Image created with gemini-3.1-flash-image-preview. Image prompt: 1960s limited-animation cel of the Pink Panther standing in profile wearing an oversized boxy black VR headset, one long pink finger extended to touch a tiny floating cartoon butterfly, flat turquoise background with generous negative space and loose black ink outlines, bold hand-lettered title text reading AR/VR across the top in playful mid-century cartoon typography.
Fable 5 is nuts. I vibe coded terminator vision replays with no LiDAR or IMU, just 2D videos from Ray-Bans, GoPros, and iPhones — all fused into a 4D reconstruction of my shooting range sessions. Full pipeline in the video ft. audio-waveform sync, SAM3 masked colmap & pi3″
https://x.com/bilawalsidhu/status/2077132368721190965
ByteDance just released UniVR-34B on Hugging Face The first model to learn complex reasoning, physical dynamics, and long-term planning directly from visual demonstrations — no text chains needed.”
https://x.com/HuggingPapers/status/2076513044340097501
Absolutely love this! Like a volumetric “tiny planet” effect”
https://x.com/bilawalsidhu/status/2077852867801612508
Action-controllable world models are evolving fast. LingBot-World-Infinity can run an unbroken session of real-time world generation for up to an hour. A distilled model can stream 720p at 60 fps. World models are going to be a critical piece in training robotic agents for”
https://x.com/TheHumanoidHub/status/2075960719846334689
Most “AI makes games” demos are just a clip that plays back the same way every time. PixVerse Game is chasing the harder version: you describe what you want, that intent gets turned into game mechanics and an AI agent, and a real-time video stream responds to it. Player intent,”
https://x.com/kimmonismus/status/2077002223612276866
A new paradigm for robot learning that unifies latent world modeling and action generation. Astribot has introduced Lumo-2, a latent world-action model for robot control. – Validated on a real robot through 20+ intricate chores, extending beyond simple benchmark testing. – A”
https://x.com/TheHumanoidHub/status/2077824134172791162
Most world models fall apart after a few seconds. Common failure modes include texture smearing, warped geometry, and scenes that no longer look real. LingBot-World 2.0 from @robbyant_brain seems to hold 720p at 60 fps for a full hour of interaction. That’s impressive. Here”
https://x.com/omarsar0/status/2077058222339338748
if you want to make a minecraft-like planetary simulator, try out muse spark 1.1″
https://x.com/alexandr_wang/status/2075683798281490551
Simulate realistic touch at massive scale! {📌 with open code & sim integration released} A scalable tactile sensor simulator integrated into the Genesis physics engine that enables high-throughput parallel training of dexterous”
https://x.com/IlirAliu_/status/2077301186646946020
🤔What does it take to train an omni world model from scratch? 📽️Petabytes of video. 6⃣pipeline stages. And every improvement in data quality pays off twice when you’re training a model that both generates and understands video. Our Reka Labs’ data team on how it works →”
https://x.com/RekaAILabs/status/2077043205854707813
Robbyant released LingBot-VA 2.0, a video-action model built natively for robot control, not a generic video generator with actions bolted on. It predicts how a scene will change and how to act in it, grounding control in physical dynamics. Core ideas: – Learns world knowledge”
https://x.com/TheHumanoidHub/status/2076744031976222894
WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images” TL;DR: feed-forward 3D Gaussian Splatting for unposed photos that disentangles geometry from appearance, enabling sota novel view synthesis and appearance editing from sparse in-the-wild images.”
https://x.com/Almorgand/status/2077432202745290838
>be openai >release gpt 5.6 sol >max thinking budgets, full psycho >benchmark results take few days to roll in >”best model ever” >reviews locked in >4 days later >silently nerf it >nobody re-tests lol >users still paying full price >not realizing the model they benchmarked”
https://x.com/ns123abc/status/2076498300312703349
An interesting part of this work is autonomous damage recovery. We trained the cells to not only recognize their shape, but also detect missing neighbors across six spatial directions with 95% accuracy. As shown in the animation, starting from just a small seed cluster, the”
https://x.com/SakanaAILabs/status/2076930948348674248
Mini 6 dof Arm. 3D printed planetary gearboxs & more… [📍GitHub link below ] A mini 6-axis arm driven by stepper motors with custom 3D printed split ring planetary gearboxs and an inverted belt differential wrist with custom bearings, driven by low-cost stepper motors and”
https://x.com/IlirAliu_/status/2075851609767051545
sol ultra – recreate san francisco as a 3d voxel city, make no mistakes.”
https://x.com/bilawalsidhu/status/2076377868083310717
IronSight turns 2D range footage into a replayable 4D world — with shot detection, 3D target tracking, and a camera you can move anywhere. Seeing my own runs reconstructed from every angle is ridiculously fun. Can’t wait till we can run this tech in real time.”
https://x.com/bilawalsidhu/status/2075558907771052447
Leave a Reply