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 #AIshow more

Super excited about Hydra-0 from Hongyu Li and team!... The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.show more

Depth Any Video with Scalable Synthetic Data AI physicists... and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.show more

I'll always root for a team that open-sources its... best work, and Robbyant just did it properly. Robbyant, Ant Group's embodied-AI company, released LingBot-Vision, a vision foundation model for robots, and the part I love is the data. They trained it on 161M images, filtered down from 2B raw ones and mostly pulled straight from the open web, with no human labels, no edge detectors, no depth sensors anywhere in the loop. It learns the exact edges of objects from raw pixels. That's roughly a tenth of the data DINOv3 saw, and under a third of the training. And it shows in the results. On depth, working out how far away things are, the 1B model edges out a 7B on NYU-Depth. It also powers LingBot-Depth 2.0, which reads the surfaces cameras usually choke on, glass and mirrors, and halves indoor depth error. LingBot-Vision is fully open. Weights from the 1.1B flagship down to a tiny 21M version, code, and the paper. This is the timeline I want more of. Robbyantshow more

a Vietnamese AI engineer just built a real-time system... that counts objects moving down a conveyor belt. it runs on ultralytics' objectcounter. train a detector, define the region you care about, and it handles the rest. works for anything on a line, parts, packages, produce. the clever bit: instead of hand-labeling thousands of frames, he took a single frame, pre-annotated it with meta's segment anything (sam-2, built into ultralytics), and trained yolo11-nano on just that. one annotated frame, and it tracks objects accurately across the entire video.show more

NVIDIA just released a very impressive text-to-video paper. Video... Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:show more

Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D... diffusion model that explicitly models object articulation, paving the way for richer, more realistic assets in embodied AI and simulation: – Generates fully articulated 3D objects – Physically plausible joints & motion – High-fidelity 3D Gaussian appearance – Supports generation from a single real image arXiv: Project: Code (coming soon):show more

Trained on zero real-world data. Learned to walk, pick... up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:show more

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.show more

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.show more

We’ve seen humanoid robots walk around for a while,... but when will they actually help with useful tasks in daily life? The challenge here is the diversity and complexity of real-world scenes. Our new work tackles this problem via 3D visuomotor policy learning. Using data from only 1 scene, our Improved 3D Diffusion Policy (iDP3) enables a full-sized humanoid robot to autonomously pick&place objects, pour water, and wipe tables, in the wild open world. (and all these skills are useful, right?) Web: Fully open-sourced code:show more

Check out this Stereo4D paper from Google DeepMind. It's... a pretty clever approach to a persistent problem in computer vision -- getting good training data for how things move in 3D. The key insight is using VR180 videos -- those stereo fisheye videos we launched back in 2017 for YouTubeVR. It was always clear that structured stereo datasets would be valuable for computer vision -- and we launched some powerful VR tools with it back in 2017 (link below). But what's the game changer now in 2024 is the scale -- they're providing 110K high quality clips :-) That's the kind of massive, real-world AI dataset that was just a dream back then! They're using it to train this model called DynaDUSt3R that can predict both 3D structure and motion from video frames. Which means it tracks how objects move between frames while simultaneously reconstructing their 3D shape. And given we're dealing with real stereoscopic content, results are notably better than synthetic data, giving you a faithful rendition of the real-world with a diverse set of subject matter. It's one of those through lines when tackling a timeless mission like mapping the world or spatial computing -- VR content created for immersion becoming the foundation for teaching machines to understand how the world moves. Sometimes innovation chains together in unexpected ways! Links to projects below⛓️show more

How can robots reliably place objects in diverse real-world... tasks? 🤖🔍 Placement is tough—objects vary in shape and placement modes (such as stacking, hanging, and insertion), making it a challenging problem. We introduce AnyPlace, a two-stage method trained purely on synthetic data to predict diverse placement poses of unseen objects for real-world tasks. Read on for more👇show more

We just ran one of the largest robot models... that exists today, all without a local GPU. And it’s running real-time at <50 ms overhead. Scaling laws are becoming real for physical AI. Perceptron’s Isaac 0.5 is one of the largest open-source models, sitting at 36B total parameters. Perceptron AI joins other frontier robotics labs like Dyna Robotics and Generalist in showing the need to massively scale pre-training data, from a 1000s to millions of hours of video. Specifically, they show that the more egocentric video the model is trained on, the less teleop data that it needs to achieve the same loss. At Dreamscale Labs (YC F26) (YC F26), we’ve noticed an important truth here: data and training compute do not just scale in isolation. The model sizes must increase too, and GPT-6 Astra has given a glimpse into what a trillion-parameter robotics model could do. We’re building to serve that future - one that is not constrained by the bottlenecks of on-board compute, but rather, allowing large models to run fast over the cloud. Reach out if you’re interested in our work.show more

Robots don’t just need better brains. They need WAY... more real-world data. 🤖 And collecting high-quality dexterous robot data at scale is one of the hardest problems in physical AI. A fascinating approach is emerging: Wearable human demonstrations + structurally matched dexterous robots. Instead of humans directly teleoperating a robot, Chinese embodied AI startup X Square Robot's TwinDEX system captures the motion, contact, and visual information needed to train the robot — while keeping the data closer to the hardware that will actually execute the task. Early results show promising performance on tool use, fine manipulation, and complex contact-rich tasks. If this approach scales, it could change how we build real-world robotics datasets. The next frontier of physical AI might not be bigger models. It might be better data.show more

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:show more

NVIDIA finally released Neuralangelo's source code! The model can... turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.show more

Coarse2Real (C2R) transfers simple 3D renderings into realistic style... video. Check our paper and project page to learn how to hedge small amount of synthetic paired data with real non-pair data for training the C2R model. We will release the model soon!show more