“😎Halliday Glasses — Smartglasses with an incredible display! #CES2025 #AR @JimHarris”
https://x.com/EvanKirstel/status/1876115641692045733
“We’re basically building the matrix inside the matrix, aren’t we?”
https://x.com/bilawalsidhu/status/1875594331014521117
“Yup, we’re definitely building the matrix inside the matrix.”
https://x.com/bilawalsidhu/status/1875946181127475703
NVIDIA Redefines Game AI With ACE Autonomous Game Characters | GeForce News | NVIDIA
https://www.nvidia.com/en-us/geforce/news/nvidia-ace-autonomous-ai-companions-pubg-naraka-bladepoint/
“5. A neural wristband that turns your hand into a mouse or keyboard by Mudra Link”
https://x.com/rowancheung/status/1877043456553492870
“Emma-X teaches robots to think ahead spatially while executing complex manipulation tasks Emma-X introduces a new way to make robots understand and execute complex tasks by combining visual understanding with spatial reasoning and grounded task planning. —–”
https://x.com/rohanpaul_ai/status/1877280190394503582
merve on X: “ViTPose — best open-source pose estimation model just landed to @huggingface transformers 🕺🏻💃🏻 See how to use on the next one ⤵️ https://t.co/lQYvT064Wu” / X – https://x.com/mervenoyann/status/1877360767478952012
“New DARPA challenge: Computational Imaging Detection and Ranging (CIDAR)”
https://x.com/jwt0625/status/1874641841548939587
“Y’all expecting RTX 5090, cool specs and stuff. But do you fully internalize what Jensen said about graphics? That the new card uses neural nets to generate 90+% of the pixels for your games? Traditional ray-tracing algorithms only render ~10%, kind of a “rough sketch”, and then”
https://x.com/DrJimFan/status/1876466699731669463
“This is just magical what Jensen just said about graphics in CES 2025 Generating 3 additional frames with AI for every frame that is calculated, all at 4K. i.e. in this, the traditional ray-tracing algorithm only calculates 2mn pixels out of the 33mn pixels and rest are”
https://x.com/rohanpaul_ai/status/1876541585497767985
“”The future of Computer Graphics is neural rendering. We ray trace only the pixels we need and we generate with AI all the other pixels” – Jensen Huang”
https://x.com/rohanpaul_ai/status/1876555375568433170
“100% AI-generated dashcam footage. The line between reality and imagination continues to blur.
https://x.com/bilawalsidhu/status/1876036292301238438
“ColorFlow makes auto-colorizing cartoons easy It enhances diffusion-based colorization by using a retrieval-augmented pipeline that ensures identity preservation and reference accuracy. Paper: “ColorFlow: Retrieval-Augmented Image Sequence Colorization” → Proposes a
https://x.com/rohanpaul_ai/status/1876946305890533671
“AniDoc transforms simple sketches into fluid, colored animations Paper: “AniDoc: Animation Creation Made Easier” Key Techniques: → Video Diffusion-Based Line Art Colorization: AniDoc leverages video diffusion models to convert black-and-white sketch sequences into colored
https://x.com/rohanpaul_ai/status/1876943589772501342
AI startup Odyssey’s new tool can generate photorealistic 3D worlds | TechCrunch
AI startup Odyssey’s new tool can generate photorealistic 3D worlds
“The future is unfolding before our eyes at CES 2025, a world that’s more sci-fi than reality. 23 wild reveals so far: 🧵 1/n. Halliday Glasses: 3.5-inch AI smart glasses with a tiny monitor @Halliday_Global The AI can talk to you in them. I so want one.
https://x.com/rohanpaul_ai/status/1877672721636835396
Rembrand raises $23 million Series A for virtual product placement
https://www.axios.com/pro/media-deals/2025/01/02/rembrand-virtual-product-placement
“I recorded my screen, it took me less than 10 minutes to go from text -> 3d printed object. I brainstormed with Gemini, used Imagen 3.0 to create the image, used Trellis to turn it into a GLB, translated that into an STL and printed it with my wife’s bambulabs printer. I’ve
https://x.com/andrew_n_carr/status/1874933780114514166
“Dawn of Jets, a VR aerial combat game with a fully interactive cockpit, recently entered early access on Quest. Details here:
https://x.com/UploadVR/status/1876267647110730137
“Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up
https://x.com/janusch_patas/status/1875051591700795785
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
https://igl-hkust.github.io/das/
“🚀 Our latest work, VideoLifter, is here! VideoLifter converts long video sequences into 3D representations with unprecedented speed, achieving 82% faster training while maintaining state-of-the-art accuracy. 🔗 Explore the details and visuals on our project page:
https://x.com/CongWenyan0320/status/1876511270741975056
“YOU DON’T NEED TO GO TO EGYPT TO LOOK INSIDE THE PYRAMIDS ANYMORE Thanks to Harvard University, we can now explore the Pyramids of Giza in 3D and 360°, complete with explanations. Source: @semestasains
https://x.com/MarioNawfal/status/1874768574117503279
“HOLY SHIT – generate 3D mesh from a single image in LESS THAN A SECOND 🤯
https://x.com/reach_vb/status/1877100242534912068
“As announced in partnership with @NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on @NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a
https://x.com/StabilityAI/status/1877079954267189664
[2412.20911v1] TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation
https://arxiv.org/abs/2412.20911v1
“Released by @RealityLabs Research at #ECCV2024, Nymeria is a large-scale multimodal egocentric dataset for full-body motion understanding with potential applications in VR/MR headsets, smart glasses and more. More on this work + access to the dataset ➡️
https://x.com/AIatMeta/status/1877058463706325326
A ‘Holy Grail’ of Science Is Getting Closer – The Atlantic
https://www.theatlantic.com/technology/archive/2025/01/generative-ai-virtual-cell/681246/
Apple Vision Pro
“Apple stops Vision Pro production amid weak demand and customer dissatisfaction | A super-high price tag and lack of compelling apps is a bad combination
https://x.com/EvanKirstel/status/1875024294310264853
Robot Training
“Introducing NVIDIA Cosmos, an open-source, open-weight Video World Model. It’s trained on 20M hours of videos and weighs from 4B to 14B. Cosmos offers two flavors: diffusion (continuous tokens) and autoregressive (discrete tokens); and two generation modes: text->video and
https://x.com/DrJimFan/status/1876516972512559170
NVIDIA Cosmos video dataset – Dr Alan D. Thompson – LifeArchitect.ai
Cosmos World Foundation Model Platform for Physical AI | Research
https://research.nvidia.com/publication/2025-01_cosmos-world-foundation-model-platform-physical-ai
Cosmos – a nvidia Collection
https://huggingface.co/collections/nvidia/cosmos-6751e884dc10e013a0a0d8e6
World Models
“We’re excited to share some updates on Genesis since its release: 1. We made a detailed report on benchmarking Genesis’s speed and its comparison with other simulators”
https://x.com/zhou_xian_/status/1877044465527095562
“DeepMind has ambitious plans to make massive generative models that simulate the world. I’m hiring for a new team with this mission. Come build with us!
https://x.com/_tim_brooks/status/1876327325916447140
Google is forming a new team to build AI that can simulate the physical world | TechCrunch
Google is forming a new team to build AI that can simulate the physical world
“World Foundation Models (WFMs) are essentially pre-trained on open-world video data, which you can then fine-tune it on your specific application with less labels (be it autonomous driving or robotic arms) This release matters so much for embodied applications because labelling
https://x.com/mervenoyann/status/1876677250977767729
