Image created with Flux Pro v1.1 Ultra. Image prompt: CU Boulder brand style — CU Gold & Black, Helvetica Neue, Flatirons, Tuscan-vernacular sandstone + red-tile roofs; engineering lab bench, practical lab lighting, low-angle close-up, subtle Flatirons contour linework; integrate the category “ARVR” via Prop: student wearing AR headset with controllers, subtle UI grid reading “ARVR”; natural light, clean professional inspiring tone, crisp focus, subtle grain, editorial composition
Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind’s Genie 3 shook the AI world with real-time interactive world models. But… it wasn’t open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long https://x.com/Skywork_ai/status/1955237399912648842
RT @Skywork_ai: Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind’s Genie 3 sh…”” / X https://x.com/slashML/status/1955320183976767673
Damn it worked! Genie 3 world –> inpaint UI –> 4x topaz AI upscale –> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I’ve seen. I think Google has stumbled upon the killer app for VR — the literal holodeck. https://x.com/bilawalsidhu/status/1954229425199034753
Lmao. We got open source genie ONE WEEK after Google’s announce. Meanwhile, Odyssey has a launch around the corner too. The future is generated, not rendered.”” / X https://x.com/bilawalsidhu/status/1955342603324453305
RT @altryne: This Genie-3 video is mind boggling, especially this edited out part, the airplane collides with the sphere, bounces off, the…”” / X https://x.com/_rockt/status/1955025996547232170
Tired: painting to video Wired: painting to worlds This is a closest glimpse we’ve seen to a real life holodeck https://x.com/bilawalsidhu/status/1953959597301235943
Here are two ways to create this effect: Option 1: Motion track to analyze the camera movement and spatial positioning throughout the shot. Capture HDRs of the lighting environment to accurately recreate the illumination conditions. Create a detailed 3D model of the action https://x.com/c_valenzuelab/status/1955687077825183952
3D is really hard, and far from a solved problem. SIGGRAPH always brings this into focus for me. Recreating a bowl of strawberries — down to the fuzzy hair and material microstructures is no small feat — but it’s doable. Now consider those strawberries actually sit on a https://x.com/bilawalsidhu/status/1955059735595811130
Meta × Niantic is a big deal. Quest gets Lightship-grade 3D mapping, spatial anchors, and VPS localization – plus primitives like object detection & semantic segmentation. That’s the spatial computing stack shipped into the hands of devs today. https://x.com/bilawalsidhu/status/1953822369622925607
HTC Unveils VIVE Eagle AI Glasses https://www.vive.com/us/newsroom/2025-08-14/
Matrix-3D does a smart thing: generate a full 360 panorama first, then extend temporally with camera control, then lift it to 3D Sidesteps multi-view consistency hell, and gets you the largest explorable volumes we’ve seen from text-to-3D And it’s OSS: https://x.com/bilawalsidhu/status/1955646231713337502
The elevators in this hotel are in dire need of maintenance. I really expected more from a 5 star in SF. https://x.com/bilawalsidhu/status/1955267837276099072
Macro scale 3d reconstructions are so cool https://x.com/bilawalsidhu/status/1953655989057527865
Genie 3 can basically do one-shot / single-image 3D reconstruction. Turns a 2D painting into an explorable 3D world, and holy crap the fidelity is nuts. No NeRF, no 3D mesh and blows any image-to-3D tech I’ve seen out of the water. https://x.com/bilawalsidhu/status/1954166512475906217
Genie 3 is great, but IMO and IOI gold alone don’t impress me one bit. It’s just RL- maxxing. I want to see real world results. Show me that these results transfer to any other useful task.”” / X https://x.com/scaling01/status/1955052735918670246
LightSwitch: Multi-view Relighting with Material-guided Diffusion TL;DR: material-relighting diffusion framework; relights an arbitrary number of input images to a target lighting condition while incorporating cues from inferred intrinsic properties; (1/2) https://x.com/Almorgand/status/1955655723985309967
A conversation with @demishassabis on world models (genie 3), deep think, the need for better evals (game arena), and our progress towards AGI. https://x.com/OfficialLoganK/status/1954951468878090552
There have been a lot of crazy many-camera rigs created for the purpose of capturing full spatial video. I recall a conversation at Meta that was basically “we are going to lean in as hard as possible on classic geometric computer vision before looking at machine learning https://x.com/ID_AA_Carmack/status/1955302165653926058
You might notice something new in Copilot Labs today… https://x.com/mustafasuleyman/status/1953845057389478255
No Pose at All Self-Supervised Pose-Free 3DGS from Sparse Views”” TLDR: 3DGS + no poses during training/inference; shared feature extraction backbone; simultaneous prediction of 3D Gaussian primitives+camera poses in a canonical space from unposed (1 feed-forward step). https://x.com/Almorgand/status/1953480959573037419
🚀We are thrilled to open-source Hunyuan-GameCraft, a high-dynamic interactive game video generation framework built on HunyuanVideo. It generates playable and physically realistic videos from a single scene image and user action signals, empowering creators and developers to https://x.com/TencentHunyuan/status/1955839140173631656
A single, generalist control policy that solves diverse tasks at test-time, no fine-tuning needed: Researchers from UC Berkeley, Stanford, and the RAI Institute have unveiled DiffuseCLoC, a guided diffusion framework for physics-based character look-ahead control. Instead of https://x.com/IlirAliu_/status/1954084945552404675
