Image created with Gemini. Image prompt: A wide sunlit landscape of green hills, a turquoise swimming pool with hand-drawn white ripple squiggles, a winding terracotta road and a hot yellow sun, constructed as a grid of slightly offset and overlapping rectangular photo-collage panels where the same hill and pool repeat from mismatched angles, flat saturated acrylic colors, hard-edged shapes with no shading, high noon light with no shadows, visible tablet-drawn line, high horizon and generous empty white sky.
Apple Beat Google to It! Hyper-Realistic Maps at WWDC 2026 — Gaussian Splats & the ongoing 3D maps land grab to own the substrate that connects the physical and digital world. Hopping on with @RadianceFields to discuss.
https://x.com/bilawalsidhu/status/2064146894930989138
holy crap! apple just beat google to the punch — 3d gaussian splatting is coming to apple maps. these 3d scenes are made from oblique aerial imagery. but unlike blobby photogrammetry — no more broccoli trees, no more melted powerlines — ground level detail that actually holds
https://x.com/bilawalsidhu/status/2064057313057439795
ICYMI google’s been shipping gaussian splats in maps for a while — but tucked inside immersive view and indoor only. I used it heavily in NYC. Meanwhile apple’s bringing radiance fields to 300+ cities this fall, built from aerial imagery. Surprised they didn’t drop ground-level
https://x.com/bilawalsidhu/status/2064187152930365502
Apple’s gaussian splat maps are rolling out on the developer beta! I hope they make a legit vision pro app – would be dope to drop into a city with the homies embodied as persona avatars.
https://x.com/bilawalsidhu/status/2064494805023911966
Déjà View: Looping Transformers for Multi-View 3D Reconstruction”” TL;DR: a recurrent transformer reuses the same block for iterative camera pose and depth refinement, outperforming much larger feed-forward reconstruction models with only 117M parameters.
https://x.com/Almorgand/status/2062548330320650713
R³: 3D Reconstruction via Relative Regression”” TL;DR: replaces global pose regression with confidence-weighted relative pose estimation, enabling scalable streaming and offline 3D reconstruction with only 372M parameters.
https://x.com/Almorgand/status/2064457403551092753
🎉 Meet vLLM-Omni v0.22.0, a major upgrade for omnimodal world models and production-grade multimodal serving. 🌍 Day-0 @NVIDIAAI Cosmos 3 world models: text, image, audio, video, and action, in and out. 🤖 Robot serving: DreamZero + OpenPI realtime API. 🎙️ Production TTS:
https://x.com/vllm_project/status/2064013506882703421
You may have recently heard claims that video generation models are “”dumb”” about physics, and only “”world models”” (V-JEPA, specifically) have a valid internal model of physics. This turns out to be false. In a recent paper, researchers show that a LINEAR probe of diffusion
https://x.com/giffmana/status/2064718736783823145
1X has hired Samarth Sinha to lead its new World Models research group. Samarth was previously a founding researcher at Luma AI, scaling large multimodal models. The mandate: build the next generation of foundation world models for NEO humanoid, trained on large-scale,
https://x.com/TheHumanoidHub/status/2062595716946784758
A new v0 robotics benchmark by independent researcher that tests robot foundation models on four tasks: Requiring spatial reasoning, geometric understanding, occlusion handling, and visuospatial planning. Using a low-cost open-source SO-101 robotic arm. The tasks progress in
https://x.com/IlirAliu_/status/2063894548821016989
A zero-shot video-language reward model. Trained on over 1M trajectories from 21 robot embodiments. It predicts: Frame-level task progress and generalizes zero-shot to unseen tasks, scenes, and robots, yielding 2.4-4.5x better success rates in: Online/offline RL, data
https://x.com/IlirAliu_/status/2063168037964877993
Boston Dynamics taught Atlas a Rabona kick. Learned from human mocap, retargeted to Atlas, trained in sim via RL, deployed zero-shot to the real robot. Soccer skills demand whole-body coordination, and similar recipe transfers to warehouse work.
https://x.com/TheHumanoidHub/status/2062607675339497680
If you can teach a robot a new skill in under an hour, you’ve just made your whole lab more flexible overnight. Pharma and biotech need automation that’s flexible enough for unstructured work… yet auditable enough to trust in regulated environments. That combination doesn’t
https://x.com/IlirAliu_/status/2062958380239511894
Leave a Reply