Image created with Gemini. Image prompt: Hand-painted Studio Ghibli style seaside optician shop window at golden hour, row of VR headset visors each fronted with a smiling porcelain carnival mask with rose-blush cheeks, a small girl on cobblestones lifting one mask-visor to reveal hollow gears and her own soft reflection inside, bold clean painted signboard above the window spelling ‘AR/VR’, warm terracotta rooftops and teal harbor beyond, soft gouache watercolor backgrounds, cel-shaded characters, cinematic wide square framing, wistful cozy mood.
Fable: “Last and First Men is out of copyright. I want you to make a movie that features a reading of it with appropriate mixes of animation and images using access to the APIs you have (elevenlabs, hugging face) . Give me the first 10-15 minutes, ending at an appropriate break.
https://x.com/emollick/status/2072872373758382497
Today, we’re introducing SimFoundry, our real2sim2real framework at NVIDIA GEAR that automatically turns real-world scenes into simulation-ready worlds from a single image or video. Website:
https://t.co/Iw38VtarSA Paper:
https://t.co/GcDYAUfVwP This work marks a major step for”
https://x.com/yukez/status/2072697990402170906
LeWorld model becomes ADAPTIVE and meets MODEL-PREDICTIVE CONTROL AdaJEPA by Yann LeCun and colleagues performs actions, then checks the predicted latent state versus the observed and adapts at TEST TIME. Similar to meta-learning … Paper:
https://x.com/gklambauer/status/2072213633640075366
Forget lidar. One single camera. Runs in real time & is open source: A streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. End-to-end. Optimization tricks, cleanup steps? Nope. And it beats both streaming and even some offline methods.”
https://x.com/IlirAliu_/status/2070568712264929475
“This is the difference between describing a shot and directing one.” Video models are getting so good that people are finally getting 3d pilled Way more fun to grab a phone and record the exact camera move you want vs. endlessly hitting the slot machine”
https://x.com/bilawalsidhu/status/2070654502718316870
Yeah this is cool! Get the ads-b track of the actual helicopter → line up timing with cable news footage → estimate camera field of view to match the 3d view with the real footage. And volia a 3d recreation!”
https://x.com/bilawalsidhu/status/2072857221147324418
3D + AI is a helluva combo. If you don’t want to wrangle blender but want give this hybrid workflow a shot then try @intangibleai – super accessible to author 3d content and run it through your models of choice – all in one tool.”
https://x.com/bilawalsidhu/status/2071788896749515065
This tech maps the physical world in 3d and snaps it perfectly to my camera feed at 60 fps. Visual Positioning Systems (VPS) are the under hyped backbone of spatial computing. This is how we connect the world of bits & atoms.”
https://x.com/bilawalsidhu/status/2071396483459633358
Most evaluations of world models ask, “Does this look right?” 🌎 We built WorldModelGym to ask a different question: if an agent actually uses this model to make decisions, does it still choose well? 🏋️🏃♂️🏁🦾 A simulation can look physically plausible and still lead an agent”
https://x.com/RekaAILabs/status/2072325792558956573
REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image” TLDR: reconstructs simulation-ready 3D scenes from a single image by combining agentic physical scene understanding with physics-constrained optimization.”
https://x.com/Almorgand/status/2071984726512906605
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction” TL;DR: formulates sparse-view 3D reconstruction as flow matching over continuous 3D Gaussian parameters, generating plausible unseen geometry with fewer Gaussians than grid-aligned methods.”
https://x.com/Almorgand/status/2072352053599306191
Most world models predict what happens next. Sora predicts pixels, JEPA compresses observations. NEO tries to figure out why something happened instead. Example: show it a shape moving left then down, and instead of just reconstructing that motion, it learns “left” and “down
https://x.com/LiorOnAI/status/2072380547603829224
🎮🕹️🖥️ CS2-10k is now available on @huggingface 🚀 600,000+ egocentric gameplay videos. 10,000+ hours. Every frame paired with the exact keyboard, mouse, and 3D position data that produced it. If you’re working on world models, action-conditioned video generation, or egocentric”
https://x.com/RekaAILabs/status/2071970771233038475
A true survey highlight: World Action Models: A Survey by @NUSingapore World Action Models (WAMs) are embodied systems that connect future prediction directly to action. → WAMs unify Vision-Language-Action policies with predictive world models. This survey covers: WAM”
https://x.com/TheTuringPost/status/2070790639021920356
Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild” TL;DR: combines temporally consistent single-view 3D priors, deformable Gaussian Splatting, and diffusion-guided optimization to reconstruct challenging dynamic scenes from monocular videos.”
https://x.com/Almorgand/status/2070162025146163211
Greyboxed 3d to final pixels workflows looking real good these days. And open source too?! C’mon we have it too good”
https://x.com/bilawalsidhu/status/2070534360911012092
We just open-sourced 3DREAL ! A new render-to-real IC-LoRA for LTX-2.3 from fal: turn any 3D / CG / game render into high 3d render, photorealistic, film-quality video, keeping your exact composition and camera move using the first frame.”
https://x.com/fal/status/2070523006770630813
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE” TL;DR: injects spherical positional embeddings into pretrained diffusion transformers to generate seamless 360° panoramas and videos without any training or optimization.”
https://x.com/Almorgand/status/2072721320350044316
Leave a Reply