Yichen Sheng @Coding_Black

Can't wait to see some of you in Berlin!

NVIDIA GTC @NVIDIAGTC

a week ago

Open models are how developers build AI they can own. Not just weights. Model families, post-training recipes, evaluation tools, and supporting data give teams the ability to inspect, adapt, and deploy AI for real applications. At GTC Berlin, Bryan Catanzaro, VP of Applied Deep

6 10 67 14K 8

Hello everyone! Me and @davnords will be presenting RoMa v2 and LoMa back-to-back at 9AM in the Geometry, Localization, Matching & Motion spotlight session at #ECCV2026

Impressed by GPT-Astra’s CoT ! This Kung Fu demo is built from scrach in Blender and takes the reference video + simple prompt as input. The CoT reasoning really show a grasp of kinematics, joint coordination, and body motion ! Reference video comes from PhysAvater @qingqing_zhao_ @yang_zheng18

GPT-6 Astra feels deeply personal. In summer 2024, during my internship with #NVIDIACosmos team, we started Scenethesis(research.nvidia.com/labs/cosmos-la…) with GPT-4o: an agent that could imagine a 3D scene, ground it through promt/vision, align it with physics, judge the result before replaning. Those were good old days. Two years later, the dream has grown far beyond a single scene. Astra brings much stronger multimodal reasoning and long-horizon tool use; Blender and Unreal are becoming canvases for intelligence. Watching the base model advance this quickly is astonishing—and incredibly exciting. The mission ahead excites me most: agents that create, simulate, and explore worlds; accumulate knowledge from experience; and keep evolving—for games, robotics, and embodied AI. Huge congratulations to the brilliant @OpenAI team. What a beautiful moment for the agentic world!

OpenAI @OpenAI

3 weeks ago

GPT-6 Astra is the most intelligent and aligned model in the world, and sets a new state of the art for computer use, browsing, software engineering, cybersecurity, science, and professional work. openai.com/index/gpt-6-as…

213 633 11K 3.4M 1K

🚀🚀 We officially release DLSS 5, a real-time, 3D-guided neural rendering stage that transforms rendered frames into vivid, realistic scenes while preserving developer-authored content and design intent. To achieve both enhanced realism and real-time rendering at up to 4K resolution, we develop a one-step pixel-space diffusion model. Compared with offline foundation models such as GPT Image 2 and Gemini 3 Pro, DLSS 5 delivers strong realism while much more faithfully preserving the input content, identity, and scene structure. Looking ahead, we’re continuing to push on realism, controllability, temporal stability, and efficiency. Stay tuned! Check out our technical report for more on how we think about generative modeling for gaming: research.nvidia.com/labs/adlr/file… I feel excited to finally see DLSS 5 released! As a researcher working on visual generative modeling, it’s especially meaningful to see our fundamental research make its way into a real product. This has actually been a very special journey for me—from exploring research ideas, to building our first working prototype, and then working closely with the team to turn the research, step by step, into DLSS 5. Proud of what our team has accomplished! We’d love to hear your thoughts on how we can continue improving the technology and where generative rendering can take the future of gaming. Discussions are very welcome!

Edward Liu @edliu1105

3 weeks ago

We’re publishing a deeper technical report on why generation is needed for the next leap toward photorealism. VRAM and compute limit both the scene abstraction and the number of rays we can afford. Previous DLSS reconstructs from that representation—so even perfect

28 41 403 126K 143

There we go 🚀 youtu.be/5khwlu2qD9U

Have to correct your misunderstanding of my sentence. My original sentence: PT *faithfully* simulate the scene. The bottleneck is that the assets are a real-world approximation. This approximation leads to fake feeling. There does exist many games with great assets, PT makes them look incredible.

@Timebringer @edliu1105 DLSS5 is deterministic in inference time. Generative methods can still be deterministic in inference.

I feel incredibly lucky that my first project after finishing my PhD became #DLSS5. In my first 1:1 with @edliu1105, I created this slide to show what I believed next-generation rendering could become. For me, this was the beginning of the journey. My North Star for rendering has always been a world indistinguishable from footage captured by a real camera. The realism upper bound for existing #DLSS is path tracing (PT). PT can faithfully simulate the scene we describe—but that scene remains an approximation of the real world. As a result, it still looks fake, plastic, far from visually realistic in most of the current gaming. The rise of generative models opened a complementary path. Early results gave us enough signal to pursue a belief: learned real-world appearance priors could work with physically based rendering—not replace it—to move beyond this ceiling. DLSS 5 is our first step: a generative video model that operates in real time at up to 4K while remaining grounded in the authored scene. Getting here took years. Skepticism pushed us to clarify the idea, strengthen the system, and make the evidence more rigorous. I’m deeply grateful for the leadership of @edliu1105, @drewtao and @ctnzr, and for our team’s extraordinary execution. I’m proud that we have demonstrated a new research and design space in graphics rendering—one that deserves much more exploration. If you work in graphics, vision, or generative models, I hope you’ll read our technical report and join us in exploring it.

Edward Liu @edliu1105

3 weeks ago

We’re publishing a deeper technical report on why generation is needed for the next leap toward photorealism. VRAM and compute limit both the scene abstraction and the number of rays we can afford. Previous DLSS reconstructs from that representation—so even perfect

28 41 403 126K 143

People are worrying about AI takes over human's jobs. After vibe coding for months, I confirmed(a lot of times) I am the bottleneck. So no need to scale agents, we need to scale human labors to maximize productivity actually 😅😅😅

A super cool world model that you can control the action as well.

Ruili Feng @feng_ruili_frl

2 months ago

We made an Elden Ring boss fight playable inside a real-time video world model. Text is not a scene prompt. It is the controller. Play Incantation: reactor.inc/incantation

2 6 20 20K 8

Remember to join this keynote to know more about DLSS5.

Edward Liu @edliu1105

2 months ago

x.com/i/article/2078…

3 12 42 7K 2

Look forward to it!

NVIDIA @nvidia

3 months ago

The future of computer graphics is here, and it's built by AI. ✨ Don't miss the NVIDIA Research Keynote at SIGGRAPH 2026 for live demos and research examples showcasing breakthrough neural rendering, world models, and simulation methods across creative tools, industrial design,

46 75 297 83K 24

A new era of computer graphics is emerging through AI, with new speaker Edward Liu joining NVIDIA Research and Engineering leaders Jan Kautz and Ming-Yu Liu. Join the 'SIGGRAPH 2026 Sponsored Keynote, Next Era of Graphics — Neural Rendering, World Models, and Simulation' This session will explore the latest advances in neural rendering, world foundation models, and AI-driven simulation through breakthrough research and live demonstrations. s2026.siggraph.org/program/keynot…

Glad to share our PixelDiT work to the community! Many thanks to all coauthors and contributors. This is the first research project I initiate and lead after joining NVIDIA. Thanks for the support from our ADLR team. We will continue pushing the research on pixel diffusion. Check our project page for paper, code, and weights: pixeldit.github.io

NVIDIA AI @NVIDIAAI

4 months ago

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel

20 36 256 28K 80

Heading to #CVPR2026! I’m excited to present our work: I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners 📍 Denver 🗓 June 6, 4:45–6:45 PM MDT For years, learning-based interactive 3D scene generation has been shaped and constrained by 3D-FRONT. Methods learn layout distributions from this dataset, making their spatial priors tightly coupled to its limited diversity, and spatial relation statistics. In I-Scene, we answer a key question: ❓ Where do spatial priors for interactive 3D scene generation come from when data is limited? Our finding is surprisingly simple: strong 3D instance models already encode rich spatial priors. By reprogramming an instance-level model with scene-context attention and view-centric space, I-Scene can generalize to interactive 3D scenes without relying on heavily annotated scene datasets. 🌟 Key takeaways: 1️⃣ View-centric space matters for spatial relationships 2️⃣ Randomly composed objects can provide surprisingly strong supervision 3️⃣ Strong instance models can serve as a foundation for real-to-sim 3D scene generation Come by and chat if you’re interested in #GenAI, #SpatialIntelligence, #RealToSim, or #EmbodiedAI!

Nemotron 3 Ultra: Frontier smart. 5X faster. 30% cheaper. 💚💚💚

Cool world action model!

Ruili Feng @feng_ruili_frl

4 months ago

“Carve nature at its joints.” — after Plato We built WALL-WM, an event-centric World Action Model. Fixed chunks cut by clock. Semantic events cut by embodied dynamics. Instead of predicting fixed-length action chunks, WALL-WM learns through action-grounded events: reach,

1 2 15 4K 13

Try it out!

Lu Ling @LuLing26466911

4 months ago

🚀 Want to see how we do real-to-sim from a single input image? We’re releasing the code for I-Scene #CVPR2026! ✨Highlights: - Stronger scene generalization trained on randomly composed objects - Scalable data generation for downstream tasks - Supports both 3D Gaussian

2 19 123 14K 112

Glad to be selected as an Outstanding Reviewer. Appreciate the AC’s recognition. For reviewers who worked hard but were not selected: please don’t be discouraged. The process can be random. I’ve tried to keep my review quality high for years, and only got selected this year. Every responsible reviewer is a hero, selected or not. Your effort is not wasted — you are helping the community and making the right choice for science.

#CVPR2026 @CVPR

4 months ago

We are grateful to all of the 17,491 reviewers who helped make #CVPR2026 possible. We are especially pleased to recognize the following Outstanding Reviewers, whose high-quality reviews (as judged by their Area Chairs) placed them among the top 5% of reviewers.

keyboard_arrow_left Previous keyboard_arrow_right Next

5 43 226 102K 31