Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Using the provided reference image, preserve the exact square faceted perfume bottle with warm amber-gold liquid, crystal stopper, pure white background, soft shadow, and clean white label typography, but replace the label text with ‘Video’ in matching serif font and drape a delicate sterling silver chain around the bottle neck with a tiny dainty film reel or clapperboard pendant, maintaining high-fashion jewelry aesthetic and studio lighting quality.
We’re releasing SAM 3.1: a drop-in update to SAM 3 that introduces object multiplexing to significantly improve video processing efficiency without sacrificing accuracy. We’re sharing this update with the community to help make high-performance applications feasible on smaller,
https://x.com/AIatMeta/status/2037582117375553924
Exclusive | The Sudden Fall of OpenAI’s Most Hyped Product Since ChatGPT – WSJ
https://www.wsj.com/tech/ai/the-sudden-fall-of-openais-most-hyped-product-since-chatgpt-64c730c9
ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination”” TL;DR: reconstructs geometry, materials, and lighting jointly from sparse views with disentangled illumination for fast, relightable 3D assets
https://x.com/Almorgand/status/2037543988803121660
RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting”” TL;DR: continuous-time 4D Gaussian splatting enabling flexible retiming and high-fidelity dynamic scene reconstruction
https://x.com/Almorgand/status/2037195538659962940
So true. Makes zero sense that Epic Games Reality Scan app doesn’t support native 3D gaussian splat training. Nor does it make sense that Sketchfab doesn’t support viewing/sharing of 3DGS files. Could be two layups. Instead, so many users pose/register their 3D scans in
https://x.com/bilawalsidhu/status/2038044805763133719
This the closest tech we have to straight up memory capture. Immortalize a space, place, or moment in time and relive it forever. Truly the most future proof medium at our disposal. Start with static 3D scans today — 4D capture will only get cheaper.
https://x.com/bilawalsidhu/status/2038309334585590153
How developers can use Veo 3.1 Lite for AI video generation
https://blog.google/innovation-and-ai/technology/ai/veo-3-1-lite/
Veo 3.1 Lite now available in Gemini API and @GoogleAIStudio. Designed for rapid prototyping and high-volume video generation, starting at $0.05/sec. 🪶 – 1/2 the cost of Veo 3.1 Fast. – Text-to-Video (T2V) & Image-to-Video (I2V). – Landscape (16:9) and Portrait (9:16) format –
https://x.com/_philschmid/status/2039014102811427263
Video’s here to stay – introducing Veo 3.1 Lite, our most cost efficient video generation model to date, and on April 7th we are also reducing the price for Veo 3.1 Fast : )
https://x.com/OfficialLoganK/status/2039015034286694618
Introducing GLM-5V-Turbo: Vision Coding Model – Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts. – Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for
https://x.com/Zai_org/status/2039371126984360085
Introducing GLM-5V-Turbo: Vision Coding Model – Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts. – Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for
https://x.com/Zai_org/status/2039371126984360085?s=20
Breaking: OpenAI is canning Sora (mobile app, API and video capabilities in ChatGPT). It’s finished training its latest model, codenamed Spud, as CEO Sam Altman shifts his reports. w/ @amir
https://x.com/steph_palazzolo/status/2036534198245134380
OpenAI Exposure Set for Ark ETFs as Investor Demand for Pre-IPO Stakes Grows – Bloomberg
https://www.bloomberg.com/news/articles/2026-03-31/ark-etfs-to-add-openai-stake-as-retail-investors-chase-tech-boom
Grok’s video generation is in its sloppy imagination phase. The real-world action+video data from Tesla’s fleet of vehicles and Optimus will ground the slop into accurate physics. It then becomes useful slop that Optimus can use for training data and evaluation.
https://x.com/TheHumanoidHub/status/2037198531061309821
Today we’re also introducing the Runway Fund, an investment vehicle dedicated to backing the next generation of companies building across AI, media and world simulation. For the past several years, we’ve been investing quietly with this fund, backing a range of companies,
https://x.com/runwayml/status/2038984561132990836
A sign that human creativity is a bottleneck is that this year everyone can generate almost any image or video they can think of for nearly free and the April Fools posts are basically just as bad as any other year.
https://x.com/emollick/status/2039379053480914959
Leave a Reply