact neural basis, WorldString aims to connect dynamic object modeling with neural simulation and foundation models, enabling a scalable path toward richer representations of the physical world.

In the era of 10T-parameter foundation models 😈, can we still build next-generation world representations using 🦥 a single RTX 3090 GPU? We introduce WorldString (a name inspired by string theory), a tiny neural network representation for reconstructing dynamic world instances, ranging from articulated motion and skeletal skinning to soft-body deformation. 🔥 We view object representation as the core primitive of world modeling: the basic executable unit from which perception, interaction, simulation, and generation can be built. With a compact neural basis, WorldString aims to connect dynamic object modeling with neural simulation and foundation models, enabling a scalable path toward richer representations of the physical world.

Xueyan Zou

38,299 views • 1 month ago

(1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a theoretical derivation to create radiance fields directly from meshes. Thus, we can obtain GT training data for generative NeRF methods.

(1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a theoretical derivation to create radiance fields directly from meshes. Thus, we can obtain GT training data for generative NeRF methods.

Matthias Niessner

16,835 views • 1 year ago

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.

AK

161,453 views • 3 years ago

"We believe that we must do all we can to create the conditions for love to flourish. That is how we invest in our future." A brilliant day highlighting the vital role businesses can play in The Royal Foundation Centre for Early Childhood. The focus was clear: to ensure the next generation develops the uniquely human skills needed to thrive in a world of rapid technological change, we need to focus on the earliest years of life.

"We believe that we must do all we can to create the conditions for love to flourish. That is how we invest in our future." A brilliant day highlighting the vital role businesses can play in The Royal Foundation Centre for Early Childhood. The focus was clear: to ensure the next generation develops the uniquely human skills needed to thrive in a world of rapid technological change, we need to focus on the earliest years of life.

The Prince and Princess of Wales

121,320 views • 8 months ago

Brainless !! This was the generation who normalised cheating in marriage and glorified it as well ! The results of which our generation is Facing and we are not ok with it !! May we become the last generation who tolerate cheating Husbands and give a better life to our Girlies next 🌸

Brainless !! This was the generation who normalised cheating in marriage and glorified it as well ! The results of which our generation is Facing and we are not ok with it !! May we become the last generation who tolerate cheating Husbands and give a better life to our Girlies next 🌸

Dr Ramsha Mir

36,634 views • 3 months ago

🌪️🚸For #DRRday – 13 October 2024 – we are calling for a world where children are taught about reducing disaster risk, where places of learning are places of safety. Are YOU ready to empower the next generation for a resilient future? ➡️ #areYouReady24

🌪️🚸For #DRRday – 13 October 2024 – we are calling for a world where children are taught about reducing disaster risk, where places of learning are places of safety. Are YOU ready to empower the next generation for a resilient future? ➡️ #areYouReady24

UNDRR

14,051 views • 1 year ago

New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower the community to build upon our work. ➡️ Read the technical report: ➡️Download the open weights: ➡️Download the code:

New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower the community to build upon our work. ➡️ Read the technical report: ➡️Download the open weights: ➡️Download the code:

AI at Meta

313,857 views • 10 months ago

As a mom of two teenagers, I’m personally aware of the challenges facing our youth. From social media, to environmental toxins, to ingredients in our food, we can and we must do better to help our next generation thrive.

As a mom of two teenagers, I’m personally aware of the challenges facing our youth. From social media, to environmental toxins, to ingredients in our food, we can and we must do better to help our next generation thrive.

Senator Katie Boyd Britt

50,331 views • 1 year ago

Seed-Music A Unified Framework for High Quality and Controlled Music Generation discuss: We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio.

Seed-Music A Unified Framework for High Quality and Controlled Music Generation discuss: We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio.

AK

32,967 views • 1 year ago

✨✨ Announcing Open Source Dataset from excavators in real construction sites retrofitted by Flywheel (YC S25)! ✨✨ This 100hrs of observation+action data enables training autonomy models for excavators. We were able to train a small task model from 6 hours of dataset on a Kubota U17 on Y Combinator demo day! Link in comments!

✨✨ Announcing Open Source Dataset from excavators in real construction sites retrofitted by Flywheel (YC S25)! ✨✨ This 100hrs of observation+action data enables training autonomy models for excavators. We were able to train a small task model from 6 hours of dataset on a Kubota U17 on Y Combinator demo day! Link in comments!

Jash Mota

36,617 views • 10 months ago

i made an automated content generation engine inside of post bridge :) generate 2x2 style vids in bulk, in a few clicks! these type of vids have brought my apps 10,000+ downloads for $0 here's how you can do the same:

i made an automated content generation engine inside of post bridge :) generate 2x2 style vids in bulk, in a few clicks! these type of vids have brought my apps 10,000+ downloads for $0 here's how you can do the same:

jack friks

78,828 views • 1 year ago