Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

3/ One emergent capability I find remarkable is long-term consistency, especially because we don’t use any explicit 3D representations or priors. Simply training the model to generate the next frame auto-regressively teaches it to maintain physical consistency across time

Agrim Gupta

5,616 subscribers

41,474 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Another use case with Nano Banana Pro (Video is fully narrated so don't forget to turn on the sound 🔊) Image to 3D Model For 3D Printing 1 - Generate an image of a vinyl toy character. I generated a character called Peelbert. 2 - Generate multiple outfits for Peelbert while retaining consistency. Nano Banana Pro's consistency and understanding of outfit changes is superb. 3 - Use Hunyuan 3.0 to do image to 3D model 4 - Save as STL and 3D Print. Nano Banana Pro to the real world 👍

Another use case with Nano Banana Pro (Video is fully narrated so don't forget to turn on the sound 🔊) Image to 3D Model For 3D Printing 1 - Generate an image of a vinyl toy character. I generated a character called Peelbert. 2 - Generate multiple outfits for Peelbert while retaining consistency. Nano Banana Pro's consistency and understanding of outfit changes is superb. 3 - Use Hunyuan 3.0 to do image to 3D model 4 - Save as STL and 3D Print. Nano Banana Pro to the real world 👍

Travis Davids

44,133 просмотров • 9 месяцев назад

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

19,020 просмотров • 5 месяцев назад

The new Gen 4.5 update feels like an incredible unlock, especially for narrative work and consistency across scenes. Whenever I test new models internally, I find that the best way to evaluate performance is to use them to build a story. Here’s one I’ve always wanted to see brought to life.

The new Gen 4.5 update feels like an incredible unlock, especially for narrative work and consistency across scenes. Whenever I test new models internally, I find that the best way to evaluate performance is to use them to build a story. Here’s one I’ve always wanted to see brought to life.

Cristóbal Valenzuela

38,505 просмотров • 7 месяцев назад

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵

Chubby♨️

37,776 просмотров • 8 месяцев назад

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

Georgia Gkioxari

116,120 просмотров • 8 месяцев назад

Claude Opus 5 + Omni Flash is crazy... i gave opus 5 my best workflow and it turned it into a skill i can copy and paste into any llm to generate videos like this. - image prompts - omni flash video prompts - character consistency - product consistency everything in one place, it's crazy... here's how the video looks like:

Claude Opus 5 + Omni Flash is crazy... i gave opus 5 my best workflow and it turned it into a skill i can copy and paste into any llm to generate videos like this. - image prompts - omni flash video prompts - character consistency - product consistency everything in one place, it's crazy... here's how the video looks like:

0x ROAS

36,238 просмотров • 1 месяц назад

John Mozeliak says there's still plenty of time for the #STLCards' lineup to find some consistency: "The one thing I'd ask from our fan base right now is a little bit of patience, because we do think that we do have the talent to win."

John Mozeliak says there's still plenty of time for the #STLCards' lineup to find some consistency: "The one thing I'd ask from our fan base right now is a little bit of patience, because we do think that we do have the talent to win."

FanDuel Sports Network Midwest

674,869 просмотров • 3 лет назад

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency

AK

31,997 просмотров • 2 лет назад

Most kickers and punters are wasting their time in the gym. Not because they’re lazy—but because they’re following the wrong plan. You don’t need more squats or deadlifts. You need movements that actually translate to the field—ones that build strength, power, speed, explosion, agility, balance and flexibility. These aren’t just “football workouts.” They’re specialist-specific exercises designed to help you perform under pressure and hit the ball with consistency. 💥 Add any of the exercises in this video to your next workout. 📩 Comment “TRAINING” and we’ll help you maximize your workouts to build power and consistency.

Most kickers and punters are wasting their time in the gym. Not because they’re lazy—but because they’re following the wrong plan. You don’t need more squats or deadlifts. You need movements that actually translate to the field—ones that build strength, power, speed, explosion, agility, balance and flexibility. These aren’t just “football workouts.” They’re specialist-specific exercises designed to help you perform under pressure and hit the ball with consistency. 💥 Add any of the exercises in this video to your next workout. 📩 Comment “TRAINING” and we’ll help you maximize your workouts to build power and consistency.

Carney Coaching

18,683 просмотров • 1 год назад

🚀🚀🚀Introducing HY World 1.5 (WorldPlay)! We have now open-sourced the most systemized, comprehensive real-time world model framework in the industry. In HY World 1.5, we develop WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. You can generate and explore 3D worlds simply by inputting text or images. Walk, look around, and interact like you're playing a game. Highlights: 🔹Real-Time: Generates long-horizon streaming video at 24 FPS with superior consistency. 🔹Geometric Consistency: Achieved using a Reconstituted Context Memory mechanism to dynamically rebuild context from past frames to alleviate memory attenuation 🔹Robust Control: Uses a Dual Action Representation for robust response to user keyboard and mouse inputs. 🔹Versatile Applications: Supports both first-person and third-person perspectives, enabling applications like promptable events and infinite world extension. 👉🏻Try it now: 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical Report:

🚀🚀🚀Introducing HY World 1.5 (WorldPlay)! We have now open-sourced the most systemized, comprehensive real-time world model framework in the industry. In HY World 1.5, we develop WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. You can generate and explore 3D worlds simply by inputting text or images. Walk, look around, and interact like you're playing a game. Highlights: 🔹Real-Time: Generates long-horizon streaming video at 24 FPS with superior consistency. 🔹Geometric Consistency: Achieved using a Reconstituted Context Memory mechanism to dynamically rebuild context from past frames to alleviate memory attenuation 🔹Robust Control: Uses a Dual Action Representation for robust response to user keyboard and mouse inputs. 🔹Versatile Applications: Supports both first-person and third-person perspectives, enabling applications like promptable events and infinite world extension. 👉🏻Try it now: 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical Report:

Tencent Hy

189,802 просмотров • 8 месяцев назад

ELON: AIs NEED CONSISTENCY OR THEY GO INSANE “There just needs to be consistency. If it's okay to have, let's say, black, or Asian, or Indian pride, it should be okay to have white pride, too. That's just a consistency question. If it's okay to be proud of one religion, it should be okay to be proud of, I guess, all religions—as long as part of that religion is not exterminating people who are not in that religion. It's really just ensuring consistency to eliminate bias. So, if it's possible to be racist against one race, it is possible to be racist against any race. Arguing against that is a logical inconsistency that makes AIs go insane.” Source: Elon Musk on The Joe Rogan Experience Joe Rogan, October 31, 2025

ELON: AIs NEED CONSISTENCY OR THEY GO INSANE “There just needs to be consistency. If it's okay to have, let's say, black, or Asian, or Indian pride, it should be okay to have white pride, too. That's just a consistency question. If it's okay to be proud of one religion, it should be okay to be proud of, I guess, all religions—as long as part of that religion is not exterminating people who are not in that religion. It's really just ensuring consistency to eliminate bias. So, if it's possible to be racist against one race, it is possible to be racist against any race. Arguing against that is a logical inconsistency that makes AIs go insane.” Source: Elon Musk on The Joe Rogan Experience Joe Rogan, October 31, 2025

Mario Nawfal

49,143 просмотров • 8 месяцев назад

ELON: AIs NEED CONSISTENCY OR THEY GO INSANE “There just needs to be consistency. If it's okay to have, let's say, black, or Asian, or Indian pride, it should be okay to have white pride, too. That's just a consistency question. If it's okay to be proud of one religion, it should be okay to be proud of, I guess, all religions—as long as part of that religion is not exterminating people who are not in that religion. It's really just ensuring consistency to eliminate bias. So, if it's possible to be racist against one race, it is possible to be racist against any race. Arguing against that is a logical inconsistency that makes AIs go insane.” Source: Elon Musk on The Joe Rogan Experience Joe Rogan, October 31, 2025

ELON: AIs NEED CONSISTENCY OR THEY GO INSANE “There just needs to be consistency. If it's okay to have, let's say, black, or Asian, or Indian pride, it should be okay to have white pride, too. That's just a consistency question. If it's okay to be proud of one religion, it should be okay to be proud of, I guess, all religions—as long as part of that religion is not exterminating people who are not in that religion. It's really just ensuring consistency to eliminate bias. So, if it's possible to be racist against one race, it is possible to be racist against any race. Arguing against that is a logical inconsistency that makes AIs go insane.” Source: Elon Musk on The Joe Rogan Experience Joe Rogan, October 31, 2025

Mario Nawfal

128,433 просмотров • 9 месяцев назад

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

AK

161,530 просмотров • 2 лет назад

The truth is the truth - it stays the same yesterday, today, and tomorrow. You don’t have to remember it, because it simply is. When someone is telling the truth, their words don’t shift depending on who’s asking the question or what new information comes out. Lies are different. Lies are exhausting. They have to be remembered, re-remembered, and adjusted on the fly. One interview to the next, one statement to the next, the details blur. The story evolves, not because new facts emerged, but because evidence surfaced that contradicted the lie. So the narrative has to change to survive. That’s how you spot it. Not by emotion. Not by volume. But by consistency. The truth stands still. Lies scramble to keep up. And no matter how long it takes, the truth always catches up in the end. (Huge shoutout and thank you to Yvonne for this amazing video.)

The truth is the truth - it stays the same yesterday, today, and tomorrow. You don’t have to remember it, because it simply is. When someone is telling the truth, their words don’t shift depending on who’s asking the question or what new information comes out. Lies are different. Lies are exhausting. They have to be remembered, re-remembered, and adjusted on the fly. One interview to the next, one statement to the next, the details blur. The story evolves, not because new facts emerged, but because evidence surfaced that contradicted the lie. So the narrative has to change to survive. That’s how you spot it. Not by emotion. Not by volume. But by consistency. The truth stands still. Lies scramble to keep up. And no matter how long it takes, the truth always catches up in the end. (Huge shoutout and thank you to Yvonne for this amazing video.)

TESTIFY: Defending the Truth

53,835 просмотров • 8 месяцев назад

1/ Can molecular AI move past hard-coded Graph Neural Networks and embrace scalable Transformers that discover molecular structure on their own? We demonstrate that you can train a 1B parameter Transformer model without any graph priors or physical inductive biases. And surprisingly, not only can it maintain competitive performance under equal compute on the Open Molecules 2025 dataset… it’s faster than a 6M parameter equivariant GNN, and exhibits scaling laws that don’t saturate. We use this as a starting point to investigate emergent internal representations, and find that it adaptively discovers molecular structure! Check out the interactive demo on our website: And our paper: In collaboration with Toby Kreiman, Yutong Bai, Fadi, Elizabeth, and Eric Qu. Here’s a video showing how the Transformer learns distance-aware attention patterns (purple gradient) that adapt to atomic environments 👇

1/ Can molecular AI move past hard-coded Graph Neural Networks and embrace scalable Transformers that discover molecular structure on their own? We demonstrate that you can train a 1B parameter Transformer model without any graph priors or physical inductive biases. And surprisingly, not only can it maintain competitive performance under equal compute on the Open Molecules 2025 dataset… it’s faster than a 6M parameter equivariant GNN, and exhibits scaling laws that don’t saturate. We use this as a starting point to investigate emergent internal representations, and find that it adaptively discovers molecular structure! Check out the interactive demo on our website: And our paper: In collaboration with Toby Kreiman, Yutong Bai, Fadi, Elizabeth, and Eric Qu. Here’s a video showing how the Transformer learns distance-aware attention patterns (purple gradient) that adapt to atomic environments 👇

Aditi Krishnapriyan

39,631 просмотров • 10 месяцев назад

MVDream: Multi-view Diffusion for 3D Generation paper page: propose MVDream, a multi-view diffusion model that is able to generate geometrically consistent multi-view images from a given text prompt. By leveraging image diffusion models pre-trained on large-scale web datasets and a multi-view dataset rendered from 3D assets, the resulting multi-view diffusion model can achieve both the generalizability of 2D diffusion and the consistency of 3D data. Such a model can thus be applied as a multi-view prior for 3D generation via Score Distillation Sampling, where it greatly improves the stability of existing 2D-lifting methods by solving the 3D consistency problem. Finally, we show that the multi-view diffusion model can also be fine-tuned under a few shot setting for personalized 3D generation, i.e. DreamBooth3D application, where the consistency can be maintained after learning the subject identity.

MVDream: Multi-view Diffusion for 3D Generation paper page: propose MVDream, a multi-view diffusion model that is able to generate geometrically consistent multi-view images from a given text prompt. By leveraging image diffusion models pre-trained on large-scale web datasets and a multi-view dataset rendered from 3D assets, the resulting multi-view diffusion model can achieve both the generalizability of 2D diffusion and the consistency of 3D data. Such a model can thus be applied as a multi-view prior for 3D generation via Score Distillation Sampling, where it greatly improves the stability of existing 2D-lifting methods by solving the 3D consistency problem. Finally, we show that the multi-view diffusion model can also be fine-tuned under a few shot setting for personalized 3D generation, i.e. DreamBooth3D application, where the consistency can be maintained after learning the subject identity.

AK

294,496 просмотров • 3 лет назад

“For Africa, energy is not simply a development issue. It is the foundation of industrial growth, and competitiveness. At the centre of this endeavour, is the question of investment. Too often, investors hesitate because they perceive many risks in Africa. We must work to strengthen regulation, ensure consistency and accountability, in order to build confidence and attract long-term capital.” President Kagame | Opening of the 2nd Nuclear Energy Innovation Summit for Africa #NEISA2026

“For Africa, energy is not simply a development issue. It is the foundation of industrial growth, and competitiveness. At the centre of this endeavour, is the question of investment. Too often, investors hesitate because they perceive many risks in Africa. We must work to strengthen regulation, ensure consistency and accountability, in order to build confidence and attract long-term capital.” President Kagame | Opening of the 2nd Nuclear Energy Innovation Summit for Africa #NEISA2026

Presidency | Rwanda

27,262 просмотров • 3 месяцев назад

SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes abs: paper page: Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or virtual-asset creation. We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our dynamic-NeRF method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. It then reconstructs the deformations of an estimated canonical model of the geometry and appearance in an online fashion. Since this canonical model is time-invariant, we obtain correspondences even for long-term, long-range motions. We employ neural scene representations to parametrize the components of our method. Like prior dynamic-NeRF methods, we use a backwards deformation model. We find non-trivial adaptations of this model necessary to handle larger motions: We decompose the deformations into a strongly regularized coarse component and a weakly regularized fine component, where the coarse component also extends the deformation field into the space surrounding the object, which enables tracking over time. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.

SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes abs: paper page: Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or virtual-asset creation. We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our dynamic-NeRF method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. It then reconstructs the deformations of an estimated canonical model of the geometry and appearance in an online fashion. Since this canonical model is time-invariant, we obtain correspondences even for long-term, long-range motions. We employ neural scene representations to parametrize the components of our method. Like prior dynamic-NeRF methods, we use a backwards deformation model. We find non-trivial adaptations of this model necessary to handle larger motions: We decompose the deformations into a strongly regularized coarse component and a weakly regularized fine component, where the coarse component also extends the deformation field into the space surrounding the object, which enables tracking over time. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.

AK

76,380 просмотров • 3 лет назад

Current world models often separate spatial reasoning from temporal modeling, leading to consistency bottlenecks and scaling limits. We developed RAYNOVA, a 4D world foundation model, to address this by unifying space and time into a single representation via a pure auto-regressive framework. The result: Data-driven high-fidelity simulation data that scales across any vehicles, anywhere. Read the full technical breakdown:

Current world models often separate spatial reasoning from temporal modeling, leading to consistency bottlenecks and scaling limits. We developed RAYNOVA, a 4D world foundation model, to address this by unifying space and time into a single representation via a pure auto-regressive framework. The result: Data-driven high-fidelity simulation data that scales across any vehicles, anywhere. Read the full technical breakdown:

Applied Intuition

11,252 просмотров • 3 месяцев назад