正在加载视频...

视频加载失败

返回首页

Massive update for AI Engineers! Training diffusion models just got a lot easier. dLLM is an open-source library that does for diffusion models what Hugging Face did for transformers. Here's why this matters: Traditional autoregressive models generate text left-to-right, one token at a time. Diffusion models work differently -...

akshay_pachaar's profile picture

Akshay 🚀

290,477 subscribers

64,011 次观看 • 10 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.
0:19

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.

AK

25,465 次观看 • 2 年前

Most recent diffusion language model research (that I’ve seen) seems to be using masking as the noising process. It looks like, however, most closed-source models (Google Gemini Diffusion and possibly Inception Labs’ Mercury) use a different noising process, where instead of masking tokens, they replace them with different tokens (either with a random token or a semantically similar token). I wondered how they were getting such high throughput with the latter noising process, since I believed that optimizing inference with KVCache approximation would be more difficult (for various reasons). I visualized this noising process with tiny-diffusion and compared it to normal unmasking, and was very surprised to see how fast the generation “settles” into a reasonable output, and then only slightly refines afterwards, requiring much fewer steps in total. Unmasking (where tokens are never remasked, the typical implementation) is inherently limited in generation speed by the fact that an increase in tokens decoded per step leads to more errors due to the mismatch between individual and marginal token probability distributions we sample from. The token replacement noising process seems to have a much different set of characteristics. Because we sample each token per step, every token makes “progress” towards the final output each iteration (in addition to *potentially* giving other tokens more information in future steps). Generally, masking has outperformed other noising processes, which is probably why most research focused on it (using smaller models). But the paper referred to in the retweet shows that random replacement as a noising process may scale better as model size increases. Big labs might have noticed these results much earlier (due to having drastically more training resources and being able to test larger models), which may explain the discrepancy in the choice of noising process. I’m gonna test this with larger models, since tiny-diffusion only has 10M parameters.
0:13

Most recent diffusion language model research (that I’ve seen) seems to be using masking as the noising process. It looks like, however, most closed-source models (Google Gemini Diffusion and possibly Inception Labs’ Mercury) use a different noising process, where instead of masking tokens, they replace them with different tokens (either with a random token or a semantically similar token). I wondered how they were getting such high throughput with the latter noising process, since I believed that optimizing inference with KVCache approximation would be more difficult (for various reasons). I visualized this noising process with tiny-diffusion and compared it to normal unmasking, and was very surprised to see how fast the generation “settles” into a reasonable output, and then only slightly refines afterwards, requiring much fewer steps in total. Unmasking (where tokens are never remasked, the typical implementation) is inherently limited in generation speed by the fact that an increase in tokens decoded per step leads to more errors due to the mismatch between individual and marginal token probability distributions we sample from. The token replacement noising process seems to have a much different set of characteristics. Because we sample each token per step, every token makes “progress” towards the final output each iteration (in addition to *potentially* giving other tokens more information in future steps). Generally, masking has outperformed other noising processes, which is probably why most research focused on it (using smaller models). But the paper referred to in the retweet shows that random replacement as a noising process may scale better as model size increases. Big labs might have noticed these results much earlier (due to having drastically more training resources and being able to test larger models), which may explain the discrepancy in the choice of noising process. I’m gonna test this with larger models, since tiny-diffusion only has 10M parameters.

nathan (in sf)

40,440 次观看 • 8 个月前

Show-o One Single Transformer to Unify Multimodal Understanding and Generation discuss: We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.
0:13

Show-o One Single Transformer to Unify Multimodal Understanding and Generation discuss: We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.

AK

124,085 次观看 • 2 年前

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.
0:13

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.

Michael Black

22,353 次观看 • 9 个月前

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation
0:19

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

AK

41,830 次观看 • 3 年前

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.
0:17

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.

AK

375,160 次观看 • 3 年前

We release Diamond Maps💎 unlocking accurate and efficient guidance for diffusion models. Our experiments show that our methods scale incredibly well. Excited to see what people will build with this! Accurate guidance has been a notoriously hard problem, but in this work, we’re bringing TWO (!) solutions to the table. The recipe for success: 1️⃣ Speed: Use distilled models (flow maps, mean flows, consistency models). 2️⃣ Exploration: Inject stochasticity to properly explore your search space. Because this fundamentally improves anything using flow matching and diffusion, we see a lot of potential for applications across audio, robotics, molecules, and beyond. Paper: Code: Huge thanks to an amazing team: Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong (Kelly) He, Zeynep Akata, Tommi Jaakkola, Nicholas Boffi, and Max Simchowitz. It was awesome bringing this to life together!
0:12

We release Diamond Maps💎 unlocking accurate and efficient guidance for diffusion models. Our experiments show that our methods scale incredibly well. Excited to see what people will build with this! Accurate guidance has been a notoriously hard problem, but in this work, we’re bringing TWO (!) solutions to the table. The recipe for success: 1️⃣ Speed: Use distilled models (flow maps, mean flows, consistency models). 2️⃣ Exploration: Inject stochasticity to properly explore your search space. Because this fundamentally improves anything using flow matching and diffusion, we see a lot of potential for applications across audio, robotics, molecules, and beyond. Paper: Code: Huge thanks to an amazing team: Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong (Kelly) He, Zeynep Akata, Tommi Jaakkola, Nicholas Boffi, and Max Simchowitz. It was awesome bringing this to life together!

Peter Holderrieth

61,236 次观看 • 5 个月前

Holy sh!t ! OpenAI will have their custom inference chips ready in just a few months and deployed at scale by the end of the year! 🤯 Training chip = The heavy lifters that require massive amounts of data and power to build and teach the AI models from scratch. Inference chip = The specialized, highly efficient chips that actually run the AI and generate the answers in real-time when you use it. This is going to help OpenAI drastically cut down their massive compute costs, speed up model reasoning times, and finally break free from relying entirely on Nvidia to scale their operations.
0:14

Holy sh!t ! OpenAI will have their custom inference chips ready in just a few months and deployed at scale by the end of the year! 🤯 Training chip = The heavy lifters that require massive amounts of data and power to build and teach the AI models from scratch. Inference chip = The specialized, highly efficient chips that actually run the AI and generate the answers in real-time when you use it. This is going to help OpenAI drastically cut down their massive compute costs, speed up model reasoning times, and finally break free from relying entirely on Nvidia to scale their operations.

Chris

60,278 次观看 • 7 个月前

🚀 Early Access to Sahara AI Studio is NOW OPEN! The next phase of our testnet is here with exclusive early access to our all-in-one platform designed to transform the AI development lifecycle into a streamlined, integrated experience. Here’s everything you need to know 👇 AI development is fragmented. Devs juggle multiple tools, leading to inefficiencies & high costs. Sahara AI Studio integrates the entire AI lifecycle—from datasets & model training to secure storage & scalable compute—into one seamless experience: 📊 Data Hub: Discover, Manage, and Leverage AI-Ready Datasets Access high-quality, domain-specific, open-source and proprietary datasets through an integrated marketplace. Developers can download, import, or label datasets, making it easier to train and fine-tune models or deploy RAG pipelines. Secure uploads and seamless workflow integration enhance the experience. 🤖 Model Hub: Discover, Customize and Scale AI Workflows with Ease Discover ready-to-use open-source and proprietary models, RAG pipelines, and customizable workflows. Developers can deploy models quickly while maintaining privacy and security through Sahara Vaults. 🖥️ Compute Hub: Flexible, Scalable Compute Resources for AI Innovation Access scalable and secure computing resources tailored to diverse AI workloads. Trusted Execution Environment (TEE) capabilities ensure data privacy, while integration with top compute providers offer flexibility for developers. 🔐 Vaults: Secure Storage for AI Assets Securely store, organize, and manage datasets, models, and other assets in an encrypted central repository. Vaults offer scalability, reproducibility, and user control over AI resources. This is more than just beta testing a platform—it's your chance to help shape the future of decentralized AI development. 📅 How to Apply We're onboarding select developers in a phased approach. Early Access spots are limited, so apply now:
0:11

🚀 Early Access to Sahara AI Studio is NOW OPEN! The next phase of our testnet is here with exclusive early access to our all-in-one platform designed to transform the AI development lifecycle into a streamlined, integrated experience. Here’s everything you need to know 👇 AI development is fragmented. Devs juggle multiple tools, leading to inefficiencies & high costs. Sahara AI Studio integrates the entire AI lifecycle—from datasets & model training to secure storage & scalable compute—into one seamless experience: 📊 Data Hub: Discover, Manage, and Leverage AI-Ready Datasets Access high-quality, domain-specific, open-source and proprietary datasets through an integrated marketplace. Developers can download, import, or label datasets, making it easier to train and fine-tune models or deploy RAG pipelines. Secure uploads and seamless workflow integration enhance the experience. 🤖 Model Hub: Discover, Customize and Scale AI Workflows with Ease Discover ready-to-use open-source and proprietary models, RAG pipelines, and customizable workflows. Developers can deploy models quickly while maintaining privacy and security through Sahara Vaults. 🖥️ Compute Hub: Flexible, Scalable Compute Resources for AI Innovation Access scalable and secure computing resources tailored to diverse AI workloads. Trusted Execution Environment (TEE) capabilities ensure data privacy, while integration with top compute providers offer flexibility for developers. 🔐 Vaults: Secure Storage for AI Assets Securely store, organize, and manage datasets, models, and other assets in an encrypted central repository. Vaults offer scalability, reproducibility, and user control over AI resources. This is more than just beta testing a platform—it's your chance to help shape the future of decentralized AI development. 📅 How to Apply We're onboarding select developers in a phased approach. Early Access spots are limited, so apply now:

Sahara AI 🔆

2,700,973 次观看 • 1 年前

Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇
0:10

Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇

Stability AI

166,625 次观看 • 4 个月前

Chop the gradients ✂️! We found that truncating decoder gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.
0:19

Chop the gradients ✂️! We found that truncating decoder gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.

Felix Heide

28,467 次观看 • 5 个月前

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.
0:19

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.

elvis

47,678 次观看 • 5 个月前

World modeling and imitation learning have largely been considered two disparate worlds. In our recent work, Unified World Models, just accepted to #RSS2025, Chuning Zhu provides a dead-simple unifying solution: just train a joint diffusion model over actions and future states, but with *decoupled* diffusion time steps across these modalities. Manipulating these decoupled time steps then allows for marginalization or conditioning on actions or states; a single model can serve as a policy, forward dynamics model, video prediction model, or inverse dynamics model by simply setting diffusion timesteps carefully. The resulting model can leverage video datasets along with robot training data much more effectively, and shows improved robustness, generalization, and flexibility. This is exciting because it is frustratingly simple, scalable, and shows strong improvement on real-world robotics problems. Please refer to Chuning Zhu 's excellent thread for more details! More details/code can be found on our website and in the paper -
0:15

World modeling and imitation learning have largely been considered two disparate worlds. In our recent work, Unified World Models, just accepted to #RSS2025, Chuning Zhu provides a dead-simple unifying solution: just train a joint diffusion model over actions and future states, but with *decoupled* diffusion time steps across these modalities. Manipulating these decoupled time steps then allows for marginalization or conditioning on actions or states; a single model can serve as a policy, forward dynamics model, video prediction model, or inverse dynamics model by simply setting diffusion timesteps carefully. The resulting model can leverage video datasets along with robot training data much more effectively, and shows improved robustness, generalization, and flexibility. This is exciting because it is frustratingly simple, scalable, and shows strong improvement on real-world robotics problems. Please refer to Chuning Zhu 's excellent thread for more details! More details/code can be found on our website and in the paper -

Abhishek Gupta

11,430 次观看 • 1 年前

You can't 3D reconstruct glass from images... ...WRONG! Thanks for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AI
0:14

You can't 3D reconstruct glass from images... ...WRONG! Thanks for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AI

Jonathan Stephens

17,712 次观看 • 9 个月前

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:
0:10

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

雪踏乌云

113,347 次观看 • 2 个月前

A major question in multimodal modeling is how to leverage strong pre-trained models, such as industry-scale LLMs and VLMs, during training to avoid starting from scratch. This is important as the demand for rich and domain-specific multimodal models continues to increase, while training them from scratch is obviously impractical due to limited data and compute. The so-called “any-to-any” multimodal models can model a large diverse dictionary of modalities. That’s good. Their downside is that their architectures are often not decoder-only, which has limited their performance in practice and prevents them from leveraging strong pre-trained decoder-only models as priors. We are releasing MODUS (ICML Conference '26) a decoder-only any-to-any multimodal model to address some of these questions. A single transformer decoder predicts any modality from any others with no modality-specific heads, losses, or task pipelines. We show efficient adaptation of established models, e.g., BAGEL, to rich any-to-any multimodal modeling. We are releasing 14B to 77B parameter models. All materials are open-source. The download links and demos here 🧵
0:18

A major question in multimodal modeling is how to leverage strong pre-trained models, such as industry-scale LLMs and VLMs, during training to avoid starting from scratch. This is important as the demand for rich and domain-specific multimodal models continues to increase, while training them from scratch is obviously impractical due to limited data and compute. The so-called “any-to-any” multimodal models can model a large diverse dictionary of modalities. That’s good. Their downside is that their architectures are often not decoder-only, which has limited their performance in practice and prevents them from leveraging strong pre-trained decoder-only models as priors. We are releasing MODUS (ICML Conference '26) a decoder-only any-to-any multimodal model to address some of these questions. A single transformer decoder predicts any modality from any others with no modality-specific heads, losses, or task pipelines. We show efficient adaptation of established models, e.g., BAGEL, to rich any-to-any multimodal modeling. We are releasing 14B to 77B parameter models. All materials are open-source. The download links and demos here 🧵

Amir Zamir

24,161 次观看 • 3 个月前

Predicting the next word "only" is sufficient for language models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.
0:14

Predicting the next word "only" is sufficient for language models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.

Nando de Freitas

134,406 次观看 • 2 年前

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft paper page: Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces an instruction-tuned Video Pretraining (VPT) model for Minecraft called STEVE-1, demonstrating that the unCLIP approach, utilized in DALL-E 2, is also effective for creating instruction-following sequential decision-making agents. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent space, then training a prior to predict latent codes from text. This allows us to finetune VPT through self-supervised behavioral cloning and hindsight relabeling, bypassing the need for costly human text annotations. By leveraging pretrained models like VPT and MineCLIP and employing best practices from text-conditioned image generation, STEVE-1 costs just $60 to train and can follow a wide range of short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 sets a new bar for open-ended instruction following in Minecraft with low-level controls (mouse and keyboard) and raw pixel inputs, far outperforming previous baselines. We provide experimental evidence highlighting key factors for downstream performance, including pretraining, classifier-free guidance, and data scaling. All resources, including our model weights, training scripts, and evaluation tools are made available for further research.
0:14

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft paper page: Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces an instruction-tuned Video Pretraining (VPT) model for Minecraft called STEVE-1, demonstrating that the unCLIP approach, utilized in DALL-E 2, is also effective for creating instruction-following sequential decision-making agents. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent space, then training a prior to predict latent codes from text. This allows us to finetune VPT through self-supervised behavioral cloning and hindsight relabeling, bypassing the need for costly human text annotations. By leveraging pretrained models like VPT and MineCLIP and employing best practices from text-conditioned image generation, STEVE-1 costs just $60 to train and can follow a wide range of short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 sets a new bar for open-ended instruction following in Minecraft with low-level controls (mouse and keyboard) and raw pixel inputs, far outperforming previous baselines. We provide experimental evidence highlighting key factors for downstream performance, including pretraining, classifier-free guidance, and data scaling. All resources, including our model weights, training scripts, and evaluation tools are made available for further research.

AK

144,827 次观看 • 3 年前

TESLA HALTED MODEL S AND MODEL X PRODUCTION TO BUILD AN ARMY OF OPTIMUS ROBOTS The Fremont assembly line was torn down in 46 days. In its place, Tesla is building a line for humanoid production, aiming for a million units a year A humanoid robot is a body shaped like a human. Physical AI is the intelligence that controls that body Walking and making coffee is often just imitation learning from a scripted routine. But once the environment shifts, the learned trick stops working Language models had the entire internet to train on. Robotics has nothing close to that scale of data, which is why one giant brain hasn't worked for anyone yet The industry is moving toward modularity instead - separate models for vision, movement, and planning, each improved on its own The real question is no longer whether a robot can move impressively. It's whether it can pull its sensors into one picture of the world and adapt to whatever wasn't scripted for it
0:12

TESLA HALTED MODEL S AND MODEL X PRODUCTION TO BUILD AN ARMY OF OPTIMUS ROBOTS The Fremont assembly line was torn down in 46 days. In its place, Tesla is building a line for humanoid production, aiming for a million units a year A humanoid robot is a body shaped like a human. Physical AI is the intelligence that controls that body Walking and making coffee is often just imitation learning from a scripted routine. But once the environment shifts, the learned trick stops working Language models had the entire internet to train on. Robotics has nothing close to that scale of data, which is why one giant brain hasn't worked for anyone yet The industry is moving toward modularity instead - separate models for vision, movement, and planning, each improved on its own The real question is no longer whether a robot can move impressively. It's whether it can pull its sensors into one picture of the world and adapt to whatever wasn't scripted for it

iamigorekk

22,205 次观看 • 1 个月前