Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: Minimalist editorial illustration in Anthropic style with thick black hand-drawn lines on warm off-white background, showing three iconic streams (wavy audio line, simple eye symbol, letter A) converging into a central circle node, flat vector shapes with slight wobble, subtle paper grain texture, high contrast, lots of negative space, 16:9 split-screen layout with icon centered on left panel and warm tan right panel for bold black typography.
A conversation with the Project Genie team on the path to launching the most powerful world model to date, where they expect to see value from these models in the short term, what comes next, and more : ) Featuring: @jparkerholder @shlomifruchter and @drivascos”” https://x.com/OfficialLoganK/status/2018420009115017310
Fun to turn paintings into scenes I can walk around in using Genie 3: here are the works of Giorgio de Chirico, Munch, Turner, and the Bayeux Tapestry. I can move freely around the scenes, and, yes, they are a little weird, but its real-time dynamic image creation by the AI.”” https://x.com/emollick/status/2017852070620025250
Giving the world’s first photograph, the View from the Window at Le Gras, from 1822, to Genie 3.”” https://x.com/emollick/status/2018494862178316725
Much debate over Genie vs 3D engines. You can have both – the control of 3D scene graphs + the creativity of generative ai. Wrote this in 2024 breaking down the vision. The models are almost there. Now just imagine if Unreal / Unity productized this.”” https://x.com/bilawalsidhu/status/2018119240612536587
The capabilities of Genie 3 are strange and surprising. Sometimes NPCs are animated & move around & react, but I can’t seem to control that happening. Sometimes objects have physical properties like stretching or tearing. The world in the world model peeks through at odd times.”” https://x.com/emollick/status/2017805206419918883
Took an old photo of a WWI battlecruiser, gave it to Genie 3, and prompted it to let me play as a torpedo boat at the Battle of Jutland. Considering this is a research preview, astonishing how fast this has come. An AI dynamically generating the world with no game engine…”” https://x.com/emollick/status/2018198584508760108
The Subtle Voicebuds use AI to transcribe your words below a whisper, or in very loud spaces (like the CES show floor) https://www.engadget.com/audio/headphones/the-subtle-voicebuds-use-ai-to-transcribe-your-words-below-a-whisper-or-in-very-loud-spaces-like-the-ces-show-floor-000000019.html
Huge congratulations to the community on shipping vLLM-Omni v0.12.0rc1! 🎉 This release shifts the focus from enabling multimodal to making it production-grade–faster, stable, and standard-compliant. Highlights from the 187 commits: 🚀 Diffusion Overhaul: Integrated TeaCache,”” https://x.com/vllm_project/status/2008482657991368738
Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single”” https://x.com/IlirAliu_/status/2017884655869976975
Reinforcement Learning for Active Perception in Autonomous Navigation. [📍GitHub & Paper ] Most robots navigate as if their cameras were nailed in place. But perception is not passive. Animals move their heads and eyes constantly to decide where to go next. Robots should do”” https://x.com/IlirAliu_/status/2018762226170016109
A multimodal sleep foundation model for disease prediction | Nature Medicine https://www.nature.com/articles/s41591-025-04133-4
Leave a Reply